Position detection inside network

Abstract

To provide a system and a method for detecting presence of a human body in a network without any reference elements.SOLUTION: A system and a method use signal absorption of RF waves and forward and reflection rearward scattering of signals caused by the presence of a biological mass body in a communication network. Each node (107) in a detection network (103) constantly receives transmission without any change, and may receive it essentially continuously in a network that is used with a high frequency. Therefore, by using the detection network (103), the presence and / or position of a biological mass body (104) or (105) disposed physically within a transmission range of the network (103) can be calculated. Since the presence of a human body affects characteristics of a signal transmitted between at least two nodes (107) in the network (103), such a presence can be detected by monitoring so as to find a change in such characteristics.SELECTED DRAWING: Figure 1

Description

Background Art

[0001] Reference to Related Applications This application claims the benefit of U.S. Provisional Patent Application No. 62 / 252,954, filed on September 9, 2015, and U.S. Provisional Patent Application No. 62 / 219,457, filed on September 16, 2015, and is a continuation of U.S. Patent Application No. 15 / 084,002, filed on March 29, 2016, and currently pending, and claims the priority of U.S. Patent Application No. 15 / 227,717, filed on August 3, 2016, and currently pending. The entire disclosure of the above documents is incorporated herein by reference.

Technical Field

[0002] 1. Technical Field The present disclosure relates to the field of object detection, and more particularly to systems and methods for detecting the presence of a biological mass within a wireless communication network.

[0003] 2. Description of Related Technology Object tracking can be performed using a number of techniques. For example, a mobile transceiver may be attached to an object. Examples of such systems include global positioning position systems such as GPS that use orbiting satellites to communicate with ground transceivers. However, such systems are generally less effective and less accurate indoors where satellite signals may be blocked. Thus, other technologies such as Bluetooth® beacons are often used indoors, which calculate the position of roaming or unknown transceivers. This roaming transceiver acts as a fiducial element.

[0004] These systems have several disadvantages, such as the need for the object being tracked to include a transceiver. In some applications, the object to be tracked does not have such a fiducial element or may actively disable any such element, such as an intruder into a dwelling.

[0005] There are also other techniques that can detect and track objects without using reference elements. For example, radar is a venerable object detection system that uses RF waves to identify the range, angle, or velocity of objects, including aircraft, ships, spacecraft, guided missiles, motor vehicles, weather formations, and terrain. Radar operates by transmitting electromagnetic waves and generally uses radio frequency ("RF") waves of the electromagnetic spectrum that are reflected from any object in their path. The receiver, typically part of the same system as the transmitter, receives and processes these reflected waves to examine the characteristics of the object. Other systems similar to radar that use other parts of the electromagnetic spectrum, such as ultraviolet, visible, or near-infrared light from a laser, can also be used in a similar manner.

[0006] Radar technology does not require reference elements but has other drawbacks. For example, radar beams are susceptible to noise in the signal or irregular fluctuations in the signal due to internal electrical components, as well as noise and interference from external sources such as natural background radiation. Radar is also vulnerable to external clutter sources such as intervening objects that block the beam path and can be deceived by objects of certain sizes, shapes, and orientations. SUMMARY OF THE INVENTION

[0007] The following is a summary of the invention for the purpose of providing a basic understanding of some aspects of the invention. This summary is not intended to identify key or essential elements of the invention or to delineate the scope of the invention. The sole purpose of this section is to present some concepts of the invention in a simplified form as an introduction to the more detailed description that follows.

[0008] For these and other problems in the field of the present invention, one of the things described herein is a method for detecting the presence of a human being, the method comprising: providing a first transceiver disposed at a first position within a detection area; providing a second transceiver disposed at a second position within the detection area; a computer server communicatively coupled to the first transceiver; the first transceiver receiving a first set of wireless signals from the second transceiver via the wireless communication network; the computer server receiving a first set of signal data from the first transceiver, the first set of signal data including data regarding the characteristics of the first set of wireless signals, the characteristic data being generated as part of the normal operation of the first transceiver on the communication network; the computer server generating a baseline signal profile regarding the communication from the second transceiver to the first transceiver, the baseline signal profile being at least partially based on the wireless signal characteristics of the received first set of signal data and representing the characteristics of the wireless transmission from the second transceiver to the first transceiver when no human is present in the detection area; the first transceiver receiving a second set of wireless signals from the second transceiver via the wireless communication network; the computer server receiving a second set of signal data from the first transceiver, the second set of signal data including data regarding the characteristics of the second set of wireless signals, the characteristic data being generated as part of the normal operation of the first transceiver on the communication network; and the computer server determining whether a human is present within the detection area, the determination being at least partially based on a comparison of the wireless signal characteristics of the received second set of wireless signal data with the baseline signal profile.

[0009] In one embodiment of the method, the first set of signal characteristics includes wireless network signal protocol characteristics identified by the first transceiver.

[0010] In another embodiment of the method, the wireless network signal protocol characteristics are selected from the group consisting of received signal strength, latency, and bit error rate.

[0011] In another embodiment of the method, the method comprises the steps of: providing a third transceiver disposed at a third position within the detection area; the first transceiver receiving a third set of wireless signals from the third transceiver via the wireless communication network; the computer server receiving a third set of signal data from the first transceiver, the third set of signal data including data regarding the characteristics of the third set of wireless signals, the characteristic data being generated as part of the normal operation of the first transceiver on the communication network; the computer server generating a second baseline signal profile regarding the communication from the third transceiver to the first transceiver, the second baseline signal profile being at least partially based on the wireless signal characteristics of the received third set of signal data and representing the characteristics of the wireless transmission from the third transceiver to the first transceiver when no human is present in the detection area; the first transceiver receiving a fourth set of wireless signals from the third transceiver via the wireless communication network; the computer server receiving a fourth set of signal data from the first transceiver, the fourth set of signal data including data regarding the characteristics of the fourth set of wireless signals, the characteristic data being generated as part of the normal operation of the first transceiver on the communication network; and in the determining step, the computer server determining whether a human is present within the detection area based at least in part on a comparison of the wireless signal characteristics of the received fourth set of wireless signal data with the second baseline signal profile.

[0012] In another embodiment of the method, the determining step applies a statistical method to the second set of wireless signal data to determine the presence of a human.

[0013] In another embodiment of the method, the method includes the step of the computer server continuously determining the presence or absence of a human in the detection area, the determination being at least partially based on a comparison of the baseline signal profile with signal data including data regarding characteristics of the first set of wireless signals continuously received at the computer server from the first transceiver; and the computer further includes the step of continuously updating the baseline signal profile based on the continuously received signal data when the continuously received signal data indicates the absence of a human in the detection area.

[0014] In another embodiment of the method, the method further includes the step of the computer server identifying the number of humans present in the detection area, the identification being at least partially based on a comparison of the received second set of signal characteristics with the baseline signal profile.

[0015] In another embodiment of the method, the method further includes the step of the computer server identifying the location of one or more humans present in the detection area, the identification being at least partially based on a comparison of the received second set of signal characteristics with the baseline signal profile.

[0016] In another embodiment of the method, the method further includes the step of the computer server being operably coupled to a second system; the computer operates the second system only after the computer server detects the presence of a human in the detection area.

[0017] In another embodiment of the method, the detection network and the second system are configured to communicate using the same communication protocol.

[0018] In another embodiment of the method, the second system is an electrical system.

[0019] In another embodiment of the method, the second system is an illumination system.

[0020] In another embodiment of the method, the second system is a heating, ventilation, and air conditioning (HVAC) system.

[0021] In another embodiment of the method, the second system is a security system.

[0022] In another embodiment of the method, the second system is an industrial automation system.

[0023] In another embodiment of the method, the wireless communication protocol is selected from the group consisting of Bluetooth®, Bluetooth® Low Energy, ANT, ANT+, Wi-Fi, ZigBee, and Z-Wave.

[0024] In another embodiment of the method, the wireless communication network has a carrier frequency in the range from 850 MHz to 17.5 GHz.

