System and method for detecting occupancy using radio signals

Abstract

A sensor system for determining occupancy in a space generally includes: a transmitter wireless device that transmits radio signals through a channel in the space; a receiver wireless device that receives the transmitted radio signals that have propagated through the space; and at least one processor that implements an occupancy-centric algorithm that determines occupancy in the space based on the radio signals. The at least one processor performs the following operations: determining channel state information based on the radio signals transmitted through the channel; determining occupancy in the space based on the channel state information; and outputting an occupancy signal based on the determined occupancy.

Description

[0001] Cross-referencing related applications

[0002] This application claims the benefit of U.S. Provisional Application No. 62 / 871,235, filed July 8, 2019, the entire disclosure of which is incorporated herein by reference. Technical Field

[0003] This disclosure relates to sensing and monitoring, and more specifically, to sensing and monitoring occupancy of certain spaces and areas. This disclosure also relates to sensing and monitoring movement or changes in the environment, including the movement of animals and objects. This disclosure further relates to using sensor and / or monitor information to control certain systems within commercial and residential facilities, including but not limited to: heating, cooling, ventilation, security, lighting, electrical, and entertainment systems. This disclosure can also be used to determine occupancy in outdoor spaces and control certain outdoor systems, including but not limited to: heating, cooling, ventilation, security, lighting, electrical, and entertainment systems. Background Technology

[0004] Heating, ventilation, and cooling (HVAC) systems within buildings account for a significant portion of total energy consumption. It is estimated that in the United States, HVAC systems account for approximately 13% of current total energy consumption in buildings. Because these systems are very energy-intensive, significant energy savings could be achieved by improving their efficiency. One reason for inefficiency is that HVAC systems often operate at maximum capacity or at a capacity optimized for fully occupied buildings, even when the building or its interior space is unoccupied or underutilized (not fully occupied). Therefore, energy savings can be achieved if sensors and / or monitors exist that can detect whether a building or space is occupied or underutilized, and these sensors and / or monitors adjust the HVAC system to the appropriate levels for unoccupied or underutilized conditions. For example, heating and cooling can be reduced when the building is unoccupied. Adjusting temperature levels to lower levels when outdoor temperatures are low and to higher levels when outdoor temperatures are high is sometimes referred to as enabling temperature callback.

[0005] Various types of sensors have been developed to detect occupancy in buildings or parts of buildings, including carbon dioxide (CO2) sensors, passive infrared (PIR) sensors, motion sensors, ultrasonic and / or sound sensors, image / video sensors, and electronic device sensors. While these types of sensors offer many advantages, they are not optimal as standalone solutions due to inaccurate performance, high deployment and / or maintenance costs, the requirement for occupants to wear or carry mobile phones / tags / beacons, complex user interfaces, and privacy concerns. Therefore, a new type of sensor system is needed that is low-cost, requires minimal maintenance, is easy to install and set up, does not require occupants to carry mobile phones, beacons, or RF tags / IDs, and does not collect any personally identifiable information. Summary of the Invention

[0006] In one embodiment, a sensor system for determining occupancy in a space includes: a transmitter wireless device that transmits a radio signal through a channel in the space; a receiver wireless device that receives the transmitted radio signal that has propagated through the space; and at least one processor that implements an occupancy-centric algorithm that determines occupancy in the space based on the radio signal. In another embodiment, the at least one processor performs the following operations: determining channel state information based on the radio signal transmitted through the channel; determining occupancy in the space based on the channel state information; and outputting an occupancy signal based on the determined occupancy.

[0007] In one embodiment, the at least one processor is integrated with the receiver radio device.

[0008] In one embodiment, the at least one processor is integrated with the transmitter radio device.

[0009] In one embodiment, the system includes a computing device, with the at least one processor integrated therein. In another embodiment, the at least one processor outputs control signals to a control system. In yet another embodiment, the control system is associated with a heating, ventilation, and cooling system for the space.

[0010] In one embodiment, the control system is associated with the space's security system. In another embodiment, the control system is associated with the space's lighting system. In yet another embodiment, the control system is associated with the space's electrical system. Finally, the control system is associated with the space's entertainment system.

[0011] In one embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing amplitude information associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the amplitude information. In another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the standard deviation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the standard deviation of the amplitude and phase signals. In another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the time and frequency correlation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the time and frequency correlation of the amplitude and phase signals. In yet another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the average value of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the average value of the amplitude and phase signals. In an embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the energy in the peak values ​​of the CSI amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the energy in the peak values ​​of the CSI amplitude and phase signals.

[0012] In an embodiment, the occupancy-centric algorithm is configured to determine the occupancy status in the space based on changes in one or more of the following: signal amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, and energy expansion variation of the radio signal.

[0013] In one embodiment, a method for determining occupancy in a space includes: transmitting a radio signal through a channel in the space; receiving the transmitted radio signal that has been propagated through the space; implementing an occupancy-centric algorithm using at least one processor, the processor determining occupancy in the space based on the radio signal; determining channel state information based on the radio signal transmitted through the channel; determining occupancy in the space based on the channel state information; and outputting an occupancy signal based on the determined occupancy.

[0014] In one embodiment, the at least one processor is integrated with the receiver radio device, which receives the transmitted radio signals that have been propagated through the space. In another embodiment, the at least one processor is integrated with the transmitter radio device that transmits radio signals through the channel in the space.

[0015] In one embodiment, the method includes outputting control signals to a control system using the at least one processor, wherein the control system is associated with a heating, ventilation, and cooling system of the space. In another embodiment, the method includes outputting control signals to a control system using the at least one processor, wherein the control system is associated with a security system of the space. In another embodiment, the method includes outputting control signals to a control system using the at least one processor, wherein the control system is associated with a lighting system of the space. In another embodiment, the method includes outputting control signals to a control system using the at least one processor, wherein the control system is associated with a power system of the space. In yet another embodiment, the method includes outputting control signals to a control system using the at least one processor, wherein the control system is associated with an entertainment system of the space.

[0016] In one embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing amplitude information associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the amplitude information. In another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the standard deviation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the standard deviation of the amplitude and phase signals. In another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the time and frequency correlation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the time and frequency correlation of the amplitude and phase signals. In yet another embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the average value of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based on the average value of the amplitude and phase signals. In an embodiment, the radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing the energy in the peak values ​​of the CSI amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based on the energy in the peak values ​​of the CSI amplitude and phase signals. In an embodiment, the occupancy-centric algorithm is configured to determine the occupancy in the space based on changes in one or more of the following: signal amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, and energy expansion variation of the radio signal.

[0017] In one embodiment, a sensor system for determining occupancy in a space includes: a transmitter wireless device that transmits a radio signal through a channel in the space; a receiver wireless device that receives the transmitted radio signal that has propagated through the space; and at least one processor that implements an occupancy-centric algorithm that determines occupancy in the space based on the radio signal, the at least one processor performing the following operations: determining channel state information based on the radio signal transmitted through the channel; determining occupancy in the space based on the channel state information; determining a value chain recommendation based on the occupancy in the space of a value chain network; and outputting an occupancy signal based on the determined occupancy and the value chain recommendation.

[0018] In one embodiment, the value chain recommendation involves the health status of one or more workers. In another embodiment, the value chain recommendation involves allocating or reallocating worker resources based on the occupancy status of the space. In yet another embodiment, the value chain recommendation is based on the productivity of workers in the space.

[0019] In an embodiment, the value chain recommendation is associated with the activation or deactivation of at least one of the following: a heating system, a ventilation system, a cooling system, a security system, a lighting system, a kitchen system, a speaker system, a power system, and an entertainment system for the space.

[0020] In one embodiment, the occupancy-centric algorithm evolution causes the value chain recommendation to be redefined based on the evolution of the occupancy-centric algorithm. In another embodiment, the value chain recommendation is determined by a machine learning system that trains machine learning models, which output logistics design recommendations based on training datasets, each training dataset defining one or more features of a corresponding logistics system and results associated with that system. In yet another embodiment, the value chain recommendation is determined by an artificial intelligence system that receives requests for logistics system design recommendations and determines those recommendations based on one or more machine learning models and the requests. In yet another embodiment, the value chain recommendation is determined by a digital twin system that generates an environmental digital twin of the logistics environment combined with the logistics system design recommendations, as well as one or more physical asset digital twins, and performs simulations based on the environmental digital twin and the physical asset digital twins. In yet another embodiment, the value chain recommendation is based on logistics factors, which include one or more of the following: product type corresponding to the proposed logistics solution, one or more features of the product type, location of manufacturing sites, location of distribution agencies, location of warehouses, location of customer groups, proposed expansion areas of the organization, and supply chain characteristics. In this embodiment, the value chain recommendation is based on logistics value chain network entities, which are selected from the group consisting of: products, suppliers, manufacturers, producers, retailers, enterprises, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, dealers, supply chain infrastructure, supply chain processes, logistics processes, reverse logistics processes, demand forecasting processes, demand management processes, demand aggregation processes, machines, ships, barges, warehouses, seaports, airports, waterways, waterways, highways, railways, bridges, tunnels, online retailers, e-commerce sites, demand factors, supply factors, transportation systems, current assets, place of origin, destination, storage point, point of use, network, information technology system, software platform, distribution center, operations center, containers, container handling equipment, customs, export control, border control, drones, robots, autonomous vehicles, haulage facilities, drones / robots / AVs, waterway and port infrastructure.

[0021] In this embodiment, the supply chain infrastructure is a facility selected from the group consisting of: ships, container ships, vessels, barges, seaports, cranes, containers, container handling, shipyards, dry docks, warehouses, distribution, operations, refueling, refueling, nuclear fuel refueling, waste disposal, food supply, beverage supply, drones, robots, autonomous vehicles, aircraft, automobiles, trucks, trains, elevators, forklifts, haulage facilities, conveyors, loading docks, waterways, bridges, tunnels, airports, garages, stations, railway stations, weigh stations, inspections, roads, railways, highways, customs and border control facilities.

[0022] In this embodiment, the value chain recommendation is based on supply factors selected from the group consisting of: component availability, material availability, component location, material location, component pricing, material pricing, taxes, tariffs, import duties, taxes, import regulations, export regulations, border controls, trade regulations, customs, navigation, traffic, congestion, vehicle capacity, ship capacity, container capacity, parcel capacity, vehicle availability, ship availability, container availability, parcel availability, vehicle location, ship location, container location, port location, port availability, port capacity, storage availability, storage capacity, warehouse availability, warehouse capacity, operations center location, operations center availability, operations center capacity, asset owner identity, system compatibility, worker availability, worker skills, worker work location, commodity pricing, fuel pricing, energy pricing, route availability, route distance, route cost, and route safety factors.

[0023] In one embodiment, the value chain recommendation is determined based on a machine learning / artificial intelligence system, which determines the problem state based on detected levels of human stress in the supply chain. In another embodiment, the value chain recommendation is determined based on disruptions in the space of the value chain network. In yet another embodiment, the value chain recommendation includes operational recommendations needed to compensate for changes in operating parameters. In yet another embodiment, the value chain recommendation is determined based on physical activity data and worker data to improve value chain workflows. In yet another embodiment, the value chain recommendation includes suggestions for eliminating or limiting worker redundancy in the workflow.

[0024] In one embodiment, a method for determining occupancy in a space includes: transmitting a radio signal through a channel in the space; receiving the transmitted radio signal that has been propagated through the space; and implementing an occupancy-centric algorithm using at least one processor, the occupancy-centric algorithm being configured to: determine occupancy in the space based on the radio signal; determine channel state information based on the radio signal transmitted through the channel; determine occupancy in the space based on the channel state information; determine a value chain recommendation based on the occupancy in the space of a value chain network; and output an occupancy signal based on the determined occupancy and the value chain recommendation.

[0025] In one embodiment, the value chain recommendation involves the health status of one or more workers. In another embodiment, the value chain recommendation involves allocating or reallocating worker resources based on the occupancy status of the space. In yet another embodiment, the value chain recommendation is based on the productivity of workers in the space. In still another embodiment, the value chain recommendation is associated with the activation or deactivation of at least one of the following systems used in the space: heating, ventilation, cooling, security, lighting, kitchen, loudspeaker, electrical, and entertainment systems.

[0026] In one embodiment, the occupancy-centric algorithm evolution causes the value chain recommendation to be redefined based on the evolution of the occupancy-centric algorithm. In another embodiment, the value chain recommendation is determined by a machine learning system that trains machine learning models, which output logistics design recommendations based on training datasets, each training dataset defining one or more features of a corresponding logistics system and results related to that corresponding logistics system. In yet another embodiment, the value chain recommendation is determined by an artificial intelligence system that receives requests for logistics system design recommendations and determines the logistics system design recommendations based on one or more machine learning models and the requests.

[0027] In this embodiment, the value chain recommendation is determined by a digital twin system, which generates an environmental digital twin of the logistics environment that combines the logistics system design recommendation with one or more physical asset digital twins, and performs simulation based on the logistics environment digital twin and the one or more physical asset digital twins.

[0028] In an embodiment, the value chain recommendation is based on logistic factors, which include one or more of the following: product type corresponding to the proposed logistic solution, one or more characteristics of the product type, location of manufacturing location, location of distribution agency, location of warehouse, location of customer base, proposed expansion area of ​​the organization, and supply chain characteristics.

[0029] In this embodiment, the value chain recommendation is based on logistics value chain network entities, which are selected from the group consisting of: products, suppliers, manufacturers, producers, retailers, enterprises, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, dealers, supply chain infrastructure, supply chain processes, logistics processes, reverse logistics processes, demand forecasting processes, demand management processes, demand aggregation processes, machines, ships, barges, warehouses, seaports, airports, waterways, waterways, highways, railways, bridges, tunnels, online retailers, e-commerce sites, demand factors, supply factors, transportation systems, current assets, place of origin, destination, storage point, point of use, network, information technology system, software platform, distribution center, operations center, containers, container handling equipment, customs, export control, border control, drones, robots, autonomous vehicles, haulage facilities, drones / robots / AVs, waterway and port infrastructure.

[0030] In this embodiment, the supply chain infrastructure is a facility selected from the group consisting of: ships, container ships, vessels, barges, seaports, cranes, containers, container handling, shipyards, dry docks, warehouses, distribution, operations, refueling, refueling, nuclear fuel refueling, waste disposal, food supply, beverage supply, drones, robots, autonomous vehicles, aircraft, automobiles, trucks, trains, elevators, forklifts, haulage facilities, conveyors, loading docks, waterways, bridges, tunnels, airports, garages, stations, railway stations, weigh stations, inspections, roads, railways, highways, customs and border control facilities.

[0031] In this embodiment, the value chain recommendation is based on supply factors selected from the group consisting of: component availability, material availability, component location, material location, component pricing, material pricing, taxes, tariffs, import duties, taxes, import regulations, export regulations, border controls, trade regulations, customs, navigation, traffic, congestion, vehicle capacity, ship capacity, container capacity, parcel capacity, vehicle availability, ship availability, container availability, parcel availability, vehicle location, ship location, container location, port location, port availability, port capacity, storage availability, storage capacity, warehouse availability, warehouse capacity, operations center location, operations center availability, operations center capacity, asset owner identity, system compatibility, worker availability, worker skills, worker work location, commodity pricing, fuel pricing, energy pricing, route availability, route distance, route cost, and route safety factors.

[0032] In one embodiment, the value chain recommendation is determined based on a machine learning / artificial intelligence system, which determines the problem state based on detected levels of human stress in the supply chain. In another embodiment, the value chain recommendation is determined based on disruptions in the space of the value chain network. In yet another embodiment, the value chain recommendation includes operational recommendations needed to compensate for changes in operating parameters. In yet another embodiment, the value chain recommendation is determined based on physical activity data and worker data to improve value chain workflows.

[0033] In one embodiment, the value chain recommendations include suggestions for eliminating or limiting worker redundancy in the workflow.

[0034] Other applicable areas of this disclosure will become apparent from the detailed description provided below. It should be understood that the detailed description and specific examples are for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description

[0035] This disclosure will be more fully understood from the specific embodiments and accompanying drawings, wherein:

[0036] Figure 1A and Figure 1B Schematic diagrams of exemplary sensor systems deployed in unmanned and manned spaces are shown, respectively, according to various implementation methods.

[0037] Figure 2 It shows that it includes Figure 1A and Figure 1B A functional block diagram of a wireless device in an exemplary sensor system is shown.

[0038] Figure 3 A flowchart illustrating exemplary techniques for sensing occupancy in space provided by some implementations of this disclosure is shown. Detailed Implementation

[0039] This invention relates to a novel occupancy sensor that analyzes radio signals to determine occupancy in a space or building. In this disclosure, the terms "space," "area," "nearby," and / or "place" can refer to the internal or external space, area, vicinity, place, etc., of a room, suite, apartment, residence, building, structure, dwelling, and similar geographical location. The occupancy sensor of this disclosure can be used as a standalone sensor and / or a collaborative sensor, and can integrate signals provided by previously developed or yet-to-be-developed sensors and sensor systems. In this disclosure, such sensors and sensor systems may be referred to as other sensors and / or other sensor systems.

