WO2024039168A1 - Method for monitoring guest usage status by using at least one camera, and device supporting same - Google Patents

Abstract

The present specification relates to a method for monitoring guest usage status by using at least one camera, the method comprising the steps of: performing a check-in for a guest scheduled to stay on the basis of vehicle license plate information obtained by a first camera; identifying the type of a guest entering a room by means of guest information of the guest obtained by a second camera and re-identification (Re-ID) of the guest obtained by a third camera on the basis of the guest information; and by means of video information of a specific guest coming out of the room obtained by the third camera and re-identification of the specific guest obtained by a fourth camera on the basis of the video information of the specific guest, tracking a movement path of the specific guest.

Description

Method for monitoring guest usage status using at least one camera and device supporting the same

This specification relates to a method for monitoring a guest's usage status, and more specifically, to a method for monitoring a guest's usage status using at least one camera and a device to support the same.

There are three main ways for guests to check in at existing lodging facilities. The first method is to have the lobby manager face the customer directly, search the reservation information in the system using the reservation number or name of the person making the reservation, and provide a physical key. However, the first method has the disadvantage of having a fixed cost for manpower and a very long waiting time for check-in. There is. The second method is to provide physical keys directly to customers through an unmanned kiosk in the lobby. The second method has the effect of reducing fixed labor costs, but waiting time still occurs due to the limited number of kiosk equipment. In addition, this method is difficult for elderly guests who have difficulty using kiosks, and physical defects in low-cost kiosks can cause severe customer complaints.

The third method is check-in using a mobile key, which has fewer disadvantages due to fixed labor costs and malfunctions caused by low-cost kiosks, but it may be difficult to check-in quickly due to the time required to install and set up the check-in mobile app in the lobby for mobile key check-in. there is.

The existing methods examined earlier make it difficult to specify the type of customer who visits a hotel or other accommodation facility due to problems such as waiting time, and it is also impossible to track which facility they mainly use during their actual stay, making it difficult to conduct target marketing by customer type. Otherwise, the effect is also impossible to measure.

In addition, the lodging industry, which has traditionally maintained high fixed costs of manpower, seeks to reduce fixed costs through non-face-to-face check-in, but hopes to maintain the quality of service for guests.

Therefore, the purpose of this specification is to provide a method for analyzing the types of guests and tracking and analyzing the guests' movements through image information acquired through a plurality of cameras.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

The present specification provides a method for monitoring the usage status of guests through at least one camera, the step of performing check-in for guests scheduled to stay based on the license plate information of the vehicle obtained by the first camera. ; Confirming the type of guest entering the room through guest information acquired by a second camera and re-identification (Re-ID) of the guest obtained by a third camera based on the guest information; And tracking the movements of the specific guest through re-identification of the specific guest obtained by the fourth camera based on the video information of the specific guest coming from the room obtained by the third camera and the video information of the specific guest. It is characterized by including steps.

In addition, the method for monitoring the usage status of guests of the present specification includes the steps of analyzing the confirmed guest type and the tracked movement path of the specific guest; and generating the guest's stay history information based on the analysis results.

In addition, in this specification, the guest scheduled to stay is a guest who has made a reservation through a management system that manages guests in advance, and the guest is characterized as a guest who has completed check-in for the room.

In addition, in this specification, the guest information includes information on the number of guests staying in the room and the number of the room, and the information on the number of guests includes the number of guests staying in the room and the number of guests staying in the room. It is characterized by including video information of the number of guests staying.

In addition, in this specification, the type of guest is characterized as including at least one of the relationship between the guests staying in the room, the gender of the guests, or the age group of the guests.

In addition, in this specification, the relationship between the guests is characterized as one of friends, family, or lovers.

In addition, in this specification, the type of guest is characterized in that it is confirmed when the number of people staying in the room included in the guest information and the number of people staying in the room obtained by the third camera are the same.

Additionally, in this specification, performing the check-in includes comparing license plate information of the vehicle obtained by the first camera with license plate information of the vehicle pre-registered in the management system; and providing mobile check-in to the scheduled guest or providing direct check-in at the lobby based on the comparison result.

In addition, in this specification, the first camera is installed in the parking lot of the hotel, the second camera is installed in the lobby of the hotel, the third camera is installed in the guest room hallway of the hotel, and the fourth camera is installed in the hotel's public space. It is characterized by being installed in space.

In addition, the present specification provides a server for monitoring the usage status of guests through at least one camera, comprising: a wireless communication unit for transmitting and receiving wireless signals; Memory; and a control unit functionally connected to the wireless communication unit and the memory, wherein the control unit performs check-in for guests scheduled to stay based on license plate information of the vehicle obtained by the first camera; Confirming the type of guest entering the room through guest information obtained by a second camera and re-identification (Re-ID) of the guest obtained by a third camera based on the guest information; And to track the movements of the specific guest through re-identification of the specific guest obtained by the fourth camera based on the video information of the specific guest coming from the room obtained by the third camera and the video information of the specific guest. It is characterized by control.

This specification can provide an efficient lodging experience to guests and lodging establishment operators in the lodging industry such as hotels.

In addition, through the method provided herein, guests can quickly check-in using the guest's mobile phone after waiting for a long time at the designated check-in time in the existing lobby, so they can enter the room right away without having to go to the lobby or wait. There is an effect that can be done.

In addition, through the method provided in this specification, lodging operators can know the type of customer even in a non-face-to-face situation, such as guests who go straight up without checking in at the lobby, which can be used for future marketing.

In addition, the method provided in this specification has the effect of analyzing the tastes of the corresponding type of guest in more detail through what facilities they mainly use inside the hotel, which can be used to predict facility operation and discover future facilities.

In addition, through the method provided in this specification, the lodging facility can recognize the exact number of guests entering the room, minimize operational losses due to the accommodation of more guests compared to the number of guests shared in advance, and minimize the operating loss due to the accommodation of additional guests. It has the effect of being able to claim costs.

In addition, through the method provided in this specification, lodging facilities can receive notifications about the behavior of guests who require special care, such as the elderly and the disabled, such as falling or wandering alone at late hours, which has the effect of assisting guests' safe accommodation. There is.

The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. .

The accompanying drawings, which are included as part of the detailed description to aid understanding of the present invention, provide embodiments of the present invention, and together with the detailed description, explain technical features of the present invention.

Figure 1 is a diagram showing an example of a conceptual diagram of a guest management system to which the method proposed in this specification can be applied.

Figure 2 is a diagram showing an example of a plurality of cameras proposed in this specification.

Figure 3 is an internal block diagram to explain a device to which the method proposed in this specification can be applied.

Figure 4 is a block diagram of an AI device to which the method proposed in this specification can be applied.

Figure 5 is a diagram showing an example of a re-identification method that can be applied to the method proposed in this specification.

Figure 6 is a flowchart showing an example of a method for analyzing the type of guest and tracking the guest's movement using the information of the guest scheduled to stay in the guest management system proposed in this specification.

Figure 7 is a flowchart showing an example of a method for managing guests proposed in this specification.

Figure 8 is a flowchart showing an example of a tracking method applicable to the method proposed in this specification.

Figure 9 is a flowchart showing an example of a method for tracking a person using a camera proposed in this specification.