[0025] In another embodiment of the method, the determination of whether a human is present in the detection area is adjusted based on machine learning, which includes: identifying a first sample position of a human with a reference element in the detection area, where the first sample position is identified based on the detection of the reference element; identifying a second sample position of the human in the detection area, where the second sample position is identified without using the reference element based at least in part on a comparison of the received second set of signal data with the baseline signal profile; comparing the first sample position with the second sample position; and adjusting the identifying step based on non-reference element positions to improve the position calculation ability of the system, where the adjustment is based on the comparing step.

[0026] In another embodiment of the method, the method comprises the step of the computer server storing a plurality of historical data records indicating whether a human has been present in the detection area for a certain period of time, each of the historical data records including an indication of the number of humans detected in the detection area and the date and time when the number of humans was detected in the detection area, and the step of the computer server making the historical data records available via an interface to one or more external computer systems.

[0027] One of the things further described in this specification is a method for detecting the presence of a human, the method comprising: preparing a first transceiver disposed at a first position within a detection area; preparing a second transceiver disposed at a second position within the detection area; a computer server communicatively coupled to the first transceiver; preparing a first external system operably coupled to the computer server; preparing a second external system operably coupled to the computer server; the computer server receiving a set of baseline signal data from the first transceiver, the set of baseline signal data including characteristic data regarding signal characteristics of a first set of wireless signals received by the first transceiver from the second transceiver when no human is present within the detection area, the characteristic data being generated by the first transceiver as part of normal operation of the first transceiver on the communication network, receiving; the computer server generating a baseline signal profile regarding communication from the second transceiver to the first transceiver when no human is present within the detection area, the baseline signal profile being generated at least in part based on the characteristic data representing the characteristics of wireless transmission from the second transceiver to the first transceiver when no human is present in the detection area, generating; the computer server receiving a first set of sample baseline signal data from the first transceiver, the first set of sample baseline signal data including characteristic data regarding signal characteristics of a second set of wireless signals received by the first transceiver from the second transceiver when a human is present within the detection area, the characteristic data being generated by the first transceiver as part of normal operation of the first transceiver on the communication network, receiving;When a human is present in the detection area, the computer server generates a first sample baseline signal profile for communication from the second transceiver to the first transceiver, wherein the first sample baseline signal profile is at least partially based on the characteristic data of the first set of sample baseline signal data representing the characteristics of wireless transmission from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receives a second set of sample baseline signal data from the first transceiver, wherein the second set of sample baseline signal data includes characteristic data regarding the signal characteristics of a third set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, and the characteristic data is generated by the first transceiver as part of the normal operation of the first transceiver on the communication network; when a human is present in the detection area, the computer server generates a second sample baseline signal profile for communication from the second transceiver to the first transceiver, wherein the second sample baseline signal profile is at least partially based on the characteristic data of the second set of sample baseline signal data representing the characteristics of wireless transmission from the second transceiver to the first transceiver when a human is present in the detection area; the computer server receives a third set of sample baseline signal data from the first transceiver, wherein the third set of sample baseline signal data includes characteristic data regarding the signal characteristics of a fourth set of wireless signals received by the first transceiver from the second transceiver when a human is present in the detection area, and the characteristic data is generated by the first transceiver as part of the normal operation of the first transceiver on the communication network;Based on the determination by the computer server that the characteristic data of the third set of sample baseline signal data matches the first sample baseline signal profile, the computer server determines to operate the first external system; and based on the determination by the computer server that the characteristic data of the third set of sample baseline signal data does not match the second sample baseline signal profile, the computer server determines not to operate the second external system.

[0028] In another embodiment of the method, the determination to operate the first external system and the determination not to operate the second external system are adjusted based on machine learning, which includes: identifying a first sample position of a human with a reference element within the detection area, where the first sample position is identified based on the detection of the reference element; identifying a second sample position of the human within the detection area, where the second sample position is identified without using the reference element based at least in part on a comparison of the received second set of signal data with the baseline signal profile; comparing the first sample position with the second sample position; and adjusting the identifying step based on a non-reference element position to improve the position calculation ability of the system, and the adjustment is based on the comparing step.

[0029] In another embodiment of the method, the characteristic data of the wireless signal includes data related to signal characteristics selected from the group consisting of received signal strength, latency, and bit error rate.

[0030] In another embodiment of the method, the computer server generates the first sample baseline signal profile by applying a statistical method to the first set of sample baseline signal data, and the computer server generates the second sample baseline signal profile by applying a statistical method to the second set of sample baseline signal data.

[0031] In another embodiment of the method, the method comprises: receiving, by the computer server, an additional set of baseline signal data from the first transceiver, the additional set of signal data including characteristic data regarding signal characteristics of a second set of wireless signals received by the first transceiver from the second transceiver, the characteristic data being generated by the first transceiver as part of normal operation of the first transceiver on the communication network; and updating, by the computer server, the baseline signal profile based on the continuously received additional set of baseline signal data when the continuously received additional set of baseline signal data indicates the absence of humans in the detection area.

[0032] The method according to claim 20, further comprising: receiving, by the computer server, a set of signal data from the first transceiver, the set of signal data including characteristic data regarding signal characteristics of a second set of wireless signals received by the first transceiver from the second transceiver when one or more humans are present in the detection area, the characteristic data being generated by the first transceiver as part of normal operation of the first transceiver on the communication network; and determining, by the computer server, the quantity of humans present in the detection area based at least in part on a comparison of the set of signal data with the baseline signal profile.

[0033] In another embodiment of the method, the method further includes identifying the position of each of the one or more humans present within the detection region, the identifying being at least partially based on a comparison of the set of signal data to the baseline signal profile.

[0034] In another embodiment of the method, even when the characteristic data of the third set of sample baseline signal data matches the second sample baseline signal profile when a human is present within the detection region, the computer server determines that a human is present within the detection region and operates the first external system.

[0035] In another embodiment of the method, only when the characteristic data of the third set of sample baseline signal data matches the second sample baseline signal profile when a human is present within the detection region, the computer server determines that a human is present within the detection region and operates the second external system.

[0036] In another embodiment of the method, the wireless communication network comprises a carrier frequency in the range from 850 MHz to 17.5 GHz.

[0037] In another embodiment of the method, the method further includes the computer server storing a plurality of historical data records indicating whether a human has been present within the detection region for a certain period of time, each of the historical data records including an indication of the number of humans detected within the detection region and the date and time when the number of humans was detected within the detection region, and the computer server making the historical data records available via an interface to one or more external computer systems.

Brief Description of the Drawings

[0038]

Figure 1

Figure 2

DETAILED DESCRIPTION OF THE INVENTION

[0039] BEST MODE FOR CARRYING OUT THE INVENTION The following detailed description and disclosure are illustrative and not restrictive. This description enables those skilled in the art to clearly manufacture and use the disclosed system and method, and describes some embodiments, adjustments, changes, modifications, and uses of the disclosed system and method. Since various changes can be made to the above configuration without departing from the scope of the present disclosure, all matters included in this description or shown in the accompanying drawings should be construed as illustrative and not in a limiting sense.

[0040] Generally, this specification describes systems and methods for detecting the presence of objects in a network without reference elements. Generally, the systems and methods described in this specification use signal absorption of RF communication and forward and reflected backscattering of signals caused by the presence of a biomass in a communication network, which is generally a mesh network.

[0041] Throughout this disclosure, the term "computer" generally refers to hardware that implements functions provided by computing capabilities associated with digital computing technologies, particularly microprocessors. The term "computer" is not intended to be limited to any specific type of computing device, but is intended to include any computing device, including but not limited to: processing devices, microprocessors, personal computers, desktop computers, laptop computers, workstations, terminals, servers, clients, portable computing devices, handheld computers, smartphones, tablet computers, mobile devices, server farms, hardware appliances, minicomputers, mainframe computers, video game consoles, handheld video game products, and wearable computing devices including but not limited to eyewear, wristwear, pendants, and clip-on devices.

