Method and system for automating space use and management

Abstract

A system for automating space use and management may comprise a memory for storing instructions and a processor. The instructions, when executed by the processor, may control the system to: perform automatic environment control to control operations related to lighting, air conditioners / heaters, music, diffusers, and automatic environments according to a set time, event, and temperature; automate security management to monitor unauthorized access to a space in real time and provide a notification; automate door opening and closing; automate facility safety management to monitor issues, such as water leakage and fire, in real time and provide a notification; recognize and display a current occupancy status within the space; and automatically recognize a facility state within the space to display unavailability of the space when a malfunction occurs or cleaning is required and to automatically contact a repair or cleaning service provider.

Description

Method and system for automating the use and management of space

[0001] The present invention relates to a space management system that provides functions such as automatic environmental control of a space, automated security management, automated facility safety management, indoor occupancy status identification, and automated user reservation / management to enhance user convenience and space utilization.

[0002] Recently, with the advancement of artificial intelligence technology, it is being utilized in various fields. In particular, in the field of space management, various attempts are being made to utilize AI technology to improve space efficiency and user convenience. For example, systems are being developed to automatically control temperature, humidity, and lighting within a space, to enhance security within a space, and to monitor safety within a space.

[0003] With the recent increase in the use of smart spaces, there's a growing demand for technologies that enhance space management efficiency and user convenience. Existing space management systems require direct human intervention, leading to high management costs and poor user experience. Furthermore, they struggle to respond quickly to intrusions or facility issues that threaten the safety of the space.

[0004] Existing space management systems required users to make reservations in person or by phone, and were inherently inconvenient because they had to manually manage environmental control, security, and facility management. Furthermore, it was difficult to monitor the number of people in a space or detect equipment failures, hindering efficient space management.

[0005] The purpose of the present invention is to develop a space management system utilizing artificial intelligence technology, thereby enhancing efficient space management and user convenience. Furthermore, the present invention aims to address the problems of existing space management systems by providing a smart space automated management system that utilizes automation and artificial intelligence technologies to maximize user convenience and enhance operational efficiency.

[0006] A system for automating the use and management of a space may include a memory and a processor storing instructions. The instructions, when executed by the processor, may cause the system to perform automatic environmental control, controlling lighting, air conditioning, music, diffusers, and other operations related to the automatic environment according to set times, events, and temperatures; automate security management, monitoring and providing notifications for unauthorized entry into the space in real time; automate door opening and closing; automate facility safety management, monitoring and providing notifications for problems such as water leaks and fires in real time; recognizing and displaying the number of occupants in the space; automatically recognizing the status of equipment in the space; indicating that the space is unusable in the event of a breakdown or cleaning need, and automatically contacting a repair or cleaning company.

[0007] The server analyzes data collected from various sensors within the space to perform functions such as automatic environmental control, automated security management, automated facility safety management, occupancy status monitoring, reservation management, equipment status monitoring, and automated maintenance. The sensors detect temperature, humidity, lighting, entry / exit, and fire within the space. The application allows users to reserve spaces and check their status. The door lock controls user access and automatically changes passwords.

[0008] The space management system of the present invention can significantly enhance user convenience and space utilization. Users can make real-time reservations through the app without having to visit in person or make a phone call. It automatically controls the environment, security, and safety within the space, enabling efficient space operation. Furthermore, features such as automatic equipment status recognition and advance noise detection enable a more comfortable and safe space experience.

[0009] Automatic environmental control allows users to set the temperature, humidity, lighting, etc. within the space to their liking, allowing them to work in a comfortable environment.

[0010] Security management automation features enhance security by monitoring unauthorized entry and exit within a space in real time and notifying users of these events. Facility safety management automation features also ensure safety by monitoring issues like water leaks and fires in real time and notifying users of these events.

[0011] The occupancy tracking feature allows users to check who is in their space in real time, enabling efficient space management. The reservation management feature allows users to view space usage and make real-time reservations directly from the app, without having to visit the business or call in person.

[0012] Equipment status monitoring and automated maintenance features automatically recognize the condition of equipment within a space. If a malfunction or cleaning is required, an AI learning model identifies the space, flags it as unusable, and automatically contacts a repair or cleaning service for prompt response. Upon completion of use, the door lock password is automatically changed and displayed to the administrator, enhancing security.

[0013] FIG. 1 is a drawing for explaining a system for automating the use and management of space according to one embodiment.

[0014] Figure 2 is a block diagram illustrating the configuration of a system for automating the use and management of space according to one embodiment.

[0015] FIG. 3 is a flowchart illustrating a method for automating the use and management of space according to one embodiment.

[0016]

[0017] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, the embodiments may be modified in various ways, and the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, or alternatives to the embodiments are included within the scope of the patent application.

[0018] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of this specification includes modifications, equivalents, or alternatives that fall within the technical concept.

[0019]

[0020] FIG. 1 is a drawing for explaining a system for automating the use and management of space according to one embodiment.

[0021] As illustrated in FIG. 1, a system (100) for automating the use and management of space may include a plurality of user terminals (110-1,...), a server (120), and a database (130). In one embodiment, the database (130) is illustrated as being configured separately from the server (120), but is not limited thereto, and the database (130) may be provided within the server (120). For example, the server (120) may include a plurality of artificial intelligences for performing machine learning algorithms.

[0022] A plurality of user terminals (110-1,...), a server (120), and a database (130) can be connected to each other to communicate with each other through a network (N). The network (N) can perform wireless or wired communication among a plurality of user terminals (110-1,...), a server (120), a database (130), etc. For example, the network can perform wireless communication according to a method such as LTE (long-term evolution), LTE-A (LTE Advanced), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless BroadBand), WiFi (wireless fidelity), Bluetooth (Bluetooth), NFC (near field communication), GPS (Global Positioning System), or GNSS (global navigation satellite system). For example, the network (N) may be configured to perform wired communication according to a method such as universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), or plain old telephone service (POTS).

[0023] The database (130) can store various data. The data stored in the database (130) is data acquired, processed, or used by at least one component of a plurality of user terminals (110-1,...) and a server (120), and may include software (e.g., a program). The database (130) may include volatile and / or non-volatile memory.

[0024] In the present invention, artificial intelligence (AI, artificial intelligence learning model) refers to a technology that mimics human learning, reasoning, and perception abilities and implements them through computers, and may include concepts such as machine learning and symbolic logic. Machine learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. AI technology analyzes input data using machine learning algorithms, learns the analysis results, and makes judgments or predictions based on the learned results. Furthermore, technologies that utilize machine learning algorithms to mimic the cognitive, judgmental, and other functions of the human brain may also be included in the category of artificial intelligence.

