System and method for adaptive scheduling for actuator control

Abstract

Systems and methods may include a processor to receive time series presence data from at least one presence sensing device associated with an area, an instance including a presence detected in the area, and a time associated with the instance. The processor may determine an occupancy metric in each time slot of the region based on the presence instance and the time. The processor may generate an occupancy schedule for the region based on the occupancy metric and the history of occupancy metrics in each time slot. The occupancy schedule represents a prediction of an occupancy level of the region during each subsequent time slot in a subsequent few weeks. The processor determines comfort system actuators in the area and communicates an occupancy schedule to the comfort system actuators to actuate the comfort system actuators based on a prediction of an occupancy level of the area.

Description

Technical Field

[0001] The present disclosure generally relates to systems and methods for adaptive scheduling of actuator control, including predictive utilization and scheduling. Background Art

[0002] Typically, indoor control systems (such as comfort systems, smart home systems, HVAC systems, etc.) are pre-loaded with default schedules. It is expected that users (such as homeowners) will manually edit the schedules to customize the comfort schedules to personalize them to their needs. This is a time-consuming process that does not adapt to the user's needs over time as their usage patterns evolve over time. This problem is further compounded in more complex zoning systems, where usage schedules for up to 12 rooms are individually personalized. Summary of the Invention

[0003] In some aspects, the technology described herein relates to a method comprising: receiving, by at least one processor, time-series motion data from at least one motion sensing device associated with an area; wherein the time-series motion data comprises: at least one instance of motion detected in the area, and at least one time associated with the at least one instance; determining, by the at least one processor, an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one instance of motion and the at least one time; wherein the plurality of time slots comprises a breakdown of days of the week; generating, by the at least one processor, an occupancy schedule for the area based at least in part on: the occupancy metric associated with the area in each time slot and a history of the occupancy metric associated with the area in each time slot; wherein the occupancy schedule represents a prediction of an occupancy level of the area during each subsequent time slot in subsequent weeks; determining, by the at least one processor, at least one smart building device associated with the area; and communicating, by the at least one processor, the occupancy schedule to the at least one smart building device; wherein the occupancy schedule is configured to cause the at least one smart building device to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks.

[0004] In some aspects, the technology described herein relates to a method, further comprising predicting, by the at least one processor, the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot using an occupancy prediction machine learning model, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy schedule prediction based on a history of the occupancy metric, and the occupancy metric associated with the area in each time slot.

[0005] In some aspects, the technology described herein relates to a method further comprising: segmenting, by the at least one processor, the time series motion data into a plurality of time windows; and assigning, by the at least one processor, each of the plurality of time windows to a particular time slot among the plurality of time slots.

[0006] In some aspects, the technology described herein relates to a method further comprising: determining, by the at least one processor, an amount of motion in each of the plurality of time slots; generating, by the at least one processor, an occupancy metric associated with the amount of motion in each time slot; and determining, by the at least one processor, the occupancy metric in each time slot based at least in part on the occupancy metric in each time slot.

[0007] In some aspects, the technology described herein relates to a method wherein the amount of motion comprises at least one of: a frequency of motion in each time slot or a duration of motion in each time slot.

[0008] In some aspects, the technology described herein relates to a method further comprising: accessing, by the at least one processor, a plurality of previous occupancy metrics associated with at least one previous week; aligning, by the at least one processor, a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; and generating, by the at least one processor, the occupancy metric in each time slot based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot.

[0009] In some aspects, the technology described herein relates to a method, further comprising generating, by the at least one processor, the occupancy metric in each time slot based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot.

[0010] In some aspects, the technology described herein relates to a method further comprising: utilizing, by the at least one processor, the occupancy metric associated with the area in each time slot as a predicted occupancy state for the area; and generating, by the processor, the occupancy schedule for the area based at least in part on the predicted occupancy state.

[0011] In some aspects, the technology described herein relates to a method wherein the at least one motion sensing device includes at least one of: a security camera, an infrared motion detector, a door sensor, a window sensor, a smart light switch, a Wi-Fi router, a radio frequency identification (RFID) reader, or a smart lock.

[0012] In some aspects, the technology described herein relates to a method further comprising: utilizing, by the at least one processor, an occupancy state prediction machine learning model to predict a predicted occupancy state associated with each time slot based at least in part on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy state prediction based on a history of the occupancy metric, and the occupancy metric associated with the region in each time slot.

[0013] In some aspects, the technology described herein relates to a system comprising: at least one processor in communication with at least one non-transitory computer-readable medium having software instructions stored thereon, wherein the at least one processor, when executing the software instructions, is configured to: receive time-series motion data from at least one motion sensing device associated with an area; wherein the time-series motion data comprises: at least one instance of motion detected in the area, and at least one time associated with the at least one instance; determine an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one instance of motion and the at least one time; wherein the occupancy metric is associated with the area in each of a plurality of time slots; The plurality of time slots include a breakdown of days of the week; generating an occupancy schedule for the area based at least in part on: the occupancy metric associated with the area in each time slot and a history of the occupancy metric associated with the area in each time slot; wherein the occupancy schedule represents a prediction of an occupancy level for the area during each subsequent time slot in subsequent weeks; determining at least one intelligent building device associated with the area; and communicating the occupancy schedule to the at least one intelligent building device; wherein the occupancy schedule is configured to cause the at least one intelligent building device to actuate at least one building actuator based at least in part on the prediction of the occupancy level for the area during each subsequent time slot in subsequent weeks.

[0014] In some aspects, the technology described herein relates to a system wherein, when executing the software instructions, the at least one processor is further configured to utilize an occupancy prediction machine learning model to predict the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy schedule prediction based on a history of the occupancy metric, and the occupancy metric associated with the area in each time slot.

[0015] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing the software instructions, is further configured to: segment the time series motion data into a plurality of time windows; and assign each of the plurality of time windows to a particular time slot among the plurality of time slots.

[0016] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing the software instructions, is further configured to: determine an amount of motion in each of the plurality of time slots; generate an occupancy metric associated with the amount of motion in each time slot; and determine the occupancy metric in each time slot based at least in part on the occupancy metric in each time slot.

[0017] In some aspects, the technology described herein relates to a system wherein the amount of motion comprises at least one of: a frequency of motion in each time slot, or a duration of motion in each time slot.

[0018] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing software instructions, is further configured to: access a plurality of previous occupancy measurements associated with at least one previous week; align a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; and generate the occupancy measurement in each time slot based at least in part on the plurality of previous occupancy measurements associated with the at least one previous week and the occupancy measurement for each time slot.

[0019] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing software instructions, is further configured to: generate the occupancy metric in each time slot based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot.

[0020] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing software instructions, is further configured to: utilize the occupancy metric associated with the area in each time slot as a predicted occupancy state for the area; and generate the occupancy schedule for the area based at least in part on the predicted occupancy state.

[0021] In some aspects, the technology described herein relates to a system wherein the at least one motion sensing device includes at least one of: a security camera, an infrared motion detector, a door sensor, a window sensor, a smart light switch, a Wi-Fi router, a radio frequency identification (RFID) reader, or a smart lock.

[0022] In some aspects, the technology described herein relates to a system wherein the at least one processor, when executing software instructions, is further configured to: utilize an occupancy state prediction machine learning model to predict a predicted occupancy state associated with each time slot based at least in part on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy state prediction based on a history of the occupancy metric, and the occupancy metric associated with the region in each time slot.

[0023] In some aspects, the technology described herein relates to a non-transitory computer-readable medium comprising software instructions that, when executed, are configured to cause at least one processor to perform steps comprising: receiving time-series motion data from at least one motion sensing device associated with an area; wherein the time-series motion data comprises: at least one instance of motion detected in the area, and at least one time associated with the at least one instance; determining an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one instance of motion and the at least one time; wherein the plurality of time slots comprises a breakdown of each day of the week; generating an occupancy schedule for the area based at least in part on: the occupancy metric associated with the area in each time slot and a history of the occupancy metric associated with the area in each time slot; wherein the occupancy schedule represents a prediction of an occupancy level for the area during each subsequent time slot in subsequent weeks; determining at least one intelligent building device associated with the area; and communicating the occupancy schedule to the at least one intelligent building device; wherein the occupancy schedule is configured to cause the at least one intelligent building device to actuate at least one building actuator based at least in part on the prediction of the occupancy level for the area during each subsequent time slot in subsequent weeks.

[0024] In some aspects, the technology described herein relates to a non-transitory computer-readable medium and further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: utilizing an occupancy prediction machine learning model to predict the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy schedule prediction based on a history of the occupancy metric, and the occupancy metric associated with the area in each time slot.

[0025] In some aspects, the technology described herein relates to a non-transitory computer-readable medium, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: segmenting the time series motion data into a plurality of time windows; and assigning each of the plurality of time windows to a particular time slot among the plurality of time slots.

[0026] In some aspects, the technology described herein relates to a non-transitory computer-readable medium further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: determining an amount of motion in each of the plurality of time slots; generating an occupancy metric associated with the amount of motion in each time slot; and determining the occupancy metric in each time slot based at least in part on the occupancy metric in each time slot.

[0027] In some aspects, the technology described herein relates to a non-transitory computer-readable medium, wherein the amount of motion comprises at least one of: a frequency of motion in each time slot, or a duration of motion in each time slot.

[0028] In some aspects, the technology described herein relates to a non-transitory computer-readable medium further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: accessing a plurality of previous occupancy measurements associated with at least one previous week; aligning a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; and generating the occupancy metric in each time slot based at least in part on the plurality of previous occupancy measurements associated with the at least one previous week and the occupancy metric for each time slot.

[0029] In some aspects, the technology described herein relates to a non-transitory computer-readable medium further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: generating the occupancy metric in each time slot based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregate of each occupancy metric for each time slot.

[0030] In some aspects, the technology described herein relates to a non-transitory computer-readable medium, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: utilizing the occupancy metric associated with the area in each time slot as a predicted occupancy state for the area; and generating the occupancy schedule for the area based at least in part on the predicted occupancy state.

[0031] In some aspects, the technology described herein relates to a non-transitory computer-readable medium, wherein the at least one motion sensing device includes at least one of: a security camera, an infrared motion detector, a door sensor, a window sensor, a smart light switch, a Wi-Fi router, a radio frequency identification (RFID) reader, or a smart lock.

[0032] In some aspects, the technology described herein relates to a non-transitory computer-readable medium further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: utilizing an occupancy state prediction machine learning model to predict a predicted occupancy state associated with each time slot based at least in part on: a regression layer comprising a plurality of learned regression weights trained to associate the occupancy metric with an occupancy state prediction based on a history of the occupancy metric, and the occupancy metric associated with the region in each time slot. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various embodiments of the present disclosure may be further explained with reference to the accompanying drawings, in which like elements are referenced by like reference numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed on illustrating the principles of the present disclosure. Therefore, the specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ one or more illustrative embodiments.

[0034] Figure 1 is a block diagram of an exemplary computer-based system for adaptive and predictive actuator control based on usage and / or occupancy detection, according to one or more embodiments of the present disclosure.

[0035] Figure 2 A flowchart of an illustrative method according to one or more embodiments of the present disclosure is shown.

[0036] Figure 3 Depicted are example adaptive thermostat controls based on occupancy events according to one or more embodiments of the present disclosure.

[0037] Figure 4 Depicted are example adaptive thermostat controls based on occupancy events according to one or more embodiments of the present disclosure.

[0038] Figure 5 Depicted are example multi-zone adaptive thermostat control based on occupancy events according to one or more embodiments of the present disclosure.

[0039] Figure 6 Depicted are example adaptive thermostat controls based on occupancy events and learned temperature loss rates according to one or more embodiments of the present disclosure.

[0040] Figure 7 Depicted are example adaptive thermostat controls based on occupancy events and learned temperature loss rates according to one or more embodiments of the present disclosure.

[0041] Figure 8 Depicted are example adaptive thermostat controls based on occupancy events and learned temperature loss rates according to one or more embodiments of the present disclosure.

[0042] Figure 9 Depicted are example adaptive thermostat controls based on occupancy events and learned temperature loss rates according to one or more embodiments of the present disclosure.

[0043] Figure 10 Depicted is a block diagram of an exemplary computer-based system and platform for adaptive and predictive actuator control based on usage and / or occupancy detection, in accordance with one or more embodiments of the present disclosure.

[0044] Figure 11 Depicted is a block diagram of another exemplary computer-based system and platform for adaptive and predictive actuator control based on usage and / or occupancy detection, in accordance with one or more embodiments of the present disclosure.