[0042] As used herein, "computer" is necessarily an abstract concept of the functions provided by a single computing device equipped with the hardware and accessories characteristic of a computer in a particular role. By way of illustration and not limitation, the term "computer" with respect to a laptop computer would be understood by those skilled in the art to include functions provided by a pointer-based input device such as a mouse or trackpad, while the term "computer" with respect to an enterprise-class server would be understood by those skilled in the art to include functions provided by redundant systems such as RAID drives and dual power supplies.

[0043] Also, it is well known to those skilled in the art that the functions of a single computer may be distributed among a number of individual machines. This distribution may be functional such that a particular machine performs a particular task, or it may be a balanced form where each machine can execute most or all of the functions of any other machine and tasks are assigned based on the resources available at any given time. Thus, as used herein, the term "computer" refers to a single stand-alone self-contained device, or multiple devices operating cooperatively or independently, including but not limited to a network server farm, a "cloud" computing system, software-as-a-service, or other distributed or collaborative computer network.

[0044] One of ordinary skill in the art should also understand that a device that is not conventionally considered a "computer" may exhibit the characteristics of a "computer" in certain contexts. When such a device performs the functions of the "computer" described herein, the term "computer" includes such a device to that extent. Devices of this type include, but are not limited to, network hardware, print servers, file servers, NAS and SAN, load balancers, and any other hardware that can interact with the systems and methods described herein with respect to conventional "computers".

[0045] Throughout this disclosure, the term "software" refers to code objects, program logic, command structures, data structures and definitions, source code, executable and / or binary files, machine code, object code, compiled libraries, implementations, algorithms, libraries, or any instructions or set of instructions that are executable by a computer processor, including but not limited to a computer processor that includes a virtual processor, a runtime environment, a virtual machine, and / or an interpreter, or that can be converted into an executable form by the foregoing. One of ordinary skill in the art will understand that software can be incorporated or embedded in hardware, including but not limited to a microchip, and still be considered "software" in the context of this disclosure. For the purposes of this disclosure, software includes but is not limited to instructions stored in or storable in RAM, ROM, flash memory BIOS, CMOS, mother or daughter board circuitry, a hardware controller, a USB controller or host, peripheral devices and controllers, a video card, an audio controller, a network card, Bluetooth® and other wireless communication devices, virtual memory, storage devices and associated controllers, firmware, as well as device drivers. The systems and methods described herein contemplate the use of a computer and computer software typically stored on a computer or machine-readable storage medium or memory.

[0046] Throughout this disclosure, terms used to describe or refer to a medium that holds software, including but not limited to the terms "medium", "storage medium", and "memory", may include or exclude transient media such as signals and carrier waves.

[0047] Throughout this disclosure, the term "network" generally refers to a voice, data, or other communication network through which computers communicate with each other. The term "server" generally refers to a computer that provides services over a network, and the term "client" generally refers to a computer that accesses or utilizes services provided by a server over a network. One of ordinary skill in the art should understand that the terms "server" and "client" can refer to hardware, software, and / or a combination of hardware and software, depending on the context. One of ordinary skill in the art should further understand that the terms "server" and "client" can refer to endpoints of network communication or network connections, including but not necessarily limited to network socket connections. One of ordinary skill in the art should still further understand that a "server" can include multiple software and / or hardware that provides one or a set of services. One of ordinary skill in the art should also understand that the term "host" can, in noun form, refer to an endpoint of network communication or a network (e.g., "remote host"), and in verb form, can refer to a server that provides services over a network (e.g., "host a website") or an access point of services over a network.

[0048] Throughout this disclosure, the term "real time" refers to software operating within an operational deadline for a given event to start or complete, or for a given module, software, or system to respond, and further generally connotes that its response or execution time is substantially contemporaneous with a reference event in the context of normal user perception and the considered technical context. One of ordinary skill in the art understands that the term "real time" does not literally mean that a system processes and / or responds to input immediately, but rather that the processing and / or response by the system is sufficiently rapid that its processing or response time is perceived by a typical human as the passage of real time in the context of the operation of the program. One of ordinary skill in the art understands that if the context of operation is a graphical user interface, "real time" typically means a response time of less than one second of actual time, preferably several milliseconds or several microseconds. However, one of ordinary skill in the art also understands that in other contexts of operation, a system operating in "real time" may exhibit a delay of more than one second, particularly when network operation is involved.

[0049] Throughout this disclosure, the term "transmitter" refers to an apparatus or set of apparatuses that includes hardware, circuitry, and / or software for generating and transmitting electromagnetic waves that convey messages, signals, data, or other information. A transmitter can also include components for receiving electrical signals that include such messages, signals, data, or other information and converting them into such electromagnetic waves. The term "receiver" refers to an apparatus or set of apparatuses that includes hardware, circuitry, and / or software for receiving such transmitted electromagnetic waves and converting them into a generally electrical signal from which such messages, signals, data, or other information can be extracted. The term "transceiver" generally refers to an apparatus or system that includes both a transmitter and a receiver, such as, but not necessarily limited to, a two-way radio or a wireless networking router or access point. For purposes of this disclosure, all three terms should be understood to be interchangeable, unless otherwise specified, e.g., the term "transmitter" should be understood to imply the presence of a receiver and the term "receiver" should be understood to imply the presence of a transmitter.

[0050] For the purposes of the present disclosure, the term "detection network" refers to the wireless network used in the systems and methods of the present disclosure, which is for detecting the presence of a biological mass placed within its communication area. The detection network can use common networking protocols and standards and may be a special-purpose network, but it does not necessarily have to be. That is, the nodes within the network can be arranged for the special purpose of setting up a wireless detection network in accordance with the present invention, but they do not have to be and generally are not. A normal wireless network set up for other purposes can be used to implement the systems and methods described herein. In a preferred embodiment, this detection network uses a plurality of Bluetooth® low energy nodes. Each node operates as a computer equipped with appropriate transmitters and receivers for communicating via the network. Each of these computers always gives a unique identifier within the network when sending a message, so that the receiving computer can identify the origin of that message. Such message origin information is usually essential for the functions of the present invention as described in the detailed description. Next, the receiving computer analyzes the characteristics of the received signal, including but not limited to signal strength, bit error rate, and message delay. This detection network can be a mesh network, which means a network topology in which each node relays data from the network.

[0051] Throughout this disclosure, the term "node" refers to a start and end point of network communication, generally referring to a device that includes a wireless transceiver and is part of a detection network. A node is generally a stand-alone and self-contained networking device such as a wireless router, a wireless access point, a short-range beacon, etc. A node may be a general-purpose device or a dedicated device configured for use in the detection network described herein. By way of non-limiting example, a node may be a device with a wireless transmission function of a commercially available wireless networking device with added dedicated hardware, circuitry, components, or programming for implementing the systems and methods described herein, i.e., for detecting significant changes in signal characteristics including, but not limited to, signal strength, bit error rate, and message delay. Within the detection network, each node functions as both a transmitter of signals to the network and a receiver for other nodes to push information. In a preferred embodiment, these nodes use Bluetooth (R) Low Energy (BLE) as a wireless networking system.

[0052] Throughout this disclosure, the term "continuous" refers to anything that occurs continuously over time, whether the event is mathematically continuous or discontinuous. The generally accepted mathematical definition of a "continuous function" is a function without holes or jumps, generally described by bilateral limits. The techniques described herein are based on disturbances to an electrical communication system in which a transceiver transmits at discrete intervals and the raw data received is received discretely, i.e., at discrete time intervals. The resulting data itself may be discrete in the sense that it captures the characteristics of the system within a particular observation window (i.e., time interval). In a physical or mathematical sense, this mechanism is essentially a set of discrete time data points, meaning a discontinuous function. However, in the context of this technology, one of ordinary skill in the art should understand a system exhibiting this type of behavior as "continuous" if such measurements are made continuously over time.

