Ai enabled living space

The AI-enabled living system addresses the adaptability and technological integration challenges of conventional living spaces by using sensors, actuators, and machine learning to create a customizable, sustainable, and secure environment, enhancing comfort, safety, and health monitoring for urban dwellers.

WO2024227497A1PCT designated stage expired Publication Date: 2024-11-07SERAI AG
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
PCT/EP2023/061417
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-29
Publication Date
2024-11-07

AI Technical Summary

Technical Problem

Conventional living spaces, especially in urban areas, are not adaptable to technological integration, failing to provide smart solutions that meet the evolving needs of modern city inhabitants, particularly in terms of sustainability, safety, and health monitoring, especially for remote workers and the aging population.

Method used

A modular, AI-enabled living system that integrates precision sensors, actuators, smart devices, and machine learning algorithms to create a customizable, energy-efficient, and secure living environment, capable of adapting to individual needs and providing real-time insights and alerts, suitable for both transportable and conventional settings.

Benefits of technology

The system enhances user comfort, minimizes environmental impact, ensures safety, and monitors health, offering a flexible and sustainable living solution that can adapt to changing user needs, while maintaining privacy and security, even in the absence of internet connectivity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2023061417_07112024_PF_FP_ABST
    Figure EP2023061417_07112024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to a smart living system that uses artificial intelligence to optimize its performance and provides a secure and energy efficient living space with a focus on the health and wellness of its occupants. In particular the present invention relates to Al-enabled living spaces that use novel algorithms to collect, process, analyze and recommend sensor data. The system is highly adaptable and can be customized to meet the unique needs of each user. The present invention also relates to a novel container or a pre-fabricated house specifically designed and is suitable for the Al-enabled living space of the present invention as well as the use of the smart living system in conventional apartment flats as long as the building is suitable for technological integration.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Al ENABLED LIVING SPACE

[0002] The present invention relates to a smart living system that uses artificial intelligence to optimize its performance and provides a secure and energy efficient living space with a focus on the health and wellness of its occupants. In particular the present invention relates to Al-enabled living spaces that use novel algorithms to collect, process, analyze and recommend sensor data. The system includes precision sensors, actuators, smart devices, mobile apps, Al algorithms, and other components that work together to create insights, optimizing the user's living environment, improving the system’s efficiency and reducing its environmental impact. The system is highly adaptable and can be customized to meet the unique needs of each user. The present invention also relates to a novel container or a pre-fabricated house specifically designed and is suitable for the Al-enabled living space of the present invention as well as the use of the smart living system in conventional apartment flats as long as the building is suitable for technological integration.

[0003] In recent years, the world has experienced a rapid and unprecedented pace of change, driven by a range of factors including the COVID-19 pandemic, rapid urbanization, the effects of climate change, the increase in the elderly population and the rise of new technologies. Especially the pandemic has had a profound impact on every aspect of life, from healthcare and the economy to social and cultural norms, forcing us to rethink our ways of living and working. The things that were hard to imagine became the daily life routines, especially in relation to employment and working habits of employees. Before the pandemic working from a distance was a privilege endowed only to some exceptional experts in specific areas, which nowadays is acknowledged as the normal way of working for the average working population, unless the nature of work itself requires the physical presence of the employee. This has prompted many young adults to reassess their priorities and preferences. With the proliferation of remote work opportunities and advancements in technology, there has been a growing trend among younger adults to move away from urban centers and seek alternative lifestyles. In this context, remote employees who opt to live in rural areas away from city centers must ensure that their technological equipment is integrated into their living spaces, so as not to compromise their digital connectivity. Moreover, remote workers spending more time in their living spaces have raised their expectations for comfort and environmental impact from those spaces. Therefore, it is crucial to reassess the suitability of their current and novel living spaces and identify the necessary improvements to meet their evolving needs.

[0004] In addition, natural disasters such as earthquakes, hurricanes, wildfires, and floods have affected people all around the world, highlighting the urgent need for sustainable solutions that can help us adapt to these changing conditions. It has been apparent that the world is in a different stage of the climate change and the course of events show there will only be an increase in the number of people being affected by disasters, if not already under the effects of infectious diseases.

[0005] The world's increasing urbanization trend is exacerbating the problem highlighted by natural disasters, contrary to the sustainability and productivity-focused values indicated. This has led to a greater emphasis on optimizing energy use, minimizing waste, and promoting an eco-friendly lifestyle. Additionally, in an increasingly interconnected world, ensuring individuals' safety and security has become a significant concern. Consequently, there is a growing need for automatic protection measures that can detect potential threats and alert residents in real-time. Given the scale of urbanization and the resulting increase in the number of city dwellers, it is essential to address these problems quickly and effectively. This necessitates the development of innovative technologies and strategies that enhance the sustainability and safety of living spaces while also encouraging responsible environmental behavior among residents.

[0006] Furthermore, the gradual increase in the elderly population has posed a common challenge with far-reaching implications for healthcare systems, social and economic structures, and the overall well-being of older adults. As individuals age, they become more susceptible to chronic health conditions, leading to a higher demand for healthcare services. This trend has placed a significant strain on healthcare systems, resulting in an increased demand for healthcare professionals. Additionally, the rising prevalence of chronic health conditions has resulted in escalating healthcare costs, as more individuals require medical treatments and services, thereby exacerbating the burden on public healthcare systems. Furthermore, the aging population has also led to an increased demand for assisted living facilities and long-term care facilities, leading to a shortage of available facilities and increased costs for individuals and families. Addressing these challenges requires innovative solutions and a comprehensive approach that caters to the evolving needs of the aging population. The demand for healthcare and assisted living services is high, and older adults require assistance with daily tasks, monitoring their health, and receiving support during emergencies. Therefore, it is critical to develop innovative solutions that align with the needs of the aging population to ensure that they receive the necessary support and care.

[0007] Against this backdrop of rapid change and uncertainty, all traditional ways of living on the earth became open to discussion, which makes it inevitable to question the most relevant aspect in relation to this; i.e. conventional settlements inside apartments, in big cities all around the world. Most of the time these apartments are not suitable for technological integration for providing smart solutions to people living in these houses. Consequently, the necessity for intelligent living spaces that are adaptable to the changing needs and demands of modern cities and their inhabitants has rendered traditional living spaces that resist change and innovation obsolete. Therefore, there is definitely a need in the state of the art, for providing an alternative to living inside apartments, together with big populations, that resist the change and transformation. Most of the time it is very difficult to transform the old buildings in order to make them suitable for technological integration; the need to convince other people making it more complicated.

[0008] In the state of the art there has been several attempts to address the problems as mentioned above:

[0009] For instance, container houses are becoming increasingly popular due to their costeffectiveness and portability. Some of these container houses even use technology to enhance their functionality, sustainability, and overall living experience. As such, there are several existing solutions and technologies in the field of housing systems:

[0010] Several companies around the globe offer container monitoring systems that use sensors to track temperature, humidity, and other environmental variables. These systems provide alerts to users if any variable falls outside of a set range, allowing for quick response and maintenance. Additionally, many smart home automation systems include features, such as automated temperature control and energy usage tracking. There are also a number of existing energy management systems that use Al algorithms to optimize energy usage in commercial and industrial settings However, these systems are not specifically designed for a transportable smart living system and may not be optimized for the unique challenges of the possible environments, for a transportable and anywhere deployable living system. Nevertheless, they are not sufficient to provide a smart living space that is needed for a sustainable environment and for a smart life.

