KR20230138865A - Cafe curation device and cafe curation method - Google Patents

Abstract

A cafe curation device and a cafe curation method are provided. The cafe curation device collects cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in the cafe, and the cafe monitoring data includes at least one of status data and forecast data for the cafe interior. module; a customer data collection module that collects customer data associated with the customer from a customer terminal used by the customer; A status check signal transmission module that transmits a status check signal to the artificial intelligence-based cafe monitoring device; a cafe curation scheme determination module that determines a cafe curation scheme according to a response signal to the status confirmation signal; And it may include a cafe list creation module that generates a cafe list based on the determined cafe curation scheme and provides it to the customer terminal.

Description

Cafe curation device and cafe curation method {CAFE CURATION DEVICE AND CAFE CURATION METHOD}

The disclosure relates to a cafe curation device and a cafe curation method.

The cafe curation service is a service that collects and selects information about various cafes, adds new value, and disseminates it. When a cafe owner who wants to attract customers registers his cafe in the cafe curation service, customers can receive recommendations for cafes that suit their tastes or purpose of visit through the user terminal. In particular, the cafe curation service goes beyond simply providing information on cafes located nearby or with high review ratings based on the location of the user's terminal, and presents cafes that match the values considered important by cafe users. It is different from previous cafe recommendation services in that it does this. In order to implement more valuable cafe curation services, ways to collect information on the real-time or predicted status of cafes and utilize this for cafe curation services are being studied.

The problem we are trying to solve is Cafe Q, which can provide cafe curation services to customers based on the current status data and forecast data inside the cafe collected through artificial intelligence and IoT (Internet of Things)-based monitoring devices installed in the cafe. It provides a rationing device and cafe curation method.

A cafe curation device according to an embodiment collects cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in a cafe, and the cafe monitoring data includes at least one of status data and prediction data about the cafe interior. , cafe monitoring data collection module; a customer data collection module that collects customer data associated with the customer from a customer terminal used by the customer; A status check signal transmission module that transmits a status check signal to the artificial intelligence-based cafe monitoring device; a cafe curation scheme determination module that determines a cafe curation scheme according to a response signal to the status confirmation signal; And it may include a cafe list creation module that generates a cafe list based on the determined cafe curation scheme and provides it to the customer terminal.

In some embodiments, the status data includes table or seat arrangement status, table or seat occupancy status, noise status, visiting customer gender status, visiting customer age status, visiting customer behavior status, visiting customer stay time status, and menu order status. and data on at least one of the interior interior status, wherein the predicted data includes prediction of change in table or seat occupancy, prediction of seat atmosphere, prediction of waiting time, prediction of noise change, prediction of gender of visiting customer, prediction of age of visiting customer, and prediction of visiting customer. It may include data on at least one of behavior pattern prediction, visit purpose prediction, menu ranking prediction, recommended menu prediction, sales prediction, inventory prediction, and cafe interior atmosphere prediction.

In some embodiments, the status data and the prediction data may be anonymized within the artificial intelligence-based cafe monitoring device.

In some embodiments, the customer data may include data about at least one of customer gender, customer age, customer location, service use history, customer taste, preferred menu, cafe visit history, and predicted visit purpose.

In some embodiments, the first scheme includes a scheme that uses both the status data and the prediction data for cafe curation, and when the response signal includes a first response signal, the cafe curation scheme determination module The first scheme may be determined as the cafe curation scheme.

In some embodiments, the second scheme includes a scheme that uses the status data and does not use the prediction data for cafe curation, and when the response signal includes a second response signal different from the first response signal. , the cafe curation scheme determination module may determine the second scheme as the cafe curation scheme.

In some embodiments, the third scheme includes a scheme that does not use both the status data and the prediction data for cafe curation, and a third response where the response signal is different from the first response signal and the second response signal. If the signal is included, the cafe curation scheme determination module may determine the third scheme as the cafe curation scheme.

In some embodiments, the fourth scheme includes a scheme that uses past cafe monitoring data collected in the cafe monitoring data collection module for cafe curation, and when the response signal includes the third response signal, The cafe curation scheme determination module may determine the third scheme and the fourth scheme as the cafe curation scheme.

In some embodiments, the fifth scheme includes a scheme that uses the customer data for the curation, and the cafe curation scheme determination module is configured to determine at least one of the first to fourth schemes and the fifth scheme. can be determined by the cafe curation scheme.

In some embodiments, the device further includes a digital twin creation module that creates the interior of a cafe included in the generated cafe list as a digital twin virtual space, and the cafe list creation module includes the digital twin creation module and By operating together, the interior of a cafe included in the cafe list can be provided to the customer terminal in the form of the digital twin virtual space.

In some embodiments, the digital twin creation module may update the digital twin virtual space by reflecting changes in the status data.

In some embodiments, the digital twin creation module provides sound data corresponding to the interior of a cafe included in the cafe list to the customer terminal, so that the customer terminal plays it together when rendering the digital twin virtual space. can do.

In some embodiments, the digital twin creation module may update the sound data associated with the digital twin virtual space by reflecting changes in the status data.

In some embodiments, the cafe list creation module causes the customer terminal to display predicted data about cafes included in the cafe list in the form of at least one of text, icons, images, and videos on the screen. can be provided to.

A cafe curation method according to an embodiment collects cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in a cafe, and the cafe monitoring data includes at least one of status data and prediction data about the cafe interior. step;

collecting customer data associated with the customer from a customer terminal used by the customer; Transmitting a status confirmation signal to the artificial intelligence-based cafe monitoring device; determining a cafe curation scheme according to a response signal to the status confirmation signal; And it may include generating a cafe list based on the determined cafe curation scheme and providing it to the customer terminal.

In some embodiments, the method includes generating the interior of a cafe included in the generated cafe list as a digital twin virtual space; And it may further include providing the interior of the cafe included in the cafe list to the customer terminal in the form of the digital twin virtual space.

In some embodiments, the method may further include providing sound data associated with the digital twin virtual space to the customer terminal.

In some embodiments, the method provides predictive data for cafes included in the cafe list to the customer terminal to display the customer terminal in the form of at least one of text, icons, images, and videos on the screen. Additional steps may be included.

Figure 1 is a block diagram for explaining a cafe curation system according to an embodiment.
Figure 2 is a block diagram to explain an artificial intelligence-based cafe monitoring device according to an embodiment.
Figure 3 is a block diagram for explaining a cafe curation device according to an embodiment.
Figure 4 is a flowchart explaining a cafe curation method according to an embodiment.
Figure 5 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.
Figure 6 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.
Figure 7 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.
Figure 8 is a block diagram for explaining a cafe curation device according to an embodiment.
Figure 9 is a flowchart for explaining a cafe curation method according to an embodiment.
Figure 10 is a diagram for explaining an example of a screen displayed on a customer terminal according to an embodiment.
Figure 11 is a block diagram for explaining a computing device according to an embodiment.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification and claims, when a part is said to “include” a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

In addition, terms such as "... unit", "... unit", and "module" described in the specification may mean a unit capable of processing at least one function or operation described in the specification, which means It can be implemented in hardware, software, or a combination of hardware and software.