[0045] Figure 12 Illustrative schematic diagrams depict exemplary implementations of cloud computing(s) / architectures in which embodiments of a system for adaptive and predictive actuator control based on usage and / or occupancy detection may be specifically configured to operate in accordance with some embodiments of the present disclosure.

[0046] Figure 13An illustrative schematic diagram depicts another exemplary implementation of cloud computing(s) / architecture in which embodiments of a system for adaptive and predictive actuator control based on usage and / or occupancy detection may be specifically configured to operate in accordance with some embodiments of the present disclosure. DETAILED DESCRIPTION

[0047] In conjunction with the accompanying drawings, various detailed embodiments of the present disclosure are disclosed herein; however, it is to be understood that the disclosed embodiments are merely illustrative. In addition, each example in the examples given in conjunction with the various embodiments of the present disclosure is intended to be illustrative rather than restrictive.

[0048] Throughout the specification, unless the context clearly stipulates otherwise, the following terms adopt the meanings clearly associated herein. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same (one or more) embodiments, although it may refer to the same (one or more) embodiments. In addition, as used herein, the phrases "in another embodiment" and "in some other embodiments" do not necessarily refer to different embodiments, although it may refer to different embodiments. Therefore, as described below, various embodiments can be easily combined without departing from the scope or spirit of the present disclosure.

[0049] Furthermore, the term "based on" is not exclusive and allows for being based on additional factors that are not described unless the context clearly dictates otherwise. Furthermore, throughout the specification, the meanings of "a," "an," and "the" include plural references. The meaning of "in..." includes "in" and "on."

[0050] As used herein, the terms "and" and "or" may be used interchangeably to refer to a set of items using both conjunctions and disjunctions to encompass a complete description of combinations of items and alternatives. As an example, a set of items may be listed using the disjunction "or" or the conjunction "and." In either case, the set is to be interpreted as meaning each of the items individually as an alternative, as well as any combination of the listed items.

[0051] Figures 1 to 13Systems and methods for actuator control using adaptive and predictive scheduling in zones, such as on a per-room, per-zone, and / or per-space basis, are illustrated. The zones may be interior zones within a building and / or outside a building. The zones may be enclosed and / or open. The following embodiments provide technical solutions and technical improvements that overcome technical problems, shortcomings, and / or deficiencies in the art involving manually scheduling actuator settings, such as reactive actuation of systems and devices and thermostat set points. As explained in more detail below, the technical solutions and technical improvements herein include aspects of improved automation of scheduled actuation in actuators of devices and / or systems for active and adaptive scheduling based on usage and occupancy predictions, resulting in improved efficiency of the devices and / or systems.

[0052] This technology solution utilizes activation data from sensors (such as motion and door contact) and potentially indoor air sensors or other devices with motion sensors integrated into them as input to the comfort system to create an adaptive schedule. This provides the following advantages: in addition to optimizing the schedule based on user habits (e.g., adapting to a homeowner changing their habits because they attend night school), it also allows building systems (such as those in homes and / or commercial spaces) to adapt to usage with minimal user interaction.

[0053] The technological solution integrates comfort and safety devices to achieve a highly optimized dispatch, which will allow homeowners to maximize any cost savings in energy consumption while providing superior operation with maximum comfort.

[0054] Based on such technical features, further technical benefits become available to users and operators of these systems and methods. In addition, various practical applications of the disclosed technology are described, which provide further practical benefits to users and operators, and which are also new and useful improvements in this area.

[0055] Figure 1 is a block diagram of an exemplary computer-based system for adaptive and predictive actuator control based on usage and / or occupancy detection, according to one or more embodiments of the present disclosure.

[0056] In some embodiments, the system of actuators 104 associated with zones is configured to perform localized and / or zoning management of various aspects of the system. Examples may include comfort systems in residential and / or commercial buildings that include actuators 104 to adjust localized operation of the comfort system in specific zones of the building. In such examples, the actuators 104 may include, for example, devices for managing airflow from an HVAC system, a boiler and / or furnace and / or heating elements of an HVAC system, dampers, ductwork, hydronic heating devices, forced air heating components, air and / or hot water valves, and other devices configured to manage zoning or targeting of zone-specific comfort controls. Other examples may include smart home devices, home automation systems, lighting and / or ductwork, and the like.

[0057] In some embodiments, the term "zone" can refer to a room, partition, zone, group of rooms, outdoor space, floor of a building, or any other suitable division of a building / space associated with a system of actuators 104, or any combination thereof. Thus, in some embodiments, the actuators 104 can each be assigned to a specific zone(s) such that control of each actuator 104 can affect the condition and / or operation of the specific zone(s). In some embodiments, a zone can refer to any spatial division of a building. The term "building" can refer to any building (residential or commercial, enclosed or open), including, for example, a house, a condominium, an apartment, a mid-rise building, a high-rise building, a skyscraper, a strip mall, a shopping center, a mobile home, an amphitheater, a stadium, a patio, a gazebo, and other buildings having a space that can be divided into zones, or any combination thereof.

[0058] Throughout this disclosure, the terms "room," "zone," and "area" may be used in connection with embodiments of the systems and / or methods of the present disclosure. These terms are illustrative, and the systems and / or methods may be used for zone-level, adaptive, and predictive control of actuators according to any zone type (e.g., rooms, groupings of rooms, outdoor spaces, floors of a building, or any other suitable division of a building / space associated with a system of actuators 104, or any combination thereof).

[0059] Thus, in some embodiments, a network of different sensors and actuators can be employed to identify utilization patterns and adaptively control actuators based on the utilization patterns in each zone for zone-specific control of actuators, and therefore for zone-specific management of systems and / or devices. Thus, in some embodiments, motion sensor 108 can be connected to network 101 via edge device 106. Similarly, actuator 104 can be connected to network 101 via edge device 102. Predictive actuation system 110 can be connected to network 101 to communicate with edge devices 102 and 106 to determine utilization patterns and develop adaptive and predictive schedules for actuation of actuator 104 based on the utilization patterns. Thus, predictive actuation system 110 can utilize the different devices on network 101 to develop an efficient actuation schedule that schedules control of each actuator 104 based on utilization patterns, based on zones (e.g., zones, rooms, spaces, etc.), to more efficiently operate actuators 104 in the associated zones.

[0060] In some embodiments, edge device 102 and / or edge device 106 may include any suitable computing device. In some embodiments, a computing device may refer to any combination of hardware and / or software for performing one or more functions. For example, edge device 102 and / or 106 may include, for example, a laptop computer, a desktop computer, a smart home device, a Wi-Fi router, an access point, a border router, a gateway, a smartphone, a wearable device, or any other suitable device suitable for interfacing with sensor 108 and / or actuator 104.

[0061] In some embodiments, the edge device 102 and / or the edge device 106 may include computing resources associated with the sensor 108 and / or the actuator 104, such as, for example, a smart home or IoT system, an embedded system-on-chip (SoC) in which the sensor 108 and / or the actuator 104 are embedded, a smart home border gateway and / or hub, or other suitable smart home / IoT hardware integrated with the sensor 108 and / or the actuator 104 via hardware and / or software.

[0062] In some embodiments, the edge device 102 and / or the edge device 106 may include third-party computing hardware that interfaces with the sensor 108 and / or the actuator 104, for example, via an API, a Bluetooth connection, a Wi-Fi connection, USB, through cloud-based interaction (e.g., function and / or API calls to cloud services associated with the sensor 108 and / or the actuator 104), or through any other suitable interface. Thus, the edge device 102 and / or the edge device 106 may be programmed to interact with the sensor 108 and / or the actuator 104 to trigger changes in the operation and / or settings of the sensor 108 and / or the actuator 104. For example, the edge device 102 and / or the edge device 106 may be a smartphone or a third-party software service (e.g., such as Siri). TM , Google Assistant TM 、Amazon Alexa TM , or smart home dashboards such as Apple HomeKit, Google Home, etc.), so that the edge device 102 and / or the edge device 106 are integrated with the predictive actuation system 110, the sensor 108, and the actuator 104 via publicly exposed interfaces.

[0063] In some embodiments, sensor 108 may include any device suitable for detecting and / or identifying the presence or motion of a user. For example, the sensors 108 may include, for example, security cameras that use computer vision techniques to detect and / or identify motion, infrared motion detectors for detecting presence and / or movement, door sensors for detecting entry and / or exit relative to a particular space, window sensors for detecting entry and / or exit relative to a particular space, smart light switches for detecting use of lighting, smart lights for detecting use of lighting, a Wi-Fi router for detecting the presence and / or use of a computing device associated with a user, a radio frequency identification (RFID) reader for detecting the presence of an RFID tag associated with a user, a smart lock for detecting entry and / or exit relative to a particular space, a vibration sensor for detecting vibrations from movement in a room, a pressure sensor for detecting changes in pressure caused by movement and / or opening and closing of doors and / or windows, time-of-flight sensors such as ultrasonic, light detection and ranging (LiDAR), radar, laser, and / or infrared sensors for detecting the position and changes in position of an object, software-based setting changes and other software-based triggers and detectors, and other sensor hardware and / or software or any combination thereof.

[0064] In some embodiments, actuator 104 can refer to any controllable device within a building / space, such as one or more zones of a building / space as detailed above. In some embodiments, actuator 104 can be associated with a comfort system of a home or commercial building. Thus, actuator 104 can include one or more devices configured to manage the operation of a comfort system in a specific zone within a home or commercial building, such as, for example, managed airflow devices (e.g., dampers, micro-damper, valves, mini-diverters, etc.), discrete heating and / or cooling components of a comfort system (e.g., hydronic underfloor heating components, electric underfloor heating components, radiators, stand-alone air conditioning units, stand-alone electric heaters, radiant heating devices, ventilation ducts / ventilation, etc.), and / or system-level devices, such as, for example, system / combination boilers, hot water heaters / boilers, heat pumps, chillers, zone heating, furnaces, etc. Includes, for example, thermostats, water heaters, air conditioners, HVAC, controlled air flow devices (e.g., dampers, micro-damper, valves, mini-diverters, etc.), room level heating and / or cooling devices (e.g., hydronic underfloor, electric underfloor, electric heating, boilers, furnaces, stand-alone AC, ventilation, etc.).

[0065] In some embodiments, although the actuator 104 is described herein as being associated with a comfort system, such embodiments are illustrative. In some embodiments, the actuator 104 may alternatively or additionally be associated with other household devices for area-specific control, such as, for example, security cameras, dishwashers, ovens, microwaves, televisions, electric window shades, lighting, refrigerators, ice makers, and other actuators or any combination thereof. For example, the occupancy of a room can be used to turn off electronic devices, such as, for example, home theater equipment, televisions, lighting, ovens, stoves, ranges, and other devices that may be unnecessary and / or unsafe to keep active while the user is away. Other such appliances and devices may be controllable based on the user's occupancy / presence or any combination thereof.

[0066] In some embodiments, the terms "actuator" and / or "building actuator" may be employed. Such terms refer to actuators of a building. For example, a "home actuator" may refer to an actuator configured for use in a home, while a "commercial actuator" may be configured for use in a commercial building. As used herein, the terms "actuator" and "building actuator" refer to actuators of any building type, including, for example, houses, condominiums, apartments, mid-rise buildings, high-rise buildings, skyscrapers, strip malls, shopping centers, mobile homes, amphitheaters, stadiums, patios, pavilions, and other buildings having spaces that can be divided into zones, or any combination thereof, as detailed above.

[0067] In some embodiments, sensors 108 and actuators 104 can be integrated into a common device, such as a thermostat and / or discrete heating and / or cooling components of a comfort system with an integrated motion sensor, or can be integrated into separate devices that can communicate via network 101. Similarly, in some embodiments, edge device 102 and edge device 106 can be integrated into or can be the same device, or can be separate and independent devices that can communicate via network 101.

[0068] In some embodiments, network 101 may include any suitable computer network, including two or more computers connected to each other for the purpose of electronically transmitting data. In some embodiments, the network may include suitable network types, such as, for example, a public switched telephone network (PTSN), an integrated services digital network (ISDN), a private branch exchange (PBX), a wireless and / or cellular telephone network, a computer network including a local area network (LAN), a wide area network (WAN), or other suitable computer networks, or any other suitable network or any combination thereof. In some embodiments, a LAN may connect computers and peripheral devices in a physical area by means of a link (wire, Ethernet cable, optical fiber, wireless such as Wi-Fi, etc.) that transmits data. In some embodiments, a LAN may include two or more personal computers, printers, and high-capacity disk storage devices, file servers, or other devices or any combination thereof. LAN operating system software that interprets input and instructs networked devices may enable communication between devices to: share printers and storage devices, while accessing centrally located processors, data or programs (instruction sets), and other functionality. Devices on a LAN may also access other LANs or connect to one or more WANs. In some embodiments, a WAN may connect computers and smaller networks to a larger network over a larger geographic area. A WAN can link computers by means of cables, optical fibers or satellites, cellular data networks or other wide area connection components. In some embodiments, an example of a WAN can include the Internet.