It should be noted that the technical terms used in this specification are only used to describe specific embodiments and are not intended to limit the spirit of the technology disclosed in this specification. In addition, the technical terms used in this specification, unless specifically defined in a different way in this specification, should be interpreted as meanings generally understood by those skilled in the art in the field to which the technology disclosed in this specification belongs. It should not be interpreted in a very comprehensive sense or in an excessively reduced sense. In addition, if the technical term used in this specification is an incorrect technical term that does not accurately express the idea of the technology disclosed in this specification, it is a technical term that can be correctly understood by a person with ordinary knowledge in the field to which the technology disclosed in this specification belongs. It should be understood and replaced with . Additionally, general terms used in this specification should be interpreted as defined in the dictionary or according to the context, and should not be interpreted in an excessively reduced sense.

Terms containing ordinal numbers, such as first, second, etc., used in this specification may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be referred to as a second component, and similarly, the second component may be referred to as the first component without departing from the scope of the present invention.

Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings. However, identical or similar components will be assigned the same reference numerals regardless of the reference numerals, and duplicate descriptions thereof will be omitted.

Additionally, when describing the technology disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the technology disclosed in this specification, the detailed description will be omitted. In addition, it should be noted that the attached drawings are only intended to facilitate easy understanding of the spirit of the technology disclosed in this specification, and should not be construed as limiting the spirit of the technology by the attached drawings.

Images according to an embodiment of the present invention include both still images and moving images, unless there is a special limitation.

Figure 1 is a diagram showing an example of a conceptual diagram of a guest management system to which the method proposed in this specification can be applied.

The guest management system proposed in this specification can be used in all places (e.g. hotels, motels, etc.) and areas where people can stay, and for convenience of explanation, 'hotel' will be used as an example below. However, it should be clarified that this is not limited to this.

Referring to Figure 1, the guest management system 10 includes a plurality of cameras 100, a cloud server 200, a hotel management system 300, a user terminal 400, and a card key issuing device (kiosk, 500) and the like.

The cloud server may be referred to as a first server, and the hotel management system may be referred to as a hotel server, hotel management server, or second server.

Additionally, the cloud server and the hotel management system may be implemented as one server, and when implemented as one server, the hotel management system may include the functions of a cloud server, or the cloud server may be a function of the hotel management system. Functions may be included.

The plurality of cameras 100 may be classified into four types of cameras (first group cameras, second group cameras, third group cameras, and fourth group cameras) depending on where they are installed in the hotel.

Figure 2 is a diagram showing an example of a plurality of cameras proposed in this specification.

Referring to Figure 2, the first group camera may be a camera installed in the hotel parking lot (Figure 2a), the second group camera may be a camera installed in the hotel lobby (Figure 2b), and the third group camera may be a camera installed in the hotel lobby (Figure 2b). It may be a camera installed in the guest room hallway (FIG. 2C), and the fourth group camera (FIG. 2D) may be a camera installed in a common area of the hotel (e.g., health club, restaurant, coffee shop, etc.).

Depending on the embodiment, the second group camera may be included in the fourth group camera.

Next, the cloud server 200 receives vehicle license plate information, information on the number of guests, room information, etc. of guests scheduled to stay from a plurality of cameras and the hotel management system, and analyzes the received information to determine the number of guests. Provides information for tracking the type and movement of guests.

Next, the hotel management system 300 stores and manages reservation information for guests scheduled to stay, guest information such as the number of guests, type of guest, and guest history information regarding the type and movement of guests.

Next, the user terminal 400 provides a screen where guests scheduled to stay can access the hotel management system, and provides mobile check-in notifications, notifications about inaccessible areas, etc. to the guests.

Next, the card key issuing device 500 receives a barcode output on the user terminal or issues a card key for the room by input from the user (eg, a guest scheduled to stay).

Device internal block diagram

Figure 3 is an internal block diagram to explain a device to which the method proposed in this specification can be applied.

The device described in FIG. 3 may include a camera, a hotel management system, a cloud server, a user terminal, a card key issuing device, etc.

The devices 100, 200, 300, 400, and 500 may include a wireless communication unit 11, an input unit 12, an output unit 13, a memory 14, and a control unit 15. The components shown in FIG. 3 are not essential for implementing the device, so the device described herein may have more or fewer components than the components listed above.

More specifically, the wireless communication unit among the components may include one or more modules that enable wireless communication between a device and a wireless communication system, between a device and another device, or between a device and a server. Additionally, the wireless communication unit may include one or more modules that connect a device to one or more networks.

This wireless communication unit may include at least one of a mobile communication module, a short-range communication module, and a location information module.

The input unit may include a user input unit (eg, a touch key, a mechanical key, etc.) for receiving information from the user. The input unit may additionally include a camera or video input unit for inputting video signals, a microphone, or an audio input unit for inputting audio signals. Voice data or image data collected from the input unit can be analyzed and processed as a user's control command.

The output unit is intended to generate output related to vision, hearing, or tactile sensation, and may include at least one of a display unit, an audio output unit, a haptip module, and an optical output unit. A touch screen can be implemented by forming a layered structure with the touch sensor or being integrated with the display unit. Such a touch screen can function as a user input unit that provides an input interface between the device and the user, and at the same time, can provide an output interface between the device and the user.

Additionally, memory stores data that supports various functions of the device. The memory can store multiple application programs (application programs or applications) running on the device, data for device operation, and commands. At least some of these applications may be downloaded from an external server via wireless communication. Additionally, at least some of these applications may be present on the device from the time of shipment for the basic functions of the device (e.g., incoming and outgoing calls, receiving and sending functions). Meanwhile, an application program may be stored in memory, installed on a device, and driven by a control unit to perform an operation (or function) of the device.

In addition to operations related to the application, the control unit typically controls the overall operation of the device. The control unit can provide or process appropriate information or functions to the user by processing signals, data, information, etc. input or output through the components discussed above, or by running an application program stored in memory.

Additionally, the control unit may control at least some of the components examined with FIG. 13 in order to run an application program stored in the memory. Furthermore, the control unit may operate at least two of the components included in the device in combination with each other in order to run the application program.

At least some of the above components may cooperate with each other to implement device operation, control, or control methods according to various embodiments described below. Additionally, the operation, control, or control method of the device may be implemented on the device by running at least one application program stored in the memory.

AI device block diagram

Figure 4 is a block diagram of an AI device to which the method proposed in this specification can be applied.

The AI device 20 may be included in at least a portion of the camera 100 shown in FIG. 1 or 3 and may be equipped to perform at least a portion of AI processing.

The AI device 20 may include an AI processor 21, memory 25, and/or a communication unit 27. If the AI device is included in a camera, the communication unit 27 may be omitted.

The AI device 20 is a computing device capable of learning a neural network and can be implemented in various electronic devices such as servers, desktop PCs, laptop PCs, tablet PCs, etc., and is equipped with the Re-ID model described in FIG. 5. The method proposed in this specification can be performed.

The AI processor 21 can learn a neural network using a program stored in the memory 25. In particular, the AI processor 21 can learn a neural network for recognizing image-related data. Here, a neural network for recognizing image-related data may be designed to simulate the human brain structure on a computer, and may include a plurality of network nodes with weights that simulate neurons of a human neural network. Multiple network modes can exchange data according to each connection relationship to simulate the synaptic activity of neurons sending and receiving signals through synapses. Here, the neural network may include a deep learning model developed from a neural network model. In a deep learning model, multiple network nodes are located in different layers and can exchange data according to convolutional connection relationships. Examples of neural network models include deep neural networks (DNN), convolutional deep neural networks (CNN), Recurrent Boltzmann Machine (RNN), Restricted Boltzmann Machine (RBM), and deep trust. It includes various deep learning techniques such as deep belief networks (DBN) and Deep Q-Network, and can be applied to fields such as computer vision, speech recognition, natural language processing, and voice/signal processing.