In this specification, for clarity of explanation, embodiments targeting a cafe are described, but the scope of the present invention is not a cafe, but any store or space using an IoT device to monitor real-time status inside the store or space. This extends to curating, recommending, or suggesting stores or spaces to users based on the predicted status.

Figure 1 is a block diagram for explaining a cafe curation system according to an embodiment.

Referring to Figure 1, the cafe curation system 1 according to an embodiment includes an artificial intelligence-based cafe monitoring device (10, 11, 12), a cafe curation device (20), a customer terminal (30), and a store owner terminal ( 32) may be included. The artificial intelligence-based cafe monitoring device (10, 11, 12), cafe curation device (20), customer terminal (30), and store owner terminal (32) can exchange data with each other through the network (40).

The artificial intelligence-based cafe monitoring devices 10, 11, and 12 may be IoT devices. IoT is a technology that connects to the Internet by embedding sensing and communication functions in objects. Artificial intelligence-based cafe monitoring devices (10, 11, 12) are installed inside the cafe to monitor the cafe interior and transmit the monitoring results to the network (40). It can be transmitted to another device, for example, the cafe curation device 20. The artificial intelligence-based cafe monitoring device (10, 11, 12) can be equipped with an artificial intelligence model (e.g., deep learning model) to monitor the inside of the cafe, and is installed inside several cafes to monitor the real-time status inside the cafe. You can monitor and predict future conditions. For example, the artificial intelligence-based cafe monitoring device (10, 11) is installed inside a certain cafe (A) and can monitor and predict the status inside the cafe (A), and the artificial intelligence-based cafe monitoring device (12) is installed inside another cafe (B) and can monitor and predict the status inside the other cafe (B). The monitoring and prediction results that can be obtained from the artificial intelligence-based cafe monitoring device (10, 11) installed in the cafe (A) and the monitoring and prediction results that can be obtained from the monitoring device (12) installed in the cafe (B) are network ( It can be transmitted to the cafe curation device 20 through 40). Hereinafter, in the case where the artificial intelligence-based cafe monitoring devices (10, 11, 12) installed in cafes (A, B) provide monitoring and prediction results as cafe monitoring data to the cafe curation device (20), cafe curation The device 20 will be described in detail.

The cafe curation device 20 is based on cafe monitoring data for cafes (A, B) collected through the cafe monitoring devices 10, 11, and 12, and determines the values that customers consider important to select a cafe. Matching cafes can be presented to customers through the customer terminal 30. In some embodiments, cafe monitoring data collected through the cafe monitoring devices 10, 11, and 12 may be stored and managed in a database that the cafe curation device 20 can access.

In some embodiments, cafe monitoring data may include at least one of status data and predicted data about the interior of the cafe. The status data is generated by artificial intelligence-based cafe monitoring devices (10, 11, and 12) using sensors such as cameras and microphones and artificial intelligence technologies such as object detection, pose estimation, and semantic segmentation. This may include information about the interior of the cafe collected. Specifically, status data includes, for example, table or seat arrangement status, table or seat occupancy status, noise status, status of music played in the store, status of music playing history in the store, status of gender of visiting customers, visit It may include data on at least one of the following: customer age status, visiting customer behavior status, visiting customer stay time status, order status by menu, and internal interior status status. Meanwhile, the predicted data may include information about the interior of the cafe collected using sensors, data inferred, derived, or predicted based on an artificial intelligence inference model, or data estimated from accumulated status data. Specifically, predictive data includes, for example, prediction of changes in table or seat occupancy, prediction of seat atmosphere, prediction of waiting time, prediction of noise changes, prediction of music to be played in the store, prediction of visiting customer gender, prediction of visiting customer age group, visit It may include data on at least one of customer behavior pattern prediction, visit purpose prediction, menu ranking prediction, recommended menu prediction, sales prediction, inventory prediction, and cafe interior atmosphere prediction.

For example, forecast data on sales forecasts can be estimated from status data on order status for each menu, and visiting customer behavior patterns (e.g., computer Predictive data regarding predictions (30% work, 20% conversation, 50% rest, etc.), prediction of purpose of visit, or prediction of waiting time can be inferred. As another example, prediction data regarding seat atmosphere prediction, visiting customer gender prediction, or visiting customer age group prediction may be inferred from status data regarding visiting customer gender status or visiting customer age status status. As another example, prediction data about noise change prediction, prediction about music to be played in the store, or prediction of the atmosphere inside a cafe from status data about the noise status, music played in the store, or the status of the playing history of store music. can be inferred.

In some embodiments, the status data and predicted data may be implemented so that they are generated in the artificial intelligence-based cafe monitoring device (10, 11, 12) and only transmitted to the cafe curation device (20), and in some other embodiments, , some of the status data and predicted data are generated in the artificial intelligence-based cafe monitoring device (10, 11, 12) and delivered to the cafe curation device (20), but other part of the predicted data is generated by the cafe curation device (20). ) may be implemented to be generated by the cafe curation device 20 from cafe monitoring data transmitted to ).

In some embodiments, cafe monitoring data including status data and predicted data may be anonymized within the artificial intelligence-based cafe monitoring device 10, 11, and 12. In other words, the cafe monitoring data generated by the artificial intelligence-based cafe monitoring device (10, 11, 12) is, for example, anonymized in the process of being generated as various data as described above or after generation is completed, thereby identifying the user's identity. It is possible to prevent data that could potentially be deleted from being transmitted to the cafe curation device 20. As an example of implementation, if data on gender and number of people is extracted from the shooting data of visitors inside a cafe, only the data on gender and number of people is transmitted to the cafe curation device 20, and the shooting data is transmitted to the cafe curation device 20. It can be destroyed within the base cafe monitoring device (10, 11, 12). Accordingly, it is possible to understand and predict the current status of the cafe while protecting personal information.

In some embodiments, cafe monitoring data may be implemented as text data that follows certain standards. For example, cafe monitoring data is organized as "3 people at table 1, 1 person at table 3, 2 cups of latte, 3 cups of iced Americano, 3 women, 2 men" and is formatted as text with certain specifications such as JSON. It can be abstracted into data.

In some embodiments, one type of cafe monitoring data provided by the artificial intelligence-based cafe monitoring device 10, 11, and 12 to the cafe curation device 20 may be transmitted to the cafe curation device 20 in real time. . Specifically, the artificial intelligence-based cafe monitoring devices 10, 11, and 12 may transmit one type of cafe monitoring data to the cafe curation device 20 at a first predetermined time interval (e.g., 20 seconds). there is. Here, the predetermined time interval may be set differently depending on the specific implementation purpose and implementation environment. Meanwhile, other types of cafe monitoring data provided by the artificial intelligence-based monitoring devices 10, 11, and 12 to the cafe curation device 20 are provided at a second time interval (e.g., predetermined to be longer than the first time interval). For example, it may be transmitted to the cafe curation device 20 (several hours, several days). In other words, the type of cafe monitoring data that needs to be frequently updated in order for the cafe curation device 20 to provide the service is transmitted in real time or at short time intervals, and updates do not need to be made frequently. By allowing other types of cafe monitoring data to be transmitted at relatively long time intervals, network bandwidth can be used efficiently and the power consumption of artificial intelligence-based cafe monitoring devices (10, 11, 12) can be reduced.