[0040] The technology disclosed herein utilizes electronic devices capable of transmitting and receiving radio signals. These devices may be referred to as wireless devices, wireless equipment, access points, routers, hubs, hotspots, transceivers, antennas, etc. These devices can be integrated into other electronic devices, such as access points, routers, modems, mobile phones, computers, tablets, watches, speakers, thermostats, appliances, lighting equipment, e-readers, furniture, vehicles, cameras, GPS devices, drones, and / or personal assistants (e.g., Google Home). TM Amazon Echo TM Apple HomePod TM These devices can use WiFi and Bluetooth. TM Zig Bee TM This disclosure can communicate with other devices using standardized signaling protocols such as 5G, Ultra Wideband (UWB), and any IEEE standards (including but not limited to IEEE 802.11, IEEE 802.15.1, IEEE 802.15.3, IEEE 802.15.4, IEEE 802.16, IEEE IMT-Advanced / 3GPP, Long Term Evolution (LTE), and Near Field Communication (NFC). Additionally or alternatively, these devices may communicate using custom and / or proprietary signaling protocols. It should be understood that this disclosure can include any type of radio, radio card, and / or radio device capable of transmitting and receiving signals in the radio frequency or RF region of the electromagnetic spectrum. It should also be understood that this disclosure can include any device that comprises, includes, is embedded in, and / or is attached to a radio device.

[0041] The wireless device disclosed herein may include one or more antennas for transmitting signals, one or more antennas for receiving signals, and / or one or more antennas for both transmitting and receiving signals. In some embodiments, the antennas may be electronically or manually connected to and disconnected from circuitry in the wireless device, and / or connected to any other electronic circuitry of the wireless device. The wireless device may have one or more antennas. The antennas may be omnidirectional, nearly omnidirectional, multidirectional, or unidirectional or nearly unidirectional. Multiple antennas may be driven in a coordinated manner to guide radio signals in a predetermined direction. The propagation direction of the radio signals may be altered and / or tuned. In embodiments, radio signals transmitted by a single device but by different antennas may experience different radio environments.

[0042] The radio frequency range of the signals transmitted and received by these antennas can be single-frequency or multi-frequency, narrowband or wideband, single-channel or multi-channel, static or tunable. Radio signals may include subcarriers and / or subcarrier groups and / or subchannels. Radio signals may be frequency-multiplexed radio signals. The radio signals used in this disclosure may be frequency-hopping radio signals, which are capable of carrying multiple signals on different RF channels (carrier frequencies).

[0043] The signals generated and received via the antenna can be amplitude-modulated, frequency-modulated, phase-modulated, pulse-width modulated, polarization-modulated signals, and / or generated using any combination of modulation schemes. In embodiments, any suitable modulation format can be used, including but not limited to analog modulation, digital modulation, amplitude modulation (AM) and its variations, frequency modulation (FM) and its variations, phase modulation (PM) and its variations, polarization modulation and its variations, double-sideband modulation (DSB) and its variations, single-sideband modulation (SSB) and its variations, quadrature amplitude modulation (QAM) and its variations, orthogonal frequency division multiplexing (OFDM) and its variations, spread spectrum and its variations, and code division multiplexing and its variations.

[0044] refer to Figure 1A and Figure 1B Exemplary sensor systems 100 provided in some implementations of this disclosure may include at least two wireless devices 110 capable of transmitting and / or receiving signals arranged within space 105. Transmitter wireless device 110-1 may transmit radio signals to receiver wireless device 110-2. Receiver wireless device 110-2 may receive and process the transmitted radio signals. Although the wireless devices 110 are described as “transmitter” wireless device 110-1 and “receiver” wireless device 110-2, it should be understood that transmitter wireless device 110-1 may also have the capability to receive radio signals, and receiver wireless device 110-2 may also have the capability to transmit radio signals. For ease of description, this disclosure will describe the transmission of radio signals from transmitter wireless device 110-1 to be received at receiver wireless device 110-2; however, it should be understood that in some implementations, each wireless device 110 may both transmit and receive radio signals. In embodiments, the wireless devices 110 need not be of the same type. For example, wireless device 110-1 may be a computer, and wireless device 110-2 may be an access point. Each radio device 110 can be any radio device described in this disclosure. In some embodiments, at least two radio devices 110 can be similar devices or copies of each other.

[0045] For further reference Figure 2A functional block diagram of an exemplary wireless device 110 is shown. Wireless device 110 may represent a configuration of transmitter wireless device 110-1 and receiver wireless device 110-2. It should be understood that one or both of transmitter wireless device 110-1 and receiver wireless device 110-2 may differ from the illustrated wireless device 110. Wireless device 110 may include communication device 111 (e.g., a wireless transceiver) configured to communicate with other wireless devices 110 or other communication devices, for example, via network 200. Processor 113 may be configured to control the operation of wireless device 110. The term "processor" as used herein may refer to a single processor or two or more processors operating in a parallel or distributed architecture.

[0046] Memory 115 may be included and may take the form of any suitable storage medium (flash memory, hard disk, etc.) configured to store information at the radio device 110. In one implementation, memory 115 may store instructions executable by processor 113 to cause radio device 110 to perform at least a portion of the disclosed techniques. Any or all of the processing and storage functions of the radio device may be executed remotely on nearby hardware, or on captured hardware, or on shared hardware components and various cloud network facilities. Radio device 110 may also include input device 117 and output device 119. Input device 117 may be any hardware device configured to accept input to radio device 110. In some examples, input device 117 may receive at least one input signal from a button, dashboard, knob, or display operated by a user or occupant, indicating that someone is present in or leaving space 105 or indicating other information that can be entered into the system. Through these examples, input device 117 can receive at least one or more signals from a communication device, the signals containing user or occupant information indicating whether space 105 is currently occupied or recently occupied, or indicating a period of time when space 105 is occupied or unoccupied. Similarly, output device 119 can be any hardware device configured to provide output from wireless device 110. In embodiments, output device 119 can light up, emit sounds, send communication signals to at least one other electronic device, etc. Output device can include a display and user interface, which can be configured to prompt for input signals from the user or occupant of space 105. Although not shown, it should be understood that wireless device 110 can include other suitable components, such as a display (touch display), physical buttons, a camera, etc. As further described below, exemplary sensor system 100 can be configured to perform various techniques for sensing occupancy in space 105 using radio signals.

[0047] When different portions of the transmitted signal propagate from the transmitter to the receiver, they can travel along different spatial paths, such as the first path 120-1, the second path 120-2, and the third path 120-3 (each individually or collectively referred to as "path 120"). By way of example only, a portion of the transmitted radio signal can propagate along the shortest path from the transmitter radio device 110-1 to the receiver radio device 110-2 (the first path 120-1). This first path 120-1 can be referred to as the "line-of-sight" (LOS) path. Other portions of the transmitted radio signal can propagate through space 105 along different paths 120-2, 120-3. It should be understood that, although... Figure 1A and Figure 1B Three exemplary paths 120 are shown (first path 120-1, second path 120-2, and third path 120-3), but fewer or more paths 120 may exist, including paths 120 arranged in a “continuous frequency band”.

[0048] As the transmitted radio signal propagates from transmitter radio device 110-1 to receiver radio device 110-2, objects 140 in space 105 (walls, windows, doors and furniture, people, pets, etc.) may reflect and / or scatter and / or diffract and / or attenuate the transmitted radio signal. Different portions of the transmitted radio signal propagating along different spatial paths 120 may be attenuated and phase-shifted or time-shifted relative to other portions of the signal. Furthermore, if objects 140 move, a person breathes, has a heartbeat, or there is some other change near or along spatial path 120, different portions of the transmitted radio signal propagating along different spatial paths 120 may be attenuated and phase-shifted or time-shifted to varying degrees. At least some portions of the transmitted radio signal can be received and processed at receiver radio device 110-2. The received signal can be analyzed to determine information related to the environment (space 105) through which the radio signal travels. In this disclosure, the analysis of received radio signals to determine information related to the environment in which the radio signals have traveled can be termed environmental signal extraction (“ESE”).

[0049] The transmitted and received radio signals can be represented as functions x(t) and y(t), respectively. In some respects, the received signal y(t) can be mathematically modeled as y(t) = h(t) * x(t) + n(t), where n(t) is the noise term and h(t) is the channel response (CIR). In this example, the received radio signal y(t) propagates through space 105, and by analyzing the channel response (h(t)), information about space 105 can be determined. Such information may include, for example, whether something is moving in space 105; whether something exists in space 105; whether there is breathing in space 105 and the breathing rate; and / or whether something with a heartbeat exists in space 105 and the heartbeat rate.

[0050] Many techniques for detecting space 105 using radio signals (radar, detection, inspection, Doppler, etc.) can be used to generate a channel response that can be analyzed to detect changes in space 105. By way of example only, the channel response can be embedded in the amplitude and / or phase and / or timing of the received signal. Additionally or alternatively, the channel response can be a channel impulse response (CIR), channel frequency response (CFR), channel state information (CSI), received signal strength indication (RSSI), or any other type of channel response. Any suitable technique for extracting channel information from radio signals can be used in the sensor system 100 described herein. For ease of description, the term CSI may be used herein to refer generally to information relating to the environment or space 105 that can be extracted from the received radio signals.

[0051] As described herein, transmitter radio device 110-1 can transmit radio signals to receiver radio device 110-2, which in turn receives the transmitted signals. In some implementations, as described above, receiver radio device 110-2 can then transmit the second radio signal to transmitter radio device 110-1, which has received the second radio signal. When each of the first and second radio signals “passes through the environment of space 105,” objects 140 in space 105 (walls, windows, doors and furniture, people, pets, etc.) can reflect and / or scatter and / or diffract and / or attenuate the radio signal. The environment through which the radio signal passes may change as objects 140 and / or organisms in the environment are present and / or move in a particular or detectable manner. Different portions of the transmitted signal may be attenuated and phase-shifted or time-shifted relative to other portions of the signal, and at least some portions of the transmitted signal can be received and processed. The received signal can be analyzed at the transmitter radio device 110-1, the receiver radio device 110-2, or both the transmitter radio device 110-1 and the receiver radio device 110-2 to determine information related to the environment (space 105) in which the radio signal has traveled.

[0052] It should be understood that, according to this disclosure, the transmitted radio signals can experience an environment in which at least one person is present, moving, and / or breathing and / or having a heartbeat. As stated above, radio signals can be reflected and / or scattered and / or diffracted and / or attenuated to varying degrees when an object 140 (e.g., a person) is in one position rather than another, and / or when a person's chest expands or contracts to inhale or exhale, and / or when veins and / or arteries and / or skin contact move up and down (or in and out) with a person's heartbeat. A person in a sleeping and / or sitting position may still alter the environment in which the radio signals experience compared to radio signals experienced when no one is in the environment. A person in a sleeping and / or sitting position may also alter the environment in which the radio signals experience because their chest cavity moves in and out with each breath, which may affect the amplitude and / or phase and / or timing of radio signals propagating from one radio device to another. Additionally or alternatively, a person in a sleeping and / or sitting position may still alter the environment in which radio signals are experienced, because a part of their body pulsates with their heart rate, and these subtle movements may affect the amplitude and / or phase and / or timing of radio signals propagating from one radio device to another. A person may be completely immobile, move normally, move frequently, and / or move abnormally, which may alter the environment in which radio signals are experienced, as a person's movement may affect the amplitude and / or phase and / or timing of radio signals propagating from one radio device to another.

[0053] As radio signals propagate through space 105, they may encounter an environment in which at least one person is moving. Sensor system 100 can determine occupancy and at least one other parameter based on detected movement, such as based on transmitted and received radio signals. By way of example only, when sensor system 100 determines that a person is breathing in a place but little or no other movement is detected, sensor system 100 can determine that a person is present and that person is not moving. In a further example, sensor system 100 can associate a period of little or no movement with a person being asleep. Additionally or alternatively, sensor system 100 can associate a person's rapid movement after a period of little or no movement with a person falling and / or being injured. The signal collection, extraction, processing, etc., in this disclosure can provide information beyond human occupancy. Sensor system 100 can be used to monitor human movement, breathing, heartbeat, and to infer and / or predict and / or generate output signals indicating a person's state, health status, changes in a person's state or health status, and other characteristics of people or other objects 140 in space 105.

[0054] In some respects, sensor system 100 can individually identify and sense different individuals in space 150. By way of example only, individuals may have different respiratory rates and / or different heart rates, and these can be distinguished by sensor system 100. In a further example, different individuals may influence radio signals differently and may have radio signatures that can be identified by sensor system 100. By way of example only, some individuals may influence the amplitude and / or phase and / or timing of radio signals in a manner that can be identified by any occupancy-centric algorithm running in sensor system 100.

[0055] In some implementations, a person in a radio environment may make gestures in specific ways that can be recognized by sensor system 100. A person may raise and lower their hand, turn their thumb up to their thumb down, feign a tremor, fan themselves, or make other gestures, which sensor system 100 can then detect and recognize. The detected gestures may be included as features in an algorithm that determines whether a control system (e.g., an HVAC system) in space 105 should be adjusted. For example, a person in space 105 may make a fanning gesture, and sensor system 100 may recognize this gesture and send an output signal to a thermostat or air conditioning / refrigeration unit to lower the temperature in space 105. It should be understood that various gestures can be detected and used to initiate steps that can be taken to control, adjust, and / or alter heating, cooling, ventilation, security, lighting, electrical, entertainment, and other systems in or associated with space 105.

[0056] In some implementations, space 105 may include a plurality of transmitter radio devices 110-1 and / or a plurality of receiver radio devices 110-2. By way of example only, two or more transmitter radio devices 110-1 may transmit radio signals to at least one receiver radio device 110-2. In a further example, two or more receiver radio devices 110-2 may receive radio signals from at least one of the transmitter radio devices 110-1. In yet another example, in a particular implementation, there may be two or more radio devices 110 capable of transmitting and receiving radio signals, and any of these devices 110 may transmit and receive signals to and from any other device 110 within the range of the radio signals. In such implementations, radio signals propagating between any transmitter radio device 110-1 and any receiver radio device 110-2 in one or both directions may be reflected and / or scattered and / or diffracted and / or attenuated by walls, windows, doors and furniture, other stationary objects, people and pets, and other moving objects. Different portions of the transmitted signal may be attenuated and delayed relative to other portions of the signal, and at least some portions of the transmitted signal may be received and processed by at least one receiver radio device 110-2. The received signal may be analyzed at any one, some, or all of the radio devices 110, or even remotely (e.g., at a centralized computing device or a remote computing device accessible via a network) to determine information relating to the environment in which the radio signal has experienced. In some embodiments, the environment in which the radio signal has experienced may change as objects and / or living organisms move in space 105 and / or in a particular or detectable manner.

[0057] Radio device 110 can also receive radio signals directed at other devices, a practice known as "sniffing" communications between other radio devices. Radio device 110 can analyze such "sniffed" signals to determine information related to the environment in which these radio signals have been observed. Similar to radio signals directed at radio device 110, the environment in which "sniffed" radio signals have been observed may change as objects 140 and / or organisms move in the environment and / or in a specific or detectable manner.

[0058] Additionally or alternatively, radio device 110 may "check" one or more other radio devices 110 to initiate the transmission of data packets or data streams from the checked radio device 110. Checking may be periodic or aperiodic, and the timing of the checking may be a manually, automatically, and / or software-controlled settable parameter. In some implementations, the settable parameter may be selected and / or changed by an occupancy-centric algorithm or other algorithm running in sensor system 100.

[0059] By way of example only, at least one radio device 110 may authenticate at least one other radio device 110 at least 10 times per second, at least 10 times per minute, at least 10 times per hour, at least 10 times per day, at least 10 times per week, and / or at least 10 times per month. Upon receiving an authentication request, one or more other radio devices 110 may send data packets and / or data streams back to the authenticating radio device 110. Upon receiving an authentication request, one or more other radio devices may initiate the transmission of data packets and / or sequences of radio signals back to the authenticating radio device 110. The data packets and / or sequences of radio signals may be transmitted over a relatively short or relatively long time period, or may continue until another authentication instruction should cease transmission from the authenticated device. The authenticating radio device 110 may analyze the transmitted one or more data packets and / or one or more data streams and determine parameters of the radio environment (e.g., space 105). The parameters of the radio environment may include, but are not limited to, the distance between radio devices 110, the transmission time of radio signals, the angle of arrival of radio signals, the standard deviation of amplitude and phase signals in CSI, the time and frequency correlation of amplitude and phase signals in CSI, the average value of amplitude and phase signals in CSI, the energy in the peak amplitude and phase of CSI, the presence of objects 140 in the radio environment (space 105), the presence of moving people, breathing people, people with beating hearts in the environment, the presence of moving animals, breathing animals, animals with beating hearts in the environment, the presence of moving objects 140 in the environment, and the presence of multiple people and / or animals in the environment.

[0060] Radio signals exchanged between transmitter radio equipment 110-1 and receiver radio equipment 110-2 can be detected and processed, and amplitude and / or phase information can be extracted from some, all, or any part of the detected and processed signals. Amplitude and / or phase information can be monitored and / or stored for a period of time. By way of example only, the stored information can be associated with a specific pair of transmitter radio equipment 110-1 and receiver radio equipment 110-2, a specific transmitter-receiver antenna pair, time or time period, a specific location or place, a specific date or date range, a specific temperature or temperature range, the interruption of a monitor or sensor signal, and / or the occupancy of at least one device or control system near the radio signal. The stored information can be associated with commands that can be received from remote devices, control devices, system input devices, etc. Changes in amplitude and / or phase and / or timing information derived from the radio signal can be associated with changes in the environment (space 105) through which the radio wave passes.