[0025] Machine learning can refer to the process of training a neural network model using data processing experience. Machine learning allows computer software to improve its data processing capabilities. Neural network models are built by modeling correlations between data, and these correlations can be expressed by multiple parameters. A neural network model extracts and analyzes features from given data to derive correlations between the data. Machine learning is the process of optimizing the parameters of a neural network model by repeating this process. For example, a neural network model can learn the mapping (correlation) between inputs and outputs for data given as input-output pairs.

[0026] An artificial intelligence learning model or neural network model can be designed to implement the structure of the human brain on a computer, and can include a plurality of network nodes that simulate the neurons of a human neural network and have weights. The plurality of network nodes can have connections among themselves by simulating the synaptic activity of neurons that exchange signals through synapses. In the artificial intelligence learning model, the plurality of network nodes can be located at layers of different depths and exchange data according to convolutional connections. The artificial intelligence learning model can be, for example, an artificial neural network model, a convolutional neural network (CNN), etc. In one embodiment, the artificial intelligence learning model can be machine-learned according to a method such as supervised learning, unsupervised learning, or reinforcement learning. Machine learning algorithms that can be used to perform machine learning include decision trees, Bayesian networks, support vector machines, artificial neural networks, Ada-boost, perceptrons, genetic programming, and clustering.

[0027] CNNs are a type of multilayer perceptron (MLP) designed to require minimal preprocessing. They consist of one or more convolutional layers stacked on top of regular artificial neural network layers, with additional weight and pooling layers. This architecture allows CNNs to fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs demonstrate excellent performance in both image and audio domains. CNNs can also be trained using standard backpropagation. Compared to other feedforward neural network techniques, CNNs are easier to train and have fewer parameters.

[0028] Convolutional networks are neural networks that contain sets of nodes with bounded parameters. The increasing availability of training data and computational power, combined with advances in algorithms such as piecewise linear units and dropout training, have led to significant improvements in many computer vision tasks. With massive datasets, such as those used in many tasks, overfitting is less of a concern, and increasing network size can improve test accuracy.

[0029] Artificial Intelligence (AI) systems are computer systems that mimic human-level intelligence. Unlike existing rule-based smart systems, they are systems in which machines learn and make decisions on their own. As AI systems are used, their recognition rates improve and they can understand users' preferences more accurately. As a result, existing rule-based smart systems are gradually being replaced by AI systems based on deep learning. AI technology consists of machine learning and component technologies that utilize machine learning. Machine learning is an algorithmic technology that classifies and learns the characteristics of input data on its own. Component technologies utilize machine learning algorithms such as deep learning to mimic the cognitive and judgment functions of the human brain. They consist of technical fields such as linguistic understanding, visual understanding, inference / prediction, knowledge representation, and motion control.

[0030] Typically, applying machine learning algorithms to real-world applications requires a trial-and-error approach, due to the fundamental nature of machine learning methodology. Deep learning, in particular, requires hundreds of thousands of iterations. Because this is impossible to implement in an actual physical environment, learning is performed through simulations, where the actual environment is virtually implemented on a computer.

[0031] In the present invention, artificial intelligence (AI) refers to a technology that mimics human learning, reasoning, and perception abilities and implements them on a computer. It may include concepts such as machine learning and symbolic logic. Machine learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. AI technology analyzes input data using machine learning algorithms, learns the results of the analysis, and makes judgments or predictions based on the learned results. Furthermore, technologies that utilize machine learning algorithms to mimic the cognitive and judgment functions of the human brain can also be understood as falling under the category of AI. For example, this may include technical fields such as linguistic understanding, visual understanding, inference / prediction, knowledge representation, and motion control. Machine learning can refer to the process of training a neural network model using data processing experience. Through machine learning, computer software can improve its data processing capabilities on its own.

[0032] Machine learning can refer to the process of training a neural network model using data processing experience. Through machine learning, computer software can improve its data processing capabilities. Neural network models are built by modeling correlations between data, and these correlations can be expressed by multiple parameters. A neural network model extracts and analyzes features from given data to derive correlations between the data. This process of repeatedly optimizing the parameters of a neural network model can be called machine learning. For example, a neural network model can learn the mapping (correlation) between inputs and outputs for data given as input-output pairs. Alternatively, a neural network model can learn the relationships between inputs by deriving regularities between the given data, even when only input data is given.

[0033] An artificial intelligence learning model or neural network model can be designed to implement the structure of the human brain on a computer, and can include a plurality of network nodes that simulate the neurons of a human neural network and have weights. The plurality of network nodes can have connections among themselves by simulating the synaptic activity of neurons that exchange signals through synapses. In the artificial intelligence learning model, the plurality of network nodes can be located at layers of different depths and exchange data according to convolutional connections. The artificial intelligence learning model can be, for example, an artificial neural network model, a convolutional neural network (CNN), etc. In one embodiment, the artificial intelligence learning model can be machine-learned according to a method such as supervised learning, unsupervised learning, or reinforcement learning. Machine learning algorithms that can be used to perform machine learning include decision trees, Bayesian networks, support vector machines, artificial neural networks, Ada-boost, perceptrons, genetic programming, and clustering.

[0034] Among these, CNNs are a type of multilayer perceptron designed to utilize minimal preprocessing. CNNs consist of one or more convolutional layers stacked on top of regular artificial neural network layers, with additional weight and pooling layers. This structure allows CNNs to fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs demonstrate excellent performance in both image and audio domains. CNNs can also be trained using standard backpropagation. Compared to other feedforward artificial neural network techniques, CNNs are easier to train and have the advantage of using fewer parameters.

[0035] Convolutional networks are neural networks that contain sets of nodes with bounded parameters. The increasing availability of training data and computational power, combined with advances in algorithms such as piecewise linear units and dropout training, have led to significant improvements in many computer vision tasks. With massive datasets, such as those available for many tasks today, overfitting is less of a concern, and increasing network size improves test accuracy. Optimal utilization of computing resources becomes a limiting factor. For this purpose, distributed, scalable implementations of deep neural networks can be used.

[0036]

[0037] Figure 2 is a block diagram illustrating the configuration of a system for automating the use and management of space according to one embodiment.

[0038] A system (200) according to one embodiment may include a processor (220) and a memory (230), and some of the illustrated configurations may be omitted or replaced. A system (200) according to one embodiment may be a server or a terminal. According to one embodiment, the processor (220) is a configuration capable of performing operations or data processing related to control and / or communication of each component of the system (200), and may be configured with one or more processors. The memory (230) may store information related to the above-described method or store a program in which the above-described method is implemented. The memory (230) may be a volatile memory or a non-volatile memory. The memory (230) may store various file data, and the stored file data may be updated according to the operation of the processor (120).