For example, among the status data, data on table or seat arrangement status, table or seat occupancy status, noise status, status of music played in the store, etc. are data that must be immediately updated in the cafe curation service. It may correspond to tangible cafe monitoring data, and data on the gender of visiting customers, the age status of visiting customers, the status of visiting customer behavior, the status of visiting customer stays, the status of orders by menu, and the status of internal interior are not updated immediately. This is data that is not unreasonable, and may correspond to the other types of cafe monitoring data mentioned above. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

As another example, among the predicted data, data on table or seat occupancy change prediction, seat atmosphere prediction, waiting time prediction, noise change prediction, prediction of music to be played in the store, etc. are data that must be immediately updated in the cafe curation service. As such, it may correspond to the above type of cafe monitoring data, predicting visiting customer gender, predicting visiting customer age, predicting visiting customer behavior pattern, predicting purpose of visit, predicting menu rank, predicting recommended menu, sales forecast, inventory forecast, and cafe. Data related to internal atmosphere prediction, etc. is data that is safe even if updates are not made immediately, and may correspond to the other types of cafe monitoring data mentioned above. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

As another example, assuming that the status data is the one type of cafe monitoring data and the prediction data is the other type of cafe monitoring data, the status data is transmitted in real time or at short time intervals, and the prediction data is transmitted over a relatively long period of time. It can also be implemented to be transmitted at time intervals. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

In some embodiments, the artificial intelligence-based cafe monitoring devices 10, 11, and 12 may adjust the number of times information is transmitted to the cafe curation device 20 in consideration of computing and network resources. For example, the artificial intelligence-based cafe monitoring devices 10, 11, and 12 monitor and The prediction results may be averaged and transmitted to the cafe curation device 20 by performing the averaged results only once.

In some embodiments, the artificial intelligence-based cafe monitoring devices 10, 11, and 12 may be equipped with a processor to monitor and predict the current status of the cafe based on an artificial intelligence inference model. However, since efficient operation of computing resources is often required in an environment where the artificial intelligence cafe monitoring device (10, 11, 12) is installed, the processor can be used elaborately. Specifically, the artificial intelligence-based cafe monitoring devices 10, 11, and 12 may control the processor to use only the object detection function to acquire some of the cafe monitoring data, and may use the object detection function to acquire other data. The processor can be controlled to use the and pose estimation functions together, and to obtain other data, the processor can be controlled to use the object detection function and semantic segmentation function together. In this way, by using a mixture of object detection, pose estimation, and semantic segmentation according to the characteristics of the data to be acquired, the limited computing resources of the artificial intelligence-based cafe monitoring device (10, 11, 12) can be efficiently operated. .

For example, data related to seat occupancy status, such as table or seat arrangement status, table or seat occupancy status, table or seat occupancy change prediction, etc., and data related to customer appearance inference, e.g. visit The processor may be controlled to use the object detection function and semantic segmentation function together for data related to customer gender status, visiting customer age status, visiting customer gender prediction, and visiting customer age prediction, etc. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

As another example, the object detection function and pose estimation function are used together for data related to customer behavior inference, such as data related to visiting customer behavior status, visiting customer residence time status, visiting customer behavior pattern prediction, and visiting purpose prediction, etc. The processor can be controlled to do so. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

As another example, the processor may be controlled to use only the object detection function for data related to menu or sales estimation, such as order status by menu, menu ranking prediction, recommended menu prediction, sales prediction, inventory prediction, etc. You can. Of course, this division is illustrative, and the division may vary depending on the specific implementation purpose and implementation environment.

The customer terminal 30 may receive a curated cafe list from the cafe curation device 20 and provide a cafe curation service to the customer. To this end, the customer terminal 30 provides customer data associated with customers using the customer terminal 30 to the cafe curation device 20, allowing the cafe curation device 20 to provide a cafe curation service. Customer data can be used along with cafe monitoring data. Accordingly, the cafe curation device 20 does not simply select only cafes close to the current location or famous franchise cafes through tasks such as analyzing the correlation between cafe monitoring data and customer data, but also selects cafes that can actually provide satisfaction to customers. You can discover and recommend cafes.

In some embodiments, customer data may include data regarding at least one of customer gender, customer age, customer location, service usage history, customer tastes, preferred menu, preferred music genre, cafe visit history, and predicted visit purpose. there is. The store owner terminal 32 is a terminal used by the store owner of the cafe, and has functions such as registering cafe information and menu information in the cafe curation service, or processing orders when an order is received from a customer through the cafe curation service. can be provided to the cafe owner.

In some embodiments, the customer terminal 30 and the store owner terminal 32 may be computing devices, including a smart phone, tablet computer, wearable device, laptop computer, desktop computer, etc. Users can use the cafe curation service through applications running on the customer terminal 30 and the store owner terminal 32.

The network 40 may include a wireless network including a Wi-Fi network, a Bluetooth network, a cellular network, a wired network including a LAN (Local Area Network), and a network that is a mixture of a wireless network and a wired network.

Hereinafter, with reference to FIGS. 2 to 10, a cafe curation device and a cafe curation method according to embodiments will be described in detail.

Figure 2 is a block diagram to explain an artificial intelligence-based cafe monitoring device according to an embodiment.

Referring to FIG. 2, the artificial intelligence-based cafe monitoring device 10 according to an embodiment includes a camera 101, a memory 102, an artificial intelligence status analysis model 103, an artificial intelligence inference model 104, and data deletion. It may include a module 105 and an anonymization module 106. In this specification, the description of the artificial intelligence-based cafe monitoring device 10 can be equally applied to the artificial intelligence-based cafe monitoring devices 11 and 12.

The camera 101 can photograph the interior of a cafe and output captured data including captured images or videos. In some embodiments, the camera 101 may include a PTZ camera capable of rotation, tilt, and zoom, a fixed camera, etc. Meanwhile, in some embodiments, the camera 101 may include an RGB camera, an IR camera, etc. In order to film the interior of a cafe without blind spots, multiple cameras 101 may be installed in the cafe, and they can exchange data with each other through the network 40. Additionally, filming of the interior of the cafe using the camera 101 can be done extensively, including seats, tables, visiting customers, floors, walls, ceilings, etc.

In some embodiments, camera 101 may include a plurality of cameras assigned different roles. For example, among multiple cameras filming the same cafe, one camera is responsible for taking pictures of seats or tables, another camera is responsible for taking pictures of visiting customers, and yet another camera is responsible for taking pictures of the floor, walls, and fabric. The role may be assigned to be in charge of filming interior scenes, etc.