Meanwhile, the processor that performs the above-described functions may be a general-purpose processor (e.g., CPU), or may be an AI-specific processor (e.g., GPU) for artificial intelligence learning.

The memory 25 can store various programs and data necessary for the operation of the AI device 20. The memory 25 can be implemented as non-volatile memory, volatile memory, flash-memory, hard disk drive (HDD), or solid state drive (SDD). The memory 25 is accessed by the AI processor 21, and reading/writing/modifying/deleting/updating data by the AI processor 21 can be performed. In addition, the memory 25 uses a neural network model (e.g., deep learning model 26, Re-ID model 28) generated through a learning algorithm for data classification/recognition according to an embodiment of the present invention. You can save it.

Meanwhile, the AI processor 21 may include a data learning unit 22 that learns a neural network for data classification/recognition. The data learning unit 22 can learn standards regarding what learning data to use to determine data classification/recognition and how to classify and recognize data using the learning data. The data learning unit 22 can learn a deep learning model by acquiring learning data to be used for learning and applying the acquired learning data to the deep learning model.

The data learning unit 22 may be manufactured in the form of at least one hardware chip and mounted on the AI device 20. For example, the data learning unit 22 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or may be manufactured as part of a general-purpose processor (CPU) or a graphics processor (GPU) to be used in the AI device 20. It may be mounted. Additionally, the data learning unit 22 may be implemented as a software module. When implemented as a software module (or a program module including instructions), the software module may be stored in a non-transitory computer readable recording medium that can be read by a computer. In this case, at least one software module may be provided by an operating system (OS) or an application.

The data learning unit 22 may include a learning data acquisition unit 23 and a model learning unit 24.

The learning data acquisition unit 23 may acquire learning data required for a neural network model for classifying and recognizing data. For example, the learning data acquisition unit 23 may acquire image data and/or sample data to be input to a neural network model as training data.

The model learning unit 24 can use the acquired training data to train the neural network model to have a judgment standard on how to classify certain data. At this time, the model learning unit 24 can learn a neural network model through supervised learning that uses at least some of the learning data as a judgment standard. Alternatively, the model learning unit 24 can learn a neural network model through unsupervised learning, which discovers a judgment standard by learning on its own using training data without guidance. Additionally, the model learning unit 24 can learn a neural network model through reinforcement learning using feedback on whether the result of the situational judgment based on learning is correct. Additionally, the model learning unit 24 may learn a neural network model using a learning algorithm including error back-propagation or gradient descent.

When the neural network model is learned, the model learning unit 24 may store the learned neural network model in memory. The model learning unit 24 may store the learned neural network model in the memory of a server connected to the AI device 20 through a wired or wireless network.

The data learning unit 22 further includes a learning data preprocessing unit (not shown) and a learning data selection unit (not shown) to improve the analysis results of the recognition model or save the resources or time required for generating the recognition model. You may.

The learning data preprocessor may preprocess the acquired data so that the acquired data can be used for learning to determine the situation. For example, the learning data preprocessor may process the acquired data into a preset format so that the model learning unit 24 can use the acquired learning data for training for image recognition.

Additionally, the learning data selection unit may select data required for learning from among the learning data acquired by the learning data acquisition unit 23 or the learning data pre-processed by the pre-processing unit. The selected learning data may be provided to the model learning unit 24. For example, the learning data selection unit may detect a specific area among images acquired through a camera and select only data about objects included in the specific area as learning data.

Additionally, the data learning unit 22 may further include a model evaluation unit (not shown) to improve the analysis results of the neural network model.

The model evaluation unit inputs evaluation data into the neural network model, and when the analysis result output from the evaluation data does not satisfy a predetermined standard, the model learning unit 22 can perform re-training. In this case, the evaluation data may be predefined data for evaluating the recognition model. As an example, the model evaluation unit may evaluate the evaluation data as not meeting a predetermined standard if the number or ratio of inaccurate evaluation data exceeds a preset threshold among the analysis results of the learned recognition model for the evaluation data. there is.

The communication unit 27 can transmit the results of AI processing by the AI processor 21 to an external device.

The AI device 20 shown in FIG. 4 has been described as functionally divided into the AI processor 21, memory 25, communication unit 27, etc., but the above-mentioned components are integrated into one module and are called AI module. Let me make it clear that it can happen.

Figure 5 is a diagram showing an example of a re-identification method that can be applied to the method proposed in this specification.

With reference to Figure 5, we will look at a method of performing re-identification (hereinafter referred to as 'Re-ID').

Re-ID refers to a method of detecting the same object by comparing features between a target object that was previously found in a different time period, space, or situation and a new object that was newly detected.

First, the AI device acquires raw image data from the camera.

Afterwards, the AI device detects a person from the acquired raw image data and creates a bounding box.

Afterwards, the AI device classifies the bounding box image of the person and trains it in the Re-ID model, one of the learning models.

Afterwards, the AI device performs re-identification to find the person corresponding to the query you want to find in the person data processed as a bounding box through the trained model.

customer care service

CCTV is installed in the hotel lobby and guest room hallways, which are public spaces, for security and safety. However, CCTV footage cannot be used for service purposes due to the Personal Information Protection Act. Therefore, for the guest management service proposed in this specification, rather than using the CCTV video itself, analysis is performed to perform various functions proposed in this specification by combining data analyzed by AI with the video and external (PMS) information. Proceed.

The goal is to visualize the analyzed information and quickly convey the situation to hotel operators to increase customer service responsiveness.

More specifically, the guest management service proposed in this specification classifies and re-identifies each guest through analysis information (gender, age group, shape and clothing characteristics of the guest) that is not included in the Personal Information Protection Act in CCTV footage, and re-identifies ( The same person is assumed to be the same person in multiple camera images through Re-ID.

By comparing the guest assigned room number and number of guests registered in the management system that manages guests for each guest (or guest group), the number of guests entering the room is matched and the type of guest is estimated.

In addition, the guest management service tracks and analyzes the movements of group and individual guests through video analysis installed in public facilities such as the hotel's swimming pool, stores, and restaurants.

In addition, the guest management service transmits the guest type of the room and the movement route information during the stay to the management system after the guest's stay is completed and the guest checks out, specifies the type of guest, and determines the type and time of facility use. Travel preferences by star and type are analyzed, and the analysis results are used for target marketing.

In addition, the guest management service can be expanded from a solution that tracks and analyzes the types and movements of guests within a hotel to the retail area represented by small stores, shopping malls, and department stores.

For example, a customer management system (a system that implements the contents proposed in this specification) tracks each customer's movement from the moment the customer enters the store or shopping mall, and records the customer from the moment the actual customer makes a payment and accumulates mileage. By analyzing specific movement information, stay time in each product area, and companion information, products of high interest to customers can be analyzed in detail to conduct marketing according to customer tastes.