[0011] While there are some existing solutions that are in the field of housing systems, none of them provide the same combination of features and benefits as the present invention. The present invention is designed specifically for a smart living space which is preferably a transportable living system in order to provide an Al-enabled living space without being bound and limited by the conventional housing systems, and includes a unique combination of sensors, actuators, and Al algorithms that optimize the system’s performance and energy usage.

[0012] The existing prior art solutions in the field of housing systems are explained as below: US4891919 discloses a containerized home for shipping unassembled in a standard size cargo shipping container.

[0013] GB1029280 discloses a "monolithic" prefabricated transportable house or room unit of light weight construction having an aperture in its upper face, in which aperture an edging ring is fitted, the ring having upper and lower flanges for locating the ring in the aperture, the aperture and ring serving for lifting purposes and as a vent or chimney. KR20100089263 discloses a portable house, having an eco-friendly space with good space expandability and easy storage / movement as it folds like a drawer as a portable small house. It is easy to install / move and provides a comfortable space. Since it expands like a drawer, it requires a rail and a rigid frame structure for smooth operation. GR1 009106 discloses, a lightweight transportable house in luggage form, designed for the housing and protection of humans in the nature.

[0014] JP2007154581 discloses a conveyed type portable house extendable and reducible in a vertical direction as well as in a horizontal direction. W02021201561 & KR20210122203 disclose houses for a smart city particularly a house to be used as a coronavirus isolation room. According to the disclosures, the smart city at the base of a conventional city is necessary to quickly accommodate the population. The smart city comprises: a smart city; housing; and a road spaced at a predetermined distance and formed side by side in two rows, the upper part of which is made of metal.

[0015] Thus, it is well known in the state of the art to use pre-fabricated houses, tiny houses, containers and transportable houses as living spaces for people. It is also known to provide transportable houses to people so that people can change the location of where they live without changing the space they live in. Several prior art documents are mentioned above which deal with these problems. Additionally, individual loT devices and smart home platforms exist in the market, however none of these prior art solutions address human life quality improvement as the ultimate objective and there has never been the provision of a combined solution to all the above-mentioned problems in the prior art.

[0016] Moreover, there are other problems in residential spaces of today’s world. Consumers demand data driven suggestions and decision making in everyday living, including health services and predictive assistance for the elderly. There is no prior art solution dealing with such problems which amount to individuals living disconnected from others.

[0017] There is therefore still a need on the market for innovative designs and combinations of existing solutions as well as incorporating new technologies to living spaces, which are suitable for the improvement of human life quality by providing an alternative way of settlement, in particular a transportable and anywhere deployable housing system, without having the disadvantages of the systems of the prior art and without being bound to the limitations of conventional housing systems.

[0018] Thus, the object of the present invention is to design, build and deploy a system for creating an autonomous living space and to improve the human life quality. The objective of these intelligent living spaces is to deliver an entirely personalized lifestyle experience by deriving insights from the user's daily routines. A distinctive aspect of the system is its ability to amalgamate data from various sources, including internal sensors, personal smart devices, and external data, to achieve this aim. This feature enables the system to enhance the user's comfort, minimize environmental impact, ensure their safety, and monitor their health, even when the user is away from their living space.

[0019] Another object of the present invention is the provision of an alternative way of settlement to living in apartments in cities, with great populations. Additionally, the system has the versatility to be situated as an annex to an existing settlement, in accordance with specific requirements. In this regard, the system presents an alternative lifestyle solution for urban areas grappling with the challenges posed by rapid urbanization.

[0020] A still further object is to provide a transportable and smart living system, having the potential to offer a flexible and sustainable living solution that can help people meet the challenges of a rapidly changing world.

[0021] This object and others are achieved by the present invention which relates to an intelligent, modular and sustainable living space leveraging machine learning and loT to design, build and deploy a smart, prefabricated living space which use predictive Al technology for people. The system of the present invention is also suitable for all living spaces such as the ones in apartments, as long as the building is suitable for necessary technological integration. Thus the present invention pertains to the provision of a novel life experience through the integration of the intelligent system into living spaces. This is achieved through the use of data-driven decision-making and machine-learning techniques, which are intended to support the aforementioned experience.

[0022] Moreover, these intelligent living spaces have the ability to create digital twins of their residents while ensuring the utmost privacy and security. Additionally, their software features can be remotely expandable, thereby providing an agile solution that can adapt to the changing needs of their users.

[0023] The systems and methods described herein in the context of the present invention may provide and enable smart living spaces by control of home appliance and / or control of other devices. These systems and methods may utilize advanced data processing and / or artificial intelligence to provide smart space systems and methods that are capable of learning. Additionally, these systems and methods may integrate and interconnect devices within existing infrastructure and wired and wireless home automation networks. Some of the features described herein may utilize big data systems, machine learning and artificial intelligence algorithms, cloud computing technologies, and cloud services, for example.

[0024] The present invention has been devised to not only collect sensor data but also to process and analyze it, providing personalized recommendations to users. A notable attribute of the system is its high adaptability, which enables it to be customized to cater to the specific requirements of individual users. This unique feature facilitates the transformation of living spaces into digital twins that replicate users' preferences and behavior patterns. The present inventive technology is distinguished by its ability to consolidate all data sources pertaining to an individual's behavior. This aggregated data is subsequently transmitted to a data lake located either in the cloud or onpremises, depending on the privacy preferences of the user. Upon storage, machine learning algorithms deployed at the edge-node or in the cloud are employed to analyze behavior, identify recurring patterns, and compare against established best practices. This analysis culminates in the provision of personalized recommendations to the user, in order to guide their daily behavior. Moreover, the system's ability to remotely expand its software capabilities provides an agile solution that can swiftly adapt to changing user needs.

[0025] Systems and methods described herein may comprise one or more computers. A computer may be any programmable machine or machines capable of performing arithmetic and / or logical operations. In some embodiments, computers may comprise processors, memories, data storage devices, and / or other commonly known or novel components. These components may be connected physically or through network or wireless links. Computers may also comprise software which may direct the operations of the aforementioned components. Computers may be referred to with terms that are commonly used by those of ordinary skill in the relevant arts, such as servers, PCs, mobile devices, routers, switches, data centers, distributed computers, and other terms. Computers may facilitate communications between users and / or other computers, may provide databases, may perform analysis and / or transformation of data, and / or perform other functions. Those of ordinary skill in the art will appreciate that those terms used herein are interchangeable, and any computer capable of performing the described functions may be used. For example, though the term “server” may appear in the specification, the disclosed embodiments are not limited to servers.

[0026] In some embodiments, the computers used in the described systems and methods may be special purpose computers configured specifically for providing smart spaces. For example, a server may be equipped with specialized processors, memory, communication components that are configured to work together to perform smart space control, integration, learning as described in greater detail below.