[0039] According to one embodiment, the processor (220) can execute a program and control the system (200). The code of the program executed by the processor (220) can be stored in the memory (230). The operations of the processor (220) can be performed by loading instructions stored in the memory (230). The system (200) can be connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown in the drawing) and exchange data.

[0040] The space management system (200) of the present invention automatically controls lighting, heating and cooling, music, diffusers, automatic ventilation, etc. according to set times, events, temperatures, etc. For example, if a user reserves space use at 8:00 AM, the system automatically turns on the lighting at 7:50 AM, adjusts the heating and cooling to an appropriate temperature, and activates music and the diffuser upon the user's arrival. Furthermore, when the user leaves, the system automatically turns off the lighting, heating and cooling, music, diffusers, etc., and activates the ventilation system.

[0041] The space management system (200) of the present invention uses an artificial intelligence learning model to monitor unauthorized entry and exit within the space in real time and provide notifications to the administrator. Furthermore, it automates door opening and closing, automatically providing a door lock password when a user makes a reservation and changing the password upon completion of use.

[0042] The space management system (200) of the present invention uses an artificial intelligence learning model to monitor problems such as water leaks and fires in real time and provide notifications to the manager. This enables rapid response and ensures safety within the space. The space management system of the present invention uses an artificial intelligence learning model to recognize and display the occupancy status within the space. This allows for increased space utilization and efficient management.

[0043] The space management system (200) of the present invention allows users to reserve spaces in real time through an app. Furthermore, upon completion of use, the door lock password is automatically changed and displayed to the administrator. When a new user completes a reservation, the door lock password is automatically provided.

[0044]

[0045] FIG. 3 is a flowchart illustrating a method for automating the use and management of space according to one embodiment.

[0046] Although the process steps, method steps, and algorithms described in the flowchart of FIG. 3 are described in a sequential order, such processes, methods, and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods, and algorithms described in various embodiments of the present invention need not be performed in the order described herein. Furthermore, even if some steps are described as being performed asynchronously, in other embodiments, some of these steps may be performed concurrently.

[0047] Furthermore, the illustration of a process by depiction in the drawings does not imply that the illustrated process excludes other variations and modifications thereof, nor does it imply that the illustrated process or any of its steps is essential to one or more of the various embodiments of the present invention, nor does it imply that the illustrated process is preferred.

[0048] In operation 310, the system (e.g., the system (200) of FIG. 2) may perform automatic environmental control under the control of a processor (e.g., the processor (220) of FIG. 2). According to one embodiment, the system (200) may perform automatic environmental control to control operations related to lighting, air conditioning, music, a diffuser, and automatic environmental control according to set times, events, and temperatures. For example, the system (200) may control automatic environmental operations related to lighting, air conditioning, music, and a diffuser according to times set by a user, such as automatically turning on the lights at 6 p.m., adjusting the indoor temperature to 22 degrees, and turning on music. For example, the system may turn on bright lights and music in the morning, set the air conditioner to an appropriate temperature in the afternoon, and operate the diffuser in the evening.

[0049] The system measures indoor carbon dioxide levels through sensors and automatically activates ventilation when the concentration exceeds a preset standard, improving indoor air quality. When the outside temperature suddenly changes or unexpected weather conditions occur, the system maintains the indoor temperature within the user-defined range, preventing sudden temperature changes. Motion sensors detect user activity and automatically dim the lights or display messages recommending stretching exercises when the user remains seated for extended periods.

[0050] In operation 320, the system (200) can perform automated security management and automated facility safety management. In one embodiment, the system (200) can automate security management to monitor and notify of unauthorized entry into a space in real time. The system (200) can automate door opening and closing, and automate facility safety management to monitor and notify of issues such as water leaks and fires in real time. For example, the system (200) can monitor in real time and notify the user when unauthorized entry into a space is detected. In addition, the system (200) can automate door opening and closing, monitor facility safety issues such as water leaks and fires in real time, and notify the user.

[0051] In operation 330, the system (200) can recognize the number of people occupant in a space and automatically recognize the status of equipment in the space. According to one embodiment, the system (200) can recognize and display the number of people occupant in a space. The system (200) can automatically recognize the status of equipment in a space, and when a malfunction or cleaning is required, it can indicate that the space is unusable and automatically contact a repair or cleaning company. For example, the system (200) can diagnose the status of equipment by collecting and analyzing various data such as temperature, humidity, vibration, and noise in real time through IoT sensors attached to the equipment. The system (200) can analyze camera images to identify the external condition (cracks, deformation, etc.) and operating condition (abnormal noise, irregular movement, etc.) of the equipment and detect abnormal signs. The system (200) can predict the possibility of equipment failure based on past data and real-time data and perform preventive maintenance.

[0052] The system (200) analyzes data on the number of occupants and equipment status within a space to determine the current state of space utilization, and automatically proposes space utilization and management plans based on this data. The system (200) can propose measures to increase space utilization efficiency by considering the space's purpose, characteristics, and usage patterns. For example, the system can suggest ways to repurpose low-utilization spaces or expand high-utilization spaces.

[0053]

[0054]

[0055] According to one embodiment, the system (200) can receive a user's reservation information, determine space availability based on the reservation information, and notify the user of the space's availability. When a new user reservation is completed, the system (200) automatically provides a door lock password at the time of use. When a user enters the space, the system (200) receives entry / exit information, determines the number of occupants in the space based on the entry / exit information, and automatically controls lighting, heating / cooling, music, a diffuser, and automatic ventilation based on a set time, event, or temperature.

[0056] For example, if User A reserves a conference room from 2 PM to 4 PM, the system (200) checks whether the conference room is available at that time. If the conference room is available, it sends a reservation confirmation message to User A, notifying him or her that the conference room is available. If User B reserves a conference room from 6 PM to 8 PM, the system (200) automatically sends the conference room door lock password to User B upon completion of the reservation. When User B arrives at the conference room, enters the door lock password, and enters, the system (200) receives the user's access information and determines that User B is currently the only user in the conference room. Then, when the event time, 6 PM, arrives, the system automatically turns on the conference room lights, maintains the temperature at an appropriate level, plays music, and operates the diffuser to automatically control the spatial environment.

[0057] According to one embodiment, the system (200) monitors and provides notifications in real time for unauthorized entry into a space using an artificial intelligence learning model, monitors and provides notifications in real time for problems such as water leaks and fires using an artificial intelligence learning model, recognizes the number of people in a space in real time using an artificial intelligence learning model and displays it on an app, and controls the user to view the space usage status and make real-time reservations through the app.