[0053] The measurable energy density signature of an RF signal is affected by environmental absorbers and reflectors. Many biological masses, such as humans, are mostly water and act as significant energy absorbers. Other human attributes, such as clothing, jewelry, internal organs, etc., all further affect the measurable energy density. This is particularly true when RF communication devices, such as Bluetooth®, Wi-Fi®, ZigBee, and Z-wave transceivers, are transmitting over relatively short distances (e.g., less than 50 meters). When a human passes through the physical space of a network, it causes signal absorption and interference. Since the human body has a relatively uniform size, density, and mass composition, it can cause characteristic signal absorption, scattering, and measurable reflections. Changes in the behavior and / or characteristics of the signal are generally referred to herein as "artifacts". Such phenomena are particularly useful in the industrial, scientific, and medical bands of the RF spectrum, but are generally observable even beyond these bands.

[0054] In an RF communication system that includes a spatially separated transmitter and receiver, the signal from a given transmitter received by the receiver consists of the energy from the original transmission message that arrived at the receiver. Objects on the transmission path affect the characteristics of the final signal that arrives at the receiver.

[0055] Communication systems are generally designed to address such problems and still faithfully reproduce the message from the transmitter. As long as RF communication is affected, since humans exist as a mass of water, one such observable difference in the presence and absence of humans in a detection network is signal absorption by humans. Generally, the closer one gets to the transmitter or receiver, the greater the effect of absorption.

[0056] Generally, humans are expected to generate artifacts in a detection network in a predictable manner that can be detected or identified programmatically by a detection algorithm. Further, the artifacts can be cross-correlated in the network to determine the estimated position of the object generating the artifacts. The accuracy of this estimation varies depending on the selected / created algorithm and the devices used in an individual system.

[0057] For each given algorithm selected / created, the system constructs such detections as a combination of a baseline signal profile when no humans are present in the detection area and sample baseline signal data when humans are present in the detection area. New received sample baseline signal data can be compared to both the known sample baseline signal data and the baseline signal profile to determine the presence or absence of humans in the space.

[0058] Short-range, low-power communication networks typically operate using signals in the 2.4 GHz frequency band, which is well known to be sufficiently contained within the energy frequencies where human absorption has been observed. As described above, a human body physically placed in the detection network absorbs and / or reflects at least a portion of the signals communicated between two or more nodes. However, other effects such as forward and backscattering can also occur. By utilizing data collection within the detection network without the presence of humans to establish a baseline and further examining future elements of the data with respect to the statistically significant differences typically exhibited by the physical presence of one or more humans, regardless of whether the humans are moving, the detection network makes a determination regarding the presence or absence of humans within its network.

[0059] The communication network itself, the hardware used, and humans can cause these changes to be manifested in different ways within the network, resulting in different outcomes, but such changes are detectable. This is different from radar technology in that the detection of an object does not necessarily rely on or is not solely based on the reflection of a signal. Instead, it often depends on the opposite principle, i.e., absorption (detected through measurable changes in the signal characteristics between a transmitter and a receiver at different physical locations).

[0060] By analyzing the changes in signal characteristics between nodes within the network, things that cause chaos to the network, such as the position of a human body, can be calculated. Since simply the presence of a human body is sufficient, this system does not necessarily include reference elements and does not need to rely on movement or motion. Since reference elements are not required, the systems and methods described herein can provide an anonymous location data reporting service, without the need to associate additional components or devices with the human body being tracked, enabling data collection related to traffic, movement routes, and occupancy. Generally speaking, the systems and methods described herein operate in real time.

[0061] FIG. 1 is a schematic diagram of a system and method according to the present disclosure. In the embodiment (101) illustrated in FIG. 1, a detection network (103) including a plurality of nodes (107) is arranged within a physical space (102) such as a room, corridor, entrance, or exit. In the embodiment illustrated in FIG. 1, an indoor space (102) is used, but the systems and methods described herein are also operable in an external environment. In the illustrated embodiment, the node (107A) is communicatively connected (111) to a telecommunications network (115) such as an intranet, an interconnected network, or the Internet. The server computer (109) can also be communicatively connected (113) to the telecommunications network (115) and thus can also be connected to the connected nodes (107A). The illustrated server (109) includes programming instructions for implementing the systems described herein and for performing the steps of the methods described herein. However, in one embodiment, the functions performed by this server may be performed by one or more nodes (107) equipped with appropriate software / programming instructions or appropriately modified.

[0062] In the embodiment shown in FIG. 1, each node (107) is communicatively connected to at least one other node (107) within the detection network (103), and may further be communicatively connected to two or more or all other nodes (107) within the detection network (103). For example, in a typical wireless network deployment strategy, a plurality of wireless access points are arranged throughout the physical space 102, generally ensuring that high-quality signals are available everywhere. These nodes (107) jointly form the detection network (103) and can transmit data to each other or communicate with only one router or a set of routers. In the embodiment shown in FIG. 1, node (107A) is a wireless router, and the remaining nodes (107B), (107C), and (107D) are wireless access points. However, this is only one possible configuration. Furthermore, any node (107) does not have to be a particular type of wireless device. Any number of nodes (107) may be routers, access points, beacons, or other types of wireless transceivers. Additionally, any number of nodes (107) may be present in the embodiment, but a minimum of two is preferred. Increasing the number of nodes (107) within the space 102 increases the amount of data collected (as described elsewhere in this specification), increasing the likelihood that a person is generally sandwiched between at least two nodes (107) and improving the position resolution.

[0063] During normal operation, node (107) frequently performs wireless transmission and reception. For example, when a wireless router (107A) receives a data packet, the wireless router (107A) typically broadcasts a wireless transmission including this packet. This means that any receiver within the broadcast radius of the router (107A) can receive the signal regardless of whether it is intended for them. Similarly, when local data is received by an access point, such data is also broadcast in the same way and can be detected by other access points and routers. Even when there is no user data being actively transmitted on the network, other data is frequently transmitted. These other transmissions include status data, service scans, and data exchanges for the functions of the lower-level layers of the network stack.

[0064] Thus, each node (107) in a typical detection network (103) constantly receives transmissions without change, and in a highly utilized network, this can be substantially continuous. Therefore, the detection network (103) can be used to calculate the presence and / or location of a biomass body (104) or (105) physically located within the transmission range of the network (103). The presence of a human body affects the characteristics of the signals transmitted between two or more nodes (107) within the network (103), so such presence can be detected by monitoring to find changes in such characteristics. This detection may be performed while the data within the transmitted and received data packets is being transmitted and received. That is, this detection is incidental to the normal data exchange between two or more nodes that continues regardless of this detection. In particular, while this wireless network operates to transfer data between nodes, at the same time, it can detect the object and determine its location using the characteristics of how the data packet incorporating the data is affected by the presence of an object on the transmission path.

[0065] In the embodiment shown in FIG. 1, at least one node (107) monitors the communication signature between itself (107) and at least one other node (107) for statistically significant changes in signal characteristics, while it waits for, receives, and / or transmits communication between itself and the other node (107). The geometric shape of the physical space (102), including the presence and location of equipment within the physical environment, generally does not affect the system, because the monitoring is for statistically significant changes in signal characteristics that indicate or demonstrate human characteristics. That is, the change in signal characteristics is thought to be due to a change in an absorber or reflector, such as a human body, in the physical environment, i.e., the communication space, included in the effective range of the detection network (103). Detection of the presence of a human within the detection network (103) can be performed by using a statistical analysis method on the signal, such as by using a sensing algorithm as described elsewhere in this specification. Again, this does not require associating the human with a reference element, nor does the human need to be in a state of motion. Rather, the detection network (103) detects that the characteristics of the network communication have changed because a new object (an object that is generally a human) has been introduced into the communication space and the presence of that object has caused a change in the characteristics of the data packets being communicated between the nodes (107).