[0027] Computers may be linked to one another via a network or networks. A network may be any plurality of completely or partially interconnected computers wherein some or all of the computers are able to communicate with one another. It will be understood by those of ordinary skill that connections between computers may be wired in some cases (e.g., via Ethernet, coaxial, optical, or other wired connection) or may be wireless (e.g., via Wi-Fi, WiMax, 4G, or other wireless connection). Connections between computers may use any protocols, including connection-oriented protocols such as TCP or connectionless protocols such as UDP. Any connection through which at least two computers may exchange data may be the basis of a network.

[0028] The preferably mobile, smart living system of the present invention is designed to enhance user experience and automate various aspects of daily living by leveraging the Internet of Things (loT) and other advanced technologies. Data is obtained from a wide range of devices and resources, including surveillance cameras, smart doorbell, smart door lock, lidar sensor, smartwatches, temperature sensors, and smart light switches. All these devices are connected to the local area network (LAN) within the living space and transmit data to their respective databases.

[0029] Following data storage, Data Streaming technology is employed to retrieve data from the APIs of these devices. The extracted data is then stored in buckets and Database, depending on the specific requirements for data retention and usage.

[0030] In addition to loT devices, several external APIs, such as AccuWeather, music streaming services, and video streaming platforms, provide valuable data to the system. Similar to the loT devices, data from these APIs is retrieved and stored for further processing.

[0031] Once the data is securely stored, various applications are executed on EMR clusters using PySpark. These applications include Smart Home Intruder Detection, Auto Door Lock, Thermostat Adjustment, Auto Light Switch, Vital Health KPI Tracking, and Mental Health Tracking. Each application utilizes specialized algorithms, as detailed in the algorithm section, to analyze the data and optimize the performance of the respective smart home features.

[0032] When necessary, users are notified of any critical updates or alerts through a mobile application or web interface. This comprehensive system design ensures seamless integration of advanced technology to provide users with an efficient, safe, and comfortable living experience in their smart living space, preferably being mobile. The systems that may be controlled in the smart living space of the present invention are grouped under security, energy efficiency, health and wellness, without being limited thereof.

[0033] Here are some examples of the technologies used in transportable and Al enabled living spaces of the present invention:

[0034] Smart Technologies: Smart technologies allow the owner to control various aspects of the living space, such as lighting, temperature, and security, using a smartphone or other devices.

[0035] High-performance insulation: High-performance insulation helps to keep the living space cool in the summer and warm in the winter. This is important for energy efficiency and overall comfort.

[0036] Smart Storage Solutions: Smart storage solutions are designed to maximize the available space in a housing system. This includes built-in storage units, wall-mounted storage, and other innovative storage solutions.

[0037] Environmentally Friendly Design and Construction: The structure has a raised steel foundation system that allows vegetation to grow underneath and integrates seamlessly into the environment. The elevated design ensures proper ventilation, which is crucial for maintaining optimal thermal balance. Additionally, the system's ample windows enable natural light to permeate the interior space, contributing to a healthier living environment.

[0038] The transportable living space being an Al-enabled living space, of the present invention includes the following components:

[0039] Delicate Sensors: The system includes a variety of sensors that collect data on variables such as temperature, humidity, light, and air quality. These sensors are designed to be unobtrusive and to blend seamlessly into the living environment.

[0040] Al Algorithms: The system includes algorithms as explained in detail hereinbefore, that use machine learning and other techniques to process the sensor data and optimize the user's living environment. The algorithms are highly adaptable and can be customized to meet the unique needs of each user.

[0041] Other Components: The system includes other components such as actuators, user interfaces, and data storage and analysis systems. These components work together to create a seamless and highly optimized living environment for the user.

[0042] The Al-enabled living space system offers several advantages over existing solutions. For instance it is;

[0043] Highly Adaptable: The system is highly adaptable and can be customized to meet the unique needs of each user. The algorithms use machine learning to continuously improve the system's performance over time.

[0044] Unobtrusive Sensors: The delicate sensors are designed to be unobtrusive and to blend seamlessly into the living environment. This allows for a more natural and comfortable living experience.

[0045] Energy Efficient: The system is designed to be highly energy-efficient, with the algorithms optimizing energy usage and reducing waste.

[0046] These are just a few examples of the high-tech features that are implemented in one or more embodiments of the systems of the present invention. Thus, the present invention should not be understood by being limited to these features. As technology continues to advance, it is expected to see even more innovative and sustainable solutions for design and construction. In relation to these another advantage set forth with the present invention relies in its ease of adaptability to emerging technologies. Especially when compared with the conventional settlements in apartment buildings in big cities together with big populations, the adaptability of the present invention to developments in technology appears as an important advantage.

[0047] Accordingly, the present invention is as defined in the accompanying claims. Moreover, the present disclosure is described in more detail, but not limited to the following examples and drawings.

[0048] An advantage of providing artificial intelligence components in the living space of the present invention is to allow the effective management and analysis of different types of collected data. Another advantage is better protection of the user’s privacy.

[0049] In the absence of internet connection effective control over smart living system is maintained. When internet connection is lost, the smart living system of the present invention is managed by implementing several practical measures. First, the smart devices of the present invention are connected to a local network using protocols like Zigbee, Z-Wave, and Bluetooth, allowing them to communicate directly without the need for an external connection. Also, a home automation hub is incorporated, centralizing control and enabling offline functionality for seamless management. Moreover, use of manual control options are made available on many smart devices, such as physical switches, to operate them even in the absence of internet access. Through these proven methods, effective control over our smart home system is maintained despite the connectivity challenges. A detailed description of the Al components and how they interact with the other components of the system is explained below:

[0050] HOME SECURITY

[0051] The Smart Home Intruder Detection

[0052] Lidar sensor and camera-based home surveillance system provides notification to homeowners by applying face recognition motion detection methods in mobile houses. Lidar sensor are used at the interior area of the smart living space and camera outside of the house to provide homeowners privacy in their smart living space.

[0053] Input Data

[0054] Lidar sensors output a 3D point cloud, which is a collection of points in three- dimensional space that represent the surfaces of objects within the sensor's field of view. Each point in the point cloud has a set of coordinates that represent its position in 3D space (typically x, y, and z), as well as additional information such as intensity and reflectivity.

[0055] Both data from surveillance cameras and face pictures from the user interface are collected as matrices as you can see in the representative drawing of Fig 1 . How that data is obtained is mentioned in detail under the IOT Architecture title.

[0056] Required IOT and Data Sources

[0057] Data is collected from two different resources such as lidar sensor and surveillance camera. Both of them have great ability to provide data to cloud so output can be directly consumed as a raw data in the ML (machine learning) models of the present invention.

[0058] Al Approach

[0059] The Smart Home Intruder Detection Al System is a sophisticated, advanced solution that harnesses deep learning techniques and complex algorithms to accurately distinguish potential thieves, intruders in smart home settings. By integrating with existing loT devices, the system offers real-time analysis and monitoring, ensuring a secure and well-protected living space.