[0058] For example, STEM (200) uses an AI learning model to monitor CCTV footage inside a conference room in real time. If it detects unauthorized entry, it immediately sends a notification to the administrator. Furthermore, the AI ​​learning model analyzes temperature, humidity, and smoke sensor data inside the conference room in real time, sending a notification to the administrator if a water leak or fire risk is detected. Users can check the number of people currently in the conference room in real time through the mobile app, view the conference room reservation status, and make reservations in real time.

[0059] According to one embodiment, the system (200) automatically recognizes the status of equipment within a space using an artificial intelligence learning model, recognizes when equipment is broken or space needs cleaning, controls to display the space as unusable and automatically contact a repair / cleaning company, automatically changes the door lock password when use is complete and displays it to the administrator, and automatically provides the door lock password at the time of use when a new user reservation is completed.

[0060] For example, the system (200) uses an artificial intelligence learning model to monitor the status of equipment inside the conference room, such as air conditioning, lighting, and ventilation, in real time. If an air conditioning malfunction is detected, the system marks the conference room as unusable and automatically contacts an air conditioning repair company for prompt repairs. Furthermore, after the meeting ends, the system automatically changes the conference room door lock password and notifies the administrator of the new password. The new door lock password is automatically provided to users who reserve the conference room at the time of use.

[0061]

[0062]

[0063] According to one embodiment, the system (200) can identify a set of space reservation requests, determine whether each reservation request has been previously reserved, determine a reservation conversion value reflecting a ratio of the number of reservations to the number of requests with that characteristic, and determine a space-specific conversion value indicating a relationship between the reservation request characteristic and whether the reservation was successful based on the reservation conversion value.

[0064] For example, the system (200) receives reservation requests from customers for various spaces, such as hotel rooms, conference rooms, and banquet halls. At this time, the system (200) collects each reservation request into a set and checks whether the requests have already been previously reserved. For example, if a customer attempts to reserve a conference room for a specific date, but another customer has already made a reservation for that time, the system (200) determines that the reservation request has already been previously reserved.

[0065] According to one embodiment, the system (200) may apply a reservation conversion model for each space to a new reservation request, calculate a probability that the request will be reserved, and display the space in the search results if the calculated reservation probability is greater than or equal to a predefined reservation threshold.

[0066] For example, the system (200) analyzes the number and characteristics (e.g., room type, date, time, etc.) of previously reserved requests. This allows it to determine whether a specific room type or time slot has a high or low reservation success rate. Based on this, a reservation conversion value is calculated, and a space-specific conversion value representing the relationship between the characteristics of a customer's reservation request and the actual reservation success rate is determined. For example, if a luxury suite has a high reservation success rate on weekend evenings, the reservation conversion value for that room will be high.

[0067] For example, when a customer makes a new reservation request, the system (200) calculates the probability that the room or space will actually be booked by applying a previously calculated reservation conversion model. For example, if a customer attempts to book a luxury suite for a weekend evening, the system (200) may calculate an 80% reservation probability based on the high reservation conversion value of this room type. If this reservation probability exceeds a predefined threshold (e.g., 70%), the system (200) displays the luxury suite in the search results.

[0068] According to one embodiment, the system (200) receives information such as preferred room type, reservation date, occupied room, arrival date, check-in time, departure date, and check-out time from a customer through an input / output interface, analyzes the received information to generate an allocation matrix composed of the customer's preferred room type and room information of the corresponding facility, and identifies a room type mapped to the customer's preferred room type based on the generated allocation matrix to generate a temporary chart.

[0069] For example, when making a hotel reservation, a customer enters information such as their preferred room type (e.g., a suite), reservation date, pre-booked rooms, and arrival / departure dates and times. The system (200) analyzes this information to create an allocation matrix consisting of the customer's preferred room type and the hotel's actual room information. Based on this matrix, a temporary chart is created by matching the customer's desired room type with the actual available room types. For example, if a customer requests a suite but another customer has already reserved one, the system (200) can recognize this and suggest a different room type to the customer.

[0070] According to one embodiment, the system (200) can predict the check-in and check-out delay of customers through a pre-learned prediction model considering the weather, the arrival and departure times of customers, etc., calculate the cumulative time adjustment factor of the checking-out customers based on the predicted delay time, and assign a preferred room type to the customer in real time by considering the calculated cumulative time adjustment factor and the room change time.

[0071] For example, the system analyzes historical data to learn that on days with good weather, customers check in and check out earlier on average, but on days with bad weather, customers check in and check out later on average. Based on this, by inputting weather information and a customer's expected arrival and departure times, the system can predict the customer's check-in and check-out delays.

[0072] The system calculates the total delay time by adding up the expected delay times of guests scheduled to check out today. Taking this total delay time and the time required to change rooms into a new room into account, it selects the most suitable room type for the next guest checking in. This minimizes room change times and improves guest satisfaction.

[0073] According to one embodiment, the system (200) receives a team check-in reservation plan, accesses the accommodation information acquisition background to document the check-in team, generates a QR code representing the team, transmits the team's QR code to the team leader, has the team leader scan the QR code to upload the team members' identification information and contact information to the accommodation information acquisition background, and can assign a room number in advance when the team members' information is uploaded. The system (200) verifies the identity of each team member upon team check-in, compares the verified information with the pre-downloaded information, and issues a room card and automatically uploads the accommodation information if they match. When the team checks out, the system (200) retrieves the accommodation information of all team members to complete the check-out service and upload the accommodation information, and controls to suspend access to the team's QR code.

[0074] For example, a company might have ten people traveling together for a business trip and want to check in as a team. The system accepts this team check-in reservation, records the team's information in the accommodation information acquisition background, generates a QR code representing the team, and sends it to the team leader. When the team leader scans the QR code, the team members' identification and contact information is automatically uploaded to the system. Once this information is entered, the system can assign the team an appropriate room number in advance. When team members check in, the system verifies each member's ID and, if the information matches the pre-downloaded information, issues a room card. It also automatically records the team's accommodation information. For example, when the team checks out, the system retrieves the accommodation information for all team members, completes the check-out process, and uploads this information. It then blocks further access to the team's QR code.

[0075]

[0076] In one embodiment, the system (200) identifies a set of space reservation requests. For example, if a user requests reservations for multiple spaces, the system (200) groups them into a single set and processes them. It determines whether each reservation request has been previously reserved. For example, if a user requests a reservation for a space already reserved, the system (200) determines it as a previously reserved request and does not process it. A reservation conversion value is determined by reflecting the ratio of the number of reservation requests to the number of requests with a given characteristic. For example, the reservation conversion value is determined by calculating the ratio of reservation requests with a specific characteristic that are actually reserved.