[0069] In some embodiments, the network 101 may include the Internet, a LAN, a Zigbee network, a Z-Wave network, a Matter TMnetwork, Apple HomeKit network, or any other suitable networking technology or ecosystem, or any combination thereof. Thus, in some embodiments, the predictive actuation system 110 can provide functionality from a cloud platform, for example, via Software as a Service (SaaS), over the Internet, or as a locally hosted service on a smart home network (such as Zigbee, Z-Wave, Matter, and / or HomeKit), or via a distributed network on which one or more edge devices 102 and / or edge devices 106 are nodes, or as a local software package on one or more edge devices 102 and / or edge devices 106, or through any other suitable architecture, or any combination or hybrid thereof.

[0070] In some embodiments, the predictive actuation system 110 may include hardware components, such as a processor 116, which may include local or remote processing components. In some embodiments, the processor 116 may include any type of data processing capability, such as hardware logic circuits (e.g., application specific integrated circuits (ASICs) and programmable logic), or such as a computing device (e.g., a microcomputer or microcontroller including a programmable microprocessor). In some embodiments, the processor 116 may include data processing capabilities provided by a microprocessor. In some embodiments, the microprocessor may include memory, processing, interface resources, controllers, and counters. In some embodiments, the microprocessor may also include one or more programs stored in the memory.

[0071] Similarly, the predictive actuation system 110 may include data storage 118, such as one or more local and / or remote data storage solutions (such as, for example, a local hard drive, a solid-state drive, a flash drive, a database, or other local data storage solutions, or any combination thereof), and / or remote data storage solutions (such as a server, a mainframe, a database or cloud service, a distributed database, or other suitable data storage solutions, or any combination thereof). In some embodiments, the storage device 111 may include, for example, a suitable non-transitory computer-readable medium, such as, for example, a random access memory (RAM), a read-only memory (ROM), one or more buffers and / or caches, and other memory devices, or any combination thereof.

[0072] In some embodiments, the predictive actuation system 110 can implement a computer engine for motion event-based occupancy learning, and adaptive and / or predictive scheduling of actuators 104 based on the learned occupancy for zone-specific control of the comfort system. In some embodiments, the terms "computer engine" and "engine" identify at least one software component and / or a combination of at least one software component and at least one hardware component that is designed / programmed / configured to manage / control other software and / or hardware components (such as a library, software development kit (SDK), object, etc.).

[0073] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. In some embodiments, one or more processors may be implemented as a complex instruction set computer (CISC) or a reduced instruction set computer (RISC) processor; an x86 instruction set compatible processor, a multi-core or any other microprocessor or central processing unit (CPU). In various implementations, one or more processors may be a dual-core processor(s), a dual-core mobile processor(s), etc.

[0074] Examples of software may include software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, processes, software interfaces, application program interfaces (APIs), instruction sets, computing codes, computer codes, code segments, computer code segments, words, values, symbols, or any combination thereof. Determining whether to implement an embodiment using hardware elements and / or software elements can vary based on any number of factors, such as desired computing rates, power levels, thermal tolerances, processing cycle budgets, input data rates, output data rates, memory resources, data bus speeds, and other design or performance constraints.

[0075] In some embodiments, to learn the occupancy patterns of each zone associated with the comfort system and thereby predict comfort system utilization patterns on a zone-specific basis, the predictive actuation system 110 may include a computer engine, including, for example, an occupancy learning engine 112. In some embodiments, the occupancy learning engine 112 may include dedicated and / or shared software components, hardware components, or a combination thereof. For example, the occupancy learning engine 112 may include a dedicated processor and storage device. However, in some embodiments, the occupancy learning engine 112 may share hardware resources, including the processor 116 and data storage 118 of the predictive actuation system 110.

[0076] In some embodiments, to predict adaptive and efficient actuation schedules for actuator 104, predictive actuation system 110 may include a computer engine, including, for example, a scheduling engine 114. In some embodiments, scheduling engine 114 may include dedicated and / or shared software components, hardware components, or a combination thereof. For example, scheduling engine 114 may include a dedicated processor and memory. However, in some embodiments, scheduling engine 114 may share hardware resources, including processor 116 and data storage 118, with predictive actuation system 110.

[0077] In some embodiments, the occupancy learning engine 112 and the scheduling engine 114 are depicted as being implemented by remote systems across the network 101 from the edge device 102 and the edge device 106. However, the occupancy learning engine 112 and / or the scheduling engine 114 can be implemented locally on the edge device 102, on the edge device 106, or on a separate device that communicates with the edge device 102 and / or the edge device 106, or any suitable combination thereof.

[0078] In some embodiments, sensors 108 may be located in a specific area, such as, for example, a specific building, room, or other suitable space in which the comfort system is operating. Sensors 108 may identify motion events within the space where sensors 108 are located based on sensor readings. In some embodiments, sensors 108 may be part of a security system having motion and / or object detection sensors distributed throughout the building. Thus, each area with actuators 104 may also be associated with one or more sensors of the security system. Thus, areas associated with sensors 108 may be identified, and their presence may be detected during operation of the security system. Data from sensors 108 indicating the detected presence may be provided to predictive actuation system 110. Actuators 104 in the area of ​​sensors 108 may also be identified, and the motion and / or presence of users in that area may be used to determine utilization patterns of actuators 104.

[0079] Additionally and / or alternatively, embodiments of the sensor 108 may be employed. For example, the sensor 108 may detect entry and / or exit based on, for example, a smart lock actuation, a smart window latch, or other suitable sensor. In another example, the sensor 108 may detect and / or identify the presence and / or movement of a person within a space based on computer vision processing of an image or video feed of the space by the sensor 108 and / or the edge device 106. Other forms of presence and / or motion detection may be employed, such as, for example, access card usage, infrared motion sensors, detection of the on / off state of lights, detection of the presence and / or movement of a computing device associated with a user (e.g., a smartphone, smartwatch, laptop, tablet, etc.) via Wi-Fi, Bluetooth, NFC, and / or RFID, or any other sensing technology or any combination thereof.

[0080] In some embodiments, each motion event in a zone can be recorded and uploaded to the predictive actuation system 110, for example, via a suitable application programming interface (API) or other suitable interface connection and / or messaging technology. In some embodiments, an "API" refers to a computing interface that defines the interaction between multiple software intermediaries. An "application programming interface" or "API" defines the types of calls or requests that can be made, how the calls are made, the data format that should be used, the conventions to be followed, and other requirements and constraints. An "application programming interface" or "API" can be completely customized, component-specific, or designed based on industry standards to ensure interoperability, thereby enabling modular programming through information hiding, allowing users to use the interface independently of the implementation.

[0081] In some embodiments, motion events can be used to detect area-specific occupancy levels based on the amount of motion, such as, for example, the duration of occupancy of the area, the frequency of occupancy, the duration of each detected movement, the duration of each detected movement, or any other suitable method for quantifying occupancy. In some embodiments, for some actuators, usage patterns can be more effectively correlated with other types of activity than occupancy and / or movement, such as hot water usage, electricity usage, or other suitable measures of activity in the space. Thus, occupancy levels can be quantified based on correlated measures of the actuator's activity.

[0082] In some embodiments, the occupancy learning engine 112 can ingest occupancy levels and determine, for each time slot throughout a scheduled period (e.g., a day, a week, a month, a year, etc.), an occupancy metric that indicates the degree of occupancy experienced in the area during that time slot in the scheduled period. For example, the scheduled period can be a repeating period, and the occupancy metric can be determined over time for a particular time slot based on usage patterns. Thus, the occupancy metric represents the expected level of usage of the space based on detected motion events. In some embodiments, the occupancy metric can be generated based on, for example, a plurality of occupancy levels, usage levels, decay rates, fixed detection intervals, etc., each of which represents parameters that can be fine-tuned to optimally represent usage patterns throughout the scheduled period.

[0083] In some embodiments, occupancy metrics may be collected for each zone based on the location of each sensor 108 on the network 101. Thus, zone-specific occupancy may be evaluated in each zone of the entire building / space so that each actuator 104 of each zone may be controlled based on the zone-specific occupancy.

[0084] As an example, the learning process can start with a default or manually configured daily / weekly time schedule. Each day of the week is divided into fixed intervals, such as 15 minute time slots, resulting in 672 time periods per week. If an occupancy event has been detected in a time slot, it is determined that the time slot has the highest usage level and will go to the comfort temperature set point. During time slots where no occupancy events have been detected, the set point will be reduced to a slight setback (lower temperature) set point. When no occupancy events have been detected in two consecutive time slots, the room will further fall back to the "empty room" set point (which will give the minimum temperature). The usage level of the time slot is used as input to the comfort schedule. If the current usage is higher than the scheduled usage, the schedule is adapted to the higher level. If the scheduled usage is higher than the current usage level of the room, the scheduled usage level will "decay". After a few consecutive weeks with lower usage levels, the schedule will decay to a lower level pattern.

[0085] In some embodiments, the occupancy level of a room (the number of occupancy events over a fixed interval) can be used to determine the usage level of the room, as represented by an occupancy metric. The usage level then determines the comfort set point to use. As the occupancy level decays over time, the usage level is degraded toward more economical set points. These set points can be customized to allow for a balance between fallback and recovery of the room.

[0086] Furthermore, the room's historical usage patterns can be used to tailor future schedules to enable lifestyle schedules that can be leveraged by existing adaptive functionality that preempts early on / off of comfort systems, as described above. To avoid drastic weekly schedule changes, usage levels are decayed over time, which prevents the schedule from adapting too quickly to "one-time" empty room events while also preserving historical patterns.

[0087] Additionally or alternatively, in some embodiments, sensor activation data (when sensors 108 are activated) can be counted, accumulated, analyzed, or otherwise analyzed with respect to time to provide a more accurate view of occupancy levels and provide a more detailed picture of how the space is occupied, thereby allowing more accurate predictions of future usage and helping to set the correct comfort level.

[0088] Additionally or alternatively, in some embodiments, the armed / set state of the entire security system or of individual zones (also referred to as zones, areas, or groups) that can be individually set can be used as an additional input to generate usage. In some embodiments, when a portion of the intrusion system is armed (set), a portion of the system may be unoccupied. Thus, the occupancy learning engine 112 can track set starts and set ends and predict when the user will return to those zones. Thus, both the armed (set) state itself and the typical armed / disarmed (set / unset) times can be used to improve comfort scheduling. Thus, the occupancy learning engine 112 can use the security system so that the system is ready to use when the user is there, but the system conserves energy when the user is not there.

[0089] Additionally or alternatively, in some embodiments, external triggers (such as API calls from third-party devices and services) can be used as additional inputs to generate usage. For example, a user can use a third-party smart home integration or virtual assistant to send commands and / or requests. The commands and / or requests can be used to assess usage and / or presence in order to establish usage patterns. Thus, the occupancy learning engine 112 can track external trigger usage to improve comfort scheduling.

[0090] Additionally or alternatively, in some embodiments, multiple occupancy levels can be added (e.g., often occupied, mostly occupied, occasionally occupied, mostly empty, always empty, unused), and multiple temperature set points can be added to allow for rooms that are not actually used but are occasionally used, such as periodically entered to access something like a pantry, closet, bathroom, garage, or other space that a user may periodically enter and use.

[0091] In some embodiments, the predictive actuation system 110 can utilize the occupancy learning engine 112 to develop a predictive occupancy metric that predicts the future occupancy level of each area in the building / space based on past, historical, and / or recent occupancy metrics. In some embodiments, the occupancy learning engine 112 can develop a statistical aggregate, such as a mean, median, standard deviation, weighted average, weighted mean, percentage deviation from the mean or median, or other suitable aggregate of occupancy metrics for a particular time slot in the scheduling period. In some embodiments, the aggregate can be enhanced with a forgetting / decay rate such that more recent occupancy levels are weighted more heavily than more distant occupancy levels when developing the aggregate.