[0060] Training Process:

[0061] The training phase of the Al system of the present invention utilizes a comprehensive dataset containing images and videos of various scenarios, including routine household activities and intrusion incidents. A Convolutional Neural Network (CNN) is trained on this dataset, empowering the model to effectively differentiate between regular occupants and potential intruders. The CNN is specifically designed to identify and extract crucial features, such as body posture, movement patterns, and facial attributes, which are instrumental in accurately detecting intruders.

[0062] Algorithm Implementation:

[0063] At the heart of the Al system lies a set of intricate algorithms that process and analyze the output of the trained CNN. These algorithms utilize a combination of decisionmaking techniques, including rule-based systems and anomaly detection, to ascertain if an individual's presence and behavior within the monitored area pose a security threat. The Al system continuously refines and updates its decision-making capabilities, ensuring it remains highly accurate and effective in identifying intruders.

[0064] Integration with loT Devices:

[0065] Al solution of the present invention effortlessly integrates with a wide array of loT devices, such as smart cameras, motion sensors, and door / window sensors, providing comprehensive coverage and monitoring within the smart home environment. The Al system persistently processes data from these devices, examining the information in real-time to identify any indications of intrusion. In case a threat is detected, the system can be configured to activate alarms, send notifications to the homeowner, or initiate other predefined security responses, ensuring a rapid and effective reaction to potential security breaches.

[0066] By implementing a meticulously designed training process, deploying complex algorithms, and integrating seamlessly with loT devices, Smart Home Intruder Detection Al System of the present invention offers an unmatched security solution for smart living space of the present invention. Its capability to precisely identify potential intruders and promptly initiate security measures makes it an indispensable tool in safeguarding the living space and ensuring the well-being of its occupants.

[0067] Auto Door Lock

[0068] Input Data

[0069] User data: The smart door lock of the present invention is configured to be able to identify and authenticate users. In the context of the present invention this can be done using a range of methods such as facial recognition, fingerprint scanning, or a password.

[0070] Lock status data: The smart door lock needs to know whether the door is currently locked or unlocked. This is achieved using sensors or other input devices.

[0071] Access control data: The smart door lock is programmed with access control data, such as the data of which users are allowed to enter the property and when.

[0072] Time and date data: The smart door lock of the present invention is configured to be able to keep track of the time and date so that access control can be managed effectively.

[0073] Battery level data: The smart door lock is configured to monitor its battery level to ensure that it has sufficient power to operate.

[0074] Remote control data: The smart door lock can be remotely controlled, for example, by a smartphone application. The lock needs to be able to receive instructions and send feedback to the user.

[0075] Security event data: The smart door lock is configured to log security events such as failed attempts to gain access or when the door was locked or unlocked.

[0076] Required IOT and Data Sources

[0077] Smart doorbell and smart door lock are used as a data source. As it is described in the architecture part both of them have api which make it possible to retrieve data therefrom.

[0078] Al Approach

[0079] In order to develop a deep learning solution for an automated smart door lock system, a multi-stage process is employed that includes the training of various neural networks, algorithm implementation, and decision-making protocols. The LiDAR sensor will be integrated to determine the user's location in the house, further enhancing the automatic door lock feature. The loT devices employed for this purpose include smart doorbell and smart door lock, both of which provide APIs for seamless data retrieval and integration.

[0080] Training Process:

[0081] Facial recognition: Utilize the smart doorbell's camera feed to train a Convolutional Neural Network (CNN) for identifying and authenticating users. The CNN will process facial images and generate feature activation vectors, which can be matched against a database of known users. The network can be initialized with a pre-trained model, such as FaceNet, and fine-tuned with user-specific data.

[0082] Anomaly detection: Develop a Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM) network to identify unusual access patterns, such as multiple failed attempts or unusual access times, using the security event data.

[0083] LiDAR data processing: Train a neural network or implement a suitable algorithm to process and interpret the LiDAR data, which provides accurate distance measurements to identify the user's position concerning the smart door lock. This is achieved by training a model to recognize specific patterns or anomalies in the LiDAR data that correspond to the user's presence or absence within the house.

[0084] Algorithm Implementation:

[0085] Access control: Implement an algorithm that cross-references user data, access control data, and time and date data to determine whether a user should be granted access. This can include checking for valid credentials (e.g., facial recognition, fingerprint, or password) and verifying that access is allowed within the specified time window.

[0086] Decision-making: Develop a decision-making algorithm that processes the output of the neural networks, access control data, and other relevant input data, such as LiDAR sensor information, to decide whether the door should be locked or unlocked. The algorithm should consider factors such as user authentication status, lock status, battery level, and any detected anomalies.

[0087] Integration with loT Devices:

[0088] Connect to the smart doorbell and smart door lock APIs to retrieve necessary data and control the devices. Integrate the LiDAR sensor with the edge device to retrieve location data in real-time. Implement a communication protocol to receive remote control instructions from a smartphone application, as well as send feedback to the user regarding lock status, battery level, and security events. Integrate the trained neural networks, algorithms, and loT device APIs, including the LiDAR sensor, into a cohesive system that can be deployed on an edge device, such as a Raspberry Pi, for real-time processing and decision-making.

[0089] By following these steps, a comprehensive deep learning solution is developed to automate the locking and unlocking of a smart door lock system, ensuring enhanced security, seamless user experience, and the added functionality of detecting the user's location in the house using a LiDAR sensor.

[0090] ENERGY EFFICIENCY

[0091] Thermostat Adjustment

[0092] Input Data

[0093] Temperature readings: Smart thermostats typically have temperature sensors that can read the temperature in the room. This data is used to determine when to turn on or off the heating or cooling. Occupancy data: Smart thermostats of the present invention can use occupancy sensors or information from other smart devices to determine whether someone is in the room. This information is used to adjust the temperature accordingly.

[0094] Weather data: Smart thermostats of the present invention can use weather data to determine how to adjust the temperature. For example, if it's a hot day, the thermostat may lower the temperature to keep the room cool.

[0095] User preferences: Smart thermostats can be programmed with user preferences, such as desired temperatures at different times of day or different days of the week.

[0096] Energy usage data: Smart thermostats can track energy usage and provide feedback to users on how they can save energy and money.

[0097] Learning algorithms: Smart thermostats of the present invention also use machine learning algorithms to learn from user behavior and adjust settings accordingly.

[0098] Required IOT and Data Sources

[0099] Temperature sensors and Accuweather api are used to retrieve weather conditions.

[0100] Al Approach

[0101] The deep learning solution of the present invention efficiently manages temperature control in smart homes, utilizing sophisticated algorithms and automated decisionmaking processes. The following sections detail the training process, algorithm implementation, and decision-making steps for autonomous temperature adjustment using the input data provided. Also described is the integration of AccuWeather API for weather data and temperature sensors for temperature adjustments.

[0102] Training Process:

[0103] During the training phase, the deep learning model of the present invention employs a comprehensive dataset consisting of various temperature readings, occupancy patterns, weather conditions, and user preferences. A Recurrent Neural Network (RNN) is trained on this dataset, enabling the model to effectively learn patterns and associations between different input factors and the optimal temperature settings. The RNN is designed to recognize temporal patterns and relationships between variables, essential for accurately predicting and adjusting temperature settings.

