Patent Application
20190079476
In a conventional home system, a user can remotely control and manage home appliances via a portable device. Each home appliance is operated and controlled manually in many cases. Smart spaces may integrate control of a variety of home appliances. Smart spaces use integrated wiring technology, network communication technology, security technology, automatic control technology, and audio and video technology to integrate control of home appliances. Smart spaces networks may include control panels that a person may use to input settings, preferences, and scheduling information that the smart spaces network uses to provide automated control the various devices, appliances, and systems in the home. For example, a person may input a desired temperature and a schedule indicating when the person is away from home. The home automation system uses this information to control the heating, ventilation, and air conditioning (“HVAC”) system to heat or cool the home to the desired temperature when the person is home, and to conserve energy by turning off power-consuming components of the HVAC system when the person is away from the home.
The systems and methods described herein may provide and enable smart spaces for home appliance control and/or control of other devices. These systems and methods may utilize advanced data processing and/or artificial intelligence to provide smart spaces 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.
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.
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, etc. that are configured to work together to perform smart space control, integration, learning, etc., as described in greater detail below.
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.
Examples of systems that may be controlled by the smart spaces systems and methods described herein may include, but are not limited to, the following: security technology, indoor video intercom, home monitoring, home burglar alarm, home and cell card, household equipment, household energy, audio and video technology, centralized distribution of audio and video, background music, HVAC system, lighting systems, alarm systems, home theater, entertainment systems, other appliances, etc.
Additionally, external elements such as third party/B2B apps 152/154, third party databases 156, and/or third party ecommerce platforms 158 may be in communication with the hub 110 and/or apps 132-136 via the network 140. A system ecommerce platform 160 may also be in communication with the hub 110 and/or apps 132-136 via the network 140. The system ecommerce platform 160 may include a variety of data (e.g., external user databases 172, content management systems (CMS) 174, customer relationship managers (CRM) 176). In some embodiments, for example, the ecommerce platform 160 and/or third party platforms 158 may allow the user to install applications to display multimedia content, install IoT applications, share social media, and/or add features to receive predictions and recommendations from the smart home devices and IoT devices.
The apparatus allows the app marketplace to auto install new services and applications in background to deliver future new services, content providers and control new devices and protocols among other applications which could extend future applications and new services as they become available
Systems and methods for providing smart spaces may be capable of operating and managing various aspects of residential and/or commercial environments. In some embodiments, the system may employ an artificial intelligence (AI) system, for example comprising the hub 110 and/or the ML modules 240-260 of the server 200.
Some embodiments may connect a smart space to a cloud based or otherwise network accessible remote system. The remote system may be capable of managing and handling big data. The system may include an operating system, machine learning algorithm, and prediction modules to adapt to a user's preferences. The cloud-based system may provide out-of-home or out-of-office access to the premises and also data for the AI system.
In some embodiments the system may include an integration module configured to integrate the system, big data architecture, mobile devices, and communication protocols. Furthermore, the system may allow interoperability of third party devices, appliances, and the like thus enabling seamless integration of the above. In some embodiments, the integration module may use open standards for interoperability. For example, the open standards may comprise protocols from Home Kit, Thread, Insteon, Zigbee, ZWave, and Wi-Fi, among others. The integration module may provide integration of third party smart spaces systems and automated residential devices.
In some embodiments, the system may provide a gateway for incorporation of a full suite of smart systems (e.g., IoT devices), Example gateway devices may include a modem, a router, a network switch, a voice over internet protocol (VoIP) for digital signals device, an analog telephony adapter, or a wireless access point, or combinations of the above. The gateway may provide a mechanism to connect to different devices independent of devices manufacturer, or operating system, or firmware, etc. For example,
In some embodiments, the hub 110 may be connected to a personal computer or other device, and firmware/software to interact with the hub 110 may be downloaded and installed on the computer to further exploit the potential of the the hub 110. The hub 110 may include indicators and a user interface. In one embodiment, the software for the hub 110 may provide a user with pre-configured commands. For example, the preconfigured commands may be help, version, reset, get state/status of any device, set state of any device, bind, factory reset, network details, boot mode, date time command, and bind set.