As another example, when a VIP customer's vehicle provided with prior consent arrives at a department store, the customer management system recognizes the VIP's entry, recognizes the customer's special features in the parking lot, and informs the person in charge of entry and movement information in real time to improve customer service. Response speed can be improved.

Figure 6 is a flowchart showing an example of a method for analyzing the type of guest and tracking the guest's movement using the information of the guest scheduled to stay in the guest management system proposed in this specification.

The guest management system is based on at least four groups of cameras installed in different locations within the hotel: (1) analysis of vehicle numbers of guests scheduled to stay, (2) analysis of customers issuing room keys, (3) analysis of guest types, and (4) This can be done through the process of analyzing the movement of a specific guest.

The at least four camera groups include a first group camera installed in the hotel parking lot, a second group camera installed in the hotel lobby, a third group camera installed in the hotel room hallway, and a fourth group camera installed in the common area of the hotel. It can be included.

Each of the first-order camera, the second-order camera, the third-order camera, and the fourth-order camera may include at least one camera, and the at least one camera is learned with the Re-ID model discussed above. It may be an AI camera containing an AI device.

Referring to Figure 6, the cloud server obtains license plate information of vehicles entering (or entering) the hotel parking lot from the first car group camera installed in the hotel parking lot.

And, the cloud server receives information about customers scheduled to stay at the hotel from the hotel management system.

The hotel management system is a device in which a program for hotel management, such as guest management, is implemented as a web or app. It can provide a hotel management program to a user terminal, and may be called a hotel management server, hotel server, second server, etc. You can.

The information on guests scheduled to stay at the hotel includes vehicle license plate information, number of guests, stay date, etc. that the guest scheduled to stay at the hotel inputs when making a hotel reservation through a user terminal.

Thereafter, the cloud server compares the vehicle license plate information (first vehicle license plate information) received from the first vehicle group camera with the vehicle license plate information (second vehicle license plate information) received from the hotel management system.

As a result of the comparison, if the first vehicle license plate information and the second vehicle license plate information are the same or identical, the cloud server transmits mobile check-in notification information so that the scheduled guest can perform mobile check-in.

The mobile check-in notification information may be transmitted to the hotel management system and/or to the user terminal of the guest scheduled to stay.

The guest scheduled to stay can perform mobile check-in for the stay by recognizing the barcode result displayed on the screen of the user terminal with the barcode reader of the card key issuing device installed near the elevator (e.g., next to the elevator).

As a result of performing the mobile check-in, the guest scheduled to stay can receive a card key for the room to be stayed from the card key issuing device, and the hotel management system allows the guest scheduled to stay to stay when the mobile check-in of the guest scheduled to stay is completed. Managed as a guest.

If, as a result of the comparison, the first vehicle license plate information and the second vehicle license plate information are not the same or do not match, the guest scheduled to stay goes directly to the hotel lobby and performs a check-in procedure.

When the guest scheduled to stay performs the check-in procedure for a stay directly in the lobby, the guest scheduled to stay enters the stay information confirmed or received in the lobby into the card key issuing device (e.g. check-in kiosk) to check the room. You will be issued a card key.

Here, the stay information confirmed or received in the lobby may be transmitted to the user terminal of the guest scheduled to stay, and transmitted to the card key issuing device through communication such as NFC or Bluetooth between the user terminal and the card key issuing device. It can be.

In addition, the card key issuing device can transmit the stay information of guests for whom a card key has been issued and check-in has been completed to the hotel management system.

The guest's stay information is information entered into the card key issuing device, and may include information about the guest's room number, check-in time, number of guests, stay period, etc.

Additionally, the hotel management system may transmit the guest's stay information to the cloud server.

Here, the second group camera installed in the lobby of the hotel recognizes the person who received the card key through check-in from the card key issuing device, and captures the recognition-related shooting information and the stay information related to the guest together with the hotel management system. can be transmitted to.

The shooting information may include information about the card key recipient, the guest's companion, etc.

Through this, the hotel management system and/or the cloud server can obtain stay information related to the guest who has been issued a card key.

Next, the third group camera installed in the hotel room hallway detects the type of guest entering or leaving the guest room, and transmits the detected type information of the guest to the cloud server.

The guest type information may include meta information about all guests.

The cloud server analyzes the type of guest through information acquired by the second group camera, information obtained by the third group camera, and guest stay information provided by the hotel management system.

Here, the types of guests can be divided into family, lovers, friends, etc.

Next, the fourth group camera installed in the public space of the hotel captures a specific guest in a public facility within the hotel and transmits information related to the photographed specific guest's movement path, location, travel time, etc. to the cloud server.

The cloud server may analyze the movement route of the specific guest through the movement route-related information of the specific guest and provide the analysis result to the hotel management system.

The specific guests may include hotel VIP guests, infants, guests with disabilities, etc.

The fourth camera group may include a plurality of cameras, and at least one camera may be installed in each of the common spaces of the hotel.

The type information of the guest and the information related to the guest's movement path, which we looked at earlier, can be expressed as the guest's stay history information.

As another example, we will look at a method of directly identifying a customer without a customer identification process through vehicle-specific information such as the vehicle model.

First-tier cameras installed in hotel parking lots or around hotel entrances capture video of the surrounding area.

When a preset vehicle type is detected in the captured image, the first vehicle group camera tracks the vehicle and, when a person (or a customer) gets out of the vehicle, identifies the person as a specific customer without an identification process for the person. To judge or specify.

Here, the first vehicle group camera performs tracking of the vehicle from the time the vehicle is detected until the person exits the vehicle.

And, the first group camera transmits information about the specified or determined specific customer to the cloud server.

Thereafter, if the cloud server checks the information on a specific customer received from the first group camera and determines that the customer is managed by the hotel, the cloud server determines that the customer is a customer managed by the hotel. Mobile check-in notification information indicating that the specific customer can stay in one of the rooms is transmitted.

The mobile check-in notification information may be transmitted to the hotel management system and/or to the user terminal of the specific customer.

The specific customer can perform mobile check-in for their stay by recognizing the barcode result displayed on the screen of the user terminal with the barcode reader of the card key issuing device installed near the elevator (e.g., next to the elevator).

As a result of performing the mobile check-in, the specific customer can receive a card key for the room to be stayed from the card key issuing device, and the hotel management system manages the specific customer as a guest when the mobile check-in of the specific customer is completed. do.

In addition, the card key issuing device can transmit the stay information of a specific customer for whom a card key has been issued and check-in has been completed to the hotel management system.

The specific customer's stay information is information input into the card key issuing device, and may include information about the specific customer's room number, check-in time, number of guests, stay period, etc.

Additionally, the hotel management system may transmit the specific customer's stay information to the cloud server.

Here, the second group camera installed in the lobby of the hotel recognizes the person who received the card key through check-in from the card key issuing device, and records the hotel management together with the shooting information related to the recognition and the stay information related to the specific customer. It can be transmitted to the system.

The shooting information may include information about the card key recipient, companions of a specific customer, etc.

Through this, the hotel management system and/or the cloud server can obtain stay information related to a specific customer to whom a card key has been issued.

Next, the third group camera installed in the hotel room hallway detects the type of specific customer entering or exiting the room, and transmits the detected type information of the specific customer to the cloud server.

The specific customer type information may include meta information about all guests.

The cloud server analyzes the type of a specific customer through information acquired by the second camera, information acquired by the third camera, and stay information about the specific customer provided by the hotel management system.