[0104] Algorithm Implementation:

[0105] At the core of the deep learning solution of the present invention lies a set of advanced algorithms that process and analyze the output of the trained RNN. These algorithms use a combination of decision-making techniques, such as optimization algorithms and reinforcement learning, to determine the most appropriate temperature settings based on the input data. The deep learning solution continuously refines and updates its decision-making abilities, ensuring it remains highly efficient and effective in autonomously adjusting the temperature.

[0106] Decision Making:

[0107] The decision-making process involves interpreting the input data and using the algorithms to adjust the temperature accordingly. For instance;

[0108] Temperature readings: The solution compares the current temperature readings from the temperature sensors with the desired temperature settings and adjusts the heating or cooling systems as required.

[0109] Occupancy data: The solution takes into account the occupancy data and adjusts the temperature settings to ensure comfort and energy efficiency.

[0110] Weather data: By integrating with the AccuWeather API, the solution considers weather conditions and modifies the temperature settings to maintain a comfortable indoor environment.

[0111] User preferences: The solution adheres to user preferences for different times of the day or days of the week, adjusting the temperature settings accordingly.

[0112] Energy usage data: The solution monitors energy consumption and provides feedback to users on how to optimize temperature settings for energy efficiency.

[0113] Integration with AccuWeather API and temperature sensors:

[0114] The deep learning solution of the present invention seamlessly integrates with the AccuWeather API to acquire real-time weather data, enhancing its ability to make informed temperature adjustments. Additionally, the solution utilizes the temperature sensors to obtain accurate temperature readings and make appropriate adjustments based on the collected data.

[0115] By employing a meticulously designed training process, implementing cutting-edge algorithms, and using an intelligent decision-making process, the deep learning solution of the present invention offers a superior temperature control system for smart living spaces of the present invention. Its ability to autonomously adjust the temperature based on various input factors, along with its seamless integration with the AccuWeather API and temperature sensors, ensures optimal comfort, energy efficiency, and user satisfaction.

[0116] Auto Light Switch

[0117] Input Data

[0118] Occupancy data: This could be collected using occupancy sensors, motion sensors, or other similar technologies. It would communicate to the algorithm whether a room or space is currently occupied or not.

[0119] Ambient light data: This could be measured using light sensors or other similar technologies. It would communicate to the algorithm how much light is currently present in the space.

[0120] Time of day data: This could be obtained from a clock or other similar device. It would tell the algorithm what time it is and whether it's daytime or nighttime.

[0121] Historical usage data: This could be collected from previous light usage patterns and energy bills. It would communicate to the algorithm when and how the lights were used in the past and how much energy was consumed during those times.

[0122] User preference data: This could be collected through user surveys or other similar means. It would tell the algorithm what the users' preferences are with regard to lighting, such as whether they prefer bright or dim lighting.

[0123] Required IOT and Data Sources

[0124] Lidar sensor enables to create motion data and light sensor enables to measure current present in the space.

[0125] Al Approach

[0126] Training Process:

[0127] During the training phase, machine learning model of the present invention utilizes a comprehensive dataset containing historical data on user behavior, occupancy patterns, and ambient light levels. A supervised learning algorithm, such as a Decision Tree or Support Vector Machine (SVM), is trained on this dataset, enabling the model to effectively learn patterns and associations between different input factors and the optimal lighting conditions.

[0128] Algorithm Implementation:

[0129] At the core of the machine learning solution of the present invention lies a set of advanced algorithms that process and analyze the output of the trained model. These algorithms employ a combination of decision-making techniques, such as optimization algorithms and rule-based systems, to determine the most appropriate lighting settings based on the input data. The machine learning solution continually refines and updates its decision-making abilities, ensuring it remains highly efficient and effective in autonomously adjusting the lighting.

[0130] Decision Making for Lighting Adjustment:

[0131] The decision-making process involves interpreting the input data and using the algorithms to switch lights on or off accordingly. For instance:

[0132] Occupancy data: The solution uses the LiDAR sensor to detect motion and occupancy in the room, and it adjusts the lighting settings to ensure that lights are turned on when needed and switched off when the space is vacant.

[0133] Ambient light levels: By integrating with the light sensor, the solution measures the current light levels in the space and adjusts the lighting settings to maintain a comfortable and energy-efficient environment.

[0134] User behavior: The solution takes into account historical data on user behavior, learning from past actions and preferences to optimize lighting settings for each individual user.

[0135] Integration with LiDAR Sensor and Light Sensor:

[0136] The machine learning solution of the present invention seamlessly integrates with LiDAR sensors to acquire real-time motion data, enhancing its ability to make informed lighting adjustments. Additionally, the solution utilizes light sensors to obtain accurate ambient light level readings, allowing it to make appropriate adjustments based on the collected data.

[0137] By employing a meticulously designed training process, implementing cutting-edge algorithms, and using an intelligent decision-making process, the machine learning solution of the present invention offers a superior lighting control system for smart homes. Its ability to autonomously adjust lighting based on various input factors, along with its seamless integration with LiDAR and light sensors, ensures optimal comfort, energy efficiency, and user satisfaction.

[0138] HEALTH AND WELLNESS

[0139] Vital Health KPI Tracking

[0140] Input Data

[0141] Heart rate: A smart watch can track the user's heart rate continuously or periodically, providing a time-series data of heart rate changes over time.

[0142] Activity data: The smart watch can track a user's physical activity, such as steps taken, calories burned, distance traveled, and active minutes.

[0143] Sleep data: The smart watch can track a user's sleep quality and quantity, including total sleep time, time in bed, and time spent in different stages of sleep.

[0144] ECG (Electrocardiography) data: The smart watches that can generate an electrocardiogram (ECG) to measure the electrical activity of the heart, providing data that can be used to detect irregular heart rhythms. Blood oxygen level: The smart watches that can measure the user's blood oxygen level, which can be used to detect potential respiratory or cardiac problems.

[0145] Ambient noise level: The smart watch can measure the ambient noise level in the user's environment, which can be used to alert the user to potential hearing damage. Location data: The smart watch can track the user's location, which can be used to provide personalized recommendations based on local weather, events, or services. Occupancy data: This could be collected using occupancy sensors, motion sensors, or other similar technologies. It would communicate to the algorithm whether a room or space is currently occupied or not.

[0146] Required IOT and Data Sources

[0147] Main health data are retrieved from smart watches which are listed above. Additionally motion data are retrieved from lidar sensor to track walking style and rhythm.

[0148] Al Approach

[0149] Training Process

[0150] The Critical KPI monitoring functionality employs two sophisticated algorithms: anomaly detection and rule-based alerts. The anomaly detection algorithm capitalizes on historical user data by applying the Autoencoders deep learning method to recognize unusual patterns. Autoencoders neural networks are designed to minimize errors in reconstructing input data, which effectively identifies anomalies. When an anomaly is discovered, the system promptly alerts the user through a mobile application, keeping them up-to-date on any irregular measurements.

[0151] Algorithm Implementation

[0152] A two-fold approach is used in the solution of the present invention. Firstly, the user's walking patterns and tempo are tracked with a lidar sensor. A convolutional neural network (CNN) is employed, which is trained by each user of the living space of the present invention. This pre-trained CNN generates an array containing the user's unique walking traits for every lidar data point. This array is subsequently inputted into the Autoencoders network mentioned earlier to detect any walking anomalies that might signify an injury. If an anomaly such as an injury is detected, the user receives a notification through the mobile application.