[0061] In some respects, additional processing of amplitude and / or phase information can be performed by firmware, software programs, algorithms, processors, code, scripts, etc., which can also perform additional processing on information provided as part of standardized, custom, or proprietary communication protocols. For occupancy sensing applications, this additional processing can be referred to as occupant processing, occupancy-centric processing, occupancy-finding processing, or similar processing, and can be performed based on occupant algorithms, occupancy-centric algorithms, or similar named algorithms. Such processing techniques and algorithms can utilize and analyze signals generated by commercial or other chipsets to determine whether variations in standard signals or information derived therefrom should be interpreted as the presence of one or more occupants in space 105.

[0062] Radio signals may include one or more carrier signals. In some protocols, multiple carriers may be referred to as subcarriers or subcarrier groups. In some implementations, any or all subcarriers or subcarrier groups may be received and processed as described herein, and the influence of the environment on these subcarrier signals or groups may vary. By way of example only, each subcarrier in a radio signal may have a different center frequency, and the environmental parameters affecting the propagation of the radio signal may be frequency-dependent. Additionally or alternatively, due to the presence of a person or object 140 in space 105, the amplitude and phase or timing variations and / or amplitude and phase or timing variations may be different. It should be understood that any, some, or all subcarrier signals or groups may be used to extract information about the environment (space 105) through which the radio signal experiences. In some implementations, the number of subcarriers or groups analyzed and the subcarriers or groups analyzed may be settable parameters that can be set manually, automatically, and / or under software control, for example, these parameters may be selected and / or changed by an occupancy-centric algorithm or other algorithm running in sensor system 100.

[0063] For further reference Figure 3The document illustrates a flowchart of an exemplary processing method 300. It should be understood that method 300 is merely an example, and in some implementations, this disclosure may not be limited to the exact method shown. Furthermore, the method steps, processes, and operations described herein should not be construed as requiring execution in the specific order shown or described, unless the execution order is explicitly stated. It should also be understood that additional or alternative steps may be employed, as determined processing steps may be reordered or omitted depending on the desired implementation. The determined processes may or may not be executed in a single chip or hardware component, and may or may not be executed using separate or different programs, algorithms, processors, code, and scripts. Additionally, method 300 may be executed by the disclosed sensor system 100, which may include a single radio device 110, multiple radio devices 110 operating in combination, or one or more radio devices 110 operating in combination with one or more other devices. However, for simplicity, even though a single radio device 110, multiple radio devices 110 operating in combination, or one or more radio devices 110 operating in combination with one or more other devices in the sensor system 100 can perform individual operations, this document will describe method 300 executed by the sensor system 100.

[0064] At 310, a radio signal can be transmitted, for example, by a transmitter radio device 110-1 or similar radio device 110 as described herein. For instance, the transmitted radio signal will propagate through the environment (space 105) and be received at 320 by a receiver radio device 110, such as a receiver radio device 110-2. The received radio signal may have traversed one or both of the surrounding environments near the radio device. The breadth or range or spatial dimension of the environment traversed by the radio signal can be determined by any one or any combination of the following: the transmitter power, the receiver sensitivity, the degree of attenuation of the radio signal in the environment, the signal-to-noise ratio of the received signal, the speed or data rate of the transmitted signal, the modulation format of the radio signal, the data rate of the radio signal, the composition and size of materials and objects 140 in the radio environment, the signaling protocol used, the frequency of the transmitted signal, the processing algorithm, and the parameters of the processing algorithm in the receiver, etc.

[0065] Radio devices 110 can communicate with each other using any suitable signaling protocol. In one aspect, radio devices 110 can communicate with each other using a WiFi signaling protocol. Additionally or alternatively, radio devices 110 can communicate with each other using standardized signaling protocols such as Bluetooth™, ZigBee™, 5G, Ultra Wideband (UWB), and any IEEE standard (including but not limited to IEEE 802.11, IEEE 802.15.1, IEEE 802.15.3, IEEE 802.15.4, IEEE 802.16, IEEE IMT-Advanced / 3GPP, Long Term Evolution (LTE), and / or Near Field Communication (NFC)). Furthermore, in some implementations, radio devices 110 can communicate with each other using proprietary and / or custom signaling protocols. In other aspects, the radio devices of this disclosure can communicate with each other using signaling protocols including data packets, frames, sequences, etc., that can be used by receiver radio device 110-2 to extract channel information from signals. The radio device 110 is capable of extracting signal amplitude, phase, and timing information by analyzing received data packets, frames, sequences, or other signal characteristics. In an embodiment, the information derived from the radio signal can be correlated with environmental changes experienced by the radio wave.

[0066] In other examples, radio devices 110 can communicate with each other using the WiFi signaling protocol, and receiver radio device 110-2 can generate channel information (sometimes called channel state information or "CSI"). In the WiFi protocol, CSI can be determined by analyzing "probe frames" in 802.11ac packets and can be used to characterize how occupants and objects 140 in space 105 reflect and scatter radio signals. In some aspects, CSI can be determined by analyzing the preamble of one or more WiFi packets. Alternatively or additionally, CSI can be determined based on packets and / or portions of packets. Furthermore, CSI can be determined based on the analysis of packet frames, long and / or short preambles or multiple preambles, applicable symbols of long training fields (LTFs) and / or multiple LTFs, and / or any type of training data, signal, frame, or other characteristics of the packets.

[0067] In some respects, signal processing can be performed on some or all of the determined CSI data. For example, noise in the CSI data can be eliminated or reduced. Techniques such as phase offset cancellation can be used to eliminate sampling time offset and / or sampling frequency offset and / or carrier frequency offset. Outliers can be eliminated using techniques such as moving averages, filtering, and zeroing.

[0068] The sensor system 100 of this disclosure can implement an occupancy-centric algorithm 250. In this disclosure, the term "occupancy-centric" refers to software, programs, code, documents, processing, and other data that have been developed and / or are being used to determine the occupancy of a person in a specific radio environment by analyzing radio signals that have experienced that environment. Although Figure 2 An occupancy-centric algorithm 250 is illustrated as part of or implemented within radio device 110; however, it should be understood that the occupancy-centric algorithm 250 may be implemented in multiple radio devices 110, in one or more radio devices 110 working in combination with one or more other devices, or in any other component of sensor system 100. In an embodiment, one radio device 110-1 may be an access point, and another radio device 110-2 may be a computer. The access point may authenticate the computer, and the computer may send a wireless signal to the access point in response to the authentication. The access point may process the received signals and input these signals into the occupancy-centric algorithm 250, which may be used to analyze the signals to determine whether one or more people are in space 105. In an embodiment, analyzing the signals may include searching for one or more features in the signals and, based on the presence or strength of one or more features, outputting a signal indicating the presence of one or more people or the absence of anyone in space 105. In an embodiment, the computer may send or broadcast wireless signals without receiving authentication, and the access point may analyze the signals as described herein. In embodiments, the roles of the access point and the computer can be reversed, allowing the computer to run the occupancy-centric algorithm 250 and generate signals or output signals indicating the presence of one or more people. In embodiments, the access point can run the occupancy-centric algorithm 250 and send signals to the computer, which can generate signals or output signals indicating the presence of people. In embodiments, the occupancy-centric algorithm 250 can run on a third device or on a third wireless device 110-3. In various embodiments, some or all of the wireless devices can have a processor 113, a memory 115, an input device 117, an output device 119, and some or all of the occupancy-centric algorithm 250. Through these examples, wireless devices 110-1 and 110-2 can be similar devices, devices of the same model, different devices, and devices with a primary purpose unrelated to occupancy detection but whose wireless communication capabilities and any other capabilities described herein can be used as part of a sensor system (alone or in combination).

[0069] Occupancy-centric algorithm 250 can analyze and / or process CSI data generated by commercial chipsets and / or commercial WiFi devices. Various modifications can be made to the radio device 110 to implement occupancy-centric algorithm 250. By way of example only: (i) commercial chipsets and / or commercial WiFi devices can operate using non-factory-installed firmware and / or drivers for implementing standardized communication protocols to support some or all portions of the occupancy-centric algorithm described in this disclosure; (ii) in some aspects, certain chips and / or circuits in the radio device may need to be re-flashed or loaded with non-original equipment manufacturer (OEM) factory-installed firmware, drivers, and / or software to support some or all portions of the occupancy-centric algorithm described in this disclosure; (iii) source code developed for implementing occupancy sensing data retrieval may need to be installed in the commercial radio device to implement sensor system 100; (iv) occupancy-centric binaries and / or occupancy-centric drivers. (iv) Preview files may need to be uploaded to some or all of the radio device 110; (vi) firmware, including but not limited to OpenWrt™ firmware, may need to be uploaded to some or all of the radio device 110; (vi) some or all of the memory of at least one updatable component in any radio device 110 may be rewritten using occupancy-centric code; (vii) Ubuntu may need to be running on at least one of the radio devices 110 and / or a version of Ubuntu that is not the latest version of Ubuntu may need to be running on at least one of the radio devices 110; and / or (viii) any, some or all of the radio devices 110 in the sensor system 100 may need to be rebooted before they can operate as described herein.

[0070] Typical commercially available WiFi devices do not automatically provide access to (“public”) CSI data for analysis by third-party machine code, firmware, software, and / or processing algorithms. In some respects, such CSI data can be made accessible by re-flashing updatable components and / or uploading new drivers and / or binaries developed for accessing and analyzing the determined CSI data. If such firmware, binaries, drivers, etc., are developed to enable the use of CSI information in sensor system 110, they can be characterized as occupancy-centric.

[0071] The various tasks associated with signal reception, analysis, processing, generation, manipulation, averaging, filtering, thresholding, etc., described throughout this disclosure can be implemented in machine code and / or firmware and / or using computer languages ​​(e.g., CTM, C++TM, PythonTM, etc.). By way of example only, information related to tasks such as signal reception, analysis, processing, generation, manipulation, averaging, filtering, thresholding, etc., can reside in memory 115, which can take the form of any or any combination of binary files, drivers, RAM, non-volatile RAM, EPROM, short-term memory, long-term memory, cache memory, and / or any type of known memory or information file.

[0072] In various implementations, an occupancy-centric algorithm 250 can extract ambient signals from radio signals, referred to herein as ambient signal extraction (“ESE”). The extracted ambient signals may include, but are not limited to, the amplitude, phase, timing, energy, and / or power of the radio signal. The extracted ambient signals may be related to the entire radio signal and / or a portion of the radio signal. As an example only, in a WiFi embodiment, ambient signals can be extracted from data packets and / or portions of data packets. In other aspects, ambient signals can be extracted based on the analysis of data packet frames, long and / or short preambles or multiple preambles, applicable symbols of a long training field (LTF), any type of training data for the radio signal, the signal, the frame, or any suitable one or more portions. Further examples include analyzing one, some, or all subcarrier signals; for example, the amplitude, phase, or both amplitude and phase of only one, some, or all subcarriers can be analyzed.

[0073] In various implementations of this disclosure, the occupancy-centric algorithm 250 can compare a CSI generated in one instance with another. The occupancy-centric algorithm 250 can compare: (i) a CSI generated from one data packet with a CSI generated from another data packet; (ii) a CSI generated from one transmitter / receiver pair with a CSI generated from another transmitter / receiver pair; (iii) a CSI generated from one transmitter / receiver antenna pair with a CSI generated from another transmitter / receiver antenna pair; (iv) a CSI generated from one or more subcarriers with a CSI generated from one or more other subcarriers; (v) a CSI generated from one transmitter / receiver pair with a stored CSI; and (vi) an unprocessed CSI generated from one transmitter / receiver pair with a processed CSI. (vii) A CSI generated at one location and a CSI generated at another location; (viii) A CSI generated once and a CSI stored in a buffer, file, database, short-term or long-term memory unit or any other storage device or medium (memory 115); (ix) A CSI generated between the first device and the second device and a CSI generated between the second device and the first device; (x) A CSI generated between the first device and the second device and a CSI generated between the second device and the third device; and / or (xi) A CSI generated between the first device and the second device and a CSI generated between any other two or more devices.

[0074] Occupancy-centered algorithm 250 can process some, most, or all of the generated CSI data. In some respects, occupancy-centered algorithm 250 can apply weights to different portions of the CSI data, such that certain portions of the data can have a relatively large or small impact on the results of occupancy-centered processing. Furthermore, occupancy-centered algorithm 250 can adjust the portions of CSI data analyzed, the weighted portions, and the weights. Occupancy-centered algorithm 250 can correlate any, some, or all of the variables described herein, or any, some, or all of the variations in the variables, with the occupancy status of people in space 105 (e.g., a room or residence).

[0075] In some implementations, the occupancy-centric algorithm 250 can average some, most, or all of the CSI data. Furthermore, the occupancy-centric algorithm 250 can process amplitude and phase data separately using the same, similar, or different processing steps and variables. By way of example only, the occupancy-centric algorithm 250 can calculate average phase, time, amplitude, energy, phase transition, time variation, amplitude variation, energy variation, phase spread, time spread, amplitude spread, energy spread, phase transition spread, time variation spread, amplitude spread variation, and energy spread variation. The occupancy-centric algorithm 250 can correlate any, some, or all of the variables or variations described herein with occupancy status in space 105 (e.g., a room or residence). By way of example only, the occupancy-centric algorithm 250 can correlate an increase in average phase signal and a decrease in average amplitude signal with the presence of a person. In a further example, the algorithm can correlate a phase value change calculated for subcarrier channel 33 with the presence of a person. The occupancy-centric algorithm 250 can be adjusted and modified under machine learning or artificial intelligence control. In an embodiment, the occupancy-centric algorithm 250 may be a machine learning algorithm configured to be deployed to analyze individual and / or combined signals across the spatial domain (different antennas), time domain, and frequency domain. In an embodiment, signal characteristics may include, but are not limited to, power, angle of arrival, direction of arrival, transmission time, time of arrival, transmission time difference, received signal strength, attenuation, signal-to-noise ratio, amplitude and phase of the subcarrier, and differences in amplitude and phase as functions of time, space (antenna), and frequency (compared between subcarriers). In an embodiment, the signal characteristics that can be analyzed may also include feature variations, including abrupt changes, which can be analyzed to find patterns or features that have been determined to indicate the presence of one or more people in environment 105. In an embodiment, the occupancy-centric algorithm 250 may identify certain features extracted from radio signals as further or particularly indicative of the presence of persons, and may assign weights to different features when determining whether persons are present in space 105.

[0076] In an embodiment, the occupancy-centric algorithm 250 can be adjusted and modified based on signals input to input device 117. The performance of system 100 can be improved through machine learning algorithms and / or weight variations assigned to certain features. Users and / or occupants can input occupancy information into input device 117 and can check the accuracy of the output of the occupancy-centric algorithm 250 against the input occupancy information. The occupancy-centric algorithm can be adjusted or modified to improve personnel detection accuracy and overall system performance. In an embodiment, other sensor information collected by system 100 can indicate the presence of one or more people in space 105, and the occupancy-centric algorithm 250 can determine that no one is present in space 105. Radio device 110 can use output device 119 to send signals to users and / or occupants and / or other sensors and / or other devices and / or networks, requesting additional information to be sent to the radio device via communication device 111 and / or input device 117. This additional information can be used to modify or adjust the occupancy-centric algorithm 250 to improve its performance.

[0077] In an embodiment, the wireless device 110 may use the output device 119 to send signals to the user and / or occupant and / or other sensors and / or other devices and / or networks on a scheduled, periodic, and on-demand basis, whenever the user interacts with the system, based on a threshold crossover or some internal performance metric. In an embodiment, the output device 119 may flash to indicate that the system requires user or occupant input. The user and / or occupant may approach the wireless device and see a question on the display screen, such as “Are you home at 10 a.m.?” The user and / or occupant may press a button to touch the screen to indicate whether the answer to the question is “yes,” “no,” or “unsure.” In a further example, the output device 119 may send a message containing a set of questions to one or more user and / or occupant cellular or email accounts. The user and / or occupant may provide information in the form of answers to these questions by sending messages or electronic communications to the wireless device’s communication device 111 and / or input device 117, and the wireless device may use this information to adjust and / or modify the occupancy-centric algorithm 205. In this embodiment, the wireless device can determine and store performance data, and will not modify the occupancy-centric algorithm until a certain amount of time has elapsed, a certain measurement has been performed, or a certain amount of information has been received.

[0078] The occupancy-centric algorithm 250 can also use data from other sensors in the sensor system 100 to determine occupancy. Examples of such other sensors may include carbon dioxide (CO2) sensors, passive infrared (PIR) sensors, ultrasonic and / or sound sensors, image / vision sensors, motion sensors, and electronic device sensors. In various aspects, the occupancy-centric algorithm 250 may collect information from smart home devices such as smart lights and smart doorbells, and / or from appliances such as displays, computers, mobile phones, smartphones, personal assistants, televisions, lights, refrigerators, coffee makers, water heaters, thermostats, air conditioners, game consoles, and washing machines, and use some, most, or all of this data to help determine the occupancy of space 105. The occupancy-centric algorithm 250 may use data manually entered, for example, via buttons, dashboards, knobs, keyboards, touchscreens, mice, capacitive sensors, or resistive sensors. Additionally or alternatively, the occupancy-centric algorithm 250 may use data entered via electronic interfaces, wireless interfaces, optical interfaces, computer interfaces, network interfaces, or any type of interface used to transmit data or signals between a person and a device or between a device and other devices.