Here, the specific customer type may be divided into family, lovers, friends, etc.

Next, the fourth group camera installed in the public space of the hotel captures a specific customer in a public facility within the hotel and transmits the captured information about the specific customer's movement path, location, travel time, etc. to the cloud server.

The cloud server may analyze the movement path of the specific customer through the movement path-related information of the specific customer and provide the analysis result to the hotel management system.

The fourth camera group may include a plurality of cameras, and at least one camera may be installed in each of the common spaces of the hotel.

The type information of a specific customer and the information related to the guest's movement path, as discussed earlier, can be expressed as the guest's stay history information.

Next, the previously discussed guest system proposed in this specification includes (1) analysis of vehicle numbers of guests scheduled to stay, (2) analysis of customers issuing room keys, (3) analysis of guest types, and (4) analysis of specific guests. We will look at each step of the movement tracking analysis process in more detail in relation to the operation modes of the first to fourth group cameras.

The guest system supports guest check-in, analyzes guest types, analyzes guest movements, and tracks specific guests through a plurality of cameras, a cloud server, a user terminal hotel management system, and a card key issuing device.

In other words, the guest system receives and analyzes the vehicle number, number of guests, room information, etc. of the guest scheduled to stay from the cloud server and transmits hotel usage information about the guest's stay information, stay history information, etc. to the hotel management system. .

How to assist guests with check-in

Let's look at ways to support guest check-in.

The first group camera is installed in the hotel parking lot, the second group camera is installed in the hotel lobby, the third group camera is installed in the hotel room hallway, and the fourth group camera is installed in the hotel common area, and the first group camera is installed in the hotel common area to support guest check-in. The cameras through the third group cameras operate in an active mode, and the fourth group cameras operate in an inactive mode.

The first to fourth group cameras may operate in an active mode or an inactive mode, and the active mode or inactive mode may be instructed to be a specific mode through a hotel management system or a cloud server, or a specific mode may be set according to a user's input. It can be.

Here, the specific mode represents an active mode or an inactive mode.

First, the cloud server receives information about guests scheduled to stay at the hotel through the hotel management system.

The information of the guest scheduled to stay may be input through the guest's user terminal and transmitted to the hotel management system. The information of the guests scheduled to stay may include the names, gender, phone number, address, period of stay, number of people staying, room information, whether meals are included, payment-related information, whether the vehicle is parked, vehicle license plate information, etc. there is.

In addition, the first car group camera photographs a vehicle entering the hotel parking lot and transmits license plate information of the photographed vehicle to the cloud server.

In addition, the cloud server compares the vehicle license plate information among the information on the scheduled guest with the vehicle license plate information received from the first vehicle group camera.

As a result of the comparison, if the license plate information of the vehicle is the same or matches, the cloud server sends a notification to the hotel management system to the hotel management system about the guest scheduled to stay and makes a reservation, and the hotel management system A mobile check-in notification is sent to the user terminal of the guest scheduled to stay. In this case, the guest scheduled to stay performs mobile check-in through the user terminal, and when mobile check-in is completed, the hotel management system changes the reservation person to a guest and transmits the changed information to the cloud server.

As a result of the comparison, if the license plate information of the vehicle is not the same or does not match, the cloud server classifies the scheduled guest as unregistered and sends a notification to the hotel management system to check in directly at the lobby instead of mobile check-in. send to

If the scheduled guest classified as an unregistered person checks in directly at the hotel lobby, the hotel management system changes the scheduled guest from an unregistered person to a guest.

And, if the scheduled guest who received the notification about the mobile check-in does not perform the mobile check-in for a certain period of time through the user terminal, the hotel management system transmits an alarm about the mobile check-in again to the user terminal.

Here, when a guest scheduled to stay who is classified as an unregistered guest checks in at the hotel lobby and becomes a guest, the second group camera installed in the hotel lobby collects Re-ID information about the guest.

Re-ID information about the guest includes information about the image of the guest matching the guest among the images collected through the second group camera.

In addition, the cloud server receives information about guests who are classified as unregistered and checked in at the hotel lobby (number of guests, guest room information), etc. from the hotel management system.

In addition, the 3rd group cameras installed in the hallways of hotel rooms are categorized as reservation holders, perform mobile check-in, and collect Re-ID information about guests entering the room.

Whether the guest who checked in through the mobile device entered the room directly without going through another location can be determined by whether or not the photos were taken by both the second group camera and the third group camera within a predetermined time.

In addition, the third group camera checks the guest's Re-ID information and the number of guests and transmits them to the cloud server.

The third group camera collects Re-ID information for all people entering the guest room and transmits it to the cloud server.

Here, when the number of guests registered in the hotel management system and the number of guests information received by the third group camera are the same, the cloud server determines that the guest has completed entering the hotel room, and the hotel management The system processes the above-mentioned guest as completion of check-in.

How to analyze guest types

Next, we look at how to analyze the types of guests.

Likewise, the first group cameras are installed in the hotel parking lot, the second group cameras are installed in the hotel lobby, the third group cameras are installed in the hotel room hallway, and the fourth group cameras are installed in the common areas of the hotel. For the analysis of the guest types, the above The first group cameras, the second group cameras and the fourth group cameras operate in an inactive mode, and the third group cameras operate in an active mode.

First, the cloud server receives information about the number of guests and room information (room number, etc.) for each room on the guest room floor where the third group camera is installed from the hotel management system.

In addition, the cloud server receives gender information and age information related to the number of guests entering and leaving each room from the third group camera and analyzes it.

In addition, the cloud server filters duplicate people through Re-ID information about the number of room guests.

Then, the cloud server compares the number of people in the room registered in the hotel management system with the number of people of the same gender and age group.

If the comparison results are identical or identical, the cloud server analyzes the type of guest based on the number of people in the guest room.

Here, the third group camera classifies all people entering the guest room by Re-ID and analyzes the gender and age group of the guests.

Here, the cloud server waits until the number of people being compared becomes the same and then analyzes the type of guest based on the information obtained when the number of people becomes the same.

The types of guests can be divided into family, lovers, friends, etc.

Guest movement analysis method

Next, we will look at how to analyze guests’ movements.

Similarly, the first group cameras are installed in the hotel parking lot, the second group cameras are installed in the hotel lobby, the third group cameras are installed in the hotel room hallway, and the fourth group cameras are installed in the common areas of the hotel. For the analysis of the guest movement, the above cameras are installed. The first-order cameras and the second-order cameras operate in an inactive mode, and the third-order cameras and the fourth-order cameras operate in an active mode. When a lobby is included in the common space, the second group camera may be included in the fourth group camera and operated in an active mode.

First, the third group camera collects Re-ID information of people leaving the guest room and transmits it to the cloud server.

The cloud server selects a guest who leaves the room, and analyzes the movement path of the selected guest through images acquired by the third group camera and the fourth group camera.

When analyzing the guest's movement path, the cloud server excludes guests staying in the guest room from the comparative group for analysis and confirms the guest's entry and exit from the guest room where multiple people are staying.

The cloud server estimates the most similar person among the total number of people staying in the room using the person's Re-ID information, and includes the estimated person in the comparison target group.

And, the cloud server maintains the remaining people in the room as a group to be compared.

Additionally, in order to analyze the guest's movement path, the cloud server compares guests recognized in common areas of the hotel, such as restaurants, coffee shops, and conference rooms, with a comparison group and estimates them as previously selected guests.