In some embodiments, the gateway may be provided using a smart box or dangle. In some embodiments, the system may include an operating system based on a Google Android platform. A game controller, remote control, and/or mobile application may be used to input commands into the system, for example. In some cases the smart box may be attached to a television set, and a user may interact with the system via a television interface, for example. Optionally, the smart box may be a central standalone box including a user interface. The system may work with or without Internet, router, and/or Wi-Fi. The system may have a server installed and create a network whereby the devices may communicate with the system without the need of Internet or other separate network, for example. The smart box may connect a full suite of interconnected devices and apparatus with the cloud learning system via a built-in multi-protocol architecture that may operate and manage various aspects of human environments and interfaces. Additionally, the system may be configured to receive upgrades, add additional application to support newly introduced devices, and the like.
The system may integrate multi-protocol third party devices with intelligent discovery and intelligent mapping. The system hardware may communicate with a broad range of devices converging many standards and technologies. The communication with third party smart spaces devices may be accomplished with the use of a communications dongle which may be multi-protocol. Communication protocols supported by the dongle may include Wi-Fi, Zigbee, Zwave, Thread, Home Kit and Bluetooth Low Energy. Through the communications dongle, the system may control and communicate third party devices.
An example enclosure for the system is shown in
The system may include plug and play installation and initialization features. The plug and play functions of the system may be performed by installed gateway software. For example, when a user plugs the smart box in to a power supply a first time, a program stored in system memory may load drivers, automatically initialize the system to connect to an available network, and operationalize different modules. For example, with ZigBee, the drivers may run a network initialization sequence that may search for the best ZigBee wireless channels available, create a ZigBee network in an identified channel, get network information, store the information locally, and/or automatically upload the information to the cloud.
When the system is connected to the Internet it may launch an automatic plug and play registration process. Automatic registration process may begin when the system connects to a local network with Internet connectivity.
In
In
The system may automatically start discovering devices in different networks like LAN (through Ethernet or Wi-Fi and different protocols like upnp/dlna), ZigBee, zwave, thread, homekit, etc. The system may perform an intelligent discovery and mapping process, whereby the system may add devices locally and then push the configuration to the cloud. The configuration and auto-joining and programming may be cloned into the client's smartphones, tablets, computers, etc.
When the networks needs specific security processes (for example zwave door locks) for discovering network devices, the system may establish secure connections and protocols to perform the discovery/mapping process. In lieu of automation, an event (physical button in devices, mobile apps, web apps, etc.) trigger may be required by the system to finalize the mapping/discovery process.
The intelligent mapping software may discover devices and communication protocols from third party vendors to integrate with the system. The discovery may be accomplished through the hub 110 and server 200 communicating with the devices 120 and checking the received data against known device API data, for example. The intelligent mapping software of the integration module may automatically load the devices' characteristics to the system. Additionally, the integration module may automatically back up the data to cloud. Moreover, the intelligent mapping software may generate automatic hardware handlers. These handles may be stored and used by different modules to communicate and control with these devices.
Next, the system may send the command “get manufacturer information” with the “Node Id”. This may return the manufacturer information response from the network, The process may create a unique identifier for each new device detected. For example, the unique identifier may include a product type ID and/or a serial number of the device. The information obtained from the Zwave device may include serial number, manufacturer information, and commands supported by the device, for example. The machine learning algorithms may apply the information gathered, detect the devices' capabilities, and use the automatic user interface generation to produce the user interface for the device automatically.
Once the hub 110 is set up and devices 120 are added, the hub 110 and server 200 may begin monitoring and control of devices 120 in the smart space.
Some objects controlled by the system may be smart objects. Smart objects may include data analysis and summarization features to provide data about device type, appliance behavior recognition, usage pattern recognition, anomaly detection, geo-localization usage, automated action, and/or other features, The hub 110 and/or server 200 may detect the kind of appliance connected through the smart device. The hub 110 and/or server 200 may perform activity, room/space, and/or geolocation detection and form clusters of the detected data from the smart object. The hub 110 and/or server 200 may detect device usage patterns over time based on the data clusters. The hub 110 and/or server 200 may detect different abnormal behaviors related to the data gathered by the smart object (e.g., the usage pattern data). The smart object may transmit gathered data to the hub 110, and the hub 110 and/or server 200 may perform usage pattern and/or anomaly detection, for example. The smart object may also include Automated scenes and butlers generation.
A door/window sensor 1210 may include two units configured to be mounted in proximity to one another (one to the door/window and one to a stationary surface nearby) and sense when the door/window is opened/closed. For example, a first unit may include a front plate 1211, a fastener 1212, a circuit 1213, and a housing 1214. The second unit may include a front plate 1215, a magnet 1216, and a rear plate 1217. The circuit 1213 may detect the presence/absence of the magnetic field of the magnet 1216 and report this detection (e.g., via WiFi, Bluetooth, or some other connection) to the hub 110. This sensor may be attached to things that can be opened and closed (e.g., doors, windows, cabinets, drawers, etc.) and may generate alerts when they are opened. The open/closed sensor may detect motion with an accelerometer and/or may include sensors for temperature, humidity, and luminosity.