[0153] Integration

[0154] Lastly, a rule-based alert system is offered that does not rely on algorithms. Users supply with specific health information gathered from their smartwatches. When the submitted data falls outside the user-defined threshold in the mobile application, the system of the present invention sends an alert. For example, if a user sets a blood oxygen level threshold below 90%, system notifies the user when the reading drops below that value. This integration of user-defined rules, alongside the advanced algorithms of the present invention, enhance the overall user experience by providing personalized and timely notifications.

[0155] Mental Health Tracking

[0156] Input Data

[0157] User Streaming History: Collect data on the user's listening and viewing history, including information about the specific tracks, albums, artists, genres, and playlists for music, as well as movies, TV shows, and video genres for video streaming.

[0158] Timestamps: Record the date and time of each streaming activity to understand patterns in the user's habits, such as preferred time of day or days of the week for streaming.

[0159] Playback Duration: Keep track of how long users spend listening to each track or watching each video to identify their level of engagement with the content.

[0160] Emotional Attributes: Analyze the emotional attributes of the content being streamed, such as sentiment (positive, negative, or neutral), tempo, and energy level for music, and the mood or theme of movies and TV shows.

[0161] User Preferences: Gather data on the user's preferred content, such as favorite artists, playlists, movie genres, and other preferences to establish a baseline for their typical streaming patterns.

[0162] User Interaction: Monitor user interactions with the streaming platform, such as likes, dislikes, shares, and comments, to gain insights into their emotional responses to the content.

[0163] User Demographics: Collect demographic information about the user, such as age, gender, and location, to help contextualize their streaming patterns and preferences. External Factors: Consider external factors that may influence a user's streaming habits, such as weather, time of year, or significant events.

[0164] Required IOT and Data Sources

[0165] Music and video streaming technologies APIs like spotify, youtube, netflix etc.

[0166] Al Approach

[0167] This is a multi-variable pattern recognition problem which can be solved with an Al- based mental health tracking solution for smart living systems. It can be designed using various data sources to analyze user emotions and offer personalized insights. By processing User Streaming History, Timestamps, Playback Duration, and Emotional Attributes, the Al system identifies patterns and correlations between the user's emotional state and streaming habits. Incorporating User Preferences and User Interaction data helps the system recognize deviations from the norm, potentially detecting emotional distress or mental health concerns. User Demographics and External Factors provide context for the user's streaming habits within a broader sociocultural environment. Utilizing machine learning algorithms, the Al system continuously refines its understanding of the user's emotional well-being and generates personalized recommendations, such as calming music or uplifting movies, to support their mental health.

[0168] Training process:

[0169] Data Labeling: To train a supervised machine learning model, labeled data is necessary. Self-reported mental health data from users are collected as well as collaborating with mental health experts to review and label the collected data. This labeled data will serve as the target variable for the algorithm of the present invention. Algorithm Implementation

[0170] In addressing the issue at hand, an approach i§ adopted that entails assessing mental health through the identification of patterns. Although traditional methodologies, such as linear regression and random forest, provide some assistance, they fail to accurately represent temporal pattern alterations. Consequently, stationary algorithms are not ideally suited for the model of the present invention or the problem under consideration. Instead, the Long Short-Term Memory (LSTM) algorithm is employed, which is adept at establishing connections between music and video content, as well as their antecedents, thereby enabling effective pattern detection.

[0171] Integration

[0172] It is important to incorporate the APIs of various streaming platforms, including Spotify, YouTube, and Netflix, into the system of the present invention. As illustrated in the Internet of Things (loT) architecture section, the data obtained from these APIs will be utilized to populate the database.

[0173] By integrating these streaming APIs, the wealth of information provided by each platform is leveraged, which will significantly enhance the ability to analyze patterns and trends in user behavior. This comprehensive dataset will serve as a critical component of the loT infrastructure, enabling the development of more robust and accurate predictive models. To achieve this integration, it is necessary to first familiarize with each platform's API specifications and requirements. This involves understanding the unique authentication processes, data structures, and usage limitations for each service. Next, the application is registered with the respective developer portals to obtain the necessary API keys and access tokens.

[0174] Once the requisite credentials are obtained, proceed to develop wrapper functions or utilize existing libraries that facilitate seamless communication with each API. These functions will be responsible for extracting relevant data from the platforms, such as track details from music streaming services such as Spotify, video metadata from video sharing website such as YouTube, and show information from streaming services offering a wide variety of TV shows, movies and original content such as Netflix.

[0175] After extracting the necessary data, preprocess it by cleaning, transforming, and standardizing it into a uniform format that can be easily ingested by the database of the present invention. Also needed to ensure that the loT architecture is capable of handling data from multiple sources and can accommodate various data types and structures.

[0176] Finally, it is crucial to be mindful of the rate limits and quotas imposed by each platform's API. Strategies are implemented, such as caching or staggered requests, to avoid exceeding these limits and ensure uninterrupted data access.

[0177] By following these steps, the streaming APIs are successfully integrated into the loT architecture of the present invention, thereby maximizing the potential of the data available for analysis and pattern recognition.

[0178] Figure 1 illustrates IOT (internet of things) architecture and the letters and the numbers in the drawing refer to:

[0179] Diagram Layers

[0180] A: Perception; B: Network; C: ML (machine learning) Applications; D: Infructure

[0181] 1 : loT Thing Camera; 2: loT Thing Door Lock; 3: Smart Phone; 4: The Smart Home Intruder Detection; 5: Auto Door Lock; 6: Thermostat Adjustment; 7: Auto Light Switch; 8: Vital Health KPI Tracking; 9: Mental Health Tracking; 10: Database (Amazon DynamoDB Accelerator); 1 1 : Bucket; 12: EMR Cluster; 13: Amazon Kinesis Data Streams;

[0182] E: 3rdParty Data Sources

[0183] 14: Music Streaming; 15: Video Streaming; 16: Google IOT API; 17: Garmin IOT API 18: AccuWeather API; 19: Smart watch health data F: User Interface

[0184] According to an embodiment of the present invention, Al enabled living space is transportable anywhere in the world and deployable on every solid ground. It can be transported as fully assembled and delivered by trucks. After the location is determined, It can be placed on solid ground with a steel foundation system raised above the ground, or even elevated on water.

[0185] According to another embodiment of the present invention the living space is 24 m2and is designed for 2 people. Large windows are incorporated making the living space a bright one. Additionally, is designed to have a high ceiling. The internal volume of the living space according to this embodiment is equivalent to a 1 -bedroom flat 8x8x3; 24m2and 192 m3. The heating inside the living space is adjustable through floor heating and / or air conditioning.