[0079] The occupancy-centric algorithm 250 may include parameters that can be set manually, automatically, and / or under the control of another algorithm, processor, sensor, or other device. Such adjustable parameters may include, but are not limited to, the frequency of CSI data collection, the CSI data processed, the processing steps performed, and the data output from the algorithm, although other parameters are within the scope of this disclosure. In some implementations, the performance of the occupancy-centric algorithm 250 may be adjusted to meet certain performance metrics, such as minimizing or reducing energy consumption, minimizing or reducing required computational power / cycles, maximizing or improving sensitivity, maximizing or improving accuracy, etc. A wireless device running the occupancy-centric algorithm 250 may detect other devices in the sensor system 100 and may switch some or all processing and / or algorithmic tasks to such other devices. By way of example only, processes and / or tasks may be switched to other devices or assigned to multiple devices to extend the battery life of one or more devices, reduce the power consumption of one or more devices, and / or utilize a faster or more efficient processor.

[0080] In some exemplary implementations, a wireless device 110 using a WiFi signaling protocol can generate a so-called Received Signal Strength Indication (“RSSI”) signal. In the WiFi protocol, RSSI can be determined by analyzing 802.11 data packets and can be used to characterize how occupants and objects 140 in space 105 reflect and scatter radio signals. An occupancy-centric algorithm 250 can analyze RSSI data generated by commercial chipsets or commercial WiFi devices, and / or can analyze RSSI data that has been generated, processed, analyzed, and / or utilized by occupancy-centric machine code and / or firmware and / or drivers and / or binaries.

[0081] As an example only, the occupancy-centered algorithm 250 can compare: (i) an RSSI generated once with an RSSI generated in another; (ii) an RSSI generated at one location with an RSSI generated at another location; (iii) an RSSI generated once and / or from one or a group of data packets with an RSSI generated once and / or from another and / or another group of data packets; (iv) an RSSI generated once with an RSSI stored in a buffer, file, database, short-term or long-term memory unit or any other storage device or medium (memory 115); (v) an RSSI generated between a first device and a second device with an RSSI generated between a second device and a first device; (vi) an RSSI generated for one, some or all of the subcarriers or groups of a radio signal with an RSSI generated for one, some or all of the subcarriers or groups of a second radio signal.

[0082] Furthermore, the occupancy-centered algorithm 250 can process some, most, or all of the generated RSSI data. In some respects, the occupancy-centered algorithm 250 can apply weights to different portions of the RSSI data, such that certain portions of the data have a relatively large or small impact on the results of the occupancy-centered processing. The occupancy-centered algorithm 250 can also, or alternatively, adjust the portions of the analyzed RSSI data, the weighted portions, and the weights, and / or can correlate any, some, or all of the variables described herein, or any, some, or all of the variations in the variables, with the occupancy status of people in space 105.

[0083] Occupancy-centered algorithm 250 can average some, most, or all of the RSSI data in the RSSI data. Additionally or alternatively, occupancy-centered algorithm 250 can calculate average amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, and / or energy expansion variation. Additionally or alternatively, occupancy-centered algorithm 250 can calculate standard deviation or look for sudden changes in signal amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, and / or energy expansion variation. Any, some, or all of the variables described herein can be used by occupancy-centered algorithm 250 to determine occupancy in space 105. By way of example only, occupancy-centered algorithm 250 can correlate an increase in average energy signal and a decrease in energy expansion signal with the presence of a person. In a further example, occupancy-centered algorithm 250 can correlate an amplitude value change calculated for subcarrier channel 33 with the presence of a person. Occupancy-centered algorithm 250 can be adjusted based on a combination of machine learning, artificial intelligence, and user input.

[0084] In embodiments, the occupancy-centric algorithm 250 can determine occupancy using data from CSI data, RSSI data, or both CSI and RSSI data, or any combination of CSI and RSSI data determined for WiFi packets, frames, communications, etc. In some aspects, additional data determined by communication protocols can be analyzed and used to indicate the presence of people, moving objects 140, or animals in space 105. By way of example only, some communication protocols generate channel frequency response (“CFR”) data and / or channel impulse response (“CIR”) data, which can be used for CSI and / or RSSI data as described herein. Any combination of CFR, CIR, CSI, and RSSI data can be used by the occupancy-centric algorithm 250. Non-limiting examples include: (i) using only CFR data; (ii) using only RSSI data; and (iii) using some combination of CFR data with an ultrasound detector. It should be understood that any type or quantity of data that can be analyzed, processed, etc., to determine occupancy can be input into the occupancy-centric algorithm 250, and any combination of sensor data, other sensor data, user input, control data, and / or analysis data output can be used in the sensing system 100 described herein.

[0085] In an embodiment, the occupancy-centric algorithm 250 may use additional data obtainable from the radio signals exchanged between the analysis radio devices 110. Such data may include information relating to signal power, distance between transmitter radio device 110-1 and receiver radio device 110-2, transmission time, transmission time difference, angle of arrival, arrival time, and time difference. In various aspects, the occupancy-centric algorithm 250 may use processing techniques and algorithms used in computer vision and image processing, especially when CSI is stored in a 3D matrix representation, although other algorithms such as Multi-Signal Classification (MUSIC) algorithms may be used to analyze CSI in sensor system 100. As an example only, cross-correlation techniques may be used to process and / or analyze and / or compare CSI. In various implementations, the two CSI matrices may be cross-correlated, and the output of the cross-correlation may be a measure of the similarity or difference between the two matrices, and may be part of determining whether the radio environment (space 105) remains substantially the same or is constantly changing.

[0086] In some aspects, one or more thresholds can be set for one of the data values ​​measured and / or analyzed. Values ​​calculated and / or analyzed and / or generated exceeding and / or falling below a threshold level and / or falling within a set of thresholds can indicate occupancy in space 105. By way of example only, radio device 110 can send an output occupancy signal and / or a decision output signal to another radio device 110 and / or a control system to indicate that space 105 is occupied. The control system can perform some action upon receiving the occupancy signal and / or the decision output signal. In other implementations, the control system can perform some action upon receiving the occupancy signal and / or the decision output signal, as well as at least one other control and / or sensor and / or occupancy signal and / or decision signal, wherein the at least one other control signal can be a signal from another sensor and / or monitor, user input, a timer, a buffer, or a database containing other occupancy signals, or any other suitable device, or any combination thereof.

[0087] In some respects, a single wireless device 110 can function as a hub within a sensor system 110. The wireless device 110 functioning as a hub may include methods for executing / implementing occupancy-centric algorithms 250 (such as...). Figure 2The hub radio 110 may include hardware and / or software for performing and / or communicating with a control loop, which may, for example, control one or more devices and / or systems via network 200. The hub radio 110 may communicate with one or more other radios 110 in the sensor system 100; for example, it may receive communication signals and / or decision signals from another radio 110, which includes hardware and / or software for performing an occupation-centric algorithm 250.

[0088] The sensor system 110 may include multiple hub radios 110. In this implementation, data analysis, occupancy determination, and system control may be performed in a single radio 110 and / or in a hub radio 110. In other implementations, data analysis, occupancy determination, and system control may be performed in a distributed manner, where one or more radios 110 are responsible for performing one or more steps in a control loop.

[0089] Refer again Figure 3 Sensor system 100 may include extracting ambient signals 330 from radio signals. Ambient signal extraction may include processing the received signals and determining any portion of the received signals, such as CSI, RSSI, CFR, CIR, etc. Furthermore, ambient signal extraction may include processing any, all, or a combination of CSI, RSSI, CFR, and CIR from a single data packet, multiple data packets, a single transmitter / receiver pair, multiple transmitter / receiver pairs, multiple transmitter / receiver antenna pairs, a single transmitter / receiver subchannel, multiple transmitter / receiver subchannels, or any other combination of signals / devices. In various aspects, ambient signal extraction may include comparing measured data with data thresholds, data inputs, user inputs, other sensor inputs, previously measured data, etc. Additionally, in some aspects, ambient signal extraction may include: (i) generating an output signal that may indicate the presence of personnel in space 105; (ii) occupying control loops and / or controlled or manageable systems in space 105 and operating the system in a manner comfortable for human occupants. By way of example only, the output signal and / or determination of the output signal may indicate the presence of personnel. The output signal can be a temperature setting or temperature range that the heating / cooling system should achieve in space 105. The output signal can also be a signal suitable for input to another data analysis stage, processing stage, signal extraction stage, signal determination stage, or similar control or analysis system.

[0090] At 340, sensor system 100 can determine environmental conditions in space 105 based on the extracted environmental signals. This environmental condition determination may include processing any, all, or a combination of CSI, RSSI, CFR, and CIR from a single data packet, multiple data packets, a single transmitter / receiver pair, multiple transmitter / receiver pairs, multiple transmitter / receiver antenna pairs, a single transmitter / receiver subchannel, multiple transmitter / receiver subchannels, or any other combination of signals / devices. Environmental condition determination 340 may include comparing the generated parameters and / or values ​​with user-configurable parameters and / or values, stored parameters and / or values, calculated parameters or values, or any combination thereof. The parameters and / or values ​​that can be compared with the generated parameters and / or values ​​may change or may be variable. In embodiments, environmental determination may output one or more signals related to the radio environment.

[0091] At 350, sensor system 100 can output an occupancy signal that represents, contains, or otherwise indicates the occupancy status of space 105. In some respects, the occupancy signal indicates the presence of a person, multiple people, a certain number of people, the presence of an animal, an open window, an open door, the presence of at least one person who is not moving, a person falling, a person moving to a different space 105, or any other condition of space 105 as determined at 340.

[0092] In some respects, sensor system 100 can output occupancy signals (and / or control signals based on occupancy signals at 360°) to a system controlling the passage of radio signals through space 105. By way of example only, sensor system 110 can provide occupancy and / or control signals to heating, cooling, ventilation, security, lighting, electrical, and entertainment systems associated with space 105. Such heating systems can receive occupancy and / or control signals from sensor system 100 and can increase, decrease, or maintain the heat supplied to space 105. Similarly, cooling systems can receive occupancy and / or control signals from sensor system 100 and can increase, decrease, or maintain the cooling supply to space 105; ventilation systems can receive occupancy and / or control signals from sensor system 100 and can increase, decrease, or maintain the ventilation supply to space 105. Security systems can receive occupancy and / or control signals from sensor system 100 and can turn security systems on or off or maintain them in their current state. The lighting system can receive occupancy and / or control signals from the sensor system 100 and can increase, decrease, or maintain the amount of light supplied to the space 105. The power system can receive occupancy and / or control signals from the sensor system 100 and can increase, decrease, or maintain the amount of power supplied to the space 105. As another example, the entertainment system can receive occupancy and / or control signals from the sensor system 100 and can increase, decrease, or maintain the volume, channel, settings, etc. of any audio, video, and / or other entertainment signals supplied to the space 105.

[0093] In some implementations, sensor system 100 may provide output control signals and / or information as part of a system control feedback loop. Sensor system 100 may provide control signals at a rate of not less than 10 times per second, not less than 10 times per minute, not less than 10 times per hour, not less than 10 times per day, not less than 10 times per week, and / or not less than 10 times per month. In various implementations, sensor system 100 may provide multiple output signals based on the analysis of multiple radio signals. In embodiments, sensor system 100 may provide output signals based on the analysis of radio signals and inputs from any other type of sensor described in this disclosure.

[0094] The control loop can control any or a combination of mobile phones, computers, tablets, watches, speakers, thermostats, heating equipment, cooling equipment, ventilation equipment, lighting equipment, power plants, chargers, home appliances, routers, access points, models, e-readers, and / or personal assistants (such as Google Home, Amazon Echo, and Apple HomePod). The control loop can also control some or any combination of heating, cooling, ventilation, security, lighting, electrical, and entertainment systems, or not control any of these systems.

[0095] In an embodiment, a radio device 110 may request other radio devices 110 to transmit data extracted from radio signals received from those other radio devices. For example, a first radio device may request a second radio device to transmit CSI, RSSI, CFR, CIR, time of arrival, time difference of arrival, signal power, angle of arrival, and / or distance information for signals propagating between the first radio device and at least a second device or between at least a second device and at least a third device.

[0096] According to one example, sensor system 100 may include at least two wireless devices 110, wherein at least one wireless device 110 can analyze data from at least one radio communication link, or can communicate with a device that analyzes data from at least one radio communication link, and at least one wireless device 110 can provide control signals to a control system or device in space 105 in response to data collected from at least one communication link.

[0097] In a further example, sensor system 100 may include at least two wireless devices 110, wherein at least one wireless device 110 is integrated into a thermostat or smart thermostat. The thermostat or smart thermostat may analyze data from at least one radio communication link, or may communicate with a device analyzing data from at least one radio communication link, and the thermostat or smart thermostat may provide control signals to control the HVAC system in space 105. The smart thermostat may include some, any, or all of the hardware, software, firmware, and drivers for performing one, some, or any of the environmental signal extraction 330, environmental determination 340, and outputs 350, 360 of this disclosure.

[0098] In this embodiment, the data analysis and calculation of the control parameters can be performed remotely, for example, on a shared computer or a server communicating with one or more wireless devices 110. The results of the data analysis and control parameter determination can be transmitted via a wired communication link, a primary wired communication link, a primary optical link, a primary wireless link, or a link as a combination of wired and wireless, and may include intermediate switches, routers, access points, data format converters, etc.

[0099] Sensor system 110 may include a thermostat comprising a wireless device 110-1 and at least a second wireless device 110-2. The thermostat may receive wireless communication or information signals from at least the second wireless device 110-1 and may analyze these signals to obtain values ​​or parameters associated with the environment (space 105) to which the communication or information signals are experienced. The thermostat may store these values ​​or parameters and / or run an occupancy-centric algorithm 250 that analyzes these values ​​or parameters to determine whether space 105 includes one or more people. The thermostat may regulate heating, cooling, and / or ventilation systems in a residence based on the presence of people. For example, if people are present, the thermostat may adjust heating, cooling, and / or ventilation levels to levels determined to be suitable for human occupancy. In embodiments, levels determined to be suitable for human occupancy may be occupancy-specific, room-specific, area-specific, building-specific, time-specific, outdoor temperature-specific, season-specific, location-specific, energy price-specific, energy-specific, etc. If data analysis determines that there is no occupant, the thermostat can set the heating, cooling, and / or ventilation levels to energy-efficient levels (reverting temperature and ventilation settings).

[0100] In yet another exemplary embodiment, the sensor system 100 may include a thermostat comprising a transmitter radio device 110-1 and at least one receiver radio device 110-2. The at least one receiver radio device 110-2 may receive wireless communication or information signals from the thermostat and may analyze these signals to obtain values ​​or parameters associated with the environment (space 105) through which the communication or information signals are received. The at least one receiver radio device 110-2 may store these values ​​or parameters and / or run an occupancy-centric algorithm 250 that analyzes these values ​​or parameters to determine whether space 105 includes a person. The at least one receiver radio device 110-2 may transmit the determined values ​​or parameters to the thermostat. The at least one receiver radio device 110-2 may inform the thermostat of the presence of one or more people, or the at least one receiver radio device 110-2 may transmit data to the thermostat, which the thermostat may analyze to determine the presence of one or more people. As described herein, the thermostat may regulate heating, cooling, and / or ventilation systems in a residence based on the presence of a person.

[0101] According to an additional implementation, sensor system 100 may include a thermostat comprising a transmitter radio device 110-1 and at least one receiver radio device 110-2. The at least one receiver radio device 110-2 may receive wireless communication or information signals from the thermostat and may analyze these signals to obtain values ​​or parameters associated with the environment in which the communication or information signals have traveled. The at least one receiver radio device 110-2 may store these values ​​or parameters and / or run an occupancy-centric algorithm 250 that analyzes these values ​​or parameters to determine whether the environment includes one or more persons. The at least one receiver radio device 110-2 may transmit the determined values ​​or parameters to the thermostat. The at least one receiver radio device 110-2 may inform the thermostat of the presence of one or more persons, or at least one second device may transmit data to the thermostat, which the thermostat may analyze to determine the presence of one or more persons. The thermostat may use additional sensor inputs, user inputs, or any other type of data or information disclosed herein to determine whether an occupant is in the space and whether the heating, cooling, and / or ventilation levels in the room, area, and / or building (space 105) should be regulated.

[0102] In addition to transmitter radio device 110-1 and at least one receiver radio device 110-2, any exemplary sensor system 100 described herein may include at least one other radio device 110 (“third radio device”). Third radio device 110 may be physically combined with thermostat or receiver radio device 110-2. Third radio device 110 may be integrated into the same electronics, packaging, case, or system as thermostat or receiver radio device 110-2, or may be physically separate from or remote from thermostat and / or receiver radio device 110-2. Third radio device may generate and / or receive wireless communication or information signals from thermostat and / or receiver radio device 110-2, and may analyze these signals to obtain values ​​or parameters associated with the environment in which the communication or information signals are experienced. Third radio device may store these values ​​or parameters and / or run an occupancy-centric algorithm 250 that analyzes these values ​​or parameters to determine whether the environment includes one or more people. Third radio device may transmit the determined values ​​or parameters to thermostat and / or receiver radio device 110-2. The receiver radio device 110-2 or the thermostat, or both, may run an occupancy-centric algorithm 250 to determine whether a person is present in a room and / or area and / or building near or surrounding the thermostat, receiver radio device 110-2, and third radio device 110.