A smart plug 1220 may include an outlet 1221, a terminal 1222, one or more circuit boards 1223/1224, a housing 1225, a button 1226 that may be in contact with one or more of the circuit boards 1223/1224 and mounted in the housing 1225, and an inlet 1227/1228. The circuit boards 1223/1224 may include a circuit that may detect the presence and/or power usage of a device plugged into the outlet 1221 and report this detection (e.g., via WiFi, Bluetooth, or some other connection) to the hub 110. The smart plug may turn any electrical appliance into a smart device by simply plugging the appliance into the smart plug. The smart plug may be placed between the power outlet and the device. The smart plug, in conjunction with the system, may allow users to increase efficiency, turn devices on and off, and/or monitor and control energy consumption from anywhere. Users may be able to keep track of the energy usage and automatically interrupt the electrical supply if the smart plug detects high temperature in the environment. If the smart plug is plugged into a lamp, it may detect the lumens in the environment and turn the lamp when it gets dark. The smart plug may also dim the lights of the lamps. The smart plug 1220 may be configured to avoid covering other outlets (e.g., if the smart plug 1220 is plugged into a first outlet in a 2-outlet wall socket, it may not cover the second outlet).
A sensor unit or smart station 1230 may include a top cover 1231/1232, a bottom cover 1233, a front cover 1234, a back cover 1235, one or more fasteners 1236/1238, a power inlet 1237, and a circuit 1239, The circuit 1239 may include one or more sensors (e.g., light sensors, gas sensors, temperature sensors, etc.). The circuit 1239 may report sensor outputs (e.g., via WiFi, Bluetooth, or some other connection) to the hub 110. For example, the smart station may include a built-in camera and/or other sensors and may measure emotion, face detection, air quality, smoke, CO, temperature, pressure, presence, motion, humidity, luminosity, etc. For example, the smart station may automate lamps to turn on when darkness is detected. The smart station may detect motion using an accelerometer to remove false positives. The smart station may alert for fire and may include “Air Quality Detection” (Smart Station Protect) to send alerts and help prevent CO poisoning.
A smart socket 1240 may include a bottom cover 1241, a circuit 1242, a top cover 1243, and a socket thread 1244. The socket thread 1244 may supply power from the socket into which the smart socket 1240 is screwed to the light screwed into the smart socket 1240. The circuit 1242 may detect the presence and/or power usage of a device screwed into the smart socket 1240 and report this detection (e.g., via WiFi, Bluetooth, or some other connection) to the hub 110. The smart socket may allow a user to monitor energy usage, dim the lights, turn them on/off when from anywhere, set them in random patterns to provide the appearance of a crowded house, etc.
An infrared skipper 1250 may include a top cover 1251, one or more fasteners 1252, a circuit 1253, a middle cover 1254, and a bottom cover 1255. The circuit 1253 may include an infrared transceiver that may detect appliances using infrared remote control (e.g., televisions and other home theater components, etc.). The circuit 1253 may be configured to control such appliances as well as detect information about the appliances. The circuit 1253 may receive commands from and report data to (e.g., via WiFi, Bluetooth, or some other connection) the hub 110. Infrared is shown in this example, but in some embodiments, the skipper 1250 may communicate with appliances via Bluetooth or other connection in addition to or instead of via infrared. The skipper may function as a universal remote control and IR blaster. The skipper may be placed in a room, and it may detect all the appliances that have infrared technology (AC, TV, DVR, and audio system, for example). Using the infrared connection, the skipper may allow users to control the devices from anywhere.
The system may also include a presence tag (e.g., an RFID tag that may communicate with the hub 110 and/or a smart device such as those described above) in some embodiments. The presence tag may trigger an alert if the tag is removed from within a specified zone. The zone may be customizable using the system. For example, a child's backpack may be tagged, and the tag may trigger an alert when the child is back from school. The presence tag may be implemented with key chains, pet collars, etc. The tag may allow the system to know if the tag is within range. Optionally, the presence tag may automatically trigger actions based on a user's presence. For example, when a user walks into the living room, the system may play favorite music, turn the lights on, or preform any other customized function.