Here, when a guest is detected or discovered in a space that is not accessible to people other than the public space, the cloud server sends an alarm to the hotel management system and/or the user terminal notifying that a person has entered the inaccessible space. do.

In addition, the cloud server records and stores the moving location, moving time, staying location, and staying time of the guest in the common space for tracking movement through the image information acquired through the fourth group camera.

The cloud server excludes a guest from the comparison group when the guest is using the facilities in the public space, and includes the guest back in the comparison group when it discovers or detects the guest using the facilities in the public space and going outside, such as a hallway.

Here, the fourth group camera collects Re-ID information of people in the public space in the hotel.

Here, the second-order camera may be included in the fourth-order camera.

How to track specific customers

Next, we'll look at how to track specific customers (or specific guests).

Similarly, the first group cameras are installed in the hotel parking lot, the second group cameras are installed in the hotel lobby, the third group cameras are installed in the hotel room hallway, and the fourth group cameras are installed in the common areas of the hotel. In order to track the specific customer, The first-order cameras and the second-order cameras operate in an inactive mode, and the third-order cameras and the fourth-order cameras operate in an active mode. When a lobby is included in the common space, the second group camera may be included in the fourth group camera and operated in an active mode.

The cloud server separately stores and manages intensive care customers (e.g. VIP customers, customers with disabilities, infants, etc.).

Here, the information about the intensive management customer may be received through the hotel management system and may be set in the cloud server at a specific time (eg, night).

In order to track specific customers, such as the intensive management customers, the cloud server excludes customers staying in the room from the comparison group and checks the guest's entry and exit from rooms where multiple people are staying.

The cloud server estimates the most similar person among the total number of people staying in the room using the person's Re-ID information, and includes the estimated person in the comparison target group.

The cloud server determines whether the estimated person is the same as the intensive management customer, that is, a specific customer, and if determined to be the same, notifies the hotel management system that the specific customer has been detected.

And, the cloud server maintains the remaining people in the room as a group to be compared.

Additionally, in order to track the specific customer, the cloud server compares guests recognized in public spaces such as restaurants, coffee shops, and conference rooms with comparison groups and estimates them as specific customers.

Here, when a specific customer is detected in a space where people are not allowed to enter other than the public space, the cloud server sends an alarm to notify the hotel management system and/or the user terminal that the specific customer has entered the inaccessible space. transmit.

In addition, the cloud server records and stores the moving location, moving time, staying location, and staying time of a specific customer within the public space through information acquired through the fourth group camera.

The cloud server excludes a specific customer from the comparison group if he or she is using facilities in a public space, and includes him/her back in the comparison group if it discovers or detects that a specific customer is using facilities in a public space and coming outside, such as in a hallway.

In addition, the hotel management system can send a dedicated page to check the location of a specific customer who is an intensive management customer in real time and an alarm to notify the customer in real time.

The fourth group camera collects Re-ID information of people in the public space of the hotel.

Here, the second-order camera may be included in the fourth-order camera.

Figure 7 is a flowchart showing an example of a method for managing guests proposed in this specification.

That is, Figure 7 shows an example of a method of operating a server to monitor a guest's usage status through at least one camera.

First, the server performs check-in for guests scheduled to stay based on the vehicle license plate information obtained by the first camera (S710).

The step of performing the check-in includes comparing the license plate information of the vehicle obtained by the first camera with the license plate information of the vehicle pre-registered in the management system, and providing mobile check-in to the scheduled guest based on the comparison result. It may include providing or providing to perform check-in directly in the lobby.

In addition, the server confirms the type of guest entering the room through guest information of the guest obtained by the second camera and re-identification (Re-ID) of the guest obtained by the third camera based on the guest information. Do it (S720).

And, the server identifies the specific guest through re-identification of the specific guest obtained by the fourth camera based on the video information of the specific guest coming from the room obtained by the third camera and the video information of the specific guest. Track the movement line (S730).

The first camera may be installed in the hotel's parking lot, the second camera may be installed in the hotel's lobby, the third camera may be installed in the hotel's guest room hallway, and the fourth camera may be installed in the hotel's common space. there is.

Additionally, the server may analyze the confirmed guest type and the tracked movement path of the specific guest, and generate the guest's stay history information based on the analysis results.

Here, the guest scheduled to stay is a guest who has made a reservation through a management system that manages guests in advance, and the guest may be a guest who has completed check-in for the room.

In addition, the guest information includes information on the number of guests staying in the room and the number of the room, and the information on the number of guests includes the number of guests staying in the room and the number of guests staying in the room. May include video information.

The type of guest may include at least one of the relationship between the guests staying in the room, the gender of the guests, or the age group of the guests.

The relationship between the guests may be one of friends, family, or lovers.

The type of guest can be confirmed when the number of people staying in the room included in the guest information is the same as the number of people staying in the room obtained by the third camera.

Below, we will look in more detail at the method of tracking the movement of a specific guest in step S730.

The server checks whether the specific guest exists in the first image acquired by the third camera.

And, the server checks whether the specific guest exists in the second image obtained by the fourth camera.

And, the server determines the location of the specific guest based on whether the specific guest exists in the second image.

The location may be a handover area representing a room entrance or an area connected to another space.

And, the server updates the location information of the specific guest based on the determined location and performs tracking for the specific guest.

If the specific guest exists in the first video and the specific guest does not exist in the second video, the server checks whether the specific guest is located at the room entrance through the first video.

And, when the specific guest is located at the room entrance, the server determines that the specific guest has entered the room.

If the specific guest is not located at the room entrance, the server checks whether the guest is located in the handover area.

Additionally, the server searches for a person related to the specific guest in a space connected to the handover area, and compares the specific guest with the searched person through a re-identification (Re-ID) algorithm.

As a result of the comparison, if the specific guest and the searched person are the same or similar, the server maps the searched person to the specific guest.

Alternatively, as a result of the comparison, if the specific guest and the searched person are not the same or similar, the server determines that tracking for the specific guest has failed.

If the specific guest does not exist in the first video and the specific guest does exist in the second video, the server checks whether the specific guest is located at the room entrance through the second video.

If the specific guest is located at the room entrance, the server determines that the specific guest has left the room.

If the specific guest is not located at the room entrance, the server checks whether the guest is located in the handover area.

If the specific guest is located in the handover area, the server determines that the specific guest has moved to a space connected to the handover area.

Next, we will look at how to track people in a specific place through a camera from the perspective of camera operation.

Figure 8 is a flowchart showing an example of a tracking method applicable to the method proposed in this specification.

First, a camera (or camera group) installed at a specific location captures a video (or image).

The camera or its detector checks the captured image and determines whether a person exists within the camera's field of view (S810).

As a result of the above determination, (1) if a person exists, step S820 below is performed, and (2) if a person does not exist, step S830 below is performed.

The specific steps of S820 will be described with reference to FIG. 8A, and the specific steps of S830 will be described with reference to FIG. 8B. That is, FIG. 8A shows a procedure when a person exists in a captured image, and FIG. 8B shows a procedure when a person does not exist in a captured image.

Hereinafter, in order to avoid unclear meaning due to use of the same term, the person in step S810 will be expressed as the first person. In addition, the procedure performed when a person is present in step S810 will be described with reference to FIG. 8A, and the procedure performed when a person is not present in step S810 will be described with reference to FIG. 8b.