[0077] Based on the reservation conversion value, a space-specific conversion value indicating the relationship between reservation request characteristics and reservation success is determined. For example, based on the reservation conversion value, reservation requests with certain characteristics are identified as having a high probability of success, and this is stored as a space-specific conversion value. According to one embodiment, the system (200) applies a reservation conversion model for each space to a new reservation request to calculate the probability of the request being reserved. For example, when a user requests a reservation for a specific space, the system (200) applies the reservation conversion model for the space to calculate the reservation probability. If the calculated reservation probability is greater than a predefined reservation threshold, the space is displayed in the search results. For example, if the reservation probability is greater than 50%, the space is displayed at the top of the search results.

[0078] In one embodiment, the system (200) receives information from a customer, such as a preferred room type, reservation date, occupied room, arrival date, check-in time, departure date, and check-out time, through an input / output interface. For example, when a customer makes a reservation, the customer enters this information, and the system (200) receives and processes it. The system analyzes the received information to generate an allocation matrix consisting of the customer's preferred room type and room information at the relevant facility. For example, the system compares the customer's preferred room type with the room types available at the relevant facility to determine which room type best matches the customer's preference. Based on the generated allocation matrix, the system identifies room types that map to the customer's preferred room type and generates a temporary chart. For example, the system finds the room type most similar to the customer's preferred room type and displays it in the temporary chart.

[0079] According to one embodiment, the system (200) predicts customer check-in and check-out delays using a pre-trained predictive model, taking into account factors such as weather, customer arrival and departure times, etc. For example, since customer arrival times are more likely to be delayed on rainy days, the predictive model is trained considering this. Based on the predicted delay times, a cumulative time adjustment factor for check-out customers is calculated. For example, if the predicted delay time is 30 minutes, the cumulative time adjustment factor for check-out customers is calculated as 0.5. A preferred room type can be assigned to a customer in real time by considering the calculated cumulative time adjustment factor and the room change time. For example, if the cumulative time adjustment factor is 0.5 and the room change time is 10 minutes, the customer is assigned a room with 10 minutes more available.

[0080] In one embodiment, the system (200) receives a team check-in reservation plan. For example, if a team check-in reservation is made on a hotel reservation site, the system (200) receives the reservation information. The system accesses the accommodation information acquisition background to document the check-in team and generates a QR code representing the team. For example, the system accesses the accommodation information acquisition background to input the names, contact information, room types, etc. of team members, and generates a QR code based on these. The team's QR code is transmitted to the team leader. For example, the QR code is transmitted to the team leader's smartphone for use during check-in. The team leader scans the QR code to upload the team members' identification and contact information to the accommodation information acquisition background. For example, when the team leader scans the QR code, the team's information is automatically uploaded to the accommodation information acquisition background. Once the team members' information is uploaded, room numbers can be assigned in advance. For example, once the information upload is complete, the system (200) notifies the team leader of the pre-assigned room number. The identity of each team member is verified during team check-in. For example, when a team leader presents a QR code, the system (200) scans the QR code to verify the team members' identities. If the verified information matches the pre-downloaded information, the system issues a room card and automatically uploads the accommodation information. For example, if the verified information matches the pre-downloaded information, the system (200) issues a room card and automatically uploads the accommodation information.

[0081] When a team leaves, the system retrieves the accommodation information of all team members, completes the check-out process, and uploads the information. For example, when all team members leave, the system (200) retrieves the accommodation information of all team members, completes the check-out process, and uploads the information. Access to the team's QR code can be controlled to be suspended. For example, when all team members leave, the system (200) suspends access to the team's QR code to enhance security.

[0082]

[0083]

[0084] According to one embodiment, the system (200) may receive a customer's reservation preference, including a room type, a bed type, and a room location, from a user terminal, and may award 1 point if the customer's preferred bed type matches the bed type of the actually allocated space, and 0 points if they do not match. The system (200) may calculate a distance difference between the customer's preferred room location and the assigned room location, and award 1 point if the distance difference is less than a specified level, and award 0 points if the distance difference exceeds the specified level. The system (200) may determine a customer satisfaction allocation cost based on the score for the customer's preference and the actually matched space.

[0085] For example, if a customer inputs that he or she prefers a high-floor room with twin beds, the system (200) receives and processes this input. If the customer prefers twin beds but the assigned room actually has a single bed, a score of 0 is assigned. If the customer prefers a high-floor room but the assigned room is on a low floor, a score of 0 is assigned because the distance difference exceeds the specified level. If both the customer's preferred bed type and the room location match, the customer satisfaction allocation cost is calculated as 1 point.

[0086] In one embodiment, the system (200) may calculate the percentage of reserved space, continuously calculate the percentage of unreserved space for a specified period of time, and determine an additional cost when changing to a space type desired by the customer. The system (200) may calculate an operational efficiency allocation cost based on the percentage of reserved space, the percentage of unreserved space, and the additional cost when changing to a space type desired by the customer. The system (200) may generate a weighted cost matrix representing the total cost for each space for all customers with reservations based on the customer satisfaction allocation cost and the operational efficiency allocation cost, and may generate a reserve space allocation that selects the most suitable space for each reservation based on the weighted cost matrix.

[0087] For example, if 70% of rooms are currently booked, this is calculated and processed. If 20% of rooms remain unbooked for a week, this is also calculated and processed. If the percentage of booked rooms is high and the percentage of unbooked rooms is low, the operational efficiency allocation cost is calculated higher. Rooms with high customer satisfaction and high operational efficiency are calculated with lower weighted costs. Based on the weighted cost matrix, a reserve space allocation model can be created that selects the most appropriate space for each reservation. The optimal room allocation is performed by considering customer preferences and reservation status.

[0088] The system (200) receives the customer's reservation preferences. For example, the customer inputs into the system his / her preference for a suite as the room type, a king-size bed as the bed type, and a room with a good view as the room location.

[0089] If the customer's preferred bed type matches the bed type in the actual allocated space, a 1-point score is awarded. If they do not match, a 0-point score is awarded. For example, if a customer requested a king-size bed but the actual bed assigned was a queen-size, a 0-point score is awarded.

[0090] The system calculates the distance difference between the customer's preferred room location and the actual room location assigned. If the distance difference is less than a specified value, it receives a score of 1, and if it exceeds the specified value, it receives a score of 0. For example, if a customer requested a room with a good view but was assigned a room with a poor view, it receives a score of 0.