[0092] In some embodiments, the occupancy learning engine 112 may use an occupancy prediction machine learning model to predict a predicted occupancy metric for each time slot based on past and / or recent occupancy metrics. In some embodiments, the occupancy state machine learning model may be configured to utilize one or more exemplary AI / machine learning techniques selected from, but not limited to, decision trees, boosting, support vector machines, neural networks, nearest neighbor algorithms, naive Bayes, bagging, random forests, and the like. In some embodiments, and optionally, in combination with any of the embodiments described above or below, the exemplary neural network technology may be, but not limited to, one of a feedforward neural network, a radial basis function network, a recursive neural network, a convolutional network (e.g., U-net), or other suitable network. In some embodiments, and optionally, in combination with any of the embodiments described above or below, an exemplary implementation of a neural network may be performed as follows: a. Define the neural network architecture / model, b. transmitting input data to the exemplary neural network model, c. incrementally train an exemplary model, d. determine the accuracy for a specific number of time steps, e. applying the exemplary trained model to process newly received input data, f. Optionally and in parallel, continue training the exemplary trained model with a predetermined periodicity.

[0093] In some embodiments, and optionally in combination with any of the embodiments described above or below, an exemplary trained neural network model can specify a neural network by at least a neural network topology, a series of activation functions, and connection weights. For example, the topology of the neural network can include the configuration of the nodes of the neural network and the connections between such nodes. In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary trained neural network model can also be specified to include other parameters, including but not limited to bias term values / functions and / or aggregation functions. For example, the activation function of a node can be a step function, a sine function, a continuous or piecewise linear function, a sigmoid function, a hyperbolic tangent function, or other type of mathematical function that represents a threshold at which a node is activated. In some embodiments, and optionally in combination with any of the embodiments described above or below, an exemplary aggregation function can be a mathematical function that combines (e.g., sums, products, etc.) input signals to a node. In some embodiments, and optionally in combination with any of the embodiments described above or below, the output of the exemplary aggregation function can be used as an input to the exemplary activation function. In some embodiments, and optionally in combination with any embodiments described above or below, the bias term can be a constant value or function that can be used by the aggregation function and / or activation function to make a node more or less likely to be activated.

[0094] Thus, the occupancy state machine learning model may include a layer for ingesting occupancy metrics and outputting predicted occupancy metrics based on learned parameters of the layer. For example, for a regression model, the occupancy state machine learning model may include a regression layer of regression nodes (e.g., long short-term memory or gated recovery units or other types of nodes) having learned regression weights that are trained to relate the occupancy metrics to future occupancy metrics based on a history of the occupancy metrics.

[0095] In some embodiments, based on the predicted occupancy metrics, the predictive actuation system 110 can utilize a scheduling engine 114 to develop an occupancy schedule that schedules adjustments to the set points of the actuators 104 to provide, for example, zone-specific control of a comfort system. Thus, occupancy scheduling for a zone of actuators 104 can facilitate improved efficiency of the comfort system by selectively controlling the actuators 104 to shut down operation within that zone during times of low occupancy probability while allowing the occupancy schedule for an individual zone to control the actuators of that individual zone to activate operation of the comfort system in that zone. As detailed above, activating and / or deactivating operation of the comfort system in a particular zone can include controlling the actuators 104 to actuate, for example, HVAC ducts and / or microducts, one or more valves, a circulation component, an electric heating element, an independent air conditioning unit, a ventilation component, the like, or any combination thereof. Thus, the scheduling engine 114 can independently schedule set point adjustments for multiple individual zones associated with multiple individual actuators 104 based on detected utilization patterns specific to each zone.

[0096] In some embodiments, the scheduling engine 114 may employ a "heat map" that maps the predicted occupancy metric to each time slot in the scheduling period, such that the occupancy level is mapped throughout the scheduling period. The scheduling engine 114 may then employ the heat map to determine changes in the actuation set point throughout the scheduling period. For example, as the occupancy level rises across the time slots, the actuation set point is adjusted upward, and as the occupancy level decreases, the actuation set point may be adjusted downward. In some embodiments, the adjustment may be directly or indirectly related to the degree of change in the occupancy level. In some embodiments, the adjustment may be made relative to a user set point that establishes the user's preferences when the user occupies the space. Thus, as the occupancy level increases, the scheduling engine 114 may adjust the actuator set point toward the user set point, and as the occupancy level decreases, the scheduling engine 114 may adjust the actuator set point away from the user set point.

[0097] In some embodiments, adjustments to the actuator setpoint can be based on a trained regression model that correlates occupancy and energy usage with the actuator setpoint. Such a regression model can account for drift in losses, such as at different times of year or time of day, which can cause the actuator setpoint to deviate from actual conditions and / or actuator behavior targeted by the actual setpoint. For example, during winter months, the temperature of a space may drop more rapidly, thus causing a deviation between the thermostat setpoint and the actual temperature. When accounting for drift, the actuator 104 can be pulsed less frequently to balance efficiency with user comfort, as described in further detail below.

[0098] In some embodiments, the occupancy learning engine 112 may use an occupancy prediction machine learning model to predict occupancy scheduling predictions for each time slot based on past and / or recent occupancy metrics. In some embodiments, the occupancy prediction machine learning model may be configured to utilize one or more exemplary AI / machine learning techniques selected from, but not limited to, decision trees, boosting, support vector machines, neural networks, nearest neighbor algorithms, naive Bayes, bagging, random forests, and the like. In some embodiments, and optionally, in combination with any of the embodiments described above or below, the exemplary neural network technology may be one of, but not limited to, a feedforward neural network, a radial basis function network, a recursive neural network, a convolutional network (e.g., U-net), or other suitable networks. In some embodiments, and optionally, in combination with any of the embodiments described above or below, an exemplary implementation of a neural network may be performed as follows: a. Define the neural network architecture / model, b. transmitting input data to the exemplary neural network model, c. incrementally train an exemplary model, d. determine the accuracy for a specific number of time steps, e. applying the exemplary trained model to process newly received input data, f. Optionally and in parallel, continue training the exemplary trained model at a predetermined periodicity.

[0099] In some embodiments, and optionally in combination with any of the embodiments described above or below, an exemplary trained neural network model can specify a neural network by at least a neural network topology, a series of activation functions, and connection weights. For example, the topology of the neural network can include the configuration of the nodes of the neural network and the connections between such nodes. In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary trained neural network model can also be specified to include other parameters, including but not limited to bias term values / functions and / or aggregation functions. For example, the activation function of a node can be a step function, a sine function, a continuous or piecewise linear function, a sigmoid function, a hyperbolic tangent function, or other type of mathematical function that represents a threshold at which a node is activated. In some embodiments, and optionally in combination with any of the embodiments described above or below, an exemplary aggregation function can be a mathematical function that combines (e.g., sums, products, etc.) input signals to a node. In some embodiments, and optionally in combination with any of the embodiments described above or below, the output of the exemplary aggregation function can be used as an input to the exemplary activation function. In some embodiments, and optionally in combination with any embodiments described above or below, the bias term can be a constant value or function that can be used by the aggregation function and / or activation function to make a node more or less likely to be activated.

[0100] Thus, the occupancy prediction machine learning model may include a layer for ingesting occupancy metrics and outputting occupancy schedule predictions based on learned parameters of the layer. For example, for a regression model, the occupancy prediction machine learning model may include a regression layer of regression nodes (e.g., long short-term memory or gated recovery units or other types of nodes) having learned regression weights that are trained to associate occupancy metrics with occupancy schedule predictions based on a history of the occupancy metrics.

[0101] In some embodiments, the predictive actuation system 110 can use the scheduling engine 114 to schedule actuation of actuators 104 in a zone of, for example, a comfort system, such as scheduling actuation of a thermostat based on a temperature set point adjustment, as well as other set points and set point adjustments in one or more other systems and / or devices in the zone, such as, for example, air quality control (such as air purification / filtration and humidity control (increase or decrease)), lighting levels, ventilation, modified responses to emergency events such as smoke / fire detection, carbon monoxide, flooding, etc. (e.g., giving a broader alert to all areas where people may hear the alert), audio playback (radio / music - follows the user), and other room level systems.

[0102] The system can also be extended where such input gives knowledge of a specific user and can be extended to have multiple per-user schedules that can be overridden. In this way, we can tailor the comfort system to a specific person's profile and merge when multiple users are in the area.

[0103] In some embodiments, the predictive actuation system 110 can provide an occupancy schedule to the actuators 104 and / or edge devices 102. The actuators 104 and / or edge devices 102 can be configured to interpret the occupancy schedule to automatically adjust the actuator set points in a zone according to the time slots in the schedule period, independently of the set points in other zones. Thus, the actuators 104 can automatically and dynamically adjust their operation to account for usage patterns, thereby predicting user set points while improving efficiency when a user is not present in the zone, such as to provide zone-specific control of comfort systems. Thus, occupancy scheduling of a zone of actuators 104 can facilitate improved efficiency of comfort systems by selectively controlling the operation of actuators 104 in that zone during times of low occupancy probability, while allowing the occupancy schedule of a separate zone to control the actuators of the separate zone to enable operation of the comfort systems in that zone.

[0104] As detailed above, operation of turning the comfort system on and / or off in a particular zone may include controlling the actuator 104 to actuate, for example, HVAC ducts and / or micro-ducts, one or more valves, circulation components, electric heating elements, independent air conditioning units, ventilation components, etc., or any combination thereof.

[0105] Figure 2 A flowchart of an illustrative method according to one or more embodiments of the present disclosure is shown.

[0106] In some embodiments, the occupancy learning engine 112 may receive time-series motion data at 202 from one or more sensors 108 associated with, for example, a particular area of ​​a home, such as a room, a group of rooms, an outdoor space of the home, or other division of an area. In some embodiments, the time-series motion data may include instances of motion detected by the sensors 108 and a time associated with each instance of motion. In some embodiments, the instances of motion may include, for example, an indicator that motion was detected in the area, the type of motion detected (e.g., an activity performed by a user), the duration of the motion, the magnitude of the motion, and other motion-related data and characteristics based on data available from the sensors 108, as detailed above.

[0107] For example, in some embodiments, the sensor 108 may include a camera device, such as a smart home security camera, a motion sensor (e.g., a time-of-flight sensor using ultrasound, infrared, laser, radar, or other suitable ranging technology, or any combination thereof), or other sensors of a security system. The camera device may capture images of the motion and utilize one or more computer vision models to detect and recognize the motion, for example, based on the type of activity or movement.

[0108] In some embodiments, the occupancy learning engine 112 may segment the time-series motion data into time windows at 204 .

[0109] In some embodiments, the scheduling of the actuators 104 can be based on a scheduling period having a time slot for each occupied segment within a defined area. Thus, an occupancy metric can be established for each time slot. In some embodiments, scheduling can be based on a continuous time-based occupancy signal rather than a windowed approach. In some embodiments, a windowed approach can be more computationally efficient by avoiding continuous calculations over time and allowing occupancy to be assessed periodically. In some embodiments, the size of the time window can be any suitable size that takes into account variations in occupancy, such as, for example, one minute, five minutes, ten minutes, fifteen minutes, twenty minutes, thirty minutes, one hour, or other suitable window size to balance the adjustment of the actuation set point to accurately follow usage patterns while minimizing computational resource requirements.

[0110] In some embodiments, the time series motion data can be segmented into time windows aligned with time slots of the schedule period, e.g., based on the time and / or duration of each motion instance. Thus, the time windows of the motion data can be aligned with the time slots of the schedule period to associate occupancy, as signaled by motion, with the actuation setpoint adjustment schedule.

[0111] In some embodiments, at 206 , the occupancy learning engine 112 may develop an occupancy metric that quantifies the degree of occupancy of the region for each time window.

[0112] In some embodiments, for each time slot, the occupancy learning engine 112 may develop an occupancy metric based on motion data associated with the time slot. For example, the motion data may indicate the amount of motion, such as the number of motion instances, the duration of each instance, the frequency of the instances, the number of detected users, and other metrics of the amount of motion within the time slot.

[0113] In some embodiments, based on the amount of motion, the occupancy learning engine 112 can categorize or classify the amount of motion in the time slot according to an occupancy score. For example, the occupancy score can be a three-point scoring system where 1 represents unused, 2 represents temporarily unused, and 3 represents in use (or in other words, empty, unoccupied, and occupied, respectively), for example based on two thresholds, an upper threshold and a lower threshold.

[0114] In some embodiments, the classification can be determined based on a threshold value of the amount of exercise (such as, for example, an upper threshold and a lower threshold). In a three-point scoring system, a time slot with an amount of exercise above the upper threshold can be classified as a 3, a time slot with an amount of exercise below the lower threshold can be classified as a 1, and a time slot with an amount of exercise above the lower threshold and below the upper threshold can be classified as a 2.