First, let's look at step S820, which is performed when a person is present in step S810.

If it is determined that the first person exists in step S810, the camera checks the previously captured image (or the state of the previous captured image or previous screen) (S821).

The camera checks whether the first person is within the camera's field of view in step S821 (S822).

If the first person is present in step S822, the camera or a tracker of the camera tracks the first person and updates information related to the location of the first person (S822-1).

If the first person is not present in step S822, the camera checks whether the first person is located at the entrance (S822-2).

In step S822-2, when the first person is located at the entrance, the camera determines the first person as a new person, updates information related to the location of the first person, and tracks the first person. (S822-3).

If the first person is not located at the entrance in step S822-2, the camera checks whether the first person is located in the handover area (S823).

The handover area (or space) represents an area where one space is connected to another space and is included within the space, and the handover connects the two spaces.

If the first person is located in the handover area in step S823, the camera searches for (or searches for) the second person from the connected area (S823-1).

At this time, the camera evaluates the second person using a re-identification (Re-id) algorithm, and if the evaluation result is good, maps the second person to the first person and operates the tracker to track the second person. Tracking is performed (S823-2).

If the first person is not located in the handover area in step S823, the camera records and stores an error situation (S823-3).

Then, the camera compares a person (a third person) that was recently missed in the associated space with the first person using a re-identification algorithm.

In step S824, it is checked whether the first person and the missed person (the third person) are similar (S824).

In step S824, if the first person and the third person are similar, the camera maps the third person to the first person with low accuracy (S824-1).

In step S824, if the first person and the third person are not similar, the camera determines (or identifies) the first person as the missing person, and updates information related to the location of the first person. Perform tracking (S824-2).

Next, we will look at the case where the first person does not exist in step S810.

In step S810, if the first person does not exist, the camera checks the previously captured image (or the state of the previous screen) (S831).

The camera checks whether the first person was within the camera's field of view in step S831 (S832).

If the first person is present in step S832, the camera checks whether the first person is located in the entrance area (S832-1).

If the first person is located in the entrance area in step S832-1, the camera determines that the first person is a person who has left the place (S832-2).

If the first person is not located in the entrance area in step S832-1, the camera checks whether the first person is located in the handover area (S833).

If the first person is located in the handover area in step S833, the camera determines that the first person is a person who has moved to the associated space, and updates information related to the location of the person who has moved (S833-1 ).

If the first person is not located in the handover area in step S833-1, the camera records and stores an error situation, tags the first person as a missed person, and determines that the first person is a person who has left the location (S833 -2).

Hereinafter, the terms used in this specification are briefly defined and organized as follows.

First, location indicates the person's location and serves as the standard by which the DB is divided.

A gate represents a terminal of a closed system.

Space generally divides the area visible to the camera into space, and the area not visible to the camera is allocated as a shaded space. If shadow space is not allocated, camera tracking cannot be supported.

A handover represents an area where a space is connected to another space, is contained within a space, and a handover connects two spaces.

Invisible space refers to a place that is connected to space but cannot be seen because there is no camera.

A stair is a connecting space connected to stairs, elevators, etc., can connect different floors, and is a place where people can stay for a longer period of time than a typical invisible space.

The camera is an image sensor, and simple information (Mac, IP address, etc.) is set about where it is installed in space.

An area is a closed system and is an independent space that does not allow handover in different areas and cannot support tracking. Inside this area, occupancy can be obtained and tracking occurs.

The entrance is a state in which a new person is created in the entering space. It is limited to the case where the newly created person leaves the entering space and moves to the general area and moves to the critical area. In this case, a new person is produced.

An exit occurs when a person moves from the critical area to an exit space and then disappears from the space. In this case, the existing person is considered to have exited.

Handover can be set as incoming space or outgoing space.

The handover space consists of four points, and it needs to be wide enough to be captured by the camera at least once even if a person moves quickly.

In the same scenario as the entry/exit space, the search for a new person who entered through a handover is limited to those with whom a collision occurred among those who left through a connected handover.

It is also possible to set up a handover without a connection. The space can be moved to the invisible area through an invisible handover, or can be entered into the space through a handover from the invisible area.

A space that can be moved through the invisible handover has a separate space ID, and all people who enter this space can be used as candidates.

Alternatively, the camera can set priorities based on time to find people in another handover or an existing handover.

A missed person is a person who disappears from the general space during camera tracking, or a person who was not tracked suddenly appears in the general space.

Figure 9 is a flowchart showing an example of a method for tracking a person using a camera proposed in this specification.

Here, the camera may be installed in at least one of a hotel parking lot, a hotel entrance, a hotel lobby, or a hallway on each floor of the hotel, and the person may be a hotel guest, but is not limited to this and the tracking method of FIG. 9 is the same in other places. can be performed.

First, the camera captures the first image (S910).

Then, the camera checks whether the first person who will perform the tracking exists in the first image (S920).

Then, the camera checks the second image corresponding to the previous image of the first image (S930).

Then, the camera checks whether the first person exists in the second image (S940).

Then, the camera determines the location of the first person based on whether the first person exists in the second image (S950).

The location may be a handover area representing an entrance or exit area of a specific location or an area connected to another space.

Then, the camera determines the first person as the second person based on the determined location (S960).

The second person may be a new person who entered a specific place, a person who left a specific place, a person who moved to another space, or a person who was missed while tracking.

Then, the camera updates the determined location information of the second person and performs tracking of the second person (S970).

When the first person exists in the first image and the first person does not exist in the second image, the camera determines whether the first person is located at the entrance through the first image.

If the first person is located at the entrance, the camera may determine the first person to be the new person.

If the first person is not located at the entrance, the camera checks whether it is located in the handover area.

When the first person is located in the handover area, the camera searches for the second person in a space connected to the handover area, and identifies the first person through a re-identification (Re-ID) algorithm. The second person is mapped, and tracking is performed for the first person.

And, when the first person is not located in the handover area, the camera searches for a third person related to the first person in a space connected to the handover area.

If the first person and the third person are the same or similar, the camera maps the third person to the first person.

Alternatively, if the first person and the third person are not the same or similar, the camera determines that the first person is the missed person.

If the first person does not exist in the first image and the first person does exist in the second image, the camera determines whether the first person is located at the entrance through the second image.

If the first person is located at the entrance, the camera may determine the first person to be the person who exited.

If the first person is not located at the entrance, the camera checks whether it is located in the handover area.

If the first person is located in the handover area, the camera may determine the first person as a person who has moved to a space connected to the handover area.

Additionally, the camera may transmit information related to the second person's tracking performance to the server.

The embodiments described above combine the components and features of the present invention in a predetermined form. Each component or feature should be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. Additionally, it is possible to configure an embodiment of the present invention by combining some components and/or features. The order of operations described in embodiments of the present invention may be changed. Some features or features of one embodiment may be included in other embodiments or may be replaced with corresponding features or features of other embodiments. It is obvious that claims that do not have an explicit reference relationship in the patent claims can be combined to form an embodiment or included as a new claim through amendment after filing.

Embodiments according to the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of implementation by hardware, an embodiment of the present invention includes one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and FPGAs ( It can be implemented by field programmable gate arrays, processors, controllers, microcontrollers, microprocessors, etc.