[0091] The system determines customer satisfaction allocation costs based on scores for spaces that match customer preferences. For example, if the preference-to-actual match is perfect, a high customer satisfaction allocation cost is assigned, while if the preference-to-actual match is poor, a low customer satisfaction allocation cost is assigned.

[0092] The system determines the operating efficiency allocation cost by calculating the percentage of reserved space, the percentage of unreserved space, and the additional cost of changing to a customer's preferred space type. For example, a high reservation rate and few changes in customer requirements would result in a high operating efficiency allocation cost. A low reservation rate and frequent changes in customer requirements would result in a low operating efficiency allocation cost.

[0093] The system generates a weighted cost matrix based on customer satisfaction allocation costs and operational efficiency allocation costs, and then generates a reserve space allocation based on this matrix, selecting the most appropriate space for each reservation. For example, rooms with high customer satisfaction and operational efficiency are given priority for allocation.

[0094] According to one embodiment, the system (200) can be controlled to perform an optimized space allocation, where the spare space allocation is comprised of selections of elements of a weighted cost matrix, if spare space allocation is possible, to relax one or more constraints and to repeat the optimization until spare space allocation is possible, to generate a control signal corresponding to the spare space allocation, and to automatically electronically program one or more space keys corresponding to the spare space allocation in response to the control signal.

[0095] For example, if spare space allocation is possible, the system (200) performs optimized space allocation, where spare space allocation is comprised of selections of elements of a weighted cost matrix. For example, optimal rooms are allocated by considering customer preferences and reservation status.

[0096] If reserve space allocation is not possible, the system (200) relaxes one or more constraints and repeats the optimization process until reserve space allocation is possible. For example, it searches for and allocates a canceled room instead of a fully booked room. The system (200) generates a control signal corresponding to the reserve space allocation. For example, it sends a control signal to the room key issuance system based on the optimized room allocation information.

[0097] The system (200) can be controlled to automatically electronically program one or more space keys corresponding to the reserved space allocation in response to a control signal. For example, a room key issuing system that receives the control signal automatically programs a key for the corresponding room and provides it to the customer.

[0098] When the system (200) is capable of reserve space allocation, it selects elements of the weighted cost matrix to perform optimized space allocation. That is, it establishes the most efficient space allocation plan by considering the cost weights for each space. For example, if a specific space has a low cost weight, it is allocated first, while a space with a high cost weight is allocated last, thereby performing optimized space allocation.

[0099] Meanwhile, if reserve space allocation is not possible, the system (200) relaxes one or more constraints and repeats the optimization process. For example, the constraints are relaxed by lowering the usage priority for a specific space or adjusting the space size requirements, and the optimization process is repeated until reserve space allocation becomes possible. The system (200) generates a control signal corresponding to the reserve space allocation and automatically electronically programs one or more space keys based on the control signal. For example, the space keys are programmed by granting access to a specific space or limiting the space usage time.

[0100]

[0101]

[0102] According to one embodiment, the system (200) can measure indoor air quality within a space to obtain indoor air quality data including real-time occupancy detection information, indoor temperature and humidity information, and lighting usage status information, and can collect real-time external environment data including air temperature, precipitation, and fine dust (PM2.5) concentration. The system (200) can provide indoor air quality data and real-time external environment data as inputs to a machine learning model, and can analyze the indoor air quality data based on the machine learning results to determine whether smoking is occurring indoors.

[0103] For example, the system (200) inputs indoor air quality data such as indoor temperature, humidity, carbon dioxide concentration, and fine dust concentration, and real-time external environmental data such as air temperature, precipitation, and fine dust concentration into a machine learning model. If the system (200) detects a pattern in which carbon dioxide concentration, fine dust concentration, etc. among the indoor air quality data rapidly increases, it can determine that there has been indoor smoking. The system (200) can analyze the change pattern of carbon dioxide concentration and fine dust concentration to distinguish whether it is regular cigarette smoking or electronic cigarette smoking.

[0104] According to one embodiment, the system (200) can diagnose whether or not indoor smoking occurs and the type of smoking based on the indoor air quality data analysis results, generate a smoking detection model capable of detecting indoor smoking by learning smoking data (air quality data when smoking indoors) and non-smoking data (air quality data when not smoking indoors), and generate a smoking type classification model capable of classifying smoking types by learning cigarette data (air quality data when smoking cigarettes indoors) and electronic cigarette data (air quality data when smoking electronic cigarettes indoors). The system (200) can generate the smoking detection model and the smoking type classification model by selecting a supervised learning model including at least one of a decision tree, a random forest, XGBOOST, and an SVM.

[0105] For example, the system (200) can create a model that can determine whether or not a person is smoking by analyzing the characteristics of air quality data when smoking and not smoking indoors. The system (200) can create a model that can distinguish between smoking types by analyzing the differences in air quality data generated when smoking regular cigarettes and when smoking electronic cigarettes. For example, the system (200) can determine whether or not smoking indoors is occurring using a decision tree model, and can distinguish between cigarette and electronic cigarette smoking using an SVM model. The smoking type classification model of the system (200) can classify smoking types by learning characteristics such as fine dust, carbon dioxide, and carbon monoxide concentrations generated from cigarettes and electronic cigarettes.

[0106] According to one embodiment, the system (200) determines that there is a smoker in the room when smoking is detected a certain number of times within a certain period of time through the smoking detection model, and can diagnose a predominant smoking type by adding up the number of cigarettes and electronic cigarettes used through the smoking type classification model. The system (200) determines that the air quality is poor when the ECO2 value measured by the air quality measuring device is higher than the first reference value, the TVOC value is higher than the second reference value, the PM10 value is higher than the third reference value, and the PM2.5 value is higher than the fourth reference value, and can output a notification signal according to the air quality diagnosis result.

[0107] The system (200) determines that there is a smoker in the room if smoking is detected a certain number of times within a certain period of time through a smoking detection model. For example, if the system (200) detects smoking three or more times within 10 minutes, it determines that there is a smoker in the space. Next, the system (200) diagnoses the predominant smoking type by adding up the number of cigarettes and e-cigarettes used through a smoking type classification model. The smoking type classification model diagnoses the predominant smoking type by adding up the number of cigarettes and e-cigarettes used. For example, if the number of cigarettes used is greater than the number of e-cigarettes used, it is diagnosed as regular cigarette smoking, and if the number of e-cigarettes used is greater than the number of cigarettes used, it is diagnosed as e-cigarette smoking. For example, if two cigarettes and one e-cigarette are detected within 10 minutes, it is determined that the user's predominant smoking type is cigarettes because cigarettes are used more frequently.