[0115] In some embodiments, the occupancy learning engine 112 can use the scores for each time slot to develop a predicted occupancy metric that predicts the future occupancy level of the space based on past, historical, and / or recent occupancy metrics. In some embodiments, the occupancy learning engine 112 can perform time-based modeling, such as by developing a statistical aggregation, such as a mean, median, standard deviation, score average, score mean, percentage deviation from the mean or median, or other suitable aggregation of occupancy metrics for specific time slots in the scheduling period. In some embodiments, the aggregation can be enhanced by utilizing forgetting / decay rates so that more recent occupancy levels are scored higher than more distant occupancy levels when developing the aggregation.

[0116] In some embodiments, rather than scoring each time slot based on the amount of motion, the occupancy learning engine 112 may employ a higher score associated with an amount of motion indicating the presence of a user, and a lower score associated with an amount of motion indicating the absence of a user in the space. In some embodiments, the higher and lower scores may be separated by one or more intermediate scores indicating the likelihood of a user being present.

[0117] In some embodiments, using such a weighting scheme, the occupancy learning engine 112 can assign a higher weight or a lower weight to each time slot based on the amount of movement in the current time period. The occupancy learning engine 112 can then use the assigned scores and the aggregation of historical assigned scores to determine an occupancy metric for each time slot based on time-based modeling, such that the occupancy metric can be any of a higher score, a lower score, or one or more intermediate scores based on a reward equation with a decaying rate.

[0118] In some embodiments, at 208 , the occupancy learning engine 112 may model the time-based occupancy of the area based on the occupancy metric to provide a predicted occupancy metric that indicates usage patterns of a particular area of ​​the home.

[0119] In some embodiments, the occupancy learning engine 112 may access previous occupancy metrics associated with at least one previous set of time-series motion data. In some embodiments, the occupancy learning engine 112 may align a previous time slot of the previous set of time-series motion data with a time slot of the current time-series motion data. In some embodiments, the occupancy learning engine 112 may then use time-based occupancy modeling to generate an occupancy metric for each time slot based on the multiple previous occupancy metrics and the current occupancy score for each time slot.

[0120] In some embodiments, to model time-based occupancy, the occupancy learning engine 112 may generate a predicted occupancy metric based on the current and previous occupancy metrics for each time slot of the current and previous scheduling periods. To do so, the occupancy learning engine 112 may employ a reward function with a decaying rate that combines the current occupancy metric with the previous occupancy metric to produce a predicted weight ranging from a low weight, (one or more) intermediate weights, to a high weight. For example, the occupancy learning engine may employ a function such as the following equation (1):

[0121] where m pis a predicted occupancy metric, λ is a decay rate, m is a previous occupancy metric, s is a current occupancy score based on the time series motion data, and t is a scheduling period. Thus, the occupancy learning engine 112 can use the decay rate λ to update the occupancy metric derived for the previous scheduling period using the current occupancy score. The decay rate λ can be predefined (e.g., 2, 3, 4, 5, 6, or more), user configurable, and / or learned via a suitable optimization function using feedback from user input. Thus, the occupancy learning engine 112 can model the occupancy of a space by quantifying occupancy patterns within the space based on previous data. The occupancy model can be employed in a predictive manner to indicate the likelihood that a user will occupy or otherwise use a space in the future based on past usage behavior.

[0122] In some embodiments, at 210 , the scheduling engine 114 may predict an actuation schedule of, for example, one or more zone-specific actuators of a comfort system of a home based on a time-based occupancy model.

[0123] In some embodiments, the actuation schedule can be based on a predicted occupancy metric, such as an occupancy schedule. In some embodiments, the scheduling engine 114 can associate the degree of actuator set point adjustment with the occupancy metric for each time slot in the occupancy schedule. For example, a user may have defined a user set point and a minimum set point, whereby the user set point is the expected actuator set point when the user occupies the space, and the minimum set point is the minimum actuator set point allowed. The scheduling engine 114 can employ a predefined relationship between the occupancy metrics to generate the degree of adjustment from the user set point. The relationship can be a direct linear relationship between the user set point and the minimum set point that produces an actuator set point based on the occupancy metric for the time slot. In some embodiments, the relationship can be logarithmic, exponential, or pre-mapped (e.g., using a lookup table) to associate the actuator set point adjustment with the occupancy metric for the time slot.

[0124] In some embodiments, the actuator set points in the actuation schedule can specifically take into account time-based temperature characteristics, such as, for example, the likely temperature loss given the time of year and / or time of day. For example, in some embodiments, since the temperature loss of forced hot air versus forced hot water versus electrical heating versus hydronic heating can vary, different parameters defining the temperature characteristics of the area can be beneficial. The temperature characteristics can also depend on the area itself, such as, for example, size, shape, degree of insulation, number of windows, number of doors, exposure to the outside (e.g., via shielding in (one or more) walls or other openings), and other characteristics of the area or any combination thereof. Thus, the actuator set points can be determined based on the likelihood of user presence and the time from and / or until the user's presence according to the predicted occupancy metric.

[0125] In some embodiments, where the time-series motion data includes identified user activity, for example, based on computer vision analysis of images of the user in the space, the scheduling engine 114 can adjust the actuator setpoint based on the type of activity. For example, if the user typically exercises or is currently exercising at a particular time slot, the scheduling engine 114 can modify the temperature setpoint downward to make exercise more comfortable. Similarly, if the user is sleeping or typically sleeps, the scheduling engine 114 can modify the temperature setpoint upward to make sleeping more comfortable.

[0126] In some embodiments, when generating an actuation schedule for operating a comfort system in a zone of a home, the scheduling engine 114 can identify the actuators 104 in the zone associated with the sensors 108. In some embodiments, the actuators 104 can be indexed according to the space and / or sensor 108, such that the scheduling engine 114 can access the index to identify the actuators 104 mapped to the space and / or sensor 108. The scheduling engine 114 can then communicate the actuation schedule to the edge device 102 and / or the actuator 104. The actuation schedule can then cause the edge device 102 to control the actuator 104 according to the actuator setpoints encoded in the actuation schedule based on a prediction of the space occupancy level during each subsequent time slot in a subsequent scheduled period.

[0127] Figure 3 Depicted is an example adaptive thermostat control based on occupancy events according to one or more embodiments of the present disclosure. The dashed-dotted line depicts an actuator setpoint based on an occupancy metric including an occupancy score. The thick dashed line depicts a user setpoint manually entered by a user. The thin dashed line indicates an alternative user setpoint manually entered by a user.

[0128] Figure 4 Depicted is an example adaptive thermostat control based on occupancy events, according to one or more embodiments of the present disclosure. The dashed-dotted line depicts an actuator setpoint based on an occupancy metric including an occupancy probability. The thick dashed line depicts a user setpoint manually entered by a user. The thin dashed line indicates an alternative user setpoint manually entered by a user.

[0129] Figure 5 Depicted is an example multi-zone adaptive thermostat control based on occupancy events according to one or more embodiments of the present disclosure. The dashed-dotted line depicts an actuator setpoint based on an occupancy metric including an occupancy probability. The thick dashed line depicts a user setpoint manually entered by a user. The thin dashed line indicates an alternative user setpoint manually entered by a user.

[0130] Figure 6 、 Figure 7 、 Figure 8 and Figure 9 Depicted are example adaptive thermostat controls based on occupancy events and learned temperature loss rates according to one or more embodiments of the present disclosure.

[0131] In some embodiments, a timed temperature profile can be used to determine how dynamic the set point changes can be without compromising comfort. This is an applied (per room) value that can be learned after installation and adapted to seasonal effects on heating or cooling loads. Figure 6 、 Figure 7 、 Figure 8 and Figure 9 , the term "room" is used as an illustration of one or more embodiments of adaptive thermostat control. However, one of ordinary skill in the art will understand that Figure 6 、 Figure 7 、 Figure 8 and Figure 9 and the associated descriptions apply to embodiments using any area type, including, for example, rooms, partitions, zones, groupings of rooms, outdoor spaces, floors of a building, or any other suitable division of a building / space.

[0132] In some embodiments, a + / - 0.5°C deviation from the set point may not be detectable (by feel). Thus, the room constant can be defined as the first-order response time of a 0.5°C temperature decrease (or increase) following a downward set point change, which can result in a corresponding decrease in energy demand, in some cases as low as 0% demand. Thus, in some embodiments, if the presence detection function determines a low probability of occupancy, the set point is reduced by 0.5°C after the room first-order response time. This function can be repeated until a minimum comfort parameter is achieved. In some embodiments, each room time constant in which no presence is detected will result in a 0.5°C decrease (or increase) in the set point.

[0133] In some embodiments, the body cannot detect a 0.5°C change in ambient temperature, but each will reduce energy consumption by 5%, resulting in a 10% reduction over two time constants. Each heating and cooling step is used to update the heating ramp and first-order cooling time. This learning process adapts to both the space and the season. Furthermore, a 1°C setpoint reduction equates to a 10% energy saving. Therefore, the reduction in heat loss from the room as a result of a 0.5°C setpoint reduction is minimal, approximately 5%. This may lead one to believe that a more aggressive backoff is the correct course of action, however, such a backoff may result in significant temperature fluctuations that adversely affect comfort and HVAC equipment efficiency.

[0134] Therefore, to protect comfort levels, a room that cools quickly can have its setpoint reduced more slowly than a well-insulated room. Therefore, a variable setpoint reduction or rate of change can be employed to account for the insulation of a space. For example, a gradual reduction in the room's setpoint can be employed, tied to the room's learned performance. This gradual reduction can provide energy savings by keeping the heating control within the modulation band, thereby ensuring a reduction in heat input rather than shutting it off completely.

[0135] In some embodiments, the actuator can employ fuzzy logic to learn the percentage of demand at each potential set point. This is a feed-forward control loop with an error-correcting feedback loop on top that drives the learning and provides additional demand to bring the temperature up to the set point. The output is modulated (PWM) for on / off switching or directly modulated for communication appliances, so a 0.5°C decrease in the set point might immediately result in a decrease in heat input, but still leave a small percentage of demand, allowing the temperature to decrease in a controlled manner.

[0136] In some embodiments, as the room temperature drops, the percentage demand can be gradually increased back to the set point minus the 0.5°C fuzzy value. The logic can be timed (based on a learned time constant) and further reactive to lower the set point as the temperature drops and unoccupied conditions continue. In some embodiments, for systems that lose heat quickly, the logic can have the greatest effect in poorly insulated spaces, but can still benefit well-insulated, fast-responding spaces by making the operation more usable and adaptable.

[0137] Figure 10A block diagram of an exemplary computer-based system and platform 1000 is depicted in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and changes in the arrangement and type of components may be made without departing from the spirit or scope of the various embodiments of the present disclosure. In some embodiments, the illustrative computing devices and illustrative computing components of the exemplary computer-based system and platform 1000 can be configured to manage a large number of members and concurrent transactions, as described in detail herein. In some embodiments, the exemplary computer-based system and platform 1000 can be based on an extensible computer and network architecture that incorporates different strategies for evaluating data, caching, searching, and / or database connection pooling. An example of an extensible architecture is an architecture that is capable of operating multiple servers.