[0103] This disclosure envisions that occupancy data and occupancy status can be collected and analyzed by some or any wireless devices 110 that are within communication range of each other. That is, determining occupancy status can be a distributed process in which different devices perform different parts of data collection, generation, analysis, thresholding, and other aspects of method 300.

[0104] This disclosure envisions that one or more wireless devices 110 can communicate using one or more communication protocols. In various aspects, these wireless devices 110 can use WiFi, Bluetooth, etc. TM Zigbee TM This disclosure envisions communication with other devices using any or any combination of standardized signaling protocols such as 5G, Ultra Wideband (UWB), and any IEEE standard (including but not limited to IEEE 802.11, IEEE 802.15.1, IEEE 802.15.3, IEEE 802.15.4, IEEE 802.16, IEEE IMT-Advanced / 3GPP, Long Term Evolution (LTE), and Near Field Communication (NFC). Devices can communicate using different radio frequency bands, such as 5GHz WiFi and 2.4GHz WiFi. This disclosure contemplates the development of custom radio signaling schemes and the use of channel information extracted from these custom signaling schemes. This disclosure also contemplates the development and / or utilization of proprietary radio signaling schemes and the use of channel information extracted from these proprietary signaling schemes.

[0105] This disclosure envisions that the occupancy-centric algorithm 250 can change and evolve over time. The occupancy-centric algorithm 250 can be modified using training algorithms, learning algorithms, machine learning algorithms, artificial intelligence algorithms, etc. In some aspects, the occupancy-centric algorithm 250 itself may include at least a portion that can be considered as a learning algorithm, training algorithm, machine learning algorithm, and / or artificial intelligence algorithm. Shallow learning algorithms, deep learning algorithms, deep neural networks, etc., can be utilized to improve the performance of the sensor system 100 and / or the occupancy-centric algorithm 250.

[0106] This invention envisions that channel amplitude and / or phase and / or timing data derived from radio signal communication may not directly indicate the presence of a person in or near the radio channel. To correlate changes in channel amplitude and / or phase and / or timing data with the presence of a person, data analysis and an occupancy-centric algorithm 250 may be required. Data analysis may require analyzing multiple data frames, multiple channels, etc. Trends in certain data signals can indicate the presence of a person. A trend indicating one occupancy may differ from a trend indicating another. Therefore, this disclosure envisions that the occupancy-centric algorithm 250 can automatically or in response to some external input changing and evolving over time. External input may include, but is not limited to, other sensor data, user input, software upgrades, and other additional or different sensor devices.

[0107] In some respects, at least two radio devices 110 can communicate via a wireless channel that propagates through an environment (e.g., space 105) through which radio signals travel. A first radio device 110 can perform several checks on a second radio device 110, and the second radio device 110 can send one or more data packets to the first radio device 110 in response to the checks. The first radio device 110 can receive one or more data packets from the second radio device 110 and process these data packets to present received amplitude and / or phase and / or timing information characterizing the radio environment and / or channel. As mentioned herein, the term "CSI" can refer to amplitude and / or phase and / or timing information; however, it should be understood that CSI is merely one way of representing amplitude and / or phase and / or timing information characterizing a channel or radio environment.

[0108] The received CSIs can be real numbers, complex numbers, or a combination of real and complex numbers, can be vectors of real and / or complex numbers, and can be two-dimensional or three-dimensional matrices of real and / or complex numbers. In some aspects, the occupancy-centric algorithm 250 may include signal processing techniques and algorithms for computer vision and image processing tasks. The first radio device 110 may store some or all of the received CSIs or none of any of the received CSIs, and / or may compare some or all of the received CSIs with previously received CSIs (stored CSIs), or may not compare any of the received CSIs with previously received CSIs (stored CSIs). The first radio device 110 may compare the CSIs received from each data packet with the stored CSIs for one and / or multiple data packets and / or the average and / or running average and / or sliding window average of the stored CSIs. The stored CSI may include amplitude, phase, and timing information for each subcarrier of the radio signal, or the stored CSI may be a subset of amplitude, phase, and timing information for any or all subcarriers of the received radio signal.

[0109] The first radio device 110 can store multiple CSIs and can store multiple copies of CSIs. The multiple stored CSIs may include, but are not limited to, CSIs from: previous time periods; third or other radio devices; known times when space 105 was unoccupied; versions that have been processed in a different manner (e.g., noise removed), filtered in a different manner, have different average values, or different length average windows; versions that have been input by a user or another program; versions that have been calculated using different algorithms, etc. In an embodiment, the first radio device 110 can maintain a running average of previously received CSIs and can compare newly received CSIs to the running average. If a value calculated from a CSI deviates from the value calculated from the running average CSI in a newly received CSI, the first radio device 110 can interpret this deviation as a change consistent with human occupancy in the radio environment.

[0110] The first radio device 110 can quantify the deviation between the most recent CSI and older CSIs, and can provide different output signals based on the magnitude of the compared CSI deviation. For example, the first radio device 110 can calculate the amplitude of some subcarriers among the received subcarriers and correlate that quantity with the energy of the received signal. The first radio device 110 can average some of the received data packets to obtain the average energy of the received data packets. The first radio device 110 can continue to update the average value by calculating the average value based on previous CSIs of 2, 5, 10, 100, 1000, 10,000, 100,000, 1,000,000, or any other number of CSIs. The number of CSIs in the running average can be a configurable parameter, which can be set by a user, controller, algorithm, etc. In some aspects, the number of CSIs in the running average can be variable and can be changed to adjust system performance.

[0111] If the energy of the received signal deviates from the average energy by 0.0001%, 0.001%, 0.01%, 0.1%, 1%, 10%, 100%, or any other magnitude, the first wireless device 110 may associate this deviation with the presence of a person in the radio environment. Those skilled in the art will understand that although the deviations listed above are given as percentages, there are many ways to quantify deviations, and any of these types of quantifiers is within the scope of this disclosure. For example, thresholds and / or ranges for system metrics can be set using any type of value, quantity, ratio, percentage, etc.

[0112] In some implementations, the first radio device 110 may not associate the deviation in the CSI with human occupancy unless the deviation has a certain value and / or has been measured for a certain number of data packets and / or a certain amount of time and / or a certain frequency. The degree of deviation and / or the number of data packets with a specific CSI value and / or the amount of time at which data packets arrive at a specific CSI level and / or the frequency at which data packets arrive at a specific level can be set parameters, which can be set by a user, controller, algorithm, etc.

[0113] According to various aspects of this disclosure, the first radio device 110 can receive data packets from the second radio device 100 for a period of time before comparing newly received CSIs with previously received or stored CSIs. The first radio device 110 can receive a specific number of data packets and / or a specific amount of data packets over a specific time period, wherein the number of data packets and / or the amount of time period can be settable parameters. The first radio device 110 can analyze the received CSIs and can begin calculating CSI averages. These CSI averages can be background CSI levels and can be correlated with the state of the environment (space 105) at certain times during the operation of the sensor system 100. By way of example only, the first radio device 110 can receive data packets and calculate CSI averages when there is little or no movement in space 105, and can compare this CSI with later received CSIs to look for deviations in data aspects that could indicate the presence of one or more people. The sensor system 105 can be programmed to collect background CSIs at system startup and / or at certain times of day, days of week, certain times of month, etc., when space 105 is known to be unoccupied or potentially unoccupied. In this embodiment, multiple background CSIs can be stored and used for comparison with newly arrived CSIs. In this embodiment, multiple background CSIs can be accessed from a data marketplace having a relevant dataset that allows comparison with newly arrived CSIs. In this embodiment, different background CSIs can be compared with each other, and the sensor system 100 can monitor and / or report differences and / or trends in the background CSIs.

[0114] Sensor system 100 can continuously generate output signals (e.g., an occupancy signal at 350 and / or a control signal at 360), can generate output signals in response to a request, or can initiate output signal generation based on sensor data. If output signals are generated continuously, the level of the signal and / or the data in the signal may change to indicate changes in occupancy in space 105. By way of example only, sensor system 100 may generate an output signal each time a received CSI deviates from a stored CSI by a specific amount. Alternatively, an output signal may be generated only when a certain number of CSIs deviate by a specific amount, or when a certain number of CSIs deviate by a specific amount over a period of time, or when a certain number of CSIs deviate and some other signals, thresholds, inputs, etc., have specific values. It should be understood that the output of sensor system 100 may be based on multiple sensor inputs, environmental conditions, system settings, and other factors described herein.

[0115] As described herein, sensor system 100 can send output signals to a controller to control systems operating in the radio environment (space 105) of sensor system 100. Wireless device 110 in sensor system 100 may include a controller, or alternatively, the controller may be decoupled from wireless device 110, and the output signal may be transmitted to the controller via circuit traces, wires, optical fibers, wireless signals, optical signals, or any combination of known transmission protocols and media. In some aspects, the output signal from sensor system 100 may be part of a feedback loop for controlling systems in space 105. By way of example only, the output signal may be part of a feedback loop to control any, some, or all of heating, cooling, ventilation, security, lighting, electrical, and entertainment systems. Additionally, the output signal may be part of an open-loop control circuit or system to control any, some, or all of heating, cooling, ventilation, security, lighting, electrical, and entertainment systems.

[0116] While this disclosure describes sensor system 100 inside or outside a building, sensor system 100 can be applied to other types of scenarios and other spaces 105. By way of example only, the disclosed sensor system 100 can be used to detect the presence of people in disaster scenarios such as collapsed buildings, caves, mines, etc. In such scenarios, sensor system 100 can be used to determine whether people are present, how many people are breathing, and at what rate their hearts are beating. Similarly, sensor system 100 can be used to determine whether people are present and how many people may be hiding behind walls during hostage situations or kidnappings, and can determine whether people are present and how many people are trapped in containers, such as shipping crates, cargo crates, below the deck of a ship, etc. In addition to determining the presence of people, sensor system 100 can also be used to monitor the health status of people and / or animals in an area. By way of example only, this disclosure can generate output signals related to the respiratory rate and / or heart rate of any living organism within space 105. Such sensor system 100 can be used to monitor infant breathing and prevent sudden infant death syndrome. Such systems can also monitor the sleep patterns of patients with sleep apnea and issue alarms or adjust bed or environmental settings when the patient's breathing becomes abnormal or stops.

[0117] Sensor systems in value chain networks

[0118] The sensor system 100 can be used with value chain networks such as logistics value chain networks. Logistics value chain networks or infrastructure can include warehouses, distribution centers, ships, trucks, aircraft, order and information systems, workers, cargo airports, container ports, oceans, geographic features, railroads, roads, streets, customer residences, workplaces, etc. The parties involved can be suppliers, customers, and partners typically involved in logistics and transportation. Logistics value chain networks may involve various workflows applicable to shipping, ocean freight, ports / borders, logistics, distribution centers, reverse logistics, packaging, picking, assembly, delivery, installation, etc.

[0119] In a typical example, a value chain network, such as a logistics value chain network or supply chain, may involve a manufacturer fulfilling a product order through the supply chain, where suppliers, operating production facilities, or other product dealers or distributors in various supply environments provide products at the point of origin based on the order. Products can be transported and stored through the supply chain via various transport and distribution facilities (e.g., warehouses, operations centers) and conveying systems (e.g., trucks, trains, and other vehicles). In many cases, maritime facilities and related infrastructure (e.g., ships, barges, docks, and ports) can be used for the waterway transport of products between the point of origin and one or more destinations. Related infrastructure (including, for example, warehouses, facilities, vehicles, etc.) can be monitored by sensor system 100.

[0120] Value chain network entities may involve a wide range of value chain activities, such as supply chain activities, logistics activities, demand management and planning activities, transportation activities, shipping activities, warehousing activities, distribution and operations activities, inventory accumulation, storage and management activities, marketing activities, and many other activities involved in various value chain network processes, workflows, activities, events, and applications. Sensor system 100 can determine value chain recommendations based on monitoring occupancy data at least related to these activities in space. The object classes used for each type of value chain network entity may include products, infrastructure, workers, operators, owners, enterprises, suppliers, distributors, logistics providers, customers, dealers, etc. These applications may involve various assets, systems, devices, machines, components, equipment, facilities, individuals, or other entities mentioned in this disclosure.

[0121] Sensor system 100 can be used in value chain processes such as shipping, towing, maritime processes, inspection processes, transportation processes, loading and unloading processes, packaging / unpacking processes, configuration processes, assembly processes, installation processes, quality control processes, environmental control processes (e.g., temperature control, humidity control, pressure control, vibration control, etc.), border control processes, port-related processes, software processes (including applications, programs, services, etc.), packing and loading processes, financial processes (e.g., insurance processes, reporting processes, transaction processes, etc.), testing and diagnostic processes, security processes, safety processes, reporting processes, asset tracking processes, etc.

[0122] Value chain network entity examples

[0123] In the example, value chain network entities may include, for example: products, suppliers, manufacturers, producers, retailers, enterprises, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, dealers, supply chain infrastructure, supply chain processes, logistics processes, reverse logistics processes, demand forecasting processes, demand management processes, demand aggregation processes, machines, ships, barges, warehouses, seaports, airports, waterways, waterways, highways, railways, bridges, tunnels, online retailers, e-commerce sites, demand factors, supply factors, transportation systems, current assets, place of origin, destination, storage point, point of use, network, information technology systems, software platforms, distribution centers, operations centers, containers, container handling equipment, customs, export controls, border controls, drones, robots, autonomous vehicles, haulage facilities, drones / robots / AVs, waterway and port infrastructure, etc.

[0124] In other examples, a group of value chain network entities may include (but is not limited to) policy management applications, such as those for deploying one or more policies, rules, etc., to manage one or more value chain network entities or applications, for example, to manage the execution of one or more workflows (which may involve configuring policies on a per-workflow basis within the platform); regulatory compliance (including maritime, food and drug, medical, environmental, health, safety, tax, financial reporting, commercial, and other regulations (as described in this disclosure or as will be understood in the art)); regulatory resource allocation (e.g., connectivity, computing, human, energy, and other resources); regulatory corporate policy compliance; regulatory contracts (including smart contracts, where the platform can automatically deploy regulatory features to relevant entities and applications, such as via connectivity facilities); regulatory interactions with other entities (e.g., involving shared information and resource access policies); regulatory data access (including privacy data, operational data, status data, and many other data types); and secure access to regulatory infrastructure, products, devices, locations, etc.

[0125] Examples of workers, suppliers, and customers in a value chain network

[0126] Workers may include delivery workers, loading workers, barge workers, port workers, dockworkers, train workers, ship workers, operations center workers, warehouse workers, vehicle drivers, business managers, engineers, floor managers, demand managers, marketing managers, inventory managers, supply chain managers, cargo handling workers, inspectors, delivery personnel, environmental control managers, financial asset managers, process supervisors and workers (for any process described herein), security personnel, safety personnel, etc. Suppliers may include suppliers of all types of goods and related services, component suppliers, ingredient suppliers, material suppliers, manufacturers, etc. Customers may include consumers, licensees, companies, enterprises, value-added and other distributors, retailers, end users, distributors, and others who may purchase, license, or otherwise use a class of goods and / or related services.

[0127] Spatial examples in value chain networks

[0128] In a value chain network (e.g., a logistics value chain network), as described above, sensor system 100 can analyze channel responses to determine information about a value chain space (e.g., space 105). Space 105 can be located in ships, trucks, aircraft, barges, warehouses, ports, distribution centers, containers, container handling equipment, cargo airports, container ports, customer residences, workplaces, etc. As described above, the channel response can be a channel impulse response (CIR), channel frequency response (CFR), channel state information (CSI), received signal strength indication (RSSI), or any other type of channel response. Information about the value chain space can include, for example, whether something is moving in space 105; whether there is breathing in space 105 and the breathing rate; and / or whether something with a heartbeat is in space 105 and the heartbeat rate. In some examples, as described above, a signaling protocol (e.g., a WiFi protocol) can be used to generate channel information that can be referred to as CSI.

[0129] In some examples, space can be part of a wide range of operational facilities within a value chain network, such as loading and unloading terminals, storage and warehousing facilities, warehouses, distribution facilities and operations centers, air travel facilities (including aircraft, airports, hangars, runways, fuel depots, etc.), marine facilities (such as port infrastructure (such as wharves, yards, cranes, horizontal loading and unloading facilities, ramps, containers, container handling systems, waterways, locks, etc.), shipyard facilities, current assets (such as vessels, barges, ships, etc.), facilities and other goods at origin and / or destination, haulage facilities (such as container ships, barges and other current assets, as well as land-based vehicles and other transport systems for transporting goods, such as trucks, trains, etc.).

[0130] Occupation-centric algorithms for value chain networks

[0131] As described above, sensor system 100 can use an occupancy-centric algorithm (e.g., occupancy-centric algorithm 250) to determine human occupancy in a value chain space (e.g., space 105). The sensor system can also determine value chain recommendations based on the determined occupancy in the value chain space. For occupancy sensing applications, the occupancy-centric algorithm can be used for occupant processing, occupancy-centric processing, occupancy-finding processing, etc., which can be performed based on the occupancy-centric algorithm or other occupant algorithms, occupancy-centric algorithms, or similar naming algorithms. As described above, in some examples, sensor system 100 can identify and monitor individuals as unique to each other due to their individual radio signatures. For example, some individuals can influence the amplitude and / or phase and / or timing of radio signals in a manner recognizable by an occupancy-centric algorithm running in sensor system 100. Individually tracking individuals can include monitoring one worker per day, week, etc., through the value chain space. This information can be used to determine each worker's efficiency and / or whether that worker might interfere with other workers and / or whether that worker might have bottlenecks and requires training, etc.