[0066] To detect changes, generally, a communication baseline against which recently transmitted signals are to be compared is set. This baseline of signal characteristics between nodes (107) is generally set prior to the use of the detection network (103) as a detector. This can be done by the detection network (103) operating in a typical or normal state where no significant biological mass is placed within the physical echo transmission space of the detection network (103) and the detection network (103) communicates data packets. During such operation, the signal characteristics between two or more nodes (107) are monitored, collected, and stored in a database. In one embodiment, the server (109) receives and stores such data, but in one embodiment, one or more nodes (107) can also include a hardware system configured to receive and / or store such data.

[0067] For example, a node (107) includes special-purpose hardware and programming for use in accordance with the present disclosure, and such a node (107) can store its own signal characteristic data. Such signal characteristic data can be data related to the received energy characteristics of signals received by a particular node (107) from one or more other nodes (107). The baseline data sets a signature characteristic profile for each node (107), which is essentially a collection of data defining the typical and / or general characteristics of signals received by the node (107) in a normal operating situation where no significant biological mass is placed in the detection network (103). A node (107) can have one such profile for each other node (107) from which it receives data.

[0068] In one embodiment, after a baseline signature has been detected and collected, the detection network (103) continues to operate in generally the same or similar manner, but is then able to detect the presence of a biomass. This is done by detecting and collecting additional signal characteristics, generally in real time, as the detection network (103) operates in its normal mode of sending and receiving data packets. These newly generated real-time signal characteristic profiles are also generally the signal characteristics between two particular nodes (107) within the detection network (103), and thus can be compared to the corresponding baseline signal characteristic profiles for the same two particular nodes (107). Then, a statistically significant difference in a particular characteristic between these two profiles can be interpreted as being caused by the presence of a significant biomass, such as a human.

[0069] This comparison operation can be performed by appropriate hardware of a given node (107), or the real-time signal characteristic profile can be sent to a server (109) for processing and comparison. In a further embodiment, both are performed so that a copy of the real-time data is stored and accessible via the server, effectively providing a history of the signal characteristic profiles.

[0070] This is because, as described herein, a biomass located within a network generally causes at least some signal characteristics to vary between at least two nodes when data packets that cross and / or generally interact with that biomass are transmitted. The degree and nature of this variation are generally related to the nature of the biomass placed (e.g., size, shape, and composition) and its position within the network (103). For example, if a fruit fly flies across the detection network (103), the amount of signal change can be so small as to be indistinguishable from the natural variation of the signal characteristics. However, a larger mass, such as a human, can cause a larger and statistically significant change in the signal characteristics.

[0071] Such changes may not necessarily appear in all signal characteristic profiles of the detection network (103). For example, if this mass is located at the end of the detection network (103), the node (107) closest to that end is likely to receive a statistically significant change in signal characteristics, while the nodes on the opposite side of the detection network (103) (whose signals to each other do not pass through or around this biological mass) are likely to receive little or no statistically significant change in signal characteristics. Therefore, if the physical position of the node (107) is also known, the system can not only determine that the biological mass is present within the detection network (103), but also determine which nodes (107) are undergoing changes and calculate the magnitude of those changes, thereby enabling the calculation of its estimated position.

[0072] This can be seen in the embodiment shown in FIG. 1. In FIG. 1, assuming that only one of the humans A (104) or B (105) is present, A (104) should generally have a greater impact on the signal characteristics between the node (107C) and (107A) than between the node (107A) and (107C). Furthermore, the bidirectional influence that A (104) generally has on the signal characteristics between the nodes (107B) and (107D) should be smaller. In contrast, B (105) should have a bidirectional influence not only on the signal characteristics between the nodes (107A) and (107C), but also between the nodes (107B) and (107D).

[0073] When all the nodes communicate with each other, if A (104) and / or B (105) are not generally located on a straight line on the transmission path between the nodes, the influence of A (104) and B (105) is generally smaller. For example, since neither of the persons (104) or (105) is present on the transmission path between the nodes (107A) and (107B), it is likely that they will not have a significant impact on the communication between these nodes. However, A (104) may affect the communication between the nodes (107C) and (107D).

[0074] It should be noted that the presence or absence of a biological mass within the communication area of the detection network (103) does not always result in a change in data communication. The detection network (103) uses its standard existing protocols, means, and methods (including any form of retransmission and error checking) such that the data within the communicated data packets is expected to be reliably, accurately received, processed, and acted upon. In short, in addition to the standard data communication of the detection network, the detection process of the detection network (103) is executed.

[0075] From this, it should be understood that the data within the data packets communicated by the nodes (107) within the detection network (103) is generally not directly utilized for the detection of biological masses within the communication area of the detection network (103). That is, this data is simply data being communicated through the detection network (103) for some reason and often has nothing to do with the detection of biological masses. Further, while the present disclosure generally considers packetized communication in the form of data packets, in alternative embodiments, this data may be communicated continuously in a non-packetized form.

[0076] In one embodiment, to enable the detection network (103) to detect the presence or absence of a specific biological mass, the system includes a training aspect or step. This aspect can include one or more humans being intentionally placed at one or more locations within the network after a baseline is set, and further, one or more sets of baseline data being collected and stored. This second baseline can be used for comparison to improve the accuracy in detecting the size, shape, and / or other characteristics of the biological mass placed within the network and / or to improve the accuracy of location identification. Such training may use supervised or unsupervised learning and / or techniques known to those skilled in the field of machine learning.

[0077] In one embodiment, the detection network (103) can include a dedicated protocol that includes a control messaging structure and / or format, which can be controlled from one node (107) to another (107), making it simpler and easier to identify from which node (107) a message was transmitted, and enabling control of aspects such as the composition of the transmitted signal, the transmitted signal strength, and the signal duration. Further, such control facilitates improved processing and the identification and use by a receiver of signal quality and / or characteristics unique to the detection aspects of the network (103), which may differ from the general networking aspects that share the same network (103). By controlling the messages received on the opposing side of the transmitted and located mass, there is no need to transmit the signal as a scan or sweep an area of space, as such functions tend to require significantly more expensive equipment than that required for typical broadcast or directed transmissions between nodes (107). Generally, the messages are configured to optimally generate data for which a detection algorithm configured to optimally function in the communication network in which these messages are used is available. Generally, in such a configuration, the need to analyze the signals transmitted by the network at the waveform level can be avoided.

[0078] In the illustrated embodiment, each node (107) can generally identify the originating node (107) of a packet received by such a node (107). Such message origin information is typically encoded within the message itself, which is known to those skilled in the art of communication networks. By way of example and not limitation, to do this, one could verify data embedded in established protocols within the networking stack, or examine data transmitted by the sending node (107) for the purposes of implementing the systems and methods described herein. Typically, each node (107) is equipped with the hardware and processing capabilities suitable for analyzing received messages. Although many different topologies and messaging protocols can provide the functionality described herein, generally a mesh networking topology and communication method should result in a usable outcome.

[0079] FIG. 2 shows one embodiment (201) of a method according to the present disclosure and should be understood in relation to the system of FIG. 1. In the illustrated embodiment, the method begins (203) with establishing (203) a detection network (103) that includes a plurality of communication nodes (107) in accordance with the present disclosure. As would be well known to those skilled in the art of setting up communication systems, there are many different approaches to setting up such a network (103), and many different network (103) topologies may be executable within this framework.

[0080] Next, a digital map in memory showing the geometric shape of the physical nodes (107) of the detection network (103) can be generated (205). The detection algorithms described herein generally use information regarding where the nodes (107) are located within the physical environment (102). Data regarding such physical positions of the nodes (107) may be manually provided to an accurate diagram of the physical network environment (102) and / or, using software, an relative position map of one or more nodes (107) within the detection network (103) may be automatically generated to facilitate placement of the nodes (107) into such an environmental map or diagram.

[0081] Alternatively, for detection, the nodes (107) may be placed on a blank or empty map or diagram using a relative (not absolute) distance. Even in such a dimensionless system, messages can be generated from algorithms related to human detection within the system (101), and additional manual processing, such as user input regarding which messages are transmitted regarding the presence and / or movement of humans within the network (103), can also be included.