The memory 102 can load software and data necessary for the artificial intelligence-based cafe monitoring device 10 to operate. Specifically, the memory 102 is loaded with program code for monitoring and predicting the status of the cafe using the artificial intelligence status analysis model 103 and the artificial intelligence inference model 104, or the data deletion module 105. And program code implementing the later-described functions of the anonymization module 106 may be loaded, or data used when executing the program code may be loaded. Additionally, the memory 102 may be loaded with program code corresponding to firmware or an operating system that controls the overall operation of the artificial intelligence-based cafe monitoring device 10. In addition, the shooting data output from the camera 101 is loaded into the memory 102, and the artificial intelligence status analysis model 103 and the artificial intelligence inference model 104 store the shooting data loaded in the memory 102 as camera data ( CD) can be accessed to monitor and predict the current status inside the café and generate café monitoring data (CMD) including status data (D1) and predicted data (D2).

The artificial intelligence status analysis model 103 can generate status data (D1) based on camera data (CD). That is, the artificial intelligence status analysis model 103 can generate status data (D1) about the interior of the cafe based on camera data (CD) including images or videos. To this end, the artificial intelligence status analysis model 103 may include a deep learning model to implement object detection, pose estimation, semantic segmentation, etc.

In some embodiments, the artificial intelligence status analysis model 103 may analyze the status of empty tables or empty seats for the store based on camera data (CD) included in the store tables or seats. Here, the status of empty tables or empty seats may include not only the table or seat occupancy rate, but also information about the properties of the empty tables or empty seats, or information about the properties around the empty tables or empty seats. Here, the properties of the empty table or empty seat may include the location of the empty table or empty seat in the store, the type of empty seat (single chair, two-seat sofa, etc.), and properties surrounding the empty table or empty seat. It may also include the behavior patterns or noise level of other customers sitting at an empty table or next to an empty seat.

The artificial intelligence inference model 104 may generate prediction data (D2) based on camera data (CD). That is, the artificial intelligence inference model 104 can generate prediction data (D2) based on camera data (CD) including images or videos. Here, the predicted data may include data inferred, derived, or predicted based on at least one of camera data (CD) and status data (D1), or data estimated from accumulated status data. To this end, the artificial intelligence inference model 104 may also include a deep learning model.

In some embodiments, the artificial intelligence inference model 140 determines whether the purpose of the visiting customer's visit is rest, work on a laptop, paperwork, conversation with a person accompanying him, meeting other people, reading, etc. The purpose of the visit can be analyzed. This analysis takes camera data (CD) containing visiting customers as input and categorizes them into, for example, “relaxation”, “laptop work”, “paper work”, “conversation”, “meeting”, “reading”, etc. It can be implemented by an artificial intelligence inference model 140 that has been learned to output the purpose of the visit.

In some other embodiments, the artificial intelligence inference model 140 may analyze the interior of the store by analyzing shooting results including the floor, wall, ceiling, etc. Specifically, the interior atmosphere can be analyzed based on the color and pattern of the floor, walls, and ceiling. This analysis uses camera data (CD) about the interior of the store, including the floor, walls, and ceiling, as input, and categorizes it into, for example, “nature-friendly interior,” “modern interior,” and “office space-like interior.” It can be implemented by an artificial intelligence inference model 140 that has been learned to output the interior atmosphere.

The data deletion module 105 deletes the camera data (CD) used in the artificial intelligence status analysis model 103 and the artificial intelligence inference model 104 to generate cafe monitoring data (CMD). ) Images and videos used for creation can be safely deleted to protect personal information.

The anonymization module 106 may perform anonymization processing on cafe monitoring data (CMD). In other words, the anonymization module 106 deletes or modifies data that may identify the user during the process of creating the cafe monitoring data (CMD) or after the creation of the cafe monitoring data (CMD) is completed. When monitoring data (CMD) is provided to the cafe curation device 20, the data can be processed so that information related to identity is not transmitted together.

In some embodiments, the artificial intelligence-based cafe monitoring device 10 according to one embodiment may further include a sound collection unit 107. The sound collection unit 107 may include a microphone that can measure or record sounds occurring in the store. The sound collection unit 107 collects sounds related to music played in the store as well as noise and noise generated in the store, and can transmit the collected sound data to the memory 102. When sound data is loaded into the memory 102, the artificial intelligence status analysis model 103 identifies the noise status in the store based on the sound data, the music played in the store, and the voice of a visiting customer identified in the sound data. Status data (D1) regarding the analyzed gender status of visiting customers can be generated. Meanwhile, the artificial intelligence inference model 104 predicts noise changes based on sound data, predicts music to be played in the store, or predicts the atmosphere inside a cafe, and further makes inferences based on gender inferred from the voice of a visiting customer from sound data. Predictive data (D2) regarding prediction of gender of visiting customers, etc. can be generated.

In some embodiments, the sound collection unit 107 may be implemented outside of the artificial intelligence-based cafe monitoring device 10. Specifically, the sound collection unit 107 is implemented in the form of a sound analysis application capable of collecting sounds within the store, and can be installed and executed on the store owner terminal 32 shown in FIG. 1. Alternatively, the sound collection unit 107 is a separate device from the artificial intelligence-based cafe monitoring device 10 and may be implemented as a hardware device installed at various points inside the cafe. In this way, when the sound collection unit 107 is implemented outside the artificial intelligence-based cafe monitoring device 10, the store owner terminal 32 or the hardware device is an artificial intelligence status analysis model ( 103) and a configuration corresponding to the artificial intelligence inference model 104, as described above, the visit is analyzed from the noise status in the store, the result of identifying the music played in the store, and the voice of the visiting customer identified in the sound data. Visiting customer gender inferred based on status data (D1) on customer gender, etc., or noise change prediction, prediction of music to be played in the store, or prediction of atmosphere inside the cafe, and further based on gender inferred from the visiting customer's voice from sound data. Prediction data (D2) regarding predictions, etc. can be generated.

In some embodiments, the sound collection unit 107 may include a plurality of sound collection units 107, and accurately detect sound through difference analysis on sound data collected through the plurality of sound collection units 107. It can be implemented. Specifically, the first sound data collected through the sound collection unit 107 implemented on the store owner terminal 32, and the artificial intelligence-based cafe monitoring device 10 and implemented as a separate device at a point inside the cafe. Through difference analysis of the second sound data collected through the hardware device, the size of the noise can be measured more precisely and the music played in the store can be more accurately identified among the noise.

In some embodiments, identifying music played in a store may be implemented using an API (Application Programming Interface) that provides a service using a deep learning model, and may be used to identify music within the sound collection unit 107. It can also be implemented by embedding a deep learning model implemented as a recurrent neural network (RNN).

Figure 3 is a block diagram for explaining a cafe curation device according to an embodiment.

Referring to Figure 3, the cafe curation device 20 according to an embodiment includes a cafe monitoring data collection module 200, a status check signal transmission module 220, a cafe curation scheme determination module 230, and a cafe list. It may include a generation module 240 and a customer data collection module 250.

The cafe monitoring data collection module 200 can collect cafe monitoring data (CMD) provided from the artificial intelligence-based cafe monitoring device 10 installed in the cafe. As described above, cafe monitoring data (CMD) may include at least one of status data and predicted data. In some embodiments, the cafe monitoring data collection module 200 stores cafe monitoring data (CMD) received from the artificial intelligence-based cafe monitoring device 10 through the network 40 for each cafe using a database or storage. and can be managed.