[0138] In some embodiments, reference Figure 10, client devices 1002, 1003, and 1004 (e.g., clients) of the exemplary computer-based system and platform 1000 may include substantially any computing device capable of sending and receiving messages (with each other) to and from another computing device (e.g., servers 1006 and 1007) over a network (e.g., a cloud network) (e.g., network 1005). In some embodiments, client devices 1002 to 1004 may be personal computers, multi-processor systems, microprocessor-based or programmable consumer electronics devices, network PCs, and the like. In some embodiments, one or more of client devices 1002 to 1004 may include computing devices typically connected using a wireless communication medium, such as a cell phone, a smart phone, a pager, a walkie-talkie, a radio frequency (RF) device, an infrared (IR) device, a citizen's band radio, an integrated device combining one or more of the foregoing, or substantially any mobile computing device. In some embodiments, one or more of the client devices 1002 to 1004 may be devices capable of connecting using a wired or wireless communication medium, such as a PDA, a pocket PC, a wearable computer, a laptop computer, a tablet computer, a desktop computer, a netbook, a video game device, a pager, a smartphone, an ultra-mobile personal computer (UMPC), and / or any other device equipped to communicate via a wired and / or wireless communication medium (e.g., NFC, RFID, NBIOT, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, OFDM, OFDMA, LTE, satellite, ZigBee, etc.). In some embodiments, one or more of the client devices 1002 to 1004 may include a computer capable of running one or more applications, such as an Internet browser, a mobile application, voice calling, video games, video conferencing, and email. In some embodiments, one or more of the client devices 1002 to 1004 may be configured to receive and send web pages, etc. In some embodiments, the exemplary specifically programmed browser application of the present disclosure may be configured to receive and display graphics, text, multimedia, etc., using virtually any web-based language, including, but not limited to, Standard Generalized Markup Language (SMGL) (such as Hypertext Markup Language (HTML)), Wireless Application Protocol (WAP), Handheld Device Markup Language (HDML) (such as Wireless Markup Language (WML)), WMLScript, XML, JavaScript, etc. In some embodiments, the client devices within client devices 1002 to 1004 may be specifically programmed using Java, .Net, QT, C, C++, Python, PHP, and / or other suitable programming languages.In some embodiments of the device software, device control can be distributed among multiple independent applications. In some embodiments, software components / applications can be remotely updated and redeployed as individual units or as complete software suites. In some embodiments, the client device can periodically report status or send alerts via text or email. In some embodiments, the client device can include a data logger that can be remotely downloaded by a user using a network protocol such as FTP, SSH, or other file transfer mechanism. In some embodiments, the client device can provide several levels of user interface, such as advanced user, standard user. In some embodiments, one or more client devices within client devices 1002 to 1004 can be specifically programmed to include or execute applications to perform various possible tasks, such as, but not limited to, messaging functionality, browsing, searching, playing, streaming, or displaying various forms of content, including locally stored or uploaded messages, images, and / or videos, and / or games.

[0139] In some embodiments, exemplary network 1005 can provide network access, data transfer, and / or other services to any computing device coupled thereto. In some embodiments, exemplary network 1005 can include and implement at least one dedicated network architecture, which can be based at least in part on one or more standards set by, for example, but not limited to, the Global System for Mobile Communications (GSM) Association, the Internet Engineering Task Force (IETF), and the Worldwide Interoperability for Microwave Access (WiMAX) Forum. In some embodiments, exemplary network 1005 can implement one or more of the GSM architecture, the General Packet Radio Service (GPRS) architecture, the Universal Mobile Telecommunications System (UMTS) architecture, and the UMTS evolution known as Long Term Evolution (LTE). In some embodiments, exemplary network 1005 can include and implement the WiMAX architecture defined by the WiMAX Forum, as an alternative or in combination with one or more of the foregoing. In some embodiments, and optionally in any combination of the embodiments described above or below, exemplary network 1005 can further include, for example, at least one of a local area network (LAN), a wide area network (WAN), the Internet, a virtual LAN (VLAN), an enterprise LAN, a layer 3 virtual private network (VPN), an enterprise IP network, or any combination thereof. In some embodiments, and optionally in any combination of the above or below embodiments, at least one computer network communication over the exemplary network 1005 can be transmitted at least in part based on one or more communication modes, such as, but not limited to, NFC, RFID, Narrowband Internet of Things (NBIoT), ZigBee, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, OFDM, OFDMA, LTE, satellite, and any combination thereof. In some embodiments, the exemplary network 1005 can also include mass storage, such as a network attached storage (NAS), a storage area network (SAN), a content delivery network (CDN), or other form of computer or machine-readable media.

[0140] In some embodiments, exemplary server 1006 or exemplary server 1007 may be a web server (or series of servers) running a network operating system, examples of which may include, but are not limited to, Apache on Linux or Microsoft IIS (Internet Information Services). In some embodiments, exemplary server 1006 or exemplary server 1007 may be used for and / or provide cloud and / or network computing. Although Figure 10Not shown, but in some embodiments, example server 1006 or example server 1007 may have connections to external systems, such as email, SMS messaging, text messaging, advertising content providers, etc. Any of the features of example server 1006 may also be implemented in example server 1007, and vice versa.

[0141] In some embodiments, one or more of the exemplary servers 1006 and 1007 may be specifically programmed to perform as, in non-limiting examples, an authentication server, a search server, an email server, a social networking service server, a short message service (SMS) server, an instant messaging (IM) server, a multimedia messaging service (MMS) server, an exchange server, a photo sharing service server, an advertisement serving server, a financial / banking related service server, a travel service server, or any similar suitable service-based server for users of client devices 1001 to 1004.

[0142] In some embodiments, and optionally in combination with any of the embodiments described above or below, for example, one or more of the exemplary computing client devices 1002 to 1004, the exemplary server 1006 and / or the exemplary server 1007 may include specifically programmed software modules that may be configured to send, process, and receive information using scripting languages, remote procedure calls, email, tweets, short message service (SMS), multimedia message service (MMS), instant messaging (IM), application programming interfaces, simple object access protocol (SOAP) methods, common object request broker architecture (CORBA), HTTP (Hypertext Transfer Protocol), REST (Representational State Transfer), SOAP (Simple Object Transfer Protocol), MLLP (Minimal Lower Layer Protocol), or any combination thereof.

[0143] Figure 11A block diagram of another exemplary computer-based system and platform 1100 is depicted in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and variations in the arrangement and types of components may be made without departing from the spirit or scope of the various embodiments of the present disclosure. In some embodiments, the illustrated client devices 1102a, 1102b, and 1102n each include at least a computer-readable medium, such as a random access memory (RAM) 1108 coupled to a processor 1110 or flash memory. In some embodiments, the processor 1110 can execute computer-executable program instructions stored in the memory 1108. In some embodiments, the processor 1110 can include a microprocessor, an ASIC, and / or a state machine. In some embodiments, the processor 1110 can include a medium (e.g., a computer-readable medium) or can be in communication with a medium (e.g., a computer-readable medium) that stores instructions that, when executed by the processor 1110, cause the processor 1110 to perform one or more steps described herein. In some embodiments, examples of computer-readable media may include, but are not limited to, electronic, optical, magnetic, or other storage or transmission devices capable of providing computer-readable instructions to a processor (such as the processor 1110 of the client device 1102a). In some embodiments, other examples of suitable media may include, but are not limited to, floppy disks, CD-ROMs, DVDs, magnetic disks, memory chips, ROMs, RAMs, ASICs, configured processors, all-optical media, all-magnetic tapes or other magnetic media, or any other medium from which a computer processor can read instructions. In addition, various other forms of computer-readable media may transmit or carry instructions to a computer, including routers, private or public networks, or other transmission devices or channels (both wired and wireless). In some embodiments, the instructions may include code from any computer programming language, including, for example, C, C++, Visual Basic, Java, Python, Perl, JavaScript, and the like.

[0144] In some embodiments, the client devices 1102a to 1102n may also include a plurality of external or internal devices, such as a mouse, CD-ROM, DVD, physical or virtual keyboard, display, or other input or output devices. In some embodiments, examples of client devices 1102a to 1102n (e.g., clients) may be any type of processor-based platform connected to the network 1106, such as, but not limited to, a personal computer, a digital assistant, a personal digital assistant, a smart phone, a pager, a digital tablet, a laptop computer, an Internet appliance, and other processor-based devices. In some embodiments, the client devices 1102a to 1102n may be specifically programmed with one or more applications according to one or more of the principles / methods detailed herein. In some embodiments, the client devices 1102a to 1102n may operate on any operating system capable of supporting a browser or browser-enabled application, such as Microsoft Windows XP. TM , Windows TM In some embodiments, the client devices 1102a to 1102n shown may include, for example, a computer running Microsoft's Internet Explorer. TM , Apple Computer's Safari TM , Mozilla Firefox, and / or Opera browser applications. In some embodiments, users 1112a, 1112b, and 1112n can communicate with each other and / or other systems and / or devices coupled to the network 1106 via the exemplary network 1106 through the member computing client devices 1102a to 1102n. Figure 11 As shown in FIG, exemplary server devices 1104 and 1113 may include processors 1105 and 1114, respectively, and memory 1117 and 1116, respectively. In some embodiments, server devices 1104 and 1113 may also be coupled to a network 1106. In some embodiments, one or more client devices 1102a to 1102n may be mobile clients.

[0145] In some embodiments, at least one of the exemplary databases 1107 and 1115 can be any type of database, including a database managed by a database management system (DBMS). In some embodiments, the database managed by the exemplary DBMS can be specifically programmed to control the organization, storage, management, and / or retrieval of data in the corresponding database. In some embodiments, the database managed by the exemplary DBMS can be specifically programmed to provide query, backup and replication, implement rules, provide security, calculate, perform change and access logging, and / or automated optimization capabilities. In some embodiments, the database managed by the exemplary DBMS can be selected from Oracle Database, IBM DB2, Adaptive Server Enterprise, FileMaker, Microsoft Access, Microsoft SQL Server, MySQL, PostgreSQL, and NoSQL implementations. In some embodiments, the database managed by the exemplary DBMS can be specifically programmed to define each corresponding schema of each database in the exemplary DBMS according to a specific database model of the present disclosure, which can include a hierarchical model, a network model, a relational model, an object model, or some other suitable organization that can generate one or more applicable data structures that can include fields, records, files, and / or objects. In some embodiments, the database managed by the exemplary DBMS can be specifically programmed to include metadata about the stored data.

[0146] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may be specifically configured to operate in cloud computing / architecture 1125, such as, but not limited to, Infrastructure as a Service (IaaS) 1310, Platform as a Service (PaaS) 1308, and / or Software as a Service (SaaS) 1306 using a web browser, mobile application, thin client, terminal emulator, or other endpoint 1304. Figure 12 and Figure 13 Illustrated are schematic diagrams of exemplary implementations of cloud computing(s) / architectures in which exemplary inventive computer-based systems / platforms, exemplary inventive computer-based apparatuses, and / or exemplary inventive computer-based components of the present disclosure may be specifically configured to operate.

[0147] It is understood that at least one aspect / functionality of the various embodiments described herein can be performed in real time and / or dynamically. As used herein, the term "real time" refers to an event / action that can occur instantaneously or almost instantaneously in time when another event / action has occurred. For example, "real-time processing," "real-time computing," and "real-time execution" all relate to the performance of a calculation during the actual time that a related physical process (e.g., a user interacting with an application on a mobile device) occurs, so that the results of the calculation can be used to guide the physical process.

[0148] As used herein, the terms "dynamically" and "automatically" and their logical and / or linguistic associates and / or derivatives mean that certain events and / or actions can be triggered and / or occur without any human intervention. In some embodiments, events and / or actions according to the present disclosure can be real-time and / or based on a predetermined periodicity of at least one of the following: nanoseconds, nanoseconds, milliseconds, milliseconds, seconds, seconds, minutes, minutes, hours, hours, days, weeks, months, etc.

[0149] As used herein, the term "runtime" corresponds to any behavior that is dynamically determined during execution of a software application or at least a portion of a software application.

[0150] In some embodiments, the exemplary inventive, specifically programmed computing systems and platforms with associated devices are configured to operate in a distributed network environment, communicating with each other over one or more suitable data communications networks (e.g., the Internet, satellite, etc.), and utilizing one or more suitable data communications protocols / modes, such as, but not limited to, IPX / SPX, X.25, AX.25, AppleTalk™, TCP / IP (e.g., HTTP), Near Field Communication (NFC), RFID, Narrowband Internet of Things (NBIOT), 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, and other suitable communication modes.

[0151] In some embodiments, NFC may refer to a short-range wireless communication technology in which NFC-enabled devices are "swiped," "bumped," "tapped," or otherwise moved into close proximity to communicate. In some embodiments, NFC may include a collection of short-range wireless technologies, typically requiring a distance of 10 cm or less. In some embodiments, NFC may operate over the ISO / IEC 18000-3 air interface at 13.56 MHz and at rates ranging from 106 kbit / s to 424 kbit / s. In some embodiments, NFC may involve an initiator and a target; the initiator actively generates an RF field that can power a passive target. In some embodiments, this can enable an NFC target to take on a very simple form factor, such as a tag, sticker, key fob, or card that does not require a battery. In some embodiments, peer-to-peer NFC communication can occur when multiple NFC-enabled devices (e.g., smartphones) are in close proximity to each other.

[0152] In some embodiments, Bluetooth may represent a short-range wireless communication technology in which Bluetooth-enabled devices are paired to establish a communication link that can allow one device to send commands to another. For example, a user with a smartphone can communicate with a smart home device (such as sensor 108 or actuator 104), or a security system, or other suitable Bluetooth-enabled home system to establish settings and parameters, such as the arm / set state of the security system. The use of Bluetooth can facilitate the detection of triggers in the home system that can be used to identify presence based on the arm / set state of the home system without requiring an Internet and / or Wi-Fi connection.