[0082] In one embodiment for performing automatic node (107) location detection, the node (107) location is detected algorithmically and / or programmatically by one or more nodes (107) and / or computer servers (109) based on factors including but not necessarily limited to: the settings and configuration of the detection network (103) including the physical locations of specific hardware components such as the node (107) and the physical location of the node (107) relative to one or more other nodes (107) of each node (107); signal strength indicators; and transmission delays. In the illustrated embodiment, this step (205) further includes overlaying the generated map onto a digital map of the physical space (102) or environment (referred to herein as an "environmental map") occupied by the detection network (103) such as a floor plan of a building. This step (205) can further optionally include a scaling element for aligning the scale of the generated map with the environmental map and a user-operable and / or modifiable input element for adjusting and fine-tuning the generated map to match it with the actual geometric arrangement of the nodes (107), as would be understood by one of ordinary skill in the art. In an alternative embodiment, each node (107) may be manually placed at its appropriate location on the environmental map without using a relative position algorithm.

[0083] In any case, in this step (205), the physical positions of the nodes (107) within the detection network (103) are established, thereby facilitating the identification of the positions of the arranged biological mass bodies due to the presence of humans within the detection network (103). By placing the nodes (107) on a map (either manually or by automatic means), the nodes (107) can track the presence of humans within the network (103) based on how the baseline signal affects communication between the various nodes (107). Then, the system 101 is provided with a set of transmitted information known to the data processing algorithm and utilizes the information collected about the signals reaching the receiver. This data processing algorithm ultimately determines whether a human is present within the network (103) and / or where that human is located within the network (103).

[0084] Next, the messages are created and exchanged (207) in a format and according to a protocol that has been determined to be suitable for detecting the presence of biological mass bodies within the network (103). This can be performed using a general-purpose networking protocol known in the field of the present invention, such as the protocols of the OSI network model, or a special-purpose protocol that substitutes for or supplements such general-purpose networking protocols.

[0085] Generally, this step preferably further includes controlling and / or modifying (207) the messages transferred within the detection network (103) for the specific purpose of detecting human presence and facilitating simple statistical analysis. By controlling the exchange of messages (207), the system (101) can easily adjust parameters including, but not necessarily limited to, the transmission interval; transmission power; message length and / or content; and the intended message recipients while adapting to the common content sent via the detection network (103). To reiterate, the system does not need to rely on analysis at the waveform level and can operate within the scope of wireless communication standards.

[0086] By controlling such parameters (207), it becomes easier to form statistics and / or analytics that may be at least partially based on defined or expected message content or characteristics. Such content and / or characteristics can include, but are not limited to, transmission timestamps and / or transmission power levels. By controlling and modifying these aspects (207), it is possible to overcome hardware limitations including hardware features that result in undesirable results when used in the detection network (103) according to the present disclosure, such as an automatic gain control (AGC) circuit that may not necessarily be limited but can be incorporated into certain receiver hardware of the node (107).

[0087] In the illustrated embodiment (201), next, a significant amount of biomass, particularly a human (205), is removed from the space 102 (209). Next, a statistical baseline of the signal strength is locally created by each node (107) (211). Again, by manual and / or automatic means, by placing the nodes (107) on the map in step (205), the nodes (107) can track the presence of humans within the network (103) based on how the baseline signal is affected with respect to communication between the nodes (107).

[0088] Next, a biomass enters the detection network (103) (213), causing signal absorption and other distortions, which appear as changes in the signal characteristics between the nodes (107). These changes are detected (215) and analyzed (217) to determine whether they indicate the presence of a human or the presence of other types of biomass that the detection network (103) is configured to detect. Such detection can be further limited to at least the area between nodes, such as the internal area between three nodes on the network, but can also be performed with higher accuracy depending on the algorithms and hardware being used at that time.

[0089] Generally, this is done using a detection algorithm executed by either one or more nodes (107) or server computers (109). The nodes (107) and / or the server (109) use software to estimate the location of detected biomasses within the detection network (103) using one or more detection algorithms. Such algorithms generally compare a baseline profile to a newly detected signal and can use, or be based on, various data and other aspects, which include, but are not limited to: the settings and configuration of the detection network (103), including the physical location of specific hardware components such as the location of the nodes (107) and the physical location of one or more other nodes (107) relative to each node (107); signal strength indicators; and transmission delays.

[0090] Generally, as described elsewhere herein, these algorithms include comparing (215) a newly collected signal characteristic profile to a baseline signal characteristic profile (211) to identify changes and, based on the nature of the changes, determining whether the changes indicate the presence of a human. This determination can be made using at least in part training data developed by machine learning as described elsewhere herein.

[0091] In one embodiment, the detection algorithm can further include using one or more signal characteristic changes observed between one or more pairs of nodes (107) in the detection network (103) that are correlated with respect to time and relative influence. These factors facilitate identification of the physical location within the detection network (103) where such signal changes occurred, thereby enabling estimation of the physical location of the human that caused such signal characteristic changes and, further, using this to estimate the physical location within the detection network (103) environment where the biomass is located. Such physical location may be given as simple x, y, z coordinates in a coordinate system or may be visually indicated, such as on a map.

[0092] When multiple humans are present within the detection network (103), it is more difficult to separate the effects of these various individuals from each other, and accuracy should generally improve by adding more nodes (107). In one embodiment, techniques such as advanced filtering and predictive path algorithms can be used to separately identify the positions of multiple individuals within the network (103). Although human movement within the network (103) is not necessary for this system and method to operate properly, movement or lack of movement can be used to improve the accuracy of detection, for example, by predicting the path of an individual. This can help identify cases where an individual has statistically "disappeared" from the detection network (103), but the system has enough data to presume that the individual is still present within the network (103).

[0093] For example, if the movement path of an individual is predicted and ends near another detected individual, the system (101) may determine that these two individuals are too close for signal characteristic profile changes to separate and identify them. However, based on the movement path of this individual, it was not determined that this individual had left the detection range of the network (103). So, the algorithm determines that this individual is present, not moving, and adjacent to another detected individual. Next, when one of these two adjacent and stationary humans moves, the algorithm can again separately identify each of them and resume predicting the path based on the observed signal characteristic profile changes.

[0094] By doing so, the systems and methods according to the present disclosure can track one or more individuals within the network (103), whether or not such individuals are moving and whether or not such individuals are associated with a reference element. The identification of a particular individual may be performed using other route prediction and sensing algorithms, such as those used in the robotics industry for human tracking technology, to infer which is which person, although not necessarily limited to this. It should also be noted that individuals can have an individual and unique impact on various signal characteristics, enabling the identification of a particular individual and further distinguishing a particular individual from others. Furthermore, such impacts can be used to identify the location of a particular individual within the detection network.

[0095] Such one or more detection algorithms generally utilize the characteristics of communication signals and are configured to consider elements such as the frequency of one or more signals and the transmission power levels of those signals, although not necessarily limited to this. In one embodiment, these algorithms use a data-driven approach to detect the presence of humans by identifying the impact of human presence on signal characteristics in the RF environment within the communication network and then identifying when that impact is later observed.

[0096] For example, in one embodiment, signal characteristics that change due to the presence of a human body include the signal strength shown between nodes (107). This is particularly true within a BLE network, and statistical data regarding the signal strength over time can indicate the presence of humans within the network. By using these artifacts by one or more detection algorithms, information regarding the physical location of the object that caused the artifact can be obtained. That is, by combining various statistics regarding the artifacts captured within the network (103), the system can identify where within the physical space (102) the artifact is located, i.e., where a human is located within the network (103).

[0097] In the simplest use cases, these algorithms can simply identify changes in signal characteristics similar to those caused by the presence of a human (e.g., from training), and always trigger a detection event (219) whenever such a change relative to the baseline is detected. This may appear as an adjustment of the average, standard deviation, skew, or variance of the signal strength, depending on the system (101) being used. When the detected signal characteristic profile returns to a profile similar to the baseline, the physical environment (102) is presumed to have returned to an empty state with respect to the presence of a human.