[0108] In addition, the system (200) determines that the air quality is poor if the ECO2, TVOC, PM10, and PM2.5 values ​​measured by the air quality measuring device exceed their respective reference values. For example, the air quality may be determined to be poor if the ECO2 value is 1000 ppm or higher, the TVOC value is 500 μg / ㎥ or higher, the PM10 value is 100 μg / ㎥ or higher, and the PM2.5 value is 50 μg / ㎥ or higher. Thereafter, the system (200) may output a notification signal according to the air quality diagnosis results. For example, if the air quality is determined to be poor, a notification may be sent to the manager or user indicating that air quality improvement is necessary.

[0109] According to one embodiment, the system (200) can use the analysis results and management data to classify customers into smoking, non-smoking, and other customer groups, and further segment customers within the smoking customer group into customers whose standard deviation is more than two times the average and other customers. The system (200) can further segment customers within the non-smoking customer group into customers whose standard deviation is more than three times the average, customers whose standard deviation is less than one time the average, and other customers, and can transmit control alerts for each room by customer type and provide analysis information by customer type to the accommodation business manager terminal.

[0110] When the ECO2 value measured by the air quality meter is higher than the first standard value, the TVOC value is higher than the second standard value, the PM10 value is higher than the third standard value, and the PM2.5 value is higher than the fourth standard value, the air quality is determined to be poor. For example, when the ECO2 value is higher than 1000 ppm, the TVOC value is higher than 500 ppb, the PM10 value is higher than 100 ug / m3, and the PM2.5 value is higher than 50 ug / m3, the air quality is determined to be poor. An alarm signal is output according to the air quality diagnosis results. For example, when the air quality is determined to be poor, an alarm sound is played or a notification is sent through a smartphone app.

[0111] In one embodiment, the system (200) uses analysis results and management data to classify customers into smoking, non-smoking, and other customer groups. For example, customers are classified based on the smoking status information entered by the customer at check-in and indoor air quality measurement data. Within the smoking customer group, customers are further divided into those whose indoor air quality measurement data is at least twice the mean and those who are not. For example, within the smoking customer group, customers whose indoor air quality measurement data is at least twice the mean are classified as high-risk, and other customers are classified as low-risk.

[0112] Within the non-smoking group, customers are segmented into those with indoor air quality measurements more than three standard deviations from the mean, those with measurements less than one standard deviation from the mean, and others. For example, within the non-smoking group, customers with indoor air quality measurements more than three standard deviations from the mean are classified as special management customers, while those with measurements less than one standard deviation from the mean are classified as premium customers. Room-specific control alerts are sent based on customer type, and analysis data by customer type is provided to the accommodation management terminal. For example, ventilation systems are activated in rooms occupied by high-risk smoking customers, while air purifiers are activated in rooms occupied by special management non-smoking customers.

[0113]

[0114]

[0115] According to one embodiment, the system (200) is connected to a plurality of sensors to receive monitoring data inside a space from the sensors, analyze the received monitoring data to determine the operating status of air purification equipment inside the space, and control the operation of the equipment according to the operating status of the air purification equipment to optimize the environment inside the space.

[0116] In one embodiment, the system (200) transmits operating data and maintenance information of air purification equipment to a server, detects equipment abnormalities through a daily inspection module linked to the server, and generates a list of equipment requiring maintenance measures when necessary. For example, if the air purifier filter contamination level exceeds a certain level, a notification is provided indicating the need for filter replacement. If the fine dust concentration exceeds a certain level, the air purifier is activated, and if the carbon dioxide concentration exceeds a certain level, the ventilation system is activated.

[0117] In one embodiment, the system (200) recognizes a worker's cleaning and inspection activities through an AI camera installed within the space, transmits the information to a server, monitors dust concentration data measured by a laser dust meter within the space, and transmits a list of items requiring maintenance to the server if the dust concentration exceeds a standard. In one embodiment, the system (200) recognizes a worker's cleaning and inspection activities through an AI camera installed within the space, and transmits the information to the server. For example, the system recognizes a worker cleaning an air purifier and stores the information on the server.

[0118] The system (200) monitors dust concentration data measured by a laser dust meter within the space and, if the dust concentration exceeds a standard, transmits a list of items requiring maintenance to the server. For example, if the dust concentration exceeds a certain level, a notification is provided indicating the need for cleaning.

[0119] The system (200) is connected to a number of sensors and receives monitoring data from the space. For example, temperature sensors, humidity sensors, air quality sensors, etc. are installed, and data such as indoor temperature, humidity, and fine dust concentration are collected in real time from these sensors.

[0120] The system (200) analyzes the received monitoring data to determine the operating status of the air purification equipment within the space. For example, if the indoor temperature exceeds a set range or the fine dust concentration exceeds a standard, the system determines that the air purification equipment needs to be operated. The system (200) controls the operation of the air purification equipment based on its operating status to optimize the environment within the space. For example, the air purification equipment is automatically turned on or off and the air volume is adjusted to maintain a comfortable indoor environment.

[0121] The system (200) transmits operating data and maintenance information of air purification equipment to a server. For example, it transmits information such as equipment operating hours, filter replacement cycles, and error codes to the server. The system (200) detects equipment abnormalities through a daily inspection module linked to the server and, if necessary, generates a list of equipment requiring maintenance. For example, it detects signs of equipment performance degradation or failure and provides the manager with a list of equipment requiring maintenance.

[0122] The system (200) recognizes a worker's cleaning and inspection activities through an AI camera installed within the space and transmits the information to the server. For example, the AI ​​camera detects a worker replacing or cleaning the filter of an air purification device and transmits the information to the server. The system (200) monitors dust concentration data measured by a laser dust meter within the space and, if the concentration exceeds a standard, transmits a list of maintenance items to the server. For example, if the indoor fine dust concentration exceeds a certain level, the system determines that the filter of the air purification device needs to be replaced or cleaned and notifies the server.

[0123]

[0124] The embodiments described above may be implemented using hardware components, software components, and / or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0125] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to perform a desired operation or, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0126] Although the embodiments described above have been described with limited drawings, those skilled in the art will appreciate that various technical modifications and variations can be applied based on the above. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

Claims

1. In a system for automating the use and management of space, Memory for storing instructions; and Contains a processor, The above instructions, when executed by the processor, cause the system to Perform automatic environmental control to control lighting, heating and cooling, music, diffuser, and other automatic environmental related operations according to set times, events, and temperatures. Automating security management, real-time monitoring and notification of unauthorized entry into space, automating door opening and closing, Automating facility safety management, monitoring and providing real-time notifications for issues such as water leaks and fires. Recognize and display the number of people in the space, A system that automatically recognizes the status of equipment within a space, indicates that the space is unusable when it is broken or needs cleaning, and automatically contacts a repair or cleaning company.