[0153] The materials disclosed herein may be implemented in software or firmware, or a combination thereof, or as instructions stored on a machine-readable medium that can be read and executed by one or more processors. A machine-readable medium may include any medium and / or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable medium may include read-only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustic, or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and the like.

[0154] As used herein, the terms "computer engine" and "engine" identify at least one software component and / or a combination of at least one software component and at least one hardware component that is designed / programmed / configured to manage / control other software and / or hardware components (such as a library, software development kit (SDK), object, etc.).

[0155] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. In some embodiments, one or more processors may be implemented as a complex instruction set computer (CISC) or a reduced instruction set computer (RISC) processor; an x86 instruction set compatible processor, a multi-core or any other microprocessor or central processing unit (CPU). In various implementations, one or more processors may be a dual-core processor(s), a dual-core mobile processor(s), etc.

[0156] As used herein, computer-related systems, computer systems and systems include any combination of hardware and software.The example of software can include software component, program, application, operating system software, middleware, firmware, software module, routine, subroutine, function, method, process, software interface, application program interface (API), instruction set, computer code, computer code segment, word, value, symbol or its any combination.Determine whether to use hardware element and / or software element to realize embodiment and can change according to the factor of any number, such as expected computing rate, power level, thermal tolerance, processing cycle budget, input data rate, output data rate, memory resource, data bus speed and other design or performance constraint.

[0157] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium representing various logic within a processor, which, when read by a machine, causes the machine to manufacture logic to perform the techniques described herein. Such representations, referred to as "IP cores," may be stored on tangible machine-readable media and provided to various customers or manufacturing facilities to be loaded into manufacturing machines that manufacture logic or processors. It is noteworthy that the various embodiments described herein may of course be implemented using any appropriate hardware and / or computing software language (e.g., C++, Objective-C, Swift, Java, JavaScript, Python, Perl, QT, etc.).

[0158] In some embodiments, one or more of the exemplary computer-based systems or platforms of the present disclosure may include or be partially or fully incorporated into at least one personal computer (PC), laptop computer, ultralaptop computer, tablet computer, touchpad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), cellular phone, cellular phone / PDA combination, television, smart device (e.g., smart phone, smart tablet or smart TV), mobile Internet device (MID), messaging device, data communication device, etc.

[0159] As used herein, the term "server" should be understood to refer to a service point that provides processing, database, and communication facilities. By way of example and not limitation, the term "server" may refer to a single physical processor with associated communication and data storage and database facilities, or it may refer to a networked or clustered complex of processors and associated networking and storage devices, as well as operating software and one or more database systems and application software that support the services provided by the server. A cloud server is an example.

[0160] In some embodiments, as described in detail herein, one or more of the computer-based systems of the present disclosure can obtain, manipulate, transmit, store, transform, generate and / or output any digital object and / or data unit (e.g., from within and / or outside a particular application), which can be in any suitable form, such as, but not limited to, files, contacts, tasks, emails, messages, maps, entire applications (e.g., calculators), data points, and other suitable data. In some embodiments, as described in detail herein, one or more of the computer-based systems of the present disclosure can be implemented across one or more of a variety of computer platforms, such as, but not limited to: (1) FreeBSD, NetBSD, OpenBSD; (2) Linux; (3) Microsoft Windows TM (4) OpenVMS TM ;(5)OSX(MacOS TM ); (6) UNIX TM ; (7) Android; (8) iOS TM ;(9)EmbeddedLinux;(10)Tizen TM ;(11)WebOS TM (12) Adobe AIR TM ; (13)BREW TM ); (14) Cocoa TM (API); (15) Cocoa TM Touch; (16) JavaTM Platform; (17) JavaFX TM ;(18)QNX TM ;(19)Mono;(20)GoogleBlink;(21)AppleWebKit;(22)MozillaGecko TM ;(23)MozillaXUL;(24).NET Framework;(25)Silverlight TM ;(26)Open Web Platform;(27)OracleDatabase;(28)Qt TM ;(29)SAP NetWeaver TM ;(30)Smartface TM ;(31)Vexi TM ;(32)Kubernetes TM and (33) Windows Runtime (WinRT TM ) or other suitable computer platform, or any combination thereof. In some embodiments, the illustrative computer-based systems or platforms of the present disclosure may be configured to utilize hard-wired circuitry that may be used in place of or in combination with software instructions to implement features consistent with the principles of the present disclosure. Accordingly, implementations consistent with the principles of the present disclosure are not limited to any particular combination of hardware circuitry and software. For example, various embodiments may be embodied as software components in many different ways, such as, but not limited to, stand-alone software packages, combinations of software packages, or it may be a software package incorporated as a "tool" into a larger software product.

[0161] For example, exemplary software specifically programmed according to one or more principles of the present disclosure may be downloadable from a network (e.g., a website) as a standalone product or as an add-in package for installation in an existing software application. For example, exemplary software specifically programmed according to one or more principles of the present disclosure may also be available as a client-server software application or as a web-enabled software application. For example, exemplary software specifically programmed according to one or more principles of the present disclosure may also be embodied as a software package installed on a hardware device.

[0162] In some embodiments, the illustrative computer-based system or platform of the present disclosure may be configured to handle a number of concurrent users, which may be, but is not limited to, at least 100 (e.g., but not limited to, 100-999), at least 1,000 (e.g., but not limited to, 1,000-9,999), at least 10,000 (e.g., but not limited to, 10,000-99,999), at least 100,000 (e.g., but not limited to, 100,000-999,999), at least 1,0 ...). 00 (for example, but not limited to, 1,000,000-9,999,999), at least 10,000,000 (for example, but not limited to, 10,000,000-99,999,999), at least 100,000,000 (for example, but not limited to, 100,000,000-999,999,999), at least 1,000,000,000 (for example, but not limited to, 1,000,000,000-999,999,999,999), etc.

[0163] In some embodiments, the illustrative computer-based system or platform of the present disclosure can be configured to output to different, specifically programmed graphical user interface implementations of the present disclosure (e.g., desktop, web application, etc.). In various implementations of the present disclosure, the final output can be displayed on a display screen, which can be, but is not limited to, a computer screen, a mobile device screen, etc. In various implementations, the display can be a holographic display. In various implementations, the display can be a transparent surface that can receive a visual projection. Such a projection can convey various forms of information, images, or objects. For example, such a projection can be a visual overlay for a mobile augmented reality (MAR) application.

[0164] In some embodiments, the illustrative computer-based system or platform of the present disclosure may be configured for use in a variety of applications, which may include, but are not limited to, games, mobile device games, video chat, video conferencing, live video streaming, video streaming and / or augmented reality applications, mobile device messenger applications, and other similarly suitable computer device applications.

[0165] As used herein, the term "mobile electronic device" or the like may refer to any portable electronic device that may or may not have location tracking functionality (e.g., MAC address, Internet Protocol (IP) address, etc.) enabled. For example, a mobile electronic device may include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a Blackberry TM , pager, smart phone or any other reasonable mobile electronic device.

[0166] As used herein, the terms "proximity detection," "positioning," "position data," "position information," and "position tracking" refer to any form of position tracking technology or positioning method that can be used to provide, for example, the location of a particular computing device, system, or platform of the present disclosure and any associated computing devices based at least in part on one or more of the following technologies and devices (but not limited to): accelerometer(s), gyroscope(s), Global Positioning System (GPS); using Bluetooth TM GPS access; GPS access using any reasonable form of wireless or non-wireless communication; WiFi TM Server location data; based on Bluetooth TM location data; triangulation, such as but not limited to network-based triangulation, WiFi-based TM Triangulation of server information, based on Bluetooth TM Triangulation of server information, triangulation based on cell identity, triangulation based on enhanced cell identity, triangulation based on uplink time difference of arrival (U-TDOA), triangulation based on time of arrival (TOA), triangulation based on angle of arrival (AOA); techniques and systems using geographic coordinate systems, such as but not limited to longitude and latitude based, geodetic altitude based, Cartesian coordinate based; radio frequency identification, such as but not limited to long-range RFID, short-range RFID; use of any form of RFID tag, such as but not limited to active RFID tag, passive RFID tag, battery-assisted passive RFID tag; or any other reasonable method for determining location. For the sake of simplicity, the above variations are sometimes not listed or only partially listed; this is in no way meant to be limiting.

[0167] As used herein, the terms "cloud," "Internet cloud," "cloud computing," "cloud architecture," and similar terms correspond to at least one of the following: (1) a large number of computers connected by a real-time communications network (e.g., the Internet); (2) providing the ability to run programs or applications on many connected computers (e.g., physical machines, virtual machines (VMs)) simultaneously; or (3) a network-based service that appears to be provided by real server hardware and is actually served up by virtual hardware (e.g., virtual servers) emulated by software running on one or more real machines (e.g., allowing for on-the-fly movement and scaling up (or down) without affecting end users).

[0168] In some embodiments, the illustrative computer-based system or platform of the present disclosure may be configured to securely store and / or transmit data by utilizing one or more of encryption techniques (e.g., private / public key pairs, Triple Data Encryption Standard (3DES), block cipher algorithms (e.g., IDEA, RC2, RC5, CAST, and Skipjack), cryptographic hash algorithms (e.g., MD5, RIPEMD-160, RTR0, SHA-1, SHA-2, Tiger (TTH), WHIRLPOOL, RNGs).

[0169] As used herein, the term "user" shall have the meaning of at least one user. In some embodiments, the terms "user," "subscriber," "consumer," or "client" shall be understood to refer to a user of one or more applications as described herein and / or a consumer of data supplied by a data provider. By way of example and not limitation, the term "user" or "subscriber" may refer to a person who receives data provided by a data or service provider over the Internet in a browser session, or may refer to an automated software application that receives data and stores or processes it.

[0170] The above examples are of course illustrative rather than limiting.