The system may also include a smart wall unit that may convert any socket or switch without having to change the outlet. It may be installed inside a box in a wall, and it may be compatible with standard electrical boxes (e.g., wall sockets or switches). The smart wall unit may allow on/off switching, dimming, and energy monitoring, among other functions, similar to the smart plug 1220 and smart socket 1240 except hard-wired within the electrical box.
The system may also be configured to communicate with third party devices such as smart thermostats, plugs, and dimmers manufactured by Centralite and others; and/or door locks manufactured by Kwikset and others.
The following is an example set of smart object classification category types that may be used by the system and artificial intelligence:
Within each category, specific smart objects may be provided, for example as follows:
The system may learn different aspects of its environment (e.g., users and devices) and perform smart object classification automatically. The system may include learning algorithms tuned to apply specifically to smart spaces and commercial systems and internet of things systems and architectures. The algorithm may work in conjunction with a big data module. The big data module may detect and capture events. For example, if a user manually turns on a switch, the big data module may capture that event, or if a bulb dies, the big data module may capture that event through one or more anomaly detection modules, and so on. The system may be able to learn more efficient ways to save energy. The AI module can learn from data collected from users, sensors, actuators, etc. and provide cost saving options to home and commercial environments. The AI module may further enable users to obtain metrics from appliances and provide suggestions on functions the user may not yet be applying.
The system may learn from a user's functions and behaviors and program itself. The data gathered may be updated on a cloud. For example, the AI module may learn habits, preferences, and schedules for a full range of appliances continuously. The learning algorithms and cloud event driven architecture may allow auto programming for rules, scenarios, actions, schedules, and triggers to create and send alerts, suggestions, notifications through multi-way channels like SMS, voice call, email, push notifications, etc.
Learning algorithms may also be connected to artificial intelligence application programing interfaces (API)s that may interact with multi-cloud 3rd party APIs in order to interact with different cloud services like IFTTT, email servers, etc. Some example artificial intelligence APIs are listed below:
The learning features may enable energy saving and energy management capabilities for the system. A system may monitor energy consuming devices, user data, and environmental data collected by sensors, users, and devices such as smartphones, tablets, computers, appliances, electrical devices, etc. The system may analyze the data collected with artificial intelligence algorithms and machine learning algorithms to auto-program a set of one or more actions, rules, scenarios, notifications, suggestions, and/or alerts, and execute different actions and scenarios to provide strategic reduction of power usage in home, offices (or any space) combined with a multi-sensing, wirelessly communicating smart TV and smart TV box home gateway.
The artificial intelligence and learning algorithms may allow efficient learning for energy management and energy saving features. Different schedules, scenarios, actions, and/or rules may be created in the system and may be automatically generated based on immediate-control inputs. Artificial intelligence and machine learning methods may also be used for receiving user input relating to the user's preference and environments. The energy monitoring and management system may also run in a cloud energy monitoring and energy saving system that may interact with the system and any electrical device in a location or space.
Each of the functions described below may use machine learning.
The learning features may provide the system with anomaly detection functionality which may be used to identify abnormal behaviors related to energy consumption of devices within a smart space. The system may apply filters and classifiers to data from the devices monitored in real time or near real time to detect abnormal behavior (e.g., behavior that is different from an established pattern of normal behavior). The system may notify a user when abnormal behavior is detected.
Data received from smart devices may be processed to aggregate with historical data related to the owner, the space, and the device. The aggregated data may be filtered with a filter, fixed with the last coming events for the related device.
The real-time data collected may be used to fit and fix filters and classifiers. At the start of the life cycle of the system, or each time than an abnormal behavior is detected, filters and classifiers may be re-trained with the incoming data stream from devices in the smart space, assuming the data represent the actual normal behavior for the measured signal of the device.
A specific example of a cluster generation process 2100 for anomaly detection according to an embodiment of the invention is shown in
In one anomaly detection example, the smart object may be a light with a dimmer and/or on-off control (e.g., the smart socket described above or a light with its own smart communications and data gathering features). A filter may be set for the device based on observed historical device data. In the case of a dimmer, clusters may be formed around frequently observed dimmer settings. For example, a user may set the dimmer to 20% when they come home from work. In this case the filter may be a simple interval around the average of the historical data stream in a time window. (e.g., quartiles 2 and 10 of 11 partitions, over a window time data stream).
The baseline for the smart object may be calculated as range of minimal and maximal samples, for example taking the lowest and highest second quantiles of 11 buckets. If the number of samples covered in the date range is less than some threshold (MIN_REQ_SAMPLE_BASELINE), the baseline may be discarded.