The status check signal transmission module 220 can transmit a status check signal (SCS) to the artificial intelligence-based cafe monitoring device 10. Here, the status confirmation signal (SCS) may be a signal for checking the operation mode of the artificial intelligence-based cafe monitoring device 10 through the network 40. The artificial intelligence-based cafe monitoring device 10 may transmit a response signal (RSP) to the cafe curation scheme decision module 230 in response to the status confirmation signal (SCS).

The response signal (RSP) to the status check signal (SCS) may include a first to third response signal. The first response signal is a first operation mode in which the artificial intelligence-based cafe monitoring device 10 provides both status data (D1) and predicted data (D2) among cafe monitoring data (CMD) to the cafe curation device 20. It can mean that it is in. Differently, in the second response signal, the artificial intelligence-based cafe monitoring device 10 provides status data (D1) among cafe monitoring data (CMD) to the cafe curation device 20, but predicts data (D2) is provided to the cafe queue. This may mean that it is in a second operation mode that does not provide information to the ration device 20. The second operation mode, for example, operates only the artificial intelligence status analysis model 103 in the artificial intelligence-based cafe monitoring device 10, and prevents the artificial intelligence inference model 104 from operating or intentionally does not operate. This may be the operation mode when set.

Differently, the third response signal may mean that the artificial intelligence-based cafe monitoring device 10 is in a third operation mode in which all of the cafe monitoring data (CMD) is not provided to the cafe curation device 20. The third operation mode is, for example, a case where the artificial intelligence status analysis model 103 and the artificial intelligence inference model 104 do not operate in the artificial intelligence-based cafe monitoring device 10 or are intentionally set not to operate. It may be an operation mode, but in cases where the artificial intelligence-based cafe monitoring device 10 does not operate normally due to a malfunction or a connection through the network 40 is not established, cafe monitoring is performed from the artificial intelligence-based cafe monitoring device 10. This may even indicate a situation in which data (CMD) cannot be transmitted to the cafe curation device 20.

The cafe curation scheme determination module 230 may determine the cafe curation scheme (SCM) according to the response signal (RSP) to the status check signal (SCS) received from the artificial intelligence-based cafe monitoring device 10. . Here, the cafe curation scheme (SCM) can allow the cafe curation device 20 to specify various ways to perform cafe curation.

For example, the cafe curation scheme (SCM) may include a first scheme, and the first scheme is status data among cafe monitoring data (CMD) when the cafe curation device 20 performs cafe curation. It may be a scheme that uses both (D1) and prediction data (D2). As another example, the cafe curation scheme (SCM) may include a second scheme, and the second scheme is status data among cafe monitoring data (CMD) when the cafe curation device 20 performs cafe curation. It may be a scheme that uses (D1) and does not use prediction data (D2). As another example, the cafe curation scheme (SCM) may include a second scheme, and the second scheme may include the current status of cafe monitoring data (CMD) when the cafe curation device 20 performs cafe curation. This may be a scheme that does not use both data D1 and prediction data D2. As another example, the cafe curation scheme (SCM) may include a fourth scheme, and the fourth scheme is a cafe monitoring data collection module 200 when the cafe curation device 20 performs cafe curation. It may be a scheme that uses past cafe monitoring data (CMD) collected in. As another example, the cafe curation scheme (SCM) may include a fifth scheme, and the fifth scheme allows the cafe curation device 20 to use customer data (UD) in performing cafe curation. It could be a scheme. Of course, the scope of the present invention is not limited to the listed examples, and the cafe curation scheme (SCM) can be set in various ways depending on the specific implementation purpose and implementation environment.

In some embodiments, when the response signal (RSP) received from the artificial intelligence-based cafe monitoring device 10 includes the first response signal, the cafe curation scheme determination module 230 selects the first scheme as the cafe curation scheme. (SCM). As described above, the first response signal indicates that the artificial intelligence-based cafe monitoring device 10 provides both status data (D1) and prediction data (D2) among the cafe monitoring data (CMD), so the cafe curation device (20) can perform cafe curation using both status data (D1) and forecast data (D2) among cafe monitoring data (CMD).

In some other embodiments, when the response signal (RSP) received from the artificial intelligence-based cafe monitoring device 10 includes a second response signal different from the first response signal, the cafe curation scheme determination module 230 2 The scheme can be decided as Cafe Curation Scheme (SCM). As described above, the second response signal indicates that the artificial intelligence-based cafe monitoring device 10 provides only status data (D1) and not prediction data (D2) among cafe monitoring data (CMD), and thus The curation device 20 may perform cafe curation using only the status data (D1) among the cafe monitoring data (CMD).

In some other embodiments, when the response signal (RSP) received from the artificial intelligence-based cafe monitoring device 10 includes a third response signal different from the first response signal and the second response signal, the cafe curation scheme determination module (230) may determine the third scheme to be a cafe curation scheme (SCM). As described above, the third response signal indicates that the artificial intelligence-based cafe monitoring device 10 does not provide all of the cafe monitoring data (CMD), so the cafe curation device 20 provides the cafe monitoring data (CMD). You can perform cafe curation without using .

In some other embodiments, when the response signal (RSP) received from the artificial intelligence-based cafe monitoring device 10 includes a third response signal, the cafe curation scheme determination module 230 determines the fourth scheme along with the third scheme. The scheme can be decided as Cafe Curation Scheme (SCM). In this case, the cafe curation device 20 may perform cafe curation using past cafe monitoring data (CMD) collected in the cafe monitoring data collection module 200.

In some other embodiments, the café curation scheme determination module 230 may determine the fifth scheme together with at least one of the first to fourth schemes as the café curation scheme (SCM). In this case, at least one of status data (D1), predicted data (D2), and past cafe monitoring data (CMD) collected in the cafe monitoring data collection module 200 according to at least one of the first to fourth schemes, and , cafe curation can be performed using customer data (UD) together.

The cafe list creation module 240 generates a cafe list based on the cafe curation scheme (SCM) determined by the cafe curation scheme decision module 230, and sends this to the customer terminal 30 as cafe list data (CLD). can be provided to.

The customer data collection module 250 collects customer data (UD) associated with the customer from the customer terminal 30 used by the customer and provides cafe curation service to the cafe curation device 20, providing cafe monitoring data. Customer data can be used with . Additionally, the customer data collection module 250 can display the cafe list provided from the cafe list creation module 240 on the screen to discover and recommend cafes to customers.

In some embodiments, the cafe curation device 20 may perform cafe recommendation based on customer data (UD) or general user data. For example, while a customer visits a cafe, the cafe curation device 20 may inquire about the purpose of the visit through the customer terminal 30 and store the response as customer data (UD). Afterwards, the cafe curation device 20 can analyze the stored data and infer that the customer mainly does paperwork when he or she visits the cafe during weekday morning hours. Thereafter, when a customer searches for a cafe during weekday morning hours, the cafe curation device 20 may preferentially recommend a cafe whose interior is judged to be suitable for document work. Differently, as a result of analyzing general user data obtained from several random users, it was inferred that the purpose of visiting a cafe during weekday morning hours was mainly to meet other people. If a customer searches for a cafe during weekday morning hours, The curation device 20 may preferentially recommend cafes whose interior is judged to be suitable for meeting other people.