[0132] Occupation-centric algorithmic evolution for value chain networks

[0133] The occupancy-centric algorithm 250 can change and evolve over time relative to the value chain network (e.g., a logistics value chain network). As described above, the occupancy-centric algorithm 250 can be modified using training algorithms, learning algorithms, machine learning algorithms, artificial intelligence algorithms, etc. In some examples, the occupancy-centric algorithm 250 may include what can be considered as part of a learning algorithm, training algorithm, machine learning algorithm, and / or artificial intelligence algorithm. Shallow learning algorithms, deep learning algorithms, deep neural networks, etc., can be utilized to improve the performance of the sensor system 100 and / or the occupancy-centric algorithm 250 relative to the value chain network. The occupancy-centric algorithm 250 can change and evolve over time automatically or in response to some external input to the value network space. The sensor system 100 can determine new value chain recommendations based on the evolution of the occupancy-centric algorithm.

[0134] Monitoring and control of the value chain spatial environment system

[0135] Internet of Things (IoT) systems and devices within the value chain network can be used in conjunction with sensor system 100. For example, IoT systems and devices may include thermostats, lighting systems, and speakers, which may have onboard network connectivity and processing capabilities, typically including voice-controlled smart agents that allow devices to control and trigger certain application features, such as playing music or even changing the temperature. With increasing artificial intelligence capabilities, the computing and networking capabilities of network-enabled edge IoT devices and systems residing in the value chain network (e.g., the supply environment) and across all locations, systems, and facilities that fill the path of products within the infrastructure of the value chain network (e.g., a logistics value chain network), such as from a manufacturer's loading dock to a customer's destination, will continue to improve. There is a need and opportunity to significantly enhance the intelligence, control, and automation of all factors involved in the value chain network (e.g., based on systems and devices). Sensor system 100 may include environmental control processes (e.g., temperature control, humidity control, pressure control, vibration control, etc.). For example, sensor system 100 may include and / or occupy temperature monitoring system, heat flow monitoring system, biological measurement system, chemical measurement system, ultrasonic monitoring system, radiographic system, etc.

[0136] In the example, sensor system 100 can detect various hand gestures from workers. These detected gestures can be used to initiate steps that can be taken to control, adjust, and / or alter heating, cooling, ventilation, safety, lighting, electrical, recreational, and other systems in or associated with the value chain space (e.g., space 105). For example, a worker wiping sweat from their forehead indicates they may be hot; or a worker putting on a coat indicates they may be cold. In addition to gestures, sensor system 100 can also detect sweating, indicating it's too hot; or goosebumps or pubic hair, indicating it's too cold; and / or additionally, can measure human skin temperature. Workers can use other gestures (e.g., pointing to their ears) to indicate they cannot hear, suggesting excessive ambient noise, allowing equipment to be controlled to eliminate noise (e.g., reducing ventilation fan power), or potentially increasing equipment volume.

[0137] The output signal may include a temperature setting or temperature range that the heating / cooling system should achieve in space 105 (e.g., increasing the temperature using a heater and decreasing the temperature using AC). This output signal may be suitable for input to another data analysis stage, processing stage, signal extraction stage, signal determination stage, or similar control or analysis system to adjust the temperature accordingly. Such a heating system may receive occupancy and / or control signals from sensor system 100 and may increase, decrease, or maintain the heat supplied to space 105. Similarly, a cooling system may receive occupancy and / or control signals from sensor system 100 and may increase, decrease, or maintain the cooling capacity supplied to space 105.

[0138] Other adjustable environmental experiences include humidity, airflow, etc. Sensor system 100 can provide occupancy and / or control signals to heating systems (using heaters), cooling systems (using AC), and ventilation systems (e.g., increasing fan speed and / or starting more fans or activating fans in specific areas of a space) to reduce humidity and / or increase airflow and / or maintain humidity and airflow as needed. The ventilation system (e.g., fans) can receive occupancy and / or control signals from sensor system 100 and can increase, decrease, or maintain the amount of ventilation supplied to space 105. Ventilation can be adjusted based on noise. For example, if enough people in a room are trying to talk to each other, and workers' gestures indicate they seem unable to hear each other (which appears to be due to fan noise), the ventilation system can adjust airflow accordingly. For example, for fans closer to the workers, the motor speed might be reduced (which reduces noise), or the motor might be turned off, while for fans farther away, the motor speed might be increased. Because of the greater distance, the noise from fans farther away is less significant. Therefore, airflow can be maintained based on monitoring worker occupancy information in a specific area while minimizing noise in that specific area of ​​space 105.

[0139] In some examples, as described above, heating, cooling, and / or ventilation systems can be automatically adjusted (e.g., using thermostats) within a value chain space (e.g., space 105) based on the presence of workers. For instance, if workers are present, the thermostat can adjust the heating, cooling, and / or ventilation levels to a level suitable for human occupancy. The level determined to be suitable for human occupancy based on workflow within the value chain space (e.g., space 105) can be occupancy-specific, room-specific, area-specific, building-specific, time-specific, outdoor temperature-specific, season-specific, location-specific, energy price-specific, energy-specific, etc. If data analysis determines that there are no occupants such as workers, the heating, cooling, and / or ventilation levels can be set to energy-efficient levels (reverting temperature and ventilation settings). If there are no workers in the value chain space, energy savings can be achieved by shutting off ventilation and / or heating and / or cooling systems. Furthermore, when there are no workers in the value chain space, the heating, cooling, and / or ventilation levels can be set to a level that still adequately maintains the product (e.g., depending on the product being stored), which may be stored in the value chain space or a specific area of ​​the value chain space, thereby preventing the product from being damaged due to overheating or excessive humidity, for example.

[0140] Security systems, lighting systems, electrical systems, entertainment systems, kitchen systems (e.g., coffee makers or espresso machines), speaker or intercom systems, and other systems or equipment associated with the value chain space (e.g., space 105) can also be monitored and controlled by sensor system 100. Control and monitoring can be based on worker occupancy near equipment and usage of equipment associated with these systems. For example, if there are no workers in space 105, equipment in these systems can be deactivated or turned off (e.g., no lighting is provided due to the absence of workers) to save energy. Lighting can be adjusted based on the number of workers in specific areas of space 105, so that increased lighting may be needed when more people enter a particular area. Lighting may need to be adjusted based on sunlight from windows (e.g., due to time of day (e.g., nighttime) versus daytime light or weather (e.g., sunny or rainy), allowing for reduced lighting on sunny days and increased lighting on cloudy days or at night). The volume of the entertainment system can be automatically adjusted based on noise in space 105. The entertainment system can receive occupancy and / or control signals from sensor system 100 and can increase, decrease, or maintain the volume, channel, settings, etc., of any audio, video, and / or other entertainment signals provided. Similarly, the volume of speaker or intercom systems can be increased or decreased based on noise in the space and / or from gestures indicating workers who cannot hear each other. The power system can be monitored based on usage to optimize power consumption while minimizing power consumption when not powered on. Usage and occupancy near the kitchen system can be monitored. This allows the kitchen system to be deactivated or switched to a low-power state when no workers are nearby. Furthermore, the sensor system 100 can detect situations where kitchen system usage is excessive, enabling it to determine value chain recommendations, including adding kitchen equipment such as coffee machines where needed based on occupancy and usage data. Based on environmental experience data detected by the sensor system 100, it can monitor whether safety systems should activate safety equipment (e.g., spray fire extinguishers) and / or take other safety actions (e.g., call emergency personnel). The sensor system 100 can monitor and control safety systems, lighting systems, electrical systems, entertainment systems, kitchen systems, speaker or intercom systems, and other systems or equipment associated with the value chain space based on other factors and / or characteristics of environmental experiences detected by the sensor system 100.

[0141] Sensor system 100 can be adjusted and / or has specific settings for use during a pandemic. For example, sensor system 100 can ventilate more frequently when workers are gathered in the same space. Furthermore, ventilation can be activated such that fans in the space are specifically activated when multiple workers are within a certain fan distance range (e.g., nearby). An alarm may be triggered when occupancy data indicates that workers are not following social distancing requirements (e.g., less than six feet apart) and / or appear not to be wearing masks. The alarm can be used to indicate that ventilation filters need to be replaced before they become ineffective.

[0142] Disaster service value chain space safety system

[0143] In some examples, sensor system 100 can be used to detect the presence of workers in a disaster scenario within the value chain space. Disaster scenarios can include building, cave, or mine collapses, ship, train, or vehicle accidents, building fires, criminal activity, workplace accidents, etc. Sensor system 100 can then automatically trigger safety systems based on these detected disasters to provide an appropriate response. For example, in the event of a warehouse fire, sensor system 100 can instruct safety systems to trigger emergency equipment, such as fire alarms and / or fire extinguishers (e.g., if not already triggered), and then automatically contact emergency responders with information about the disaster, the warehouse status, and the health status of the workers.

[0144] The sensor system 100 may also include event management applications, such as for managing events, incidents, and other events that may occur in one or more environments involving value chain network entities, such as, but not limited to, vehicle accidents, worker injuries, downtime events, property damage events, product damage events, product liability events, regulatory non-compliance events, health and / or safety events, traffic congestion and / or delay events (including network traffic, data traffic, vehicle traffic, maritime traffic, manual traffic, and other traffic, and combinations thereof), product failure events, system failure events, system performance events, fraud events, abuse events, unauthorized use events, and so on.

[0145] Value chain network disruption

[0146] To prevent disruptions, sensor system 100 can detect information that helps prevent disruptions to the value chain network (e.g., a logistics value chain network). For example, occupancy signals can indicate the presence of a certain number of workers (exceeding a predetermined threshold, thus impacting workflow), the presence of animals, open windows, open doors, the presence of at least one person who is not moving, a fall, someone moving to a different space 105, or any other situation in space 105 that might impact the logistics value chain network. Sensor system 100 can determine value chain recommendations based on these disruptions. Sensor system 100 can determine that these conditions constitute disruptions based on a combination of workflow results indicating that workflow operations have been interrupted and / or occupancy information, thereby suggesting actions to eliminate or at least minimize the disruption. For example, it can be determined that when a door is frequently opened over several days, this action may affect the productivity of nearby workers, thus suggesting the use of a different door or the use of the door at a specific time of day to eliminate or at least minimize the disruption.

[0147] Monitor current occupancy based on standard occupancy data within the value chain network.

[0148] Sensor system 100 can compare the occupancy of different spaces in the value chain network with standard occupancy to prevent confusion regarding the acceptable capacity of these spaces. Sensor system 100 can then determine whether the current occupancy is higher or lower than the standard occupancy of the space to ensure worker safety and prevent accidents. Standard occupancy can be the industry maximum number of workers who can safely work in the space while complying with any government rules and / or regulations (e.g., fire prevention). Furthermore, standard occupancy can also be based on providing reasonable interaction space for workers while also allowing for efficient work based on industry standards. This maximum value may vary by space or room, making the standard occupancy of an elevator space more limited compared to that of a warehouse space. Sensor system 100 can determine value chain recommendations based on occupancy data, enabling the provision of warnings when the detected occupancy exceeds the standard occupancy in the space during any time period.

[0149] Value chain network operation recommendations

[0150] Sensor system 100 can receive data including information related to various operational parameters of the value chain network over a specific historical time period (e.g., hour, day, week, 12 months). This data can also provide information about typical values ​​of various operational parameters under normal conditions. Some examples of operational parameters may include product demand, procurement lead time, productivity, inventory levels in one or more warehouses, inventory turnover, warehousing costs, average time to transport products from the warehouse to the destination shipment, total cost of product delivery, service level, etc. Sensor system 100 can use this data to provide operational recommendations when compensation for changes in operational parameters is needed, which can be shown to improve the operation and performance of the value chain network. In some examples, simulation models of the value chain network can be created based on the data. Simulation models can help visualize the value chain network as a whole and predict how changes in operational parameters will affect the operation and performance of the value chain network. In examples, the simulation model may be the sum of multiple models of different subsystems of the value chain network.

[0151] Monitoring workers' physical activities within the value chain network

[0152] Sensor system 100 may include physical process observation systems, such as those used to track the physical activities of workers that can be used to determine value chain recommendations. These include physical activities of workers (e.g., shipping workers, delivery workers, packaging workers, picking workers, assembling workers, customers, merchants, suppliers, distributors, etc.), physical interactions between workers and other workers, interactions between workers and physical entities such as machines and equipment, and interactions between physical entities and other physical entities, including but not limited to the use of video and still image cameras, motion sensing systems (e.g., including optical sensors, LiDAR, IR, and other sensor arrays), robot motion tracking systems (e.g., tracking the movement of systems attached to people or physical entities), and so on. Machine condition monitoring systems may include onboard and external monitoring of conditions, status, operating parameters, or other measurements of the condition of any value chain entity (e.g., machines or components thereof, such as machines, clients, servers, cloud resources, control systems, displays, sensors, cameras, vehicles, robots, or other machines). Sensors and cameras in or near value chain environments (such as, but not limited to, places of origin, loading docks, vehicles or current assets used to transport goods, containers, ports, distribution centers, storage facilities, warehouses, delivery vehicles and destinations), as well as other IoT data acquisition systems (including airborne sensors, sensors or other data collectors (including click-tracking sensors)), cameras used to monitor the entire environment, dedicated cameras for specific machines, processes, workers, etc., wearable cameras, portable cameras, cameras mounted on mobile robots, cameras on portable devices such as smartphones and tablets, etc.

[0153] Sensor system 100 can interact with value chain network entities based on worker data, such as worker location (including routes taken by the location, the location of a given type of worker during a given set of events, processes, etc., how workers manipulate equipment, goods, containers, packages, products, or other items using various tools, equipment, and physical interfaces, the time of worker responses to various events (e.g., responses to alarms and warnings), procedures for workers to perform planned delivery, movement, maintenance, updating, repair, and service processes, procedures for workers to fine-tune or adjust items involved in workflows, etc. The sensor system can include physical process observation, which may include tracking the worker's position, angle, force, speed, acceleration, pressure, torque, etc., when the worker operates tools on hardware, such as on containers or packaging, or on equipment involved in handling products. Such observations can be achieved through any combination of video data, data detected within machines (e.g., data on the position of machine components detected and reported by position detectors), and data collected by wearable devices (e.g., housings containing position detectors, force detectors, torque detectors, etc., for detecting physical characteristics of human workers interacting with hardware projects for the purpose of developing training datasets). Sensor system 100 can use this physical activity data and worker data (e.g., observations of physical process interactions) to determine value chain recommendations (e.g., suggested training when needed) to improve value chain workflows.

[0154] Productivity recommendations based on value chain network efficiency

[0155] Sensor system 100 can determine value chain recommendations, including productivity recommendations, based on efficiency-related information. Based on worker output and efficiency monitored by sensor system 100 over these time periods, productivity can be based on occupancy levels per hour, day, week, etc. Furthermore, sensor system 100 can use RFID and asset tracking systems to track goods as they move through the supply chain space, and utilize time-varying occupancy data and route selection systems to improve the efficiency of route selection within and between spaces (e.g., improving transport routes between distribution buildings).

[0156] The pressure to improve value chain performance and productivity (e.g., supply chain performance) is increasing. Specifically, customer expectations for delivery speed place greater pressure on improving and optimizing supply chain efficiency. Therefore, sensor system 100 can determine value chain recommendations aimed at improving supply chain productivity. Specifically, these recommendations can specifically improve speed and personalization in relation to customer expectations. For example, recommendations can provide a unified arrangement for supply and demand. In some cases, if output (e.g., productivity) may be insufficient based on the number of workers in a space, training can be recommended. For example, the productivity of one relevant space can be compared to the productivity of another space or a standard productivity. Sensor system 100 can determine that the number of workers is sufficient for the relevant workflow, and based on the comparison, the relevant space should have higher productivity. Therefore, training can be recommended and / or the workflow of the relevant space can be further automatically surveyed to identify bottlenecks and / or disruptions that may affect productivity. For example, as part of the survey, sensor system 100 can monitor the speed of workers in the space, which can be compared to workers in other spatial sections of the same workflow or workers in a standard worker section of the same workflow.

[0157] Worker resource reallocation in value chain networks

[0158] Sensor system 100 can reallocate human assets such as worker resources based on worker flow and workflow productivity. Based on occupancy data, it may be necessary to reallocate human resources, suggesting a reallocation when determining value chain recommendations if there are spaces requiring more worker assistance, or other spaces with understaffed workers (i.e., extra bandwidth or too many workers). Based on value chain recommendations, understaffed workers may be moved to spaces requiring assistance. In other examples, if low productivity is due to a lack of training, and the number of workers is reasonable for the workflow, worker training may be necessary. Typically, value chain recommendations can be determined with the goal of matching one or more demand factors with one or more supply factors to match the needs and capabilities of value chain network entities.