To determine whether a light device has an abnormal behavior, the system ay take the last samples (from the last 24 hours or at least the last MIN_REQ_POWER_SAMPLES), count how many samples are out of the baseline range, and count how many samples are after the first anomaly. If the percentage of abnormal samples on the last samples is over some threshold (ANOMALY_TOL_LIMIT), an anomaly may be registered by the system.
Similar monitoring may be performed for smart plugs and outlets and other energy-using devices, for example based on energy use samples wherein when a percentage of abnormal samples on the last samples is over some threshold (ANOMALY_TOL_LIMIT), an anomaly may be registered by the system. In addition, the type of device plugged into a smart plug may change. Hence when an abnormal behavior is detected it may indicate that a real abnormal behavior is taking place or that the appliance connected was changed. In the latter case, the system may notify the user of the change but, over time, may learn the new behavior pattern and thus recognize that a new device has been connected and start looking for anomalies with that new device.
The system may detect anomalies in user behavior, The system may register actions executed by any user with any client through the IoT cloud to any device. The system may periodically look for anomalies in user behavior, through actions or occurrences/omissions of events, on the devices. For each kind of device, the system may store a collection of typical abnormal behavior patterns, codified as rules, against which currently monitored behavior may be evaluated, When an abnormal user behavior is detected, depending on the severity of the situation, the system might perform different actions, such as notify the user about the issue or request a secure validation of the action, denying access to the device if secure validation is not received.
The system may detect anomalies in data streaming patterns. This is a generalization of the energy anomaly detection functionality. The system may process the recently historical data and build a classifier based on clusters for time series to find the normal status of the behavior of a signal. For example, data from a smart station (e.g., temperature, humidity, luminosity, and/or activity/motion frequency) may be monitored for departures from frequently observed measurements.
The system may periodically look for anomalies in the movements of users attempting to access the IoT cloud from different geo-locations. Each time the system receives a user command from a remote location (e.g., from a user editing smart space settings in her home while she is at the office), the data sent from the device including the command may also include a GPS location of the device. The system may place a point on the map corresponding to a GPS location of the device sending the command. After several commands are received from a user, the system may generate a cluster of points over the map. Then, each time a new command is received and thus a new point appears, the system may measure the distance to the nearest centroid. An abnormal geolocation may be detected when this distance exceeds some limit.
When an abnormal user geolocation is detected, the system may notify the user about the abnormality and request a secure login, and if the secure login is not received, access to the smart space controls from the abnormally located device/account may be denied.
In one specific example, the system may use data collected by a bathroom light switch and a temperature sensor to detect average shower length and shower frequency for a user.
In another example, the system may use data collected by a smart light switch equipped with a power consumption reporting module to detect malfunctioning lights. For example, if the system determines that a light is malfunctioning, it may generate an alert to facility management notifying that a light bulb needs to be replaced.
The system may create an environment that is operating system independent. This may allow open APIs for smart spaces and commercial systems and IoTs to utilize the system's capabilities to provide a friendly environment for developers. With open APIs for software and hardware, developers may be able to integrate third party software and hardware to the system. Thus, devices 120 may be preprogrammed with the ability to communicate with the hub 110 in some cases. However, in other cases, the system may perform appliance detection automatically.
Smart devices may be used in combination with a variety of appliances to perform appliance detection, For example, a smart plug may be installed in a smart space, and an appliance which may or may not have smart IoT features may be plugged into the smart plug. The smart plug may be able to determine the type of appliance, even if the appliance itself does not have any smart features.
The smart plug may include a smart object module configured to collect data about the behavior of the events from the device. Based on the signals of the device such as energy consumption, number of on/off events, execution regimen time, and others, the smart object module may learn which appliance is connected. The smart object module may also measure the correlation of events between many different devices (other device types such as open/close, motion sensor, etc.) from the same user, or in the same network, and determine if the devices are in the same room or if the devices are working together as a composite smart object.
For example, an open/close classification may be a classifier specific for open/close devices and may run as a batch process over all the devices that have enough accumulated data and are not tagged as a specific smart object yet. A sample classifier 2500 is shown in
In some cases, the system may automatically detect composite smart objects.
In some cases, the user patterns may be used to generate automated scenes, Thus, if a user always performs some combination of actions near the same time each day, the clustering processing described above may detect this, and the system may automatically generate commands to cause the actions to be performed automatically. For example, if a user always turns on the lights and the radio when they arrive home from work at or near 7 PM each weekday, the system may generate an automated scene that may cause the hub 110 to turn on the lights and the radio at 7 PM each weekday without user input.