In other words, when selecting cafe candidates to be included in the cafe list, cafe candidates can be selected based on user data about the customer in question, or cafe candidates can be selected based on general user data. Here, the user data for the customer may be information collected from questions the customer received and responded to while visiting the cafe in the past. For example, if a customer receives an inquiry about the purpose of the visit while visiting a cafe and responds to it, information such as the content of the response, response time (or cafe visit time), and response location is stored in the customer's customer data (UD). ) can be stored as. General user data may be data obtained by the cafe curation device 30 from several anonymized users.

Figure 4 is a flowchart explaining a cafe curation method according to an embodiment.

Referring to FIG. 4, in the cafe curation method according to an embodiment, in step S401, cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in the cafe is collected, and in step S402, the customer Customer data related to the customer can be collected from the customer terminal being used. In the method, in step S403, a status confirmation signal is transmitted to an artificial intelligence-based cafe monitoring device, and in step S404, a cafe curation scheme can be determined according to a response signal to the status confirmation signal. Additionally, the method may generate a cafe list based on the determined cafe curation scheme in step S405 and provide the cafe list to the customer terminal in step S406.

For more detailed information about the cafe curation method according to an embodiment, the above-described description in relation to FIGS. 1 to 3 may be referred to, so redundant description will be omitted here.

Figure 5 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.

Referring to FIG. 5, the cafe curation device 20 according to an embodiment may store a plurality of predefined schemes (SCM1, SCM2, SCM3) in, for example, memory, registers, storage, database, etc. The cafe curation scheme decision module 230 receives a first response signal (RSP1) from the artificial intelligence-based cafe monitoring device 10, and selects a plurality of predefined schemes (SCM1, SCM2) according to the first response signal (RSP1). , SCM3), the first scheme (SCM1) can be selected. The cafe curation scheme determination module 230 may transmit the selected first scheme (SCM1) as a cafe curation scheme (SCM) to the cafe list creation module 240, and the cafe list creation module 240 may transmit the selected first scheme (SCM1) as a cafe curation scheme (SCM) to the cafe list creation module 240. According to (SCM1), a cafe list can be created using both status data (D1) and forecast data (D2) among cafe monitoring data (CMD).

The cafe list creation module 240 can provide the created cafe list to the customer terminal 30, and allows the customer terminal 30 to display status data (D1) among the cafe monitoring data (CMD) along with the cafe list on the screen. and that all of the prediction data D2 has been used may be displayed in at least one of text, icon, image, and video.

Figure 6 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.

Referring to FIG. 6, in the cafe curation device 20 according to an embodiment, the cafe curation scheme determination module 230 receives a second response signal (RSP2) from the artificial intelligence-based cafe monitoring device 10, and , the second scheme (SCM2) can be selected from a plurality of predefined schemes (SCM1, SCM2, SCM3) according to the second response signal (RSP2). The cafe curation scheme determination module 230 may transmit the selected second scheme (SCM2) as a cafe curation scheme (SCM) to the cafe list creation module 240, and the cafe list creation module 240 may transmit the selected second scheme (SCM2) as a cafe curation scheme (SCM) to the cafe list creation module 240. According to (SCM2), a cafe list can be created using only the status data (D1) and not the prediction data (D2) among the cafe monitoring data (CMD).

The cafe list creation module 240 can provide the created cafe list to the customer terminal 30, and allows the customer terminal 30 to display status data (D1) among the cafe monitoring data (CMD) along with the cafe list on the screen. The fact that only the prediction data D2 is used and that the prediction data D2 is not used may be displayed in the form of at least one of text, icon, image, and video.

Figure 7 is a block diagram for explaining the operation of a cafe curation device according to an embodiment.

Referring to FIG. 7, in the cafe curation device 20 according to an embodiment, the cafe curation scheme decision module 230 receives a third response signal (RSP3) from the artificial intelligence-based cafe monitoring device 10, and , the third scheme (SCM3) can be selected among a plurality of predefined schemes (SCM1, SCM2, SCM3) according to the third response signal (RSP3). The cafe curation scheme determination module 230 may transmit the selected third scheme (SCM3) as a cafe curation scheme (SCM) to the cafe list creation module 240, and the cafe list creation module 240 may transmit the selected third scheme (SCM3) as a cafe curation scheme (SCM) to the cafe list creation module 240. According to (SCM3), a cafe list can be created without using cafe monitoring data (CMD).

The cafe list creation module 240 can provide the created cafe list to the customer terminal 30, and allows the customer terminal 30 to display the cafe list on the screen and indicate that cafe monitoring data (CMD) has not been used. Displayed in the form of at least one of text, icons, images, and videos, or in the form of at least one of text, icons, images, and videos indicating that past cafe monitoring data (CMD) collected in the cafe monitoring data collection module 200 has been used. It can be displayed as .

Figure 8 is a block diagram for explaining a cafe curation device according to an embodiment.

Referring to FIG. 8, the cafe curation device 20 according to an embodiment includes a cafe monitoring data collection module 200, a status check signal transmission module 220, and a cafe curation device 20 according to an embodiment. It may include a curation scheme determination module 230, a cafe list creation module 240, a customer data collection module 250, and a digital twin creation module 260. The cafe monitoring data collection module 200, status confirmation signal transmission module 220, cafe curation scheme determination module 230, cafe list creation module 240, and customer data collection module 250 are related to FIG. 3. Since the above-mentioned description can be referred to, the description here will focus on the differences between the embodiment of FIG. 3 and this embodiment.

The digital twin creation module 260 creates a digital twin virtual interior of the cafe included in the cafe list generated by the cafe list creation module 240, using status data regarding the interior status of the cafe monitoring data (CMD). It can be created in space. In some embodiments, cafe monitoring data (CMD), along with status data, includes the floor plan of the cafe store, color and pattern information such as the floor, walls, and ceiling inside the cafe, and information placed in the store such as tables, chairs, and sofas. It may further include data about the shape, color, and location information of the furniture, and the digital twin creation module 260 can be implemented in a way that reproduces a virtual space according to these data.

The cafe list creation module 240 operates together with the digital twin creation module 260 to provide the interior of a cafe included in the cafe list to the customer terminal 30 in the form of a digital twin virtual space. Specifically, the cafe list creation module 240 generates a cafe list based on the cafe curation scheme (SCM) determined by the cafe curation scheme determination module 230, and converts it into a digital twin as cafe list data (CLD). It can be provided to the creation module 260 and the customer terminal 30, and the digital twin creation module 260 is a digital twin containing data about the interior of the cafe in the form of a digital twin virtual space based on cafe list data (CLD). Twin data (DTD) can be provided to the customer terminal 30. The customer terminal 30 can render the interior of the cafe in the form of a digital twin virtual space based on digital twin data (DTD) and provide it to the customer. Accordingly, customers can explore and experience the interior spaces of cafes recommended in the curry list in advance and select a cafe with an interior that suits their taste without having to visit the cafe in person.