[0098] Compared to other technologies (typically passive infrared (PIR) sensors) that require movement to function and are used for such specific purposes, the systems and methods described herein can detect the presence of a stationary human within a space (102), regardless of whether the human is moving, and more precisely can detect when a human has left the space (102). For applications such as security and occupancy sensing, it should be more difficult to fool this system. Some examples of strategies that can fool a PIR or other similar motion-based technology include holding a sheet in front of oneself when entering a space and then moving very slowly or generally remaining stationary in one place after entering. Another advantage is that this system does not necessarily require additional hardware beyond that used in normal network communication. This is because the additional software and processing capabilities are obtained by modifying external components or existing hardware, which can be done, for example, by implementing this appropriate software as a system-on-chip (SOC) attached to a commercial-off-the-shelf communication module. If additional processing power is required, one or more additional processing nodes may be added to analyze the signals propagating between nodes (107), or such workloads may be sent to a dedicated server machine (109) for processing.

[0099] The identification of a human presence and / or location may be related to the details of the type of signal being analyzed and the control of the signals transmitted between the nodes (107) of a network (103) to optimally achieve such identification. By transmitting control communication pulses within a network (103) where the original signal is known and the transmission power is adjustable, exemplary data related to signal absorption, reflection, backscattering, etc. due to the additional placement of a human between nodes (107) can be generated. A baseline system can be configured in the absence of a human, and since such a baseline is generally presumed to be statistically different from when a human is present, a change in signal characteristics can be further presumed to be due to the presence of a human within the network. By enabling an input to a timer and generally configuring the system to refine the baseline definition when the space (102) is empty, the system can periodically readjust itself to achieve higher accuracy. Although it should be known to those of ordinary skill in the art of location identification technology, generally, a tracking algorithm combines the best available triangulation calculations with statistical methods and is used in conjunction with a detection algorithm for detecting a human within a network (103).

[0100] The present disclosure does not require reference elements associated with the detected human, nor does the device communicable with the network need to be held by that human, but if such elements are placed within the system, such techniques should utilize them. By adding such elements, the computational load on the system can be alleviated and the accuracy can be improved. The systems and methods described herein do not exclude such additional functionality and can thereby enhance their capabilities. Enhancing detection using an inference engine adds to the sensing hardware the ability to recover from false alarm states or other edge cases, improving the robustness of the system.

[0101] In one embodiment, the detection network (103) implementing the systems and methods described herein may further include elements for performing operations (219) based on the detected presence and / or location of humans. To do this, for example, a control signal can be sent over the network, a computer is first used to identify the presence and / or location of humans on the network, then an operation to be taken based on the presence and / or location of humans on the network is determined, and a message for taking that operation is sent over the network. Since the communication network and the network performing the detection may be the same network, the invention described herein extends the conventional functions of the communication network to include human detection and / or location detection without requiring additional sensing hardware.

[0102] Computer elements on the network need to perform additional calculations and can skillfully create communication signals. This reduces the computational burden on the computer, and this network can function as a command and control network independently of the network as a detection network.

[0103] The present system can be used for a wide range of applications as a whole, and the range extends from any occupancy sensing for use in lighting control and / or security to counting the number of people in a space as required for heat and / or traffic maps, and to a system for tracking individual humans moving within the space. This technology may be incorporated into the network nodes themselves, or may be a combination of nodes that transmit information to processing elements (e.g., directly on the network or in the cloud) to perform calculations for determining the desired information. The final comprehensive product suite can be customized according to the application and can be used in various different ways.

[0104] No additional sensors are required and detection is effectively performed by calculating statistics from a conventional RF communication stack. Such a system prevents the collection of personal data from people walking through the space because the system only knows that approximately human-sized masses, organs, clothing, etc. have passed through, and this system does not require a separate device to function as a reference element. Thus, this technology is significantly different from conventional methods for tracking humans moving through space.

[0105] Logical extensions of the systems and methods described herein are to dynamically process functional network messages in statistical analysis to avoid or reduce additional messaging overhead of the system. In one embodiment, it is also contemplated to extend the systems and methods described herein to dynamically adjust network and / or message structures, configurations, and / or operating parameters, at least in part based on functional messages transmitted within the network.

[0106] Furthermore, since tracking is generally based on signals affected by human mass, this system does not rely on human movement to perform detection. By not relying on movement, many of the drawbacks of conventional presence sensing technologies, such as passive infrared and ultrasonic sensing technologies, are overcome.

[0107] Using signals between nodes of a communication network to detect the presence of a human within that network without the human carrying a reference element is significantly different from current non-reference element detection methods and uses the communication network in a completely novel way to perform presence sensing. The combination of the detection techniques for the purpose of detecting human presence described herein and their use as a combination of transmitters and receivers of network nodes constitutes a new type of human presence detection system that does not require additional equipment beyond what is necessary to form the communication device network itself.

[0108] The systems and methods described herein can be implemented within a communication network without affecting the operation of the network itself for normal communication purposes. This network continues to perform its primary function as a communication network, but in this case, some of the communication is used to calculate the position of humans present within the network. Since the systems and methods described herein utilize the basic operation of the network, they can more accurately detect and locate humans within the network who additionally carry a transceiver device recognized by the network. Such transceiver devices can include, for example, mobile computing devices equipped with wireless transceivers such as mobile phones, cellular phones, smartphones, tablet computers, wearable computer technology, etc., which are connected to the network and can be located by the network using conventional triangulation methods well known to those skilled in the art. Machine learning algorithms can further improve performance when such transceivers are carried by humans.

[0109] The position calculation of known transceiver devices may be compared with the position of a person determined by the non-transceiver aspects described herein. By the communication network reporting the position of reference elements and humans within the network, these two positions can be compared. Generally, since the detected position of the reference elements is more accurate than the position of a human estimated based only on network communication, the position calculation of the position of a human within the network can be adjusted using machine learning algorithms to improve the position calculation ability of the system for the next human entering the network.

[0110] Using a machine learning algorithm, this system can improve the accuracy of the location prediction algorithm based on known locations from the transceiver. This may verify previous identifications and refine future identifications. For example, if previous identifications have always deviated by the same amount, that amount may be applied as an adjustment to future identifications. By doing so, this system can continuously improve and train itself to improve human location identification within the network. Similarly, machine learning can continuously improve the detection and false alarm rates. By way of illustration and not limitation, data regarding previous movement patterns in a facility can be used to establish defaults, estimates, or expectations regarding the times or days when a particular facility is generally occupied or generally vacant. Such data can be used by the system to improve its performance.

[0111] This system can make inferences based on physical interactions with network elements. Such physical interactions can be considered reference elements at the time of interaction for the purposes of this system. As an example, when an optical switch that is part of the network is activated, this system should be able to tell that a human was present at that location at the time the switch was activated. Therefore, this system can also use that information as a known data point to which machine learning can be applied to improve predictions of future human presence. Additionally, such events can also serve as presence triggers for other purposes such as security alerts. As an example, if this system is in security mode and someone finds a way to hide their presence but still interacts with the switch, this system should determine that someone was present there and send an alert based on the interaction with the switch. Generally speaking, interactions with this system can be defined as physical and logical, and logical interactions should include typical usage patterns based on time, external inputs, etc. Such a system functions as a backup to RF presence sensing and will give the system additional machine learning algorithm capabilities.

[0112] Furthermore, the system can estimate whether a mobile transceiver in the network is actually being carried by a human, such as where in the network a human has left a device. Since the system can detect a human as a single biomass through changes in signal characteristics, the system can determine whether a transceiver is present where the human biomass is not present in the network.