[0186] Figure 2 is a plan view from top according to an embodiment of the transportable housing system. This embodiment comprises a folding desk (1 ) having dimensions 50 cm x 190 cm. The folding desk opening from the wall lifts back to the wall when not in use. Thus, it saves space when folded and creates a working place when opened, in the corner of the living area where daylight can be utilized. When folded, it can even be hidden on the wall. The Murphy bed (2) has dimensions 190cm x 140cm and can be folded and closed when not in use. In this way, it saves space. The folding dining table (3) has dimensions 50cm x 1 10 cm. It opens from the back of the folding bed. It is designed to fit 4 people. When folded, it creates an invisible surface. The skylight window (4) has dimensions 60cm x 90cm and is suitable to open. Heat-insulated joinery and glass are used. It can be controlled remotely with its integrated motor. In the kitchen (5) part of the living space MDF kitchen cabinets are used. It is resistant to water and moisture. On the interior parts of the living space formaldehyde-free interior coatings (6) are used. Different color options can be used in the interior according to request from the person to live inside the smart living space. Entrance door (7) has the same material as the exterior, thermowood, with an exterior finish. Thermowood material siding (8) since it is a pre-heat treated material, it has a high strength, long service life and easy maintenance. Electrical system (wired) underfloor heating (9) is used in the living area and bathroom. Insulated Aluminum Joinery (10) has glass consisting of layers of 6mm Temperable Low-E Glass + 16mm Cavity + 6mm Clear Float Glass.

[0187] Figure 3 is a side view of the transportable housing system according to this embodiment. It comprises a load-bearing Steel foundation system (1 ) made from galvanised HRS profile. In this way, the structure can be moved on this construction without throwing concrete on the ground. This feature makes the living space environmentally friendly. It also protects the health of the structure by providing ventilation from below. Also comprises

[0188] Bathroom door (2). Storage areas (3) are cabinets, shoe rack, shelf. Their material is poplar marine plywood which is a moisture and water-resistant natural material.

[0189] Figure 4 is an isometric drawing of the transportable housing system according to this embodiment. The length (1 ) is 807 cm and the width (2) is 300 cm. The height (3) is 300 cm (living area) + Steel foundation system (Its height may vary according to the structural characteristics of the ground). Design-specific corner glass (4) which is a floor-to-ceiling glass used on the short fagade. Front and left fagade of the living area (5), rear and right fagade of the living area (6).

[0190] An example of an Al algorithm that could be used in a smart system of the present invention:

[0191] A reinforcement learning algorithm is used to optimize the energy usage of a smart system. The algorithm learns from the system’s energy usage patterns and optimize its energy consumption by adjusting the system's settings and parameters. The reinforcement learning algorithm uses a reward function that incentivizes the system to minimize energy consumption while maintaining optimal performance.

[0192] The algorithm continuously receives input data from sensors in the system that monitor variables such as temperature, humidity, and occupancy levels. The algorithm then uses this data to make decisions on how to adjust the living space’s systems, such as adjusting the thermostat or turning off lights when the container is unoccupied. Over time, the algorithm learns which actions lead to the most energy savings and adjust its behavior accordingly.

[0193] Similarly, smart appliances that incorporate predictive Al algorithms can learn from the user's daily habits to optimize their performance and energy consumption. For example, a smart refrigerator can learn the user's eating habits and automatically adjust its temperature and settings to keep food fresher for longer periods. It can also suggest recipes based on the ingredients that are available inside the fridge, or remind the user when items are about to expire.

[0194] Another example of predictive Al technology about daily habits used in smart living spaces is a smart security system that uses Al to learn the daily routines of the occupants and detect any unusual behavior or activity. The system can use data from sensors, cameras, and other sources to identify patterns and anomalies in behavior and can alert the occupants or authorities if necessary. The system can also learn from false alarms and adjust its algorithms accordingly to reduce the likelihood of false positives in the future. Additionally, the system can provide insights into how occupants can improve their security, such as by adding additional lighting or reinforcing doors and windows in certain areas of the living spaces.

[0195] This Al algorithm could significantly reduce energy usage and costs, while maintaining optimal performance and user comfort.

[0196] Conclusion:

[0197] The Al-enabled living space system using Serai algorithms provides a new and improved way of optimizing living spaces using artificial intelligence. The system includes delicate sensors, Al algorithms, and other components that work together to create a highly optimized and comfortable living environment for the user. The system is highly adaptable, unobtrusive, and energy-efficient, making it an ideal solution for a wide range of living environments.

[0198] All embodiments of the present invention have the advantage of making city life manageable, giving people a safe haven to retreat to whenever and wherever.

[0199] An additional advantage is that all embodiments allow users to measure key metrics of their lives, allowing seamless improvement in every aspect.

[0200] The swift deployment and the shortened paperwork in all major jurisdictions, of the present invention make it an appealing property, allowing convenient expansion for one’s business.

[0201] The sustainable operations of the present invention, ensure minimal carbon footprint, embracing the ecofriendly lifestyle necessary for a sustainable world.

[0202] Several different embodiments according to the present invention are defined herein below: A system for providing a smart living space, comprising: an enclosed structural element comprising walls having an envelope structure comprising an inner layer, a structural layer, an insulation layer and an outer layer arranged sequentially from the inside to the outside of the enclosed structure, a plurality of smart objects for the detection and processing of data, wherein each smart object is either for home security, energy efficiency, health or wellness and can be located within different areas inside or on the outer part of the enclosed structure relevant to its purpose, and operationally connected to each other having the same purpose of either security, efficiency, health or wellness; by means of a wireless network wherein each of the smart object comprises at least, one sensor device for the collection of data from a pre-determined area of the living space in relation to the purpose of the smart object, at least one storage unit of said collected data, at least one processing unit with high computational capacity configured for the processing of said collected data, at least one wireless communication unit configured for the communication with at least one of the other smart objects having the same purpose of either security, efficiency, health or wellness, distribution and synchronization means of the data collected by smart objects within the same purpose group, a local area network configured to receive data from the plurality of smart objects, an artificial intelligence server in communication with the local area network comprising cluster services configured to: generate clusters of the data received from each of the smart objects; and perform processing comprising using a cluster to detect an anomaly in the smart object, identify the smart object, classify the smart object based on its purpose being either security, efficiency, health or wellness, determine a user behavior, determine a user mood, determine an energy consumption pattern, or create an automated action, or a combination thereof, generate an actuation command or a user notification according to an evaluation of applicable rules.

[0203] The system wherein the structural layer of the enclosed structural element comprises one or more of the materials selected from thermal insulation materials, waterproofing materials, acoustic insulation materials, fireproof materials, antistatic materials and structural materials.

[0204] The system wherein the structural layer of the enclosed structural element comprises one or more of the materials selected from light gauge steel, structural steel, wood, aluminum composite panel, sandwich panel, glass, fiberglass panel, plastic integrated board, corrugated polycarbonate sheets, biopolymer-based composites, foamed PU board, foamed cement, cement fiber board, gypsum board, glass, magnesium board, metal integrated wall board.

[0205] The system wherein the outer layer of the enclosed structural element comprises one or more of the materials selected from heat insulating material, fireproof material, water proofing material or anti-static material.

[0206] The system wherein the heat insulating material comprises one or more of cellular glass, rock wool, rubber-plastic board, mineral wool, polyurethane foam, polyurethane board, aerogel blanket, aluminum-coated rock wool board, aluminum-coated mineral wool board, glass wool, XPS extruded board or EPS polystyrene board.