2. In paragraph 1, The above instructions, when executed by the processor, cause the system to Receive your reservation information, Determine the availability of space based on reservation information, Inform users of space availability, When a new user reservation is completed, the door lock password is automatically provided at the time of use. When a user enters a space, entry / exit information is received, Based on the entry and exit information, we can determine the number of people in the space, Automatically control lighting, heating and cooling, music, diffuser, and automatic ventilation based on set time, event, or temperature. Using artificial intelligence learning models, we monitor and notify you of unauthorized entry and exit of spaces in real time. Using artificial intelligence learning models, we monitor and notify problems such as water leaks and fires in real time. Using an artificial intelligence learning model, it recognizes the number of people in a space in real time and displays it on the app. Allows users to view space usage status and make real-time reservations through the app, Using an artificial intelligence learning model, it automatically recognizes the status of equipment within a space, and if there is a malfunction in the equipment or the space needs cleaning, it recognizes this, marks the space as unusable, and automatically contacts a repair / cleaning company. When use is complete, the door lock password is automatically changed and displayed to the administrator. A system that automatically provides a door lock password at the time of use when a new user completes a reservation.

3. In paragraph 1, The above instructions, when executed by the processor, cause the system to Identify a set of space reservation requests and determine whether each reservation request has been previously reserved; Determine the reservation conversion value by reflecting the ratio of the number of reservations to the number of requests with that characteristic, Determine a space-specific conversion value that indicates the relationship between a reservation request characteristic and the success or failure of a reservation based on the reservation conversion value, Applying the reservation conversion model for each space to a new reservation request, calculates the probability that the request will be reserved. If the calculated reservation probability is greater than or equal to a predefined reservation threshold, the space is displayed in the search results. Receive information from customers such as preferred room type, reservation date, occupied room, arrival date, check-in time, departure date, and check-out time through input / output interfaces, Analyze the received information to create an allocation matrix consisting of the customer's preferred room type and the room information of the corresponding facility, Create a temporary chart by identifying the room types that map to the customer's preferred room types based on the generated allocation matrix, Predict customer check-in and check-out delays using a pre-trained predictive model that takes into account weather, customer arrival and departure times, etc. Calculate the cumulative time adjustment factor for checkout customers based on the predicted delay time, Assign preferred room types to customers in real time, taking into account calculated cumulative time adjustment factors and room transition times. Receive team check-in reservation plans, access accommodation information acquisition background, document the check-in team, and generate a QR code representing the team. Send the team's QR code to the team leader, Scan the QR code from the team leader to upload the team members' identification and contact information to the background of obtaining accommodation information. Once the team members' information is uploaded, we will assign room numbers in advance. When a team checks in, the identity of each team member is verified, the verified information is compared with the pre-downloaded information, and if it matches, a room card is issued and the accommodation information is automatically uploaded. A system that retrieves the accommodation information of all team members when the team leaves, completes the check-out service, uploads the accommodation information, and controls access to the team's QR code.

4. In paragraph 1, The above instructions, when executed by the processor, cause the system to Receive customer reservation preferences including room type, bed type, and room location from the user terminal; If the bed type preferred by the customer matches the bed type in the actual allocated space, 1 point is awarded; if not, 0 points are awarded. Calculate the distance difference between the assigned room location and the customer's preferred room location, and award 1 point if the distance difference is less than the specified level, and award 0 points if the distance difference exceeds the specified level. Determine the customer satisfaction allocation cost based on the score for the space that matches the customer preference, Calculate the percentage of reserved space, Calculate the percentage of spaces that remain unreserved for a specified period of time; Determine additional costs when changing to the type of space desired by the customer, Calculate operational efficiency allocation costs based on the percentage of space reserved, the percentage of space not reserved, and the additional cost when changing to the type of space desired by the customer. Generate a weighted cost matrix representing the total cost for each space for all booked customers based on the customer satisfaction allocation cost and the operational efficiency allocation cost, Generate a reserve space allocation that selects the most suitable space for each reservation based on a weighted cost matrix, If spare space allocation is possible, the spare space allocation performs an optimized space allocation consisting of selection of elements of a weighted cost matrix, If spare space allocation is not possible, one or more constraints are relaxed and optimization is repeated until spare space allocation is possible. A system for generating a control signal corresponding to a spare space allocation and controlling, in response to the control signal, to automatically electronically program one or more space keys corresponding to the spare space allocation.

5. In paragraph 1, The above instructions, when executed by the processor, cause the system to Measure indoor air quality within a space to obtain indoor air quality data including real-time occupancy detection information, indoor temperature and humidity information, and lighting usage status information. Collect real-time external environmental data including temperature, precipitation, and fine dust (PM2.5) concentration, Indoor air quality data and real-time external environmental data are provided as input to the machine learning model. Based on the machine learning results, the above indoor air quality data is analyzed to determine whether smoking occurs indoors. Based on the results of indoor air quality data analysis, we diagnose whether or not there is indoor smoking and the type of smoking. A smoking detection model capable of detecting indoor smoking is created by learning smoking data (air quality data when smoking indoors) and non-smoking data (air quality data when not smoking indoors). A smoking type classification model is created that can classify smoking types by learning cigarette data (air quality data when smoking cigarettes indoors) and e-cigarette data (air quality data when smoking e-cigarettes indoors). Create the smoking detection model and smoking type classification model by selecting a supervised learning model including at least one of a decision tree, a random forest, XGBOOST, and an SVM. If smoking is detected more than a certain number of times within a certain period of time through the above smoking detection model, it is determined that there is a smoker in the room, and the number of cigarettes and e-cigarettes used is added up through the above smoking type classification model to diagnose the predominant smoking type. When the ECO2 value measured by the air quality meter is higher than the first standard value, the TVOC value is higher than the second standard value, the PM10 value is higher than the third standard value, and the PM2.5 value is higher than the fourth standard value, the air quality is determined to be poor. It outputs a notification signal based on the air quality diagnosis results. Using the analysis results and management data, we classify customers into smokers, non-smokers, and other customer groups. Within the smoking customer group, customers are segmented into those who are more than two standard deviations from the mean and other customers. Within the non-smoking customer group, customers are segmented into customers who are more than three standard deviations from the mean, customers who are less than one standard deviation from the mean, and other customers. A system that transmits room-specific control alerts by customer type and provides customer type-specific analysis information to the accommodation business manager terminal.

Images