[0159] Eliminate or limit worker redundancy in value chain networks

[0160] Sensor system 100 can provide automated and unified coordination of supply and demand to eliminate or limit worker redundancy in value chain networks. For example, sensor system 100 can use artificial intelligence-based systems (e.g., machine learning, expert systems, self-organizing systems, and systems including such systems) to coordinate supply chain activities. The use of artificial intelligence can further enrich the emerging capabilities of adaptive systems (including Internet of Things (IoT) devices and smart products, etc.), which not only provide greater capabilities to end users but can also play a key role in the automated coordination of supply chain activities. This can be used to eliminate or at least limit redundancy, where there is too much overlap between workers performing the same task in one or more workflows. For example, in a scenario where a workflow typically requires a maximum of 6-8 workers, but currently 15 workers are involved in the same task within that workflow, sensor system 100 can determine a value chain recommendation that at least 7 workers should be removed from the workflow and moved to other workflows (i.e., worker resources are reallocated).

[0161] Monitoring the health status of workers in the value chain network

[0162] Sensor system 100 can be used to track and monitor the health status of workers in a value chain network (e.g., a logistics value chain network). For example, sensor system 100 can use a biometric system to monitor the health status of workers in the value chain space. Sensor system 100 can receive information about the health status of workers. This health information can be used to predict hazardous situations and / or prevent the spread of disease or medical disasters. Sensor system 100 can access real-time dynamic data captured by IoT devices and sensors on nearby workers to monitor and track worker health status data. These devices and sensors can support natural language capabilities, enabling them to interact with workers and answer any questions about each worker's health status. Sensor system 100 can use this health data to determine and provide value chain recommendations specific to each worker, displayed as predictions of worker health status based on the received health status data. Sensor system 100 can be configured to comply with regulatory policies (e.g., privacy policies such as HIPAA) as needed when monitoring worker health status and providing recommendations.

[0163] Sensor system 100 may include a self-organizing neural network that organizes structures or patterns in data, enabling these structures or patterns to be identified, analyzed, and labeled, for example, identifying structures as corresponding to individuals, disease conditions, health states, activity states, etc. Such networks can be used to model or represent dynamic temporal behavior, such as that involving dynamic systems, such as various disease conditions, health states, and biological systems, such as a body experiencing multiple different diseases or health conditions, where the dynamic system behavior involves complex interactions that an observer may wish to understand, diagnose, predict, control, treat, and / or optimize. For example, recurrent neural networks can be used to predict the state (e.g., maintenance state, health state, disease state, etc.) of workers (e.g., workers interacting with systems, performing actions, etc.). Sensor system 100 can use this predicted state information to determine and provide value chain recommendations to workers.

[0164] Sensor system 100 can monitor semi-perceptual problem identification, which involves only links in data and operational status of entities involved in the value chain. Problem identification can also be based on human factors, such as perceived stress levels of production supervisors, shipping workers, etc. Human factors used for semi-perceptual problem identification can be collected from sensors that facilitate the detection of human stress levels (e.g., wearable physiological sensors). Sensor system 100 can use this semi-perceptual information to determine and provide value chain recommendations to workers.

[0165] Using a digital twin-based value chain network sensor system

[0166] In some examples, sensor system 100 may use digital twins corresponding to the value chain network. Sensor system 100 may be configured to learn from training sets of results, parameters, and data collected from data sources in the value chain network, as well as data received by sensor system 100 (e.g., occupancy data), to train an artificial intelligence / machine learning system to use information from a set of digital twins. The digital twins may represent entities in the value chain network to estimate the costs and actions required for specific action processes within the value chain network.

[0167] In one example, sensor system 100 may include a warehouse twin (also known as a warehouse digital twin). A warehouse twin combines a 3D model of a warehouse with inventory and operational data, including the size, quantity, location, and demand characteristics of different products. The warehouse twin can be used to collect sensor data from the connected warehouse, as well as data on inventory and personnel movement within the warehouse. Warehouse twins can help optimize space utilization and aid in identifying and eliminating waste in warehouse operations. Using a warehouse twin to simulate the movement of products, workers, and material handling equipment allows warehouse managers to test and evaluate the potential impact of layout changes or the introduction of new equipment and processes. Sensor system 100 can use this information from the digital twin (e.g., a warehouse twin or warehouse digital twin) to determine and provide value chain recommendations for improving value chain workflows.

[0168] Warehouse Twin - Resource Reallocation

[0169] Sensor system 100 may include an exemplary warehouse digital twin suite system having a warehouse twin that can provide information on resource reallocation. The warehouse twin may reside in a virtual space representing a model of the real-world warehouse. In some examples, the warehouse twin may provide a portfolio overview of the warehouse entities in the form of a 3D information map containing all warehouse entities. Specific entities on the map can be selected to provide information on inventory, operations, and health status data. The warehouse digital twin suite system can integrate information from multiple warehouse twins and can provide a holistic view. By adjusting inventory locations and worker levels to match current or forecasted demand, the integrated view can help optimize operations across warehouse entities. Information from the warehouse digital twin suite system can be displayed. In some examples, monitoring of maximizing resource utilization can be conducted. As described above, worker resources can be reallocated, where the number of workers in one space is maximized (e.g., exceeding a threshold in terms of fill demand), while another space may require more worker resources. Sensor system 100 can use this information from a digital twin (e.g., a warehouse twin or a storage twin) to determine and provide value chain recommendations that suggest reallocating worker resources in spaces with the largest number of workers to spaces that require help / assistance.

[0170] Digital Twins - Evolution Through Training

[0171] Sensor system 100 may include analytics derived from digital twins of value chain network entities, and their interactions provide a systemic view of the value chain network and its systems, subsystems, processes, and subprocesses, which can evolve through training. This can help generate new insights into how systems and processes can evolve for the purpose of improving the performance and efficiency of various systems and processes. In an example, sensor system 100 may include a platform and application for generating and updating self-expanding digital twins representing a set of value chain entities. As more data can be collected, the self-expanding digital twin may continuously learn and expand its scope, thus potentially encountering more scenarios. Therefore, the self-expanding twin can evolve over time, undertaking more complex tasks and answering more complex questions posed by users of the self-expanding digital twin. Sensor system 100 can use this evolution to simultaneously adjust or evolve occupation-centric algorithms. Sensor system 100 can use this evolutionary information based on insights to determine and provide value chain recommendations.

[0172] Sensor system 100 can provide optimization training, such as training a neural network to optimize one or more systems based on one or more optimization methods. These methods may include Bayesian methods, parametric Bayesian classifier methods, k-nearest neighbor classifier methods, iterative methods, interpolation methods, Pareto optimization methods, algorithmic methods, etc. Feedback can be provided during the process of change and selection, for example, using a genetic algorithm that evolves one or more schemes based on feedback through a series of rounds. Sensor system 100 can use this optimization to adjust or evolve an occupation-centric algorithm based on the genetic algorithm. Sensor system 100 can use the optimization information from the neural network to determine and provide value chain recommendations.

[0173] Exemplary embodiments are provided to make this disclosure thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art. Numerous specific details, such as examples of particular components, devices, and methods, are set forth to provide a thorough understanding of embodiments of this disclosure. It will be apparent to those skilled in the art that the specific details are not required, exemplary embodiments may be presented in many different forms, and should not be construed as limiting the scope of this disclosure. In some exemplary embodiments, known processes, known device structures, and known technologies are not described in detail.

[0174] Although only a few embodiments of this disclosure have been shown and described, it will be apparent to those skilled in the art that many changes and modifications may be made to the embodiments without departing from the spirit and scope of this disclosure as described in the following claims. All patent applications and patents (both foreign and domestic) cited herein, as well as all other publications, are incorporated herein in their entirety to the full extent permitted by law.

[0175] The methods and systems described herein can be deployed, in part or in whole, on a machine on which computer software, program code, and / or instructions are executed on a processor. This disclosure can be implemented as a method on a machine, as part of a machine, or as a system or apparatus associated with a machine, or as a computer program product in a computer-readable medium that executes on one or more machines. In embodiments, the processor can be part of a server, cloud server, client, network infrastructure, mobile computing platform, fixed computing platform, or other computing platform. The processor can be any type of computing or processing device capable of executing program instructions, code, binary instructions, etc., including a central processing unit (CPU), a general-purpose processing unit (GPU), a logic board, a chip (e.g., a graphics chip, a video processing chip, a data compression chip, etc.), a chipset, a controller, a system-on-a-chip (e.g., an on-chip RF system, an on-chip AI system, an on-chip video processing system, etc.), an integrated circuit, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), an approximate computing processor, a quantum computing processor, a parallel computing processor, a neural network processor, or other types of processors. A processor can be or may include a signal processor, digital processor, data processor, embedded processor, microprocessor, or any variant such as a coprocessor (mathematical coprocessor, graphics coprocessor, communication coprocessor, video coprocessor, AI coprocessor, etc.), which can directly or indirectly facilitate the execution of program code or program instructions stored thereon. Furthermore, a processor can enable the execution of multiple programs, threads, and code. Threads can be executed concurrently to enhance processor performance and facilitate the simultaneous execution of applications. Depending on the implementation, the methods, program code, program instructions, etc., described herein can be implemented in one or more threads. Threads may spawn other threads, which may have been assigned associated priorities; the processor can execute these threads based on priorities or any other order of instructions provided in the program code. A processor or any machine utilizing it may include non-transitory memory storing the methods, code, instructions, and programs described herein and elsewhere. A processor may access a non-transitory storage medium via an interface that can store the methods, code, and instructions described herein and elsewhere. The storage medium associated with the processor for storing methods, programs, code, program instructions or other types of instructions that can be executed by a computing or processing device may include, but is not limited to, one or more of the following: CD-ROM, DVD, memory, hard disk, flash drive, RAM, ROM, cache, network-attached memory, server-based memory, etc.

[0176] The processor may include one or more cores that can enhance the speed and performance of the multiprocessor. In embodiments, the processor may be a dual-core processor, a quad-core processor, or other chip-level multiprocessors that combine two or more independent cores (sometimes referred to as wafers).

[0177] The methods and systems described herein can be deployed, in part or in whole, on machines that execute computer software on servers, clients, firewalls, gateways, hubs, routers, Infrastructure as a Service (IaaS), Platform as a Service (PaaS), or other such computer and / or network hardware or systems. The software may be associated with a server, which may include file servers, print servers, domain servers, internet servers, intranet servers, cloud servers, IaaS servers, PaaS servers, web servers, and other variations such as secondary servers, mainframe servers, distributed servers, failover servers, backup servers, server clusters, etc. A server may include one or more of the following: memory, processor, computer-readable medium, storage medium, ports (physical and virtual), communication devices, and interfaces capable of accessing other servers, clients, machines, and devices via wired or wireless media. The methods, programs, or code described herein and elsewhere may be executed by a server. Furthermore, other devices required to perform the methods as described in this application may be considered part of the infrastructure associated with the server.

[0178] The server can provide interfaces to other devices, including but not limited to clients, other servers, printers, database servers, print servers, file servers, communication servers, distributed servers, social networks, etc. Furthermore, this coupling and / or connection can facilitate remote execution of programs across networks. Networking of some or all of these devices can facilitate parallel processing of programs or methods at one or more locations without departing from the scope of this disclosure. Additionally, any device attached to the server via the interface can include at least one storage medium capable of storing methods, programs, code, and / or instructions. A central repository can provide program instructions to be executed on different devices. In this implementation, a remote repository can act as a storage medium for program code, instructions, and programs.

[0179] The software program may be associated with a client, which may include file clients, print clients, domain clients, Internet clients, intranet clients, and other variations such as auxiliary clients, host clients, distributed clients, etc. The client may include one or more of the following: memory, processor, computer-readable medium, storage medium, port (physical and virtual), communication device, and interface capable of accessing other clients, servers, machines, and devices via wired or wireless media. The methods, programs, or code described herein and elsewhere may be executed by the client. Furthermore, other devices required to perform the methods described in this application may be considered part of the infrastructure associated with the client.

[0180] The client can provide interfaces to other devices (including but not limited to servers, other clients, printers, database servers, print servers, file servers, communication servers, distributed servers, etc.). Furthermore, this coupling and / or connection can facilitate remote execution of programs across a network. Networking of some or all of these devices can facilitate parallel processing of programs or methods at one or more locations without departing from the scope of this disclosure. Additionally, any device attached to the client via the interface can include at least one storage medium capable of storing methods, programs, applications, code, and / or instructions. A central repository can provide program instructions to be executed on different devices. In this implementation, a remote repository can act as a storage medium for program code, instructions, and programs.

[0181] The methods and systems described herein can be deployed, in part or in whole, through a network infrastructure. The network infrastructure may include elements such as computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication equipment, routing devices, and other active and passive devices, modules, and / or components known in the art. Among other components, computing and / or non-computing devices associated with the network infrastructure may include storage media such as flash memory, buffers, stacks, RAM, ROM, etc. The processes, methods, program code, and instructions described herein and elsewhere can be executed by one or more network infrastructure elements. The methods and systems described herein can be used with any type of private, community, or hybrid cloud computing network or cloud computing environment, including those involving features of Software as a Service (SaaS), Platform as a Service (PaaS), and / or Infrastructure as a Service (LaaS).

[0182] The methods, program code, and instructions described herein and elsewhere can be implemented on a cellular network with multiple cells. The cellular network can be a frequency division multiple access (FDMA) network or a code division multiple access (CDMA) network. A cellular network can include mobile devices, cellular sites, base stations, repeaters, antennas, towers, etc. The cellular network can be GSM, GPRS, 3G, 4G, 5G, LTE, EVDO, mesh, or other network types.

[0183] The methods, program code, and instructions described herein and elsewhere can be implemented on or through mobile devices. Mobile devices may include navigation devices, cellular phones, mobile phones, mobile personal digital assistants, laptops, handheld computers, netbooks, pagers, e-book readers, music players, etc. Among other components, these devices may include storage media such as flash memory, buffers, RAM, ROM, and one or more computing devices. The computing device associated with the mobile device can be enabled to execute program code, methods, and instructions stored thereon. Alternatively, the mobile device may be configured to cooperate with other devices to execute instructions. The mobile device may communicate with a base station, which interacts with a server interface and is used to execute program code. The mobile device may communicate on peer-to-peer networks, mesh networks, or other communication networks. Program code may be stored on storage media associated with a server and executed by a computing device embedded within the server. A base station may include a computing device and storage media. The storage device may store program code and instructions executed by a computing device associated with the base station.

[0184] Computer software, program code, and / or instructions can be stored and / or accessed on machine-readable media, which may include: computer components, devices, and recording media that retain digital data of calculations for a sustained period of time; semiconductor memory, known as random access memory (RAM); mass storage typically used for more permanent storage, such as optical discs, magnetic storage in the form of hard disks, magnetic tapes, drum media, cards, and other types; processor registers, cache memory, volatile memory, and non-volatile memory; optical storage, such as CDs and DVDs; removable media, such as flash memory (e.g., USB flash drives or keys), floppy disks, magnetic tapes, paper tapes, punched cards, stand-alone RAM disks, zip drives, removable mass storage, offline storage, etc.; and other computer storage, such as dynamic memory, static memory, read / write memory, variable memory, read-only memory, random access memory, sequential access memory, location-addressable memory, file-addressable memory, content-addressable memory, network memory, network storage, NVMe accessible memory, PCIe-connected memory, distributed storage, etc.

[0185] The methods and systems described herein can transform physical and / or intangible articles from one state to another. The methods and systems described herein can also transform data representing physical and / or intangible articles from one state to another.

[0186] The elements described and depicted herein, including the flowcharts and block diagrams throughout the accompanying drawings, suggest logical boundaries between elements. However, according to software or hardware engineering practice, the depicted elements and their functions can be implemented on a machine using a processor with computer-executable code, capable of executing program instructions stored thereon as a monolithic software architecture, as a standalone software module, or as a module employing external routines, code, services, etc., or any combination thereof, and all such implementations are within the scope of this disclosure. Examples of such machines may include, but are not limited to, personal digital assistants, laptop computers, personal computers, mobile phones, other handheld computing devices, medical devices, wired or wireless communication devices, transducers, chips, calculators, satellites, tablets, e-books, small parts, electronic devices, devices with artificial intelligence, computing devices, network devices, servers, routers, etc. Furthermore, the elements or any other logical components depicted in the flowcharts and block diagrams can be implemented on a machine capable of executing program instructions. Therefore, although the foregoing figures and descriptions illustrate functional aspects of the disclosed system, no specific arrangement of software used to implement these functional aspects should be inferred from these descriptions unless explicitly stated or clearly understood from the context. Similarly, it should be understood that the steps identified and described above may be altered, and the order of the steps may be adapted to a specific application of the technology disclosed herein. All such changes and modifications are intended to fall within the scope of this disclosure. Therefore, the explanation and / or description of the order of the steps should not be construed as requiring these steps to be performed in a specific order, unless required by a specific application, or explicitly stated or clearly apparent from the context.

[0187] The methods and / or processes described above, and the steps associated therewith, can be implemented in hardware, software, or any combination of hardware and software suitable for a particular application. Hardware may include general-purpose computers and / or special-purpose computing devices, or specific aspects or components of a particular computing device. These processes can be implemented in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors, or other programmable devices, as well as internal and / or external memory. These processes may also be embodied, or alternatively, in application-specific integrated circuits, programmable gate arrays, programmable array logic, or any other device or combination of devices that can be configured to process electronic signals. It should also be understood that one or more processes can be implemented as computer-executable code capable of executing on a machine-readable medium.