In some embodiments, the digital twin creation module 260 includes status data of cafe monitoring data (CMD) and floor plan of the cafe store, color and pattern information such as floor, wall, and ceiling inside the cafe, tables, chairs, The digital twin virtual space can be updated by reflecting changes in data about the shape, color, and location information of furniture placed in the store, such as sofas. For example, the interior of the cafe, such as seats, tables, visiting customers, floors, walls, and ceilings, is changed, and the cafe monitoring data collection module 200 is changed from the artificial intelligence-based cafe monitoring device 10 to the changed interior interior status. Upon receiving status data about the digital twin creation module 260, the digital twin creation module 260 updates the digital twin virtual space from the status data, and digital twin data ( DTD) can be provided to the customer terminal 30. Accordingly, it is possible to enable customers to accurately experience the cafe interior in order to select the desired cafe.

In some embodiments, the digital twin creation module 260 periodically or aperiodically checks the cafe monitoring data (CMD) managed by the cafe monitoring data collection module 200 to detect whether there is a change in the interior of the cafe and whether the change occurs. If detected, the digital twin virtual space can be updated. In some other embodiments, the artificial intelligence-based cafe monitoring device 10 detects whether there is a change in the interior of the cafe and transmits an interior interior change notification signal along with cafe monitoring data (CMD) to the cafe monitoring data collection module 200. Then, the digital twin creation module 260 may update the digital twin virtual space according to the internal interior change notification signal.

In some embodiments, the status data and prediction data regarding sound data collected through the sound collection unit 107 described above with respect to FIG. 2 may be stored in the cafe monitoring data collection module 200 as cafe monitoring data (CMD). You can. The digital twin creation module 260 uses the current status data and prediction data about the interior of the cafe included in the cafe list generated by the cafe list creation module 240 to visually provide a digital twin virtual space and at the same time provide appropriate sound. You can play it.

Specifically, the digital twin creation module 260 determines the size of noise in the store, the current state of music played in the store, prediction of noise change, prediction of music to be played in the store, and atmosphere inside the cafe based on cafe monitoring data (CMD). From information such as predictions, playback sound data can be included in the digital twin data (DTD) transmitted to the customer terminal 30. Here, the playback sound data may be data about sounds to be played together when the interior of the cafe is rendered and visually expressed in the form of a digital twin virtual space based on the customer terminal 30. The customer terminal 30 can provide appropriate sound to customers while rendering the interior of the cafe in the form of a digital twin virtual space based on digital twin data (DTD) including playback sound data.

For example, if the noise level of the cafe rendered in the form of a digital twin virtual space is determined to be relatively low and quiet, the digital twin creation module 260 causes the customer terminal 30 to create a quiet ambient in the digital twin data (DTD). (ambient) Playback sound data can be included in the form of commands or information instructing to play sound. According to the corresponding playback sound data, the customer terminal 30 can acquire music according to the corresponding command or information from the terminal local or over the network and play it together when rendering inside the cafe. Alternatively, the digital twin creation module 260 may include the sound source itself of a predetermined length including quiet ambient sound as playback sound data in the digital twin data (DTD). In this case, the customer terminal 30 can receive the corresponding playback sound data and play it together when rendering the interior of the cafe. As another example, the genre of the cafe's store music rendered in the form of a digital twin virtual space is mainly rock ( rock), the digital twin creation module 260 plays the sound in the digital twin data (DTD) in the form of a command or information instructing the customer terminal 30 to play the sound corresponding to the rock genre. Data can be included. According to the corresponding playback sound data, the customer terminal 30 can acquire music according to the corresponding command or information from the terminal local or over the network and play it together when rendering inside the cafe. Alternatively, the digital twin creation module 260 may include the sound source itself of a predetermined length corresponding to the rock genre as playback sound data in the digital twin data (DTD). In this case, the customer terminal 30 can receive the corresponding playback sound data and play it together during internal rendering of the cafe.

In some embodiments, the digital twin creation module 260 reflects changes in status data and prediction data regarding sound data collected through the sound collection unit 107 in the cafe monitoring data (CMD), thereby creating a digital twin virtual space. You can update the sound played when rendering. The specific method of updating may be performed in a similar manner to the update method according to the interior interior change described above. Accordingly, it is possible to enable customers to accurately experience the cafe interior in order to select the desired cafe.

Figure 9 is a flowchart for explaining a cafe curation method according to an embodiment.

Referring to FIG. 9, the cafe curation method according to an embodiment generates a cafe list based on the determined cafe curation scheme in step S901, and includes the cafe list included in the generated cafe list in step S902. The interior of a cafe can be created as a digital twin virtual space. In the above method, in step S903, a list of cafes is provided to the customer terminal, and in step S904, the interior of the cafe included in the cafe list can be provided to the customer terminal in the form of a digital twin virtual space. Additionally, the method may update the digital twin virtual space by reflecting the status data in step S905, and provide the updated interior of the cafe in the form of a digital twin virtual space in step S905.

For more detailed information about the cafe curation method according to an embodiment, the above-described description in relation to FIGS. 1 to 8 may be referred to, and thus redundant description will be omitted here.

Figure 10 is a diagram for explaining an example of a screen displayed on a customer terminal according to an embodiment.

Referring to FIG. 10, a screen displayed on a customer terminal according to an embodiment may include a cafe list curated based on curry list data (CLD) provided from the cafe list creation module 240. For example, the screen displays cafe information for "Cafe A" and "Cafe B", specifically information about the cafe's representative image, sales performance, cafe location, distance to the cafe, estimated discount amount, etc. It can be.

The cafe list creation module 240 causes the customer terminal 30 to display status data and prediction data for cafes included in the cafe list in the form of at least one of text, icons, images, and videos on the screen. It can be provided to the customer terminal 30. For example, referring to area (A) of the screen, "Table occupancy: 36%" and "(about 30 dB)" are displayed in text as status data, and "It's quiet" and "Have a chat" as prediction data. “Like” may be displayed as text. Additionally, on the right side of area A, “expected to wait approximately 12 minutes” may be displayed in text as another prediction data.

In some embodiments, with respect to FIGS. 8 and 9 , when the customer centers which café list item is currently on the screen, or when the customer touches a café list item to view detailed information about the café that the customer is currently viewing. Rendering may be performed in the form of a digital twin virtual space as described above.

In some embodiments, with respect to FIGS. 8 and 9 , when the customer centers which café list item is currently on the screen, or when the customer touches a café list item to view detailed information about the café that the customer is currently viewing. Appropriate sound data can be played together while rendering is performed in the form of a digital twin virtual space as described above.

In some embodiments, as described above with reference to FIGS. 6 to 8 , whether any data among the cafe monitoring data (CMD) has been used may be displayed in the form of at least one of text, icons, images, and videos. For example, referring to area (A) of the screen, an icon containing the text "AI Live" is displayed if status data among cafe monitoring data (CMD) is used, or prediction data among cafe monitoring data (CMD) is displayed. If data is used, an icon containing the text “Big Data” can be displayed to help users select a cafe.