[0207] The system wherein the anti-static material comprises one or more of ceramic tile, plywood, marine plywood, gypsum board, MDF, laminate flooring, concrete, plaster, tadelak, lime, PVC coating, glass, thermowood, polyester, wood veneer, aluminum sheet, bituminous membrane, epoxy, polyurethane foam, PVC membrane, vapor barrier membrane, vapor stabilizing membrane, polyester, styrofoam, urethane foam, phenolic foam, greenhouse film, wood floor, composite floor, plastic integrated wall panel or bamboo wood fiber integrated wall panel solid wood floor.

[0208] The system wherein the interior of the enclosed structure forming the smart living space comprises at least a living area and a washing area. The system wherein a material for blocking the sunlight and / or a lightning rod are arranged outside the enclosed structure.

[0209] The system wherein the enclosed structural element comprises a vent located on the side wall of the outer layer and the ventilation opening is provided with a ventilation fan.

[0210] The system wherein the outer layer and / or the inner layer is provided with soundinsulating materials.

[0211] The system wherein the sound-insulating material comprises one or more of materials selected from sound-absorbing cotton, glass wool, mineral wool, rubber tape, cork sheet, cardboard sheet, rubber sheet, acoustic panel.

[0212] The system wherein the outer layer comprises an outer coating of aluminum foil to protect its occupants from weather conditions with particular reference to solar radiation.

[0213] The system wherein the at least one smart object comprises a lidar sensor, a door / window sensor, a camera, a smart doorbell, a smart door lock, a smart thermostat, a light sensor, a smart socket, a presence tag, a smart wall unit, a smart watch, a television, a home theater component, an appliance, a music and video streaming application or a lock, or combinations thereof.

[0214] The system of anyone of preceding claims wherein the enclosed structural element is a mobile container, a pre-fabricated house or an apartment flat.

[0215] The system wherein effective control over smart living system is maintained even in the absence of internet connection by allowing smart devices to communicate directly without the need for an external connection, incorporation of an automation hub or manual control options or combinations thereof.

Claims

CLAIMS1 . A system for providing a smart living space, comprising: an enclosed structural element comprising walls having an envelope structure comprising an inner layer, a structural layer, an insulation layer and an outer layer arranged sequentially from the inside to the outside of the enclosed structure, a plurality of smart objects for the detection and processing of data, wherein each smart object is either for home security, energy efficiency, health or wellness and can be located within different areas inside or on the outer part of the enclosed structure relevant to its purpose, and operationally connected to each other having the same purpose of either security, efficiency, health or wellness; by means of a wireless network wherein each of the smart object comprises at least, one sensor device for the collection of data from a pre-determined area of the living space in relation to the purpose of the smart object, at least one storage unit of said collected data, at least one processing unit with high computational capacity configured for the processing of said collected data, at least one wireless communication unit configured for the communication with at least one of the other smart objects having the same purpose of either security, efficiency, health or wellness, distribution and synchronization means of the data collected by smart objects within the same purpose group, a local area network configured to receive data from the plurality of smart objects, an artificial intelligence server in communication with the local area network comprising cluster services configured to: generate clusters of the data received from each of the smart objects; and perform processing comprising using a cluster to detect an anomaly in the smart object, identify the smart object, classify the smart object based on its purpose being either security, efficiency, health or wellness,determine a user behavior, determine a user mood, determine an energy consumption pattern, or create an automated action, or a combination thereof, generate an actuation command or a user notification according to an evaluation of applicable rules.

2. The system of claim 1 wherein the structural layer of the enclosed structural element comprises one or more of the materials selected from thermal insulation materials, waterproofing materials, acoustic insulation materials, fireproof materials, antistatic materials and structural materials.

3. The system of claim 2 wherein the structural layer of the enclosed structural element comprises one or more of the materials selected from light gauge steel, structural steel, wood, aluminum composite panel, sandwich panel, glass, fiberglass panel, plastic integrated board, corrugated polycarbonate sheets, biopolymer-based composites, foamed PU board, foamed cement, cement fiber board, gypsum board, glass, magnesium board, metal integrated wall board.

4. The system of anyone of claims 1 to 3 wherein the outer layer of the enclosed structural element comprises one or more of the materials selected from heat insulating material, fireproof material, waterproofing material or anti-static material.

5. The system of claim 4 wherein the heat insulating material comprises one or more of cellular glass, rock wool, rubber-plastic board, mineral wool, polyurethane foam, polyurethane board, aerogel blanket, aluminum-coated rock wool board, aluminum- coated mineral wool board, glass wool, XPS extruded board or EPS polystyrene board.

6. The system of claim 4 wherein the anti-static material comprises one or more of ceramic tile, plywood, marine plywood, gypsum board, MDF, laminate flooring, concrete, plaster, tadelak, lime, PVC coating, glass, thermowood, polyester, wood veneer, aluminum sheet, bituminous membrane, epoxy, polyurethane foam, PVC membrane, vapor barrier membrane, vapor stabilizing membrane, polyester, styrofoam, urethane foam, phenolic foam, greenhouse film, wood floor, composite floor, plastic integrated wall panel or bamboo wood fiber integrated wall panel solid wood floor.

7. The system of anyone of preceding claims wherein the interior of the enclosed structure forming the smart living space comprises at least a living area and a washing area.

8. The system of anyone of preceding claims wherein a material for blocking the sunlight and / or a lightning rod are arranged outside the enclosed structure.

9. The system of anyone of preceding claims wherein the enclosed structural element comprises a vent located on the side wall of the outer layer and the ventilation opening is provided with a ventilation fan.

10. The system of anyone of preceding claims wherein the outer layer and / or the inner layer is provided with sound-insulating materials.1 1. The system of claim 10 wherein the sound-insulating material comprises one or more of materials selected from sound-absorbing cotton, glass wool, mineral wool, rubber tape, cork sheet, cardboard sheet, rubber sheet, acoustic panel.

12. The system of anyone of preceding claims wherein the outer layer comprises an outer coating of aluminum foil to protect its occupants from weather conditions with particular reference to solar radiation.

13. The system of claim 1 , wherein the at least one smart object comprises a lidar sensor, a door / window sensor, a camera, a smart doorbell, a smart door lock, a smart thermostat, a light sensor, a smart socket, a presence tag, a smart wall unit, a smart watch, a television, a home theater component, an appliance, a music and video streaming application or a lock, or combinations thereof.

14. The system of anyone of preceding claims wherein the enclosed structural element is a mobile container, a pre-fabricated house or an apartment flat.

15. The system of anyone of preceding claims wherein effective control over smart living system is maintained even in the absence of internet connection by allowingsmart devices to communicate directly without the need for an external connection, incorporation of an automation hub or manual control options or combinations thereof.

Citation Information

Patent Citations

  • Improvement in prefabricated house- or house-room-units

    GB1029280A

  • Transportable house in luggage form

    GR1009106B

  • Conveyed type portable house

    JP2007154581A

  • Portable house

    KR1020100089263A

  • Waterproof insulation ring and insulated valve chamber using the same

    KR1020230039198A