The system may also use clustering to perform an energy audit.
Based on these determinations, the system may recommend when to condition the atmosphere (using energy for heating or cooling and ventilation), and when to use natural ventilation, according to the weather forecast and reading the various sensors from home. Smart objects (e.g., thermostat) may be scheduled to work at the optimal times based on the energy audit analysis to achieve improved energy efficiency. In some cases, this may be combined with hard rules. In one example, detection of door/window smart object with status open while the thermostat is on and cooling or heating may trigger a notification and, depending of the configuration, turn off the thermostat. In another example, if it is raining and the automatic sprinkler is working, the system may to turn of the sprinkler and/or notify the user.
The system may summarize the environment based on collected data. The information from some or all sensors in the smart space may be collected and summarized it a data structure useful to data analytics and may be displayed to a user. Example screenshots of the data presentations are shown in
In some embodiments, the system may use real time or near real time information collected about the user (e.g., coming from user pattern, geolocation, smart objects, voice recognition, social networks interactions, and other sources) to perform an interpretation about the mood of the user. According to the results, the system may perform different actions such as suggesting activities and/or adjusting the environment.
The system may give users a two dimensional (e.g., floor plan) and/or three dimensional (e.g., 3D model generated by, for example, Away 3D, Paper Vision, and/or WebGL) virtual representation for devices and smart objects within their environment. The system may create locally and remotely virtual representations of smart objects. Representations may be detected using the data generated above (e.g., by looking at signal strengths between devices and the hub 110, power use of devices, audio volume, temperature, etc.) Representing the smart objects in a virtual scenario may allow the system to create intelligent agents which can self-create automated planning and scheduling of events and notifications with little user interaction (e.g., presentation for approval and drag and drop interaction). The intelligent agents may use machine learning and artificial intelligence algorithms to teach the system how the smart objects are used and may continuously learn user preferences. Non-smart objects like lamps, lights, or plugs may be turned into smart objects with accessories designed to turn them into smart objects as discussed above, and thus may be virtually represented in the system as well. Objects represented in the system may form a grid of interconnected devices which form a network of ubiquitous computing, sending information to the machine learning algorithms to better learn user preferences.
The system may optionally provide a user interface factory (UIF) software to automatically generate custom user interfaces. The UIF may use the plug and play installation/configuration architecture along with intelligent discovery, mapping, and/or learning algorithms to generate custom user interfaces for devices. For example, a new or/and unknown device may trigger an event that may provide automatic commands to the software to detect a device's features and automatically generate a UI for the device. This may allow the system to control any device or brand without the intervention of new software to support new devices. For example, when a Z-wave device is discovered, intelligent mapping may read the command classes (or clusters in zigbee) and generate a user interface that contains widgets according to features and capabilities of the command classes discovered. The generated UI may feed back to the learning algorithms and AI module. The AI module may capture the unknown/new device user interactions and preferences and may create improvements to the user interface. The UI generated by the UI factory may be operating system independent.
While various embodiments have been described above, it should be understood that they have been presented by way of example and not limitation. It will be apparent to persons skilled in the relevant art(s) that various changes in form and detail can be made therein without departing from the spirit and scope. In fact, after reading the above description, it will be apparent to one skilled in the relevant art(s) how to implement alternative embodiments.
In addition, it should be understood that any figures that highlight the functionality and advantages are presented for example purposes only. The disclosed methodologies and systems are each sufficiently flexible and configurable such that they may be utilized in ways other than that shown.
Although the term “at least one” may often be used in the specification, claims and drawings, the terms “a”, “an”, “the”, “said”, etc. also signify “at least one” or “the at least one” in the specification, claims, and drawings.
Finally, it is the applicant's intent that only claims that include the express language “means for” or “step for” be interpreted under 35 U.S.C. 112(f). Claims that do not expressly include the phrase “means for” or “step for” are not to be interpreted under 35 U.S.C. 112(f).
This application is a continuation of U.S. application Ser. No. 14/939,997, filed Nov. 12, 2015, which claims priority from U.S. Provisional Application No. 62/078,337, filed Nov. 11, 2014, the entirety of which is incorporated by reference herein.
| Number | Date | Country | |
|---|---|---|---|
| 62078337 | Nov 2014 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 14939997 | Nov 2015 | US |
| Child | 16189076 | US |