Figure 11 is a block diagram to explain a computing device according to an embodiment.

Referring to FIG. 11 , an artificial intelligence cafe monitoring device, a cafe curation device, a customer terminal, and a store owner terminal according to embodiments may be implemented using the computing device 50.

Computing device 50 includes a processor 501, memory 502, a storage device 503, a display device 504 that communicate over a bus 509, and a connection to a network 40 for communication with other entities. It may include at least one of a network interface device 505 that provides and an input/output interface device 506 that provides a user input interface or a user output interface. Of course, the computer device 50, although not shown in FIG. 11, may further include any electronic device necessary to implement the technical ideas described in this specification.

The processor 501 may be implemented in various types such as an Application Processor (AP), Central Processing Unit (CPU), Graphic Processing Unit (GPU), Neural Processing Unit (NPU), and may include a memory 502 or a storage device ( 503) may be any electronic device that executes a stored program or command. In particular, the processor 501 may be configured to implement the functions or methods described above with respect to FIGS. 1 to 10, and calculations specialized for artificial intelligence in relation to the cafe curation device and cafe curation method according to embodiments are performed. Can be processed on GPU or NPU.

Memory 502 and storage device 503 may include various types of volatile or non-volatile storage media. For example, the memory 502 may include read-only memory (ROM) or random access memory (RAM), and the memory 502 may be located inside or outside the processor 501, and may include a known It can be connected to the processor 501 through various means. Meanwhile, examples of the storage device 503 include a hard disk drive (HDD) or a solid state drive (SSD), and the scope of the present invention is not limited to the elements listed above for explanation.

At least some of the cafe curation devices and cafe curation methods according to embodiments may be implemented as programs or software running on the computing device 50, and such programs or software may be stored in a computer-readable medium. .

Meanwhile, at least some of the cafe curation devices and cafe curation methods according to embodiments may be implemented using hardware of the computing device 50, or may be implemented as separate hardware that can be electrically connected to the computing device 50. It may be possible.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and common knowledge in the technical field to which the present invention pertains using the basic concept of the present invention defined in the following claims. Various modifications and improvements of those who have also fall within the scope of the present invention.

Claims (18)

A cafe monitoring data collection module that collects cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in the cafe, and the cafe monitoring data includes at least one of status data and prediction data about the cafe interior;
a customer data collection module that collects customer data associated with the customer from a customer terminal used by the customer;
A status check signal transmission module that transmits a status check signal to the artificial intelligence-based cafe monitoring device;
a cafe curation scheme determination module that determines a cafe curation scheme according to a response signal to the status confirmation signal; and
Comprising a cafe list creation module that generates a cafe list based on the determined cafe curation scheme and provides it to the customer terminal.
Cafe curation device. According to paragraph 1,
The above status data is,
Status of table or seat arrangement, status of table or seat occupancy, status of noise, status of music played in the store, status of music playing history in the store, status of gender of visiting customers, status of age of visiting customers, status of visiting customer behavior, visiting customers Contains data on at least one of the following: stay time status, menu order status, and interior interior status,
The predicted data is,
Prediction of change in table or seat occupancy, prediction of seat atmosphere, prediction of waiting time, prediction of noise change, prediction of music to be played in the store, prediction of visiting customer gender, prediction of visiting customer age group, prediction of visiting customer behavior pattern, prediction of visit purpose, menu ranking A cafe curation device comprising data on at least one of forecasts, recommended menu forecasts, sales forecasts, inventory forecasts, and cafe interior atmosphere forecasts. According to paragraph 1,
A cafe curation device in which the status data and the predicted data are anonymized within the artificial intelligence-based cafe monitoring device. According to paragraph 1,
The customer data is,
A cafe curation device that includes data on at least one of customer gender, customer age, customer location, service usage history, customer taste, preferred menu, cafe visit history, and predicted visit purpose. According to paragraph 1,
The first scheme includes a scheme that uses both the current status data and the predicted data for cafe curation,
When the response signal includes a first response signal, the cafe curation scheme determination module determines the first scheme as the cafe curation scheme. According to clause 5,
The second scheme includes a scheme that uses the status data and does not use the prediction data for cafe curation,
When the response signal includes a second response signal different from the first response signal, the cafe curation scheme determination module determines the second scheme as the cafe curation scheme. According to clause 6,
The third scheme includes a scheme that does not use both the status data and the prediction data for cafe curation,
If the response signal includes a third response signal different from the first response signal and the second response signal, the cafe curation scheme determination module determines the third scheme as the cafe curation scheme. lation device. In clause 7,
The fourth scheme includes a scheme that uses past cafe monitoring data collected in the cafe monitoring data collection module for cafe curation,
When the response signal includes the third response signal, the cafe curation scheme determination module determines the third scheme and the fourth scheme as the cafe curation scheme. According to clause 8,
A fifth scheme includes a scheme that uses the customer data for the curation,
The cafe curation scheme determination module is a cafe curation device that determines at least one of the first to fourth schemes and the fifth scheme as the cafe curation scheme. According to paragraph 1,
Further comprising a digital twin creation module that creates the interior of the cafe included in the generated cafe list as a digital twin virtual space,
The cafe list creation module operates together with the digital twin creation module to provide the interior of the cafe included in the cafe list to the customer terminal in the form of the digital twin virtual space. According to clause 10,
The digital twin creation module is a cafe curation device that updates the digital twin virtual space by reflecting changes in the status data. According to clause 10,
The digital twin creation module provides sound data corresponding to the interior of the cafe included in the cafe list to the customer terminal, allowing the customer terminal to play it together when rendering the digital twin virtual space, cafe curation. Device. According to clause 12,
The digital twin creation module is a cafe curation device that updates the sound data associated with the digital twin virtual space by reflecting changes in the status data. According to paragraph 1,
The cafe list creation module is,
A cafe curation device that provides prediction data about cafes included in the cafe list to the customer terminal so that the customer terminal displays it in the form of at least one of text, icons, images, and videos on the screen. Collecting cafe monitoring data provided from an artificial intelligence-based cafe monitoring device installed in the cafe, wherein the cafe monitoring data includes at least one of status data and prediction data about the cafe interior;
collecting customer data associated with the customer from a customer terminal used by the customer;
Transmitting a status confirmation signal to the artificial intelligence-based cafe monitoring device;
determining a cafe curation scheme according to a response signal to the status confirmation signal; and
Comprising the step of generating a cafe list based on the determined cafe curation scheme and providing it to the customer terminal.
How to curate a cafe. According to clause 15,
Creating the interior of a cafe included in the generated cafe list as a digital twin virtual space; and
A cafe curation method further comprising providing the interior of a cafe included in the cafe list to the customer terminal in the form of the digital twin virtual space. According to clause 16,
Cafe curation method further comprising providing sound data related to the digital twin virtual space to the customer terminal. According to clause 15,
A cafe curation method further comprising providing predicted data about cafes included in the cafe list to the customer terminal so that the customer terminal displays it in the form of at least one of text, icons, images, and videos on the screen. .

Images