[0188] Computer executable code can be created using structured programming languages ​​(such as C), object-oriented programming languages ​​(such as C++), or any other high- or low-level programming languages ​​(including assembly language, hardware description languages, and database programming languages ​​and techniques). These stored languages ​​can be stored, compiled, or interpreted to run on one of the aforementioned devices, as well as on heterogeneous combinations of processors, processor architectures, or combinations of different hardware and software, or on any other machine capable of executing program instructions. Computer software can utilize virtualization, virtual machines, containers, terminal facilities, container quays, and other capabilities.

[0189] Therefore, in one aspect, the methods and combinations thereof described above can be embodied in computer-executable code, which, when executed on one or more computing devices, performs its steps. In another aspect, the methods can be embodied in a system that performs its steps and can be distributed across devices in various ways, or all functionality can be integrated into a dedicated, stand-alone device or other hardware. In yet another aspect, means for performing the steps associated with the above-described processes can include any of the aforementioned hardware and / or software. All these permutations and combinations are intended to fall within the scope of this disclosure.

[0190] While this disclosure has been made in conjunction with preferred embodiments shown and described in detail, various modifications and improvements will become apparent to those skilled in the art. Therefore, the spirit and scope of this disclosure are not limited to the foregoing examples, but should be understood in the broadest sense permitted by law.

[0191] In the context of describing this disclosure (particularly in the context of the claims), the terms “a,” “an,” and “the,” and similar indicative terms, should be interpreted as encompassing both the singular and plural, unless otherwise stated herein or clearly contradicted by the context. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (i.e., meaning “including but not limited to”). Unless otherwise stated herein, descriptions of numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into this specification as if it were separately referenced herein. Unless otherwise stated herein or clearly contradicted by the context, all methods described herein may be performed in any suitable order. Unless otherwise stated, the use of any and all example or exemplary language (e.g., “such as”) provided herein is intended only to better illustrate this disclosure and does not constitute a limitation on the scope of this disclosure. The term “group” can include a group having a single member. No language in the specification should be construed as indicating that any unclaimed element is essential to the practice of this disclosure.

[0192] While the foregoing written description enables those skilled in the art to create and use content that is currently considered the best available model, those skilled in the art will understand and appreciate the existence of variations, combinations, and equivalents of the specific embodiments, methods, and examples described herein. Therefore, this disclosure should not be limited to the foregoing embodiments, methods, and examples, but rather to all embodiments and methods within the scope and spirit of this disclosure.

[0193] All documents referenced in this document are incorporated herein by reference as if they were presented in their entirety.

Claims

1. A sensor system for determining occupancy in a space, comprising: A transmitter wireless device that transmits radio signals through a channel in the space; A receiver wireless device that receives the transmitted radio signals that have been propagated through the space; as well as At least one processor implements an occupancy-centric algorithm that determines occupancy in the space based on the radio signal, wherein the at least one processor performs the following operations: Channel state information is determined based on the radio signals transmitted through the channel; The occupancy status in the space is determined based on the channel state information; Output an occupancy signal based on the determined occupancy status; as well as The occupancy-centric algorithm is configured to determine the occupancy status in the space based on changes in the amplitude spread of the radio signal; The radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing amplitude information associated with the one or more subcarriers, and (ii) determining the occupancy in the space based at least on the amplitude information; The amplitude information includes at least amplitude expansion; The processor is also used to generate value chain recommendations based on the detected occupancy.

2. The sensor system of claim 1, wherein the at least one processor is integrated with the receiver wireless device.

3. The sensor system of claim 1, wherein the at least one processor is integrated with the transmitter radio device.

4. The sensor system of claim 1 further includes a computing device, wherein the at least one processor is integrated with the computing device.

5. The sensor system according to claim 1, wherein the at least one processor outputs a control signal to the control system.

6. The sensor system of claim 5, wherein the control system is associated with a heating, ventilation, or cooling system for the space.

7. The sensor system of claim 5, wherein the control system is associated with a safety system of the space.

8. The sensor system of claim 5, wherein the control system is associated with the lighting system of the space.

9. The sensor system of claim 5, wherein the control system is associated with the power system of the space.

10. The sensor system of claim 5, wherein the control system is associated with the entertainment system of the space.

11. The sensor system of claim 1, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the standard deviation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based at least on the standard deviation of the amplitude and phase signals.

12. The sensor system of claim 1, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the time and frequency correlation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based at least on the time and frequency correlation of the amplitude and phase signals.

13. The sensor system of claim 1, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the average values ​​of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based at least on the average values ​​of the amplitude and phase signals.

14. The sensor system of claim 1, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the energy in the peaks of the CSI amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based at least on the energy in the peaks of the CSI amplitude and phase signals.

15. The sensor system of claim 1, wherein the occupancy-centered algorithm is configured to determine occupancy in the space based on changes in one or more of the following: signal amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, or energy expansion variation of the radio signal.

16. A method for determining occupancy in a space, the method comprising: Radio signals are transmitted through channels in the space; Receive the transmitted radio signal that has been propagated through the space; as well as An occupancy-centric algorithm is implemented using at least one processor, the processor performing the following operations: determining occupancy status in the space based on the radio signal; determining channel state information based on the radio signal transmitted through the channel; determining occupancy status in the space based on the channel state information; and outputting an occupancy signal based on the determined occupancy status; The radio signal includes one or more subcarriers, and the at least one processor performs the following operations: (i) analyzing amplitude information associated with the one or more subcarriers, and (ii) determining the occupancy in the space based at least on the amplitude information; The amplitude information includes at least amplitude expansion; The processor is also used to generate value chain recommendations based on the detected occupancy.

17. The method of claim 16, wherein the at least one processor is integrated with a receiver radio device that receives the transmitted radio signal that has been propagated through the space.

18. The method of claim 16, wherein the at least one processor is integrated with a transmitter radio device that transmits radio signals through the channel in the space.

19. The method of claim 16, further comprising using the at least one processor to output a control signal to a control system, wherein the control system is at least associated with a heating, ventilation, or cooling system of the space.

20. The method of claim 16, further comprising using the at least one processor to output a control signal to a control system, wherein the control system is associated with a safety system of the space.

21. The method of claim 16, further comprising using the at least one processor to output a control signal to a control system, wherein the control system is associated with a lighting system of the space.

22. The method of claim 16, further comprising using the at least one processor to output a control signal to a control system, wherein the control system is associated with a power system of the space.

23. The method of claim 16, further comprising using the at least one processor to output a control signal to a control system, wherein the control system is associated with an entertainment system of the space.

24. The method of claim 16, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the standard deviations of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based at least on the standard deviations of the amplitude and phase signals.

25. The method of claim 16, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the time and frequency correlation of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining, at least based on the time and frequency correlation of the amplitude and phase signals, the occupancy in the space.

26. The method of claim 16, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the average values ​​of amplitude and phase signals associated with the one or more subcarriers, and (ii) determining occupancy in the space based at least on the average values ​​of the amplitude and phase signals.

27. The method of claim 16, wherein the radio signal comprises one or more subcarriers, and wherein the at least one processor performs the following operations: (i) analyzing the energy in the peak values ​​of the CSI amplitude and phase signals associated with the one or more subcarriers, and (ii) determining the occupancy in the space based at least on the energy in the peak values ​​of the CSI amplitude and phase signals.

28. The method of claim 16, wherein the occupancy-centered algorithm is adapted to determine occupancy in the space based on changes in one or more of the following: signal amplitude, energy, amplitude variation, energy variation, amplitude expansion, energy expansion, amplitude expansion variation, or energy expansion variation of the radio signal.

29. A sensor system for determining occupancy in a space, comprising: A transmitter wireless device that transmits radio signals through a channel in the space; A receiver wireless device that receives the transmitted radio signals that have been propagated through the space; as well as At least one processor implements an occupancy-centric algorithm that determines occupancy in the space based on the radio signal, wherein the at least one processor performs the following operations: Channel state information is determined based on the radio signals transmitted through the channel; The occupancy status in the space is determined based on the channel state information; Value chain recommendations are determined based on the occupancy status of the space within the value chain network. as well as Based on the determined occupancy status and the value chain recommendation, an occupancy signal is output.

30. The sensor system of claim 29, wherein the value chain recommendation involves the health status of one or more workers.

31. The sensor system of claim 29, wherein the value chain recommendation involves allocating or reallocating worker resources based on the occupancy status in the space.

32. The sensor system of claim 29, wherein the value chain recommendation is measured based on the productivity of workers in the space.

33. The sensor system of claim 29, wherein the value chain recommendation is associated with at least one of the activation or deactivation of at least one of a heating system, ventilation system, refrigeration system, security system, lighting system, kitchen system, speaker system, power system, or entertainment system for the space.

34. The sensor system of claim 29, wherein the occupancy-centric algorithm evolution causes the value chain recommendation to be redefined based on the evolution of the occupancy-centric algorithm.

35. The sensor system of claim 29, wherein the value chain recommendation is determined at least by a machine learning system based on a trained machine learning model, and wherein the machine learning model outputs logistics design recommendations based on a training dataset, wherein each training dataset defines one or more features of the corresponding logistics system or results related to the corresponding logistics system.

36. The sensor system of claim 29, wherein the value chain recommendation is determined based on an artificial intelligence system, the artificial intelligence system receiving a request for a logistics system design recommendation and determining the logistics system design recommendation based on one or more machine learning models and the request.

37. The sensor system of claim 29, wherein the value chain recommendation is determined by a digital twin system, the digital twin system generating an environmental digital twin of the logistics environment combined with the logistics system design recommendation and one or more physical asset digital twins, wherein the digital twin system performs simulation based on the logistics environment digital twin and the one or more physical asset digital twins.

38. The sensor system of claim 29, wherein the value chain recommendation is based on logistic factors, which include one or more of the following: product type corresponding to the proposed logistic solution, one or more characteristics of the product type, location of manufacturing location, location of distribution agency, location of warehouse, location of customer base, proposed expansion area of ​​organization, or supply chain characteristics.

39. The sensor system of claim 29, wherein the value chain recommendation is based on one or more logistics value chain network entities, the logistics value chain network entities including the following related entities: products, suppliers, manufacturers, producers, retailers, enterprises, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, dealers, supply chain infrastructure, supply chain processes, logistics processes, reverse logistics processes, demand forecasting processes, demand management processes, demand aggregation processes, machines, ships, warehouses, seaports, airports, waterways, highways, railways, bridges, tunnels, online retailers, e-commerce sites, demand factors, supply factors, transportation systems, current assets, place of origin, destination, storage point, point of use, network, information technology system, software platform, distribution center, operations center, containers, container handling equipment, customs, export control, border control, drones, robots, autonomous vehicles, haulage facilities, waterway and port infrastructure.

40. The sensor system of claim 39, wherein the supply chain infrastructure includes one or more of the following related facilities: ships, seaports, cranes, containers, container handling facilities, shipyards, dry docks, warehouses, distribution facilities, operating facilities, refueling and refueling facilities, waste disposal facilities, food supply, beverage supply, drones, robots, autonomous vehicles, aircraft, automobiles, trucks, trains, elevators, forklifts, hauling facilities, conveyors, loading docks, waterways, bridges, tunnels, airports, garages, stations, railway stations, weighing stations, inspection facilities, roads, railways, customs or border control facilities.

41. The sensor system of claim 29, wherein the value chain recommendation is based on one or more of the following supply factors: component availability, material availability, component location, material location, component pricing, material pricing, taxes, import regulations, export regulations, border controls, trade regulations, customs, navigation, traffic, congestion, vehicle capacity, ship capacity, container capacity, parcel capacity, vehicle availability, ship availability, container availability, parcel availability, vehicle location, ship location, container location, port location, port availability, port capacity, storage availability, storage capacity, warehouse availability, warehouse capacity, operations center location, operations center availability, operations center capacity, asset owner identity, system compatibility, worker availability, worker skills, worker work location, commodity pricing, fuel pricing, energy pricing, route availability, route distance, route cost, or route safety factors.

42. The sensor system of claim 29, wherein the value chain recommendation is determined at least based on a machine learning / artificial intelligence system, which determines the problem state based on detected levels of human stress in the supply chain.

43. The sensor system of claim 29, wherein the value chain recommendation is determined at least based on the interruption situation in the space of the value chain network.

44. The sensor system of claim 29, wherein the value chain recommendation includes operational recommendations required to compensate for changes in operating parameters.

45. The sensor system of claim 29, wherein the value chain recommendation is determined at least based on physical activity data and worker data to improve value chain workflow.

46. ​​The sensor system of claim 29, wherein the value chain recommendation includes suggestions for eliminating or limiting worker redundancy in the workflow.

47. A method for determining occupancy in a space, the method comprising: Radio signals are transmitted through channels in the space; Receive the transmitted radio signal that has been propagated through the space; as well as An occupancy-centric algorithm is implemented using at least one processor, the occupancy-centric algorithm being configured to: determine the occupancy status in the space based on the radio signal; and determine channel state information based on the radio signal transmitted through the channel; The occupancy status in the space is determined based on the channel state information; a value chain recommendation is determined based on the occupancy status in the space of the value chain network; and an occupancy signal is output based on the determined occupancy status and the value chain recommendation.

48. The method of claim 47, wherein the value chain recommendation involves the health status of one or more workers.

49. The method of claim 47, wherein the value chain recommendation involves allocating or reallocating worker resources based on the occupancy status of the space.

50. The method of claim 47, wherein the value chain recommendation is based at least on the productivity of workers in the space.

51. The method of claim 47, wherein the value chain recommendation is associated with at least one of the activation or deactivation of at least one of a heating system, ventilation system, refrigeration system, security system, lighting system, kitchen system, speaker system, electrical system, or entertainment system for the space.

52. The method of claim 47, wherein the occupancy-centric algorithmic evolution causes the value chain recommendation to be redefined based on the evolution of the occupancy-centric algorithm.

53. The method of claim 47, wherein the value chain recommendation is determined by a machine learning system based on a machine learning model trained thereon, the machine learning model outputting logistics design recommendations based at least on a training dataset, wherein each training dataset defines one or more features of a corresponding logistics system or results related to the corresponding logistics system.

54. The method of claim 47, wherein the value chain recommendation is at least determined based on an artificial intelligence system, the artificial intelligence system receiving a request for a logistics system design recommendation and determining the logistics system design recommendation based on one or more machine learning models or the request.

55. The method of claim 47, wherein the value chain recommendation is determined by a digital twin system, the digital twin system generating an environmental digital twin of the logistics environment combined with the logistics system design recommendation and one or more physical asset digital twins of the physical assets, wherein the digital twin system performs simulation based at least on the logistics environment digital twin and the one or more physical asset digital twins.

56. The method of claim 47, wherein the value chain recommendation is based at least on logistic factors, which include one or more of the following: product type corresponding to the proposed logistic solution, one or more characteristics of the product type, location of manufacturing location, location of distribution facilities, location of warehouses, location of customer groups, proposed expansion areas of the organization, or supply chain characteristics.

57. The method of claim 47, wherein the value chain recommendation is based at least on logistics value chain network entities, which are associated with the following entities: products, suppliers, manufacturers, producers, retailers, enterprises, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, dealers, supply chain infrastructure, supply chain processes, logistics processes, reverse logistics processes, demand forecasting processes, demand management processes, demand aggregation processes, machines, ships, warehouses, seaports, airports, waterways, highways, railways, bridges, tunnels, online retailers, e-commerce sites, demand factors, supply factors, transportation systems, current assets, place of origin, destination, storage point, point of use, network, information technology system, software platform, distribution center, operations center, containers, container handling equipment, customs, export controls, border controls, drones, robots, autonomous vehicles, haulage facilities, waterway or port infrastructure.

58. The method of claim 47, wherein the supply chain infrastructure comprises one or more of the following facilities: ships, seaports, cranes, containers, container handling facilities, shipyards, dry docks, warehouses, distribution facilities, operating facilities, refueling and refueling facilities, waste disposal facilities, food supply, beverage supply, drones, robots, autonomous vehicles, aircraft, automobiles, trucks, trains, elevators, forklifts, haulage facilities, conveyors, loading docks, waterways, bridges, tunnels, airports, garages, stations, railway stations, weighing stations, inspection facilities, roads, railways, customs or border control facilities.

59. The method of claim 47, wherein the value chain recommendation is based on one or more of the following supply factors: component availability, material availability, component location, material location, component pricing, material pricing, taxes, import regulations, export regulations, border controls, trade regulations, customs, navigation, traffic, congestion, vehicle capacity, ship capacity, container capacity, parcel capacity, vehicle availability, ship availability, container availability, parcel availability, vehicle location, ship location, container location, port location, port availability, port capacity, storage availability, storage capacity, warehouse availability, warehouse capacity, operations center location, operations center availability, operations center capacity, asset owner identity, system compatibility, worker availability, worker skills, worker work location, commodity pricing, fuel pricing, energy pricing, route availability, route distance, route cost, or route safety factors.

60. The method of claim 47, wherein the value chain recommendation is determined at least based on a machine learning / artificial intelligence system, which determines the problem state based on detected levels of human stress in the supply chain.

61. The method of claim 47, wherein the value chain recommendation is determined at least based on the disruption situation in the space of the value chain network.

62. The method of claim 47, wherein the value chain recommendation includes operation recommendations required to compensate for changes in operating parameters.

63. The method of claim 47, wherein the value chain recommendation is determined based on at least one of physical activity data or worker data to improve value chain workflow.

64. The method of claim 47, wherein the value chain recommendation includes recommendations for eliminating or limiting worker redundancy in the workflow.

Images