In the case of implementation by firmware or software, an embodiment of the present invention may be implemented in the form of a module, procedure, function, etc. that performs the functions or operations described above. Software code can be stored in memory and run by a processor. The memory is located inside or outside the processor and can exchange data with the processor through various known means.

It is obvious to those skilled in the art that the present invention can be embodied in other specific forms without departing from the essential features of the present invention. Accordingly, the above detailed description should not be construed as restrictive in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

The method of monitoring the usage status of guests using the camera of the present invention has been explained focusing on the example of application to CCTV, but it can be applied to various other video systems.

Claims (37)

1. In a method for monitoring the guest usage status through at least one camera,

   Performing check-in for guests scheduled to stay based on vehicle license plate information obtained by the first camera;

   Confirming the type of guest entering the room through guest information acquired by a second camera and re-identification (Re-ID) of the guest obtained by a third camera based on the guest information; and

   Tracking the movement of the specific guest through re-identification of the specific guest obtained by the fourth camera based on the video information of the specific guest coming from the room obtained by the third camera and the video information of the specific guest A method comprising:
2. According to claim 1,

   Analyzing the confirmed type of guest and the tracked movement path of the specific guest; and

   The method further comprising generating stay history information of the guest based on the analysis results.
3. According to claim 1,

   The above-mentioned guests are those who have reserved their stay through a management system that manages guests in advance.

   A method characterized in that the guest is a customer who has completed check-in for the room.
4. According to claim 1,

   The guest information includes information about the number of guests staying in the room and the number of the room,

   A method wherein the information on the number of guests includes the number of guests staying in the room and video information of the number of guests staying in the room.
5. According to claim 1,

   The method characterized in that the type of guest includes at least one of the relationship between the guests staying in the room, the gender of the guest, or the age of the guest.
6. According to claim 5,

   A method wherein the relationship between the guests is one of friends, family, or lovers.
7. According to clause 6,

   A method characterized in that the type of guest is confirmed when the number of people staying in the room included in the guest information is the same as the number of people staying in the room obtained by the third camera.
8. The method of claim 3, wherein performing the check-in comprises:

   Comparing vehicle license plate information obtained by the first camera with vehicle license plate information pre-registered in the management system;

   A method comprising providing mobile check-in to the scheduled guest or providing the guest to perform direct check-in in a lobby based on the comparison result.
9. According to claim 1,

   The first camera is installed in the hotel's parking lot, the second camera is installed in the hotel's lobby, the third camera is installed in the hotel's guest room hallway, and the fourth camera is installed in the hotel's common space. How to feature.
10. The method of claim 1, wherein the step of tracking the movement of a specific guest includes:

    confirming whether the specific guest exists in the first image acquired by the third camera;

    confirming whether the specific guest exists in a second image acquired by the fourth camera;

    determining a location of the specific guest based on the presence or absence of the specific guest in the second image; and

    and updating location information of the specific guest based on the determined location location.
11. According to claim 10,

    The method is characterized in that the location is a handover area representing a room entrance or an area connected to another space.
12. According to claim 11,

    When the specific guest is present in the first image and the specific guest is not present in the second image, the method further includes checking whether the specific guest is located at the room entrance through the first image. How to.
13. According to claim 12,

    A method characterized in that, when the specific guest is located at the entrance of the room, it is determined that the specific guest has entered the guest room.
14. According to claim 12,

    If the specific guest is not located at the room entrance, the method further comprises checking whether the specific guest is located in the handover area.
15. According to claim 14,

    Searching for a person related to the specific guest in a space connected to the handover area; and

    The method further comprising comparing the specific guest and the searched person through a re-identification (Re-ID) algorithm.
16. According to claim 15,

    When the specific guest and the searched person are the same or similar, the method comprising mapping the searched person to the specific guest.
17. According to claim 15,

    When the specific guest and the searched person are not the same or similar, determining that tracking of the specific guest has failed.
18. According to claim 10,

    When the specific guest does not exist in the first video and the specific guest does exist in the second video, the method further includes checking whether the specific guest is located at the room entrance through the second video. How to do it.
19. According to clause 18,

    A method characterized in that, when the specific guest is located at the room entrance, it is determined that the specific guest has left the room.
20. According to clause 18,

    If the specific guest is not located at the room entrance, the method further comprises checking whether the specific guest is located in the handover area.
21. According to claim 20,

    A method characterized in that, when the specific guest is located in the handover area, it is determined that the specific guest has moved to a space connected to the handover area.
22. In the server for monitoring the usage status of guests through at least one camera,

    A wireless communication unit for transmitting and receiving wireless signals;

    Memory; and

    A control unit functionally connected to the wireless communication unit and the memory, wherein the control unit includes,

    Perform check-in for guests scheduled to stay based on vehicle license plate information obtained by the first camera;

    Confirming the type of guest entering the room through guest information obtained by a second camera and re-identification (Re-ID) of the guest obtained by a third camera based on the guest information; and

    Control to track the movement of the specific guest through re-identification of the specific guest obtained by the fourth camera based on the video information of the specific guest from the room obtained by the third camera and the video information of the specific guest A server characterized in that.
23. In a method of tracking a person using a camera,

    Taking a first image;

    checking whether a first person to perform the tracking exists in the first image;

    confirming a second image corresponding to a previous image of the first image;

    confirming whether the first person exists in the second image;

    determining a location of the first person based on whether the first person exists in the second image;

    determining the first person as a second person based on the determined location location; and

    A method comprising updating the determined location information of the second person and performing tracking on the second person.
24. According to clause 23,

    The method is characterized in that the location is a handover area representing an entrance or exit of a specific location or an area connected to another space.
25. According to clause 24,

    A method characterized in that the second person is a new person who entered a specific place, a person who left a specific place, a person who moved to another space, or a person who was missed while tracking.
26. According to claim 25,

    When the first person exists in the first image and the first person does not exist in the second image, the step of confirming whether the first person is located at the entrance through the first image. How to feature.
27. According to clause 26,

    When the first person is located at the entrance, the method is characterized in that determining the first person as the new person.
28. According to clause 26,

    If the first person is not located at the entrance, the method further comprises checking whether the first person is located in the handover area.
29. According to clause 28,

    searching for a third person related to the first person in a space connected to the handover area; and

    The method further comprising comparing the first person and the third person through a re-identification (Re-ID) algorithm.
30. According to clause 29,

    If the first person and the third person are the same or similar, the method comprising mapping the third person to the first person.
31. According to clause 29,

    If the first person and the third person are not the same or similar, the first person is determined to be the second person,

    wherein the second person is the missed person.
32. According to claim 25,

    When the first person does not exist in the first image and the first person exists in the second image, it further includes checking whether the first person is located at the entrance through the second image. A method characterized by:
33. According to clause 32,

    When the first person is located at the entrance, the method is characterized in that determining the first person as the person who exited.
34. According to clause 32,

    If the first person is not located at the entrance, the method further comprises checking whether the first person is located in the handover area.
35. According to clause 34,

    When the first person is located in the handover area, the method is characterized in that determining the first person as a person who has moved to a space connected to the handover area.
36. According to clause 23,

    The method further comprising transmitting information related to the second person's tracking performance to a server.
37. According to clause 23,

    The camera is installed in at least one of a hotel parking lot, a hotel entrance, a hotel lobby, or a hallway on each floor of the hotel,

    A method, characterized in that the person is a guest of the hotel.

Images