[0113] As a side effect of being able to collect various signal characteristics and process them with various algorithms, the system can perform many detection calculations simultaneously and achieve different performance criteria for the same system. As an example, the same communication network can be used for multiple detections associated with lighting and security, but the collected statistical data can be processed in different ways but simultaneously for these two uses. By doing so, the lighting application can have a short detection time although the false alarm rate is high, while the security application can have a slightly longer detection time while reducing the false alarm rate. The signal characteristics processed by the system may vary depending on the application, but all are obtained from that communication network and can be processed simultaneously in many ways. Such processing methods may encapsulate into many sets of different sample baseline signal data for determining detections against a baseline signal profile.

[0114] In one embodiment of the system according to the present disclosure, the system includes a communication system capable of confirming the presence of one or more humans from information regarding signals between two or more computers on a network, and each computer includes: a transceiver for communication; and a computing element for performing calculations, and each computer transmits a signal to one or more other computers on the network, the signal including a unique identifier of the computer that sent the signal, and each computer processes the received signal for confirming the presence of one or more humans, and the one or more humans do not need to carry a device capable of communicating with the network.

[0115] In one embodiment of such a system, the algorithm uses a statistical method to confirm the presence of one or more humans. In a further embodiment of such a system, the statistical method identifies the number of people present on-site. In yet another embodiment of such a system, the system can identify the physical location of the one or more humans on the network. In a still different embodiment of such a system, the system can track the physical location of the one or more humans over time. In yet another embodiment of such a system, the system controls devices on the network using information regarding the presence of one or more humans. In one embodiment, the network is a mesh network.

[0116] In one embodiment, the computer identifies their relative physical locations and further identifies the relative physical locations of the one or more humans on the network. In a further embodiment, the statistical method is applied to the measurement of signal strength to identify the presence of humans. According to a further embodiment, the transmitted signal is controlled to facilitate the detection of the presence of humans. In a further embodiment, the power level of the transmitted signal is controlled to facilitate the presence of humans. In another embodiment, the system functions as an occupancy sensing system. In a further embodiment, the occupancy sensing system controls a lighting system. In a further embodiment, the network used for controlling the lighting system and the network used for occupancy sensing utilize the same communication technology and hardware. In a further embodiment, the communication technology used by the computer is selected from the list consisting of Bluetooth® Low Energy, Wi-Fi, ZigBee, and Z-Wave.

[0117] In a further embodiment, the system functions as a sensing system for security purposes. In a further embodiment, the above security sensing system controls a security system. In a further embodiment, the network for controlling the above security system and the network used for security sensing utilize the same communication technology and hardware. In a further embodiment, the system functions as a human detector of a robot system. In a further embodiment, the above robot system is provided with a computer that identifies the relative positions of various elements of the robot system with respect to each other. In a further embodiment, the network for controlling the above robot system and the network functioning as the human detector of the above system utilize the same communication technology and hardware.

[0118] In another embodiment, the system uses machine learning to improve its detection ability, where a human carrying a reference element trains the system by: (1) using known location identification techniques to identify the location of the above reference element; (2) using the above system to identify the location of the above human; (3) comparing the location calculated by the above method (1) in this paragraph with the above method (2) in this paragraph; (4) adjusting the above location identification method using a machine learning algorithm to improve the location calculation ability of the above system, which is achieved through the above steps.

[0119] In another embodiment, the system can estimate the presence of humans in the above network based on some form of interaction of these humans with one or more computers of the above network. In a further embodiment, the system can use the estimated presence of humans as an input for machine learning to improve its detection ability.

[0120] In one embodiment of the system according to the present disclosure, the system includes a communication system capable of verifying the stationary and moving presence of one or more humans from information regarding signals between two or more computers on the network, where each computer includes: a transceiver for communication; and a computing element for performing computations. Each computer transmits a signal to one or more other computers on the network, and the signal includes a unique identifier of the computer that sent the signal. Each computer processes the signals received to verify the presence of one or more humans. The one or more humans do not need to carry a device capable of communicating with the network.

[0121] In one embodiment, the algorithm uses a statistical method to verify the presence of one or more humans. In another embodiment, the statistical method identifies the number of humans present. In another embodiment, the system can identify the physical location of the one or more humans on the network. In another embodiment, the system can track over time the physical location of the one or more humans on the network. In another embodiment, the system controls devices on the network using information regarding the presence of one or more humans. In another embodiment, the information regarding the presence of one or more humans is available to one or more systems not directly related to the identification of presence. In another embodiment, the system has the ability to perform self-optimization to achieve a given performance according to one or more pre-set criteria.

[0122] In other embodiments, the communication protocol or network is generally defined by a standards committee and is not limited to, but includes, protocols such as Bluetooth® Low Energy, Wi-Fi, ZigBee, and Z-Wave. In another embodiment, the statistical method is applied to the measurement of signal strength received to identify human presence. In another embodiment, the transceiver device on the network can be selected and operated by the system for the purpose of facilitating human detection. In another embodiment, the power level of the signal transmitted is controlled to facilitate human presence. In another embodiment, the system functions as an occupancy sensing system for a lighting system. In another embodiment, the occupancy sensing system controls the lighting system. In another embodiment, the network used for controlling the lighting system and the network used for occupancy sensing utilize the same communication technology and hardware.

[0123] In another embodiment, the system functions as a sensing system for security purposes. In another embodiment, the security sensing system controls the security system. In another embodiment, the network used for controlling the security system and the network used for security sensing utilize the same communication technology and hardware. In another embodiment, the system functions as an occupancy sensing sensor for a heating, ventilation, and air conditioning (HVAC) system. In another embodiment, the occupancy sensing system controls the HVAC system. In another embodiment, the network used for controlling the HVAC system and the network used for occupancy sensing utilize the same communication technology and hardware.

[0124] In another embodiment, the system uses machine learning to improve its detection capabilities, where a human carrying the reference element trains the system by: (1) using known location identification techniques to identify the location of the reference element; (2) using the system to identify the location of the human; (3) comparing the location calculated in (1) of this paragraph with (2) of this paragraph; and (4) adjusting the location identification method using a machine learning algorithm to improve the location calculation ability of the system.

[0125] In another embodiment, the system can estimate the presence of humans in the network based on their interaction with any of the computers in the network in some manner. In another embodiment, the system can use the estimated presence of humans as input to machine learning to improve its detection capabilities.

[0126] This specification describes a communication system that can confirm the stationary and moving presence of one or more humans from information about signals between two or more computers on the network. Each computer includes a transceiver for communication and a computing element for performing calculations. Each computer transmits a signal to one or more other computers on the network, and the signal includes a unique identifier of the computer that sent the signal. Each computer processes the received signal for confirming the presence of one or more humans in two or more ways to achieve separate performance criteria that serve two or more purposes simultaneously. The one or more humans do not need to carry a device capable of communicating with the network.

[0127] In one embodiment, the algorithm uses two or more statistical methods to confirm the presence of one or more humans according to two or more sets of performance criteria. In another embodiment, the system has the ability to perform self-optimization to achieve two or more sets of performance according to two or more pre-set criteria. In other embodiments, the communication protocol or network is generally defined by a standards committee and includes, but is not limited to, protocols such as Bluetooth® Low Energy, Wi-Fi, ZigBee, and Z-Wave. In another embodiment, the two or more statistical methods are applied to the measurement of signal strength received to identify the presence of humans according to two or more sets of performance criteria. In another embodiment, the system uses machine learning to improve the detection ability of two or more methods for identifying presence, where a human carrying a reference element trains the system by: (1) using known location identification techniques to identify the location of the reference element; (2) using the system to identify the location of the human; (3) comparing the location calculated in (1) of this paragraph with (2) of this paragraph; (4) adjusting the location identification method using a machine learning algorithm to improve the location calculation ability of the system, which is achieved through the above.

[0128] The present invention has been disclosed in connection with the description of several embodiments, including those currently considered to be preferred embodiments. However, this detailed description is intended to be illustrative and should not be understood as limiting the scope of the present disclosure. As would be understood by those of ordinary skill in the art, other embodiments than those detailed herein are also included in the present invention. Modifications and changes to the described embodiments are possible without departing from the spirit and scope of the present invention.

Claims

[Claim 1] The invention as described in the specification or drawings.

Images