[0171] At least some aspects of the present disclosure will now be described with reference to the following numbered clauses. 1. A method comprising: receiving, by at least one processor, time-series presence data from at least one presence sensing device associated with an area; The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; determining, by the at least one processor, an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time; wherein the plurality of time slots comprises a breakdown of each day of the week; The region is generated by the at least one processor based at least in part on Domain occupancy scheduling: the occupancy metric associated with the area in each time slot, and a history of the occupancy metric associated with the area in each time slot; wherein the occupancy schedule represents a prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks; determining, by the at least one processor, at least one comfort system actuator associated with the zone; and communicating, by the at least one processor, the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks. 2. The method of clause 1, further comprising predicting, by the at least one processor, the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot using an occupancy prediction machine learning model, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot. 3. The method according to the preceding clause, further comprising: dividing, by the at least one processor, the time series existence data into a plurality of time windows; and Each time window of the plurality of time windows is assigned, by the at least one processor, to a particular time slot of the plurality of time slots. 4. A method according to any preceding clause, further comprising: determining, by the at least one processor, a presence in each of the plurality of time slots; generating, by the at least one processor, an occupancy metric associated with the presence in each time slot; and The occupancy metric in each time slot is determined, by the at least one processor, based at least in part on the occupancy metric in each time slot. 5. The method of clause 4, wherein the amount present comprises at least one of: The frequency of occurrence in each time slot, or The duration of existence in each time slot. 6. The method according to clause 4, further comprising: accessing, by the at least one processor, a plurality of previous occupancy metrics associated with at least one previous week; aligning, by the at least one processor, a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated by the at least one processor based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot. 7. The method according to clause 6, further comprising: The occupancy metric in each time slot is generated, by the at least one processor, based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot. 8. The method according to clause 7, further comprising: utilizing, by the at least one processor, the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; and The occupancy schedule for the zone is generated, by the processor, based at least in part on the predicted occupancy state. 9. A method according to any preceding clause, wherein the at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment. 10. A method according to any preceding clause, further comprising: The method further comprises: utilizing, by the at least one processor, an occupancy state prediction machine learning model to predict a predicted occupancy state associated with each time slot based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot. 11. A system comprising: at least one processor in communication with at least one non-transitory computer-readable medium having software instructions stored thereon, wherein the at least one processor, when executing the software instructions, is configured to: Receive a time series presence signal from at least one presence sensing device associated with an area. In data; The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; Determining an occupancy associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time measure; wherein the plurality of time slots comprises a breakdown of each day of the week; Generating an occupancy schedule for the zone based at least in part on: the occupancy metric associated with the area in each time slot, and a history of occupancy metrics associated with the area during each time slot; wherein the occupancy schedule represents a prediction of occupancy levels for the area during each subsequent time slot in subsequent weeks; determining at least one comfort system actuator associated with the zone; and communicating the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks. 12. The system of clause 11, wherein, upon executing the software instructions, the at least one processor is further configured to utilize an occupancy prediction machine learning model to predict the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot. 13. The system of any of clauses 11 to 12, wherein the at least one processor, when executing the software instructions, is further configured to: Splitting the time series data into multiple time windows; and Each time window of the plurality of time windows is assigned to a specific time slot of the plurality of time slots. 14. The system of any of clauses 11 to 13, wherein the at least one processor, when executing the software instructions, is further configured to: determining a presence in each of the plurality of time slots; generating an occupancy metric associated with the presence in each time slot; and The occupancy metric in each time slot is determined based at least in part on the occupancy metric in each time slot. 15. The system of clause 14, wherein the presence comprises at least one of: The frequency of occurrence in each time slot, or The duration of existence in each time slot. 16. The system of clause 14, wherein the at least one processor, when executing the software instructions, is further configured to: accessing a plurality of previous occupancy metrics associated with at least one previous week; aligning a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot. 17. The system of clause 16, wherein the at least one processor, when executing the software instructions, is further configured to: The occupancy metric in each time slot is generated based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot. 18. The system of clause 17, wherein the at least one processor, when executing the software instructions, is further configured to: utilizing the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; and The occupancy schedule for the area is generated based at least in part on the predicted occupancy state. 19. The system of any of clauses 11 to 18, wherein the at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment. 20. The system of any of clauses 11 to 19, wherein the at least one processor, when executing the software instructions, is further configured to: Utilizing the occupancy state prediction machine learning model, a predicted occupancy state associated with each time slot is predicted based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot. 21. A non-transitory computer-readable medium comprising software instructions that, when executed, are configured to cause at least one processor to perform steps comprising: Receive a time series presence signal from at least one presence sensing device associated with an area. In data; The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; Determining an occupancy associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time measure; wherein the plurality of time slots comprises a breakdown of each day of the week; Generating an occupancy schedule for the zone based at least in part on: the occupancy metric associated with the area in each time slot, and a history of the occupancy metric associated with the area in each time slot; wherein the occupancy schedule represents a prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks; determining at least one comfort system actuator associated with the zone; and communicating the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks. 22. The non-transitory computer-readable medium of clause 21, further comprising software instructions that, when executed, are configured to cause the at least one processor to: predict the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot using an occupancy prediction machine learning model, The occupancy prediction machine learning model includes a trained prediction layer, wherein the trained prediction layer includes parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot. 23. The non-transitory computer-readable medium of any of clauses 21 to 22, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: Splitting the time series data into multiple time windows; and Each time window of the plurality of time windows is assigned to a specific time slot of the plurality of time slots. 24. The non-transitory computer-readable medium of any of clauses 21 to 23, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: determining a presence in each of the plurality of time slots; generating an occupancy metric associated with the presence in each time slot; and The occupancy metric in each time slot is determined based at least in part on the occupancy metric in each time slot. 25. The non-transitory computer-readable medium of clause 24, wherein the amount present comprises at least one of: The frequency of occurrence in each time slot, or The duration of existence in each time slot. 26. The non-transitory computer-readable medium of clause 24, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: accessing a plurality of previous occupancy metrics associated with at least one previous week; aligning a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot. 27. The non-transitory computer-readable medium of clause 26, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: The occupancy metric in each time slot is generated based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot. 28. The non-transitory computer-readable medium of clause 27, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: utilizing the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; and The occupancy schedule for the area is generated based at least in part on the predicted occupancy state. 29. The non-transitory computer-readable medium of any one of clauses 21 to 28, wherein the at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment. 30. The non-transitory computer-readable medium of any of clauses 21 to 29, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: Utilizing the occupancy state prediction machine learning model, a predicted occupancy state associated with each time slot is predicted based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

[0172] The publications cited throughout this document are hereby incorporated by reference in their entirety. Although one or more embodiments of the present disclosure have been described, it is understood that these embodiments are illustrative only and not restrictive, and that many modifications may become apparent to those skilled in the art, including that the various embodiments of the inventive methods, illustrative systems and platforms, and illustrative devices described herein may be used in any combination with one another. Furthermore, the various steps may be performed in any desired order (and any desired steps may be added and / or any desired steps may be eliminated).

Claims

1. A method comprising: receiving, by at least one processor, time-series presence data from at least one presence sensing device associated with an area; The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; determining, by the at least one processor, an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time; wherein the plurality of time slots comprises a breakdown of each day of the week; Generating, by the at least one processor, an occupancy schedule for the area based at least in part on: the occupancy metric associated with the area in each time slot, and a history of occupancy metrics associated with the area in each time slot; wherein the occupancy schedule represents a prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks; determining, by the at least one processor, at least one comfort system actuator associated with the zone; and communicating, by the at least one processor, the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks.

2. The method of claim 1 , further comprising predicting, by the at least one processor, the occupancy schedule based at least in part on the occupancy metric associated with the zone in each time slot using an occupancy prediction machine learning model, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

3. The method according to any one of claims 1 to 2, further comprising: Splitting the time series existence data into a plurality of time windows by the at least one processor; as well as Each time window of the plurality of time windows is assigned, by the at least one processor, to a particular time slot of the plurality of time slots.

4. The method according to any one of claims 1 to 3, further comprising: determining, by the at least one processor, a presence in each of the plurality of time slots; generating, by the at least one processor, an occupancy metric associated with the presence in each time slot; as well as The occupancy metric in each time slot is determined, by the at least one processor, based at least in part on the occupancy metric in each time slot.

5. The method according to claim 4, wherein The amount present includes at least one of the following: The frequency of presence in each time slot, or The duration of existence in each time slot.

6. The method according to any one of claims 1 to 4, further comprising: accessing, by the at least one processor, a plurality of previous occupancy metrics associated with at least one previous week; aligning, by the at least one processor, a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated by the at least one processor based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot.

7. The method according to any one of claims 1 to 6, further comprising: The occupancy metric in each time slot is generated, by the at least one processor, based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot.

8. The method according to any one of claims 1 to 7, further comprising: utilizing, by the at least one processor, the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; as well as The occupancy schedule for the zone is generated, by the processor, based at least in part on the predicted occupancy state.

9. The method according to any one of claims 1 to 8, wherein The at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment.

10. The method according to any one of claims 1 to 9, further comprising: The method further comprises: utilizing, by the at least one processor, an occupancy state prediction machine learning model to predict a predicted occupancy state associated with each time slot based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

11. A system comprising: at least one processor in communication with at least one non-transitory computer-readable medium having software instructions stored thereon, wherein the at least one processor, when executing the software instructions, is configured to: receiving time-series presence data from at least one presence sensing device associated with the area; The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; determining an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time; wherein the plurality of time slots comprises a breakdown of each day of the week; Generating an occupancy schedule for the zone based at least in part on: the occupancy metric associated with the area in each time slot, and a history of occupancy metrics associated with the area in each time slot; wherein the occupancy schedule represents a prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks; determining at least one comfort system actuator associated with the zone; and communicating the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks.

12. The system according to claim 11, wherein Upon executing the software instructions, the at least one processor is further configured to predict the occupancy schedule based at least in part on the occupancy metric associated with the area in each time slot using an occupancy prediction machine learning model, wherein the occupancy prediction machine learning model comprises a trained prediction layer comprising parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

13. The system according to any one of claims 11 to 12, wherein: The at least one processor, when executing the software instructions, is further configured to: Splitting the time series data into multiple time windows; and Each time window of the plurality of time windows is assigned to a specific time slot of the plurality of time slots.

14. The system according to any one of claims 11 to 13, wherein: The at least one processor, when executing the software instructions, is further configured to: determining a presence in each of the plurality of time slots; generating an occupancy metric associated with the presence in each time slot; as well as The occupancy metric in each time slot is determined based at least in part on the occupancy metric in each time slot.

15. The system according to claim 14, wherein: The amount present includes at least one of the following: The frequency of presence in each time slot, or The duration of existence in each time slot.

16. The system according to any one of claims 11 to 14, wherein: The at least one processor, when executing the software instructions, is further configured to: accessing a plurality of previous occupancy metrics associated with at least one previous week; aligning a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot.

17. The system according to any one of claims 11 to 16, wherein: The at least one processor, when executing the software instructions, is further configured to: The occupancy metric in each time slot is generated based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot.

18. The system according to any one of claims 11 to 17, wherein: The at least one processor, when executing the software instructions, is further configured to: utilizing the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; and The occupancy schedule for the area is generated based at least in part on the predicted occupancy state.

19. The system according to any one of claims 11 to 18, wherein: The at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment.

20. The system according to any one of claims 11 to 19, wherein The at least one processor, when executing the software instructions, is further configured to: Utilizing the occupancy state prediction machine learning model, a predicted occupancy state associated with each time slot is predicted based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

21. A non-transitory computer-readable medium comprising software instructions that, when executed, are configured to cause at least one processor to perform steps comprising: receiving time-series presence data from at least one presence sensing device associated with the area; in, The time series existence data includes: at least one presence instance detected in the area, and at least one time associated with the at least one instance; determining an occupancy metric associated with the area in each of a plurality of time slots based at least in part on the at least one presence instance and the at least one time; wherein the plurality of time slots comprises a breakdown of each day of the week; Generating an occupancy schedule for the zone based at least in part on: the occupancy metric associated with the area in each time slot, and a history of occupancy metrics associated with the area in each time slot; wherein the occupancy schedule represents a prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks; determining at least one comfort system actuator associated with the zone; and communicating the occupancy schedule to the at least one comfort system actuator; wherein the occupancy schedule is configured to cause the at least one comfort system actuator to actuate at least one building actuator based at least in part on the prediction of the occupancy level of the area during each subsequent time slot in subsequent weeks.

22. The non-transitory computer-readable medium of claim 21 , further comprising software instructions that, when executed, are configured to cause the at least one processor to: utilize an occupancy prediction machine learning model to predict the occupancy schedule based at least in part on the occupancy metric associated with the zone in each time slot, in, The occupancy prediction machine learning model includes a trained prediction layer including parameters trained to generate the occupancy schedule based on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy schedule prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

23. The non-transitory computer-readable medium of any one of claims 21 to 22, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: Splitting the time series data into multiple time windows; and Each time window of the plurality of time windows is assigned to a specific time slot of the plurality of time slots.

24. The non-transitory computer-readable medium of any one of claims 21 to 23, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: determining a presence in each of the plurality of time slots; generating an occupancy metric associated with the presence in each time slot; and The occupancy metric in each time slot is determined based at least in part on the occupancy metric in each time slot.

25. The non-transitory computer readable medium of claim 24, wherein: The amount present includes at least one of the following: The frequency of presence in each time slot, or The duration of existence in each time slot.

26. The non-transitory computer-readable medium of any one of claims 21 to 24, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: accessing a plurality of previous occupancy metrics associated with at least one previous week; aligning a plurality of previous time slots of the at least one previous week with the plurality of time slots of the week; The occupancy metric in each time slot is generated based at least in part on the plurality of previous occupancy metrics associated with the at least one previous week and the occupancy metric for each time slot.

27. The non-transitory computer-readable medium of any one of claims 21 to 26, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: The occupancy metric in each time slot is generated based at least in part on a decay rate applied to each previous occupancy metric for each time slot and an aggregation of each occupancy metric for each time slot.

28. The non-transitory computer-readable medium of any one of claims 21 to 27, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: utilizing the occupancy metric associated with the region in each time slot as a predicted occupancy state of the region; and The occupancy schedule for the area is generated based at least in part on the predicted occupancy state.

29. The non-transitory computer-readable medium of any one of claims 21 to 28, wherein: The at least one presence sensing device comprises at least one of: security cameras, Infrared presence detector, Door sensor, Window sensor, Smart light switches, Wi-Fi router, Radio Frequency Identification (RFID) readers, Smart lock, Vibration sensing, pressure sensing, ultrasound, LiDAR, radar, or Local set point adjustment.

30. The non-transitory computer-readable medium of any one of claims 21 to 29, further comprising software instructions that, when executed, are configured to cause the at least one processor to perform the following steps: Utilizing the occupancy state prediction machine learning model, a predicted occupancy state associated with each time slot is predicted based at least in part on: a regression layer comprising a plurality of learned regression weights trained to relate the occupancy metric to an occupancy state prediction based on a history of the occupancy metric, and The occupancy metric associated with the area in each time slot.

Images