KR102478928B1 - Detecting location within a network - Google Patents

Abstract

Systems and methods are provided for detecting the presence of a body in a fiducial element-free network using signal absorption and signal forward and backscatter of radio frequency (RF) propagation caused by the presence of a biological mass in a communication network.

Description

Location detection within a network {DETECTING LOCATION WITHIN A NETWORK}

CROSS REFERENCES TO RELATED APPLICATIONS

This application is a continuation of U.S. Utility Patent Application No. 15/713,309, filed on September 22, 2017, and is a continuation of U.S. Utility Patent Application No. 15/713,219, filed on September 22, 2017; It is a continuation of U.S. Utility Patent Application Serial No. 15/674,487, filed on August 10, 2017; and a continuation of U.S. Utility Application Serial No. 15/674,328, filed on August 10, 2017. Application Serial No. 15/713,219 is a continuation-in-part of U.S. Utility Application No. 15/674,328, filed on August 10, 2017, which is a continuation-in-part of U.S. Utility Application No. 15/600,380, filed on May 19, 2017, which is It is a continuation of U.S. Utility Patent Application No. 15/227,717, filed on August 3, 2016, which is a continuation of Provisional Patent Application No. 62/262,954, filed on November 9, 2015, and U.S. Patent Application No. Claims the benefit of Provisional Patent Application No. 62/219,457. Application Serial No. 15/713,309 is a continuation of U.S. Utility Patent Application No. 15/674,487, filed on August 10, 2017, which is a continuation of U.S. Utility Patent Application No. 15/674,328, filed on August 10, 2017, which is It is a continuation-in-part of U.S. Utility Application No. 15/600,380, filed on May 19, 2017, which is a continuation-in-part of U.S. Utility Application No. 15/227,717, filed on August 3, 2016, which is filed on November 9, 2015. It claims the benefit of U.S. Provisional Patent Application No. 62/252,954, filed on September 16, 2015, and U.S. Provisional Patent Application No. 62/219,457, filed on September 16, 2015. Application No. 15/227,717, filed on March 29, 2016 and Patent No. 9,474,042 is a continuation of U.S. Utility Patent Application No. 15/084,002, published on October 18, 2016, which in turn is also a continuation of U.S. Provisional Patent Application Nos. 62/252,954 and 2015, filed on November 9, 2015. We claim the benefit of US Provisional Patent Application No. 62/219,457, filed on September 16, 2011. The entire disclosures of these documents are incorporated herein by reference.

field of invention

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 in a wireless communication network.

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 systems such as GPS that use orbiting satellites to communicate with terrestrial transceivers. However, these systems are generally less effective indoors where satellite signals are blocked and accuracy is poor. Therefore, other technologies such as Bluetooth(TM) beacons that calculate the location of roaming or unknown transceivers are often used indoors. The roaming transceiver serves as a fiducial element.

These systems have several disadvantages, among them being that the object being tracked must contain a transceiver. In certain applications, the object to be tracked will either not have this origin element or will actively disable any such element, such as an intruder in the home.

There are other techniques that can detect and track objects without using fiducial elements. For example, radar is a useful object detection system that uses RF waves to determine the range, angle, or speed of objects including aircraft, ships, spacecraft, guided missiles, automobiles, weather formations, and terrain. Radars operate by transmitting electromagnetic waves, using waves in the radio frequency ("RF") electromagnetic spectrum that are generally reflected from any object in their path. A receiver, typically part of the same system as the transmitter, receives and processes these reflected waves to determine 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 lasers, can also be used in a similar manner.

Radar technology does not require a fiducial element, but has other disadvantages. For example, radar signals are susceptible to signal noise, or random fluctuations in the signal caused by internal electrical components, as well as noise and interference from external sources such as natural background radiation. Radar is also susceptible to sources of external interference, such as inclusions blocking the beam path, and can be fooled by objects of a particular size, shape, and orientation.

The following is a summary of the invention to provide a basic understanding of some aspects of the invention. This summary is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some concepts of the invention in a simplified form as a prelude to the more detailed description that is presented later.

Because of these and other problems in the art, in this application, among other things, a method for detecting the presence of a human body is described, the method comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within the detection area; a computer server communicatively coupled to the first transceiver; the first transceiver receives a first set of radio signals from the second transceiver over the wireless communication network; The computer server receives a first set of signal data from the first transceiver, the first set of signal data comprising data relating to characteristics of the first set of radio signals, the characteristic data comprising the communication network created as part of normal operation of the first transceiver on the the computer server generates a baseline signal profile for communication from the second transceiver to the first transceiver, the baseline signal profile based at least in part on characteristics of radio signals in the first set of signal data; ; indicating characteristics of radio transmission from the second transceiver to the first transceiver when no human body is present in the detection area; the first transceiver receives a second set of radio signals from the second transceiver over the wireless communication network; The computer server receives a second set of signal data from the first transceiver, the second set of signal data comprising data relating to characteristics of the second set of radio signals, the characteristic data comprising the communication network created as part of normal operation of the first transceiver on the and the computer server determines whether a human body is present within the detection area, the determination based at least in part on comparing wireless signal characteristics in the received second set of wireless signal data to the baseline signal profile.

In an embodiment of the method, the first set of signal characteristics includes radio network signal protocol characteristics determined by the first transceiver.

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.

In another embodiment of the method, the method comprises; providing a third transceiver disposed at a third location within the detection area; the first transceiver receives a third set of radio signals from the third transceiver over the wireless communication network; The computer server receives a third set of signal data from the first transceiver, the third set of signal data comprising data relating to characteristics of the third set of radio signals, the characteristic data comprising the communication network created as part of normal operation of the first transceiver on the The computer server generates a second baseline signal profile for communication from the third transceiver to the first transceiver, the second baseline signal profile at least in accordance with characteristics of a radio signal in the third set of signal data. partially based; and indicating a characteristic of the radio transmission from the third transceiver to the first transceiver when no human body is present in the detection area. the first transceiver receives a fourth set of radio signals from the third transceiver over the wireless communication network; The computer server receives a fourth set of signal data from the first transceiver, the fourth set of signal data comprising data relating to characteristics of the fourth set of radio signals, the characteristic data comprising the communication network created as part of normal operation of the first transceiver on the and wherein the computer server determines whether a human body is present within the detection area, based at least in part on comparing wireless signal characteristics in the received fourth set of wireless signal data to the second baseline signal profile. do.

In another embodiment of the method, the determining step applies a statistical method to the second set of radio signal data to determine the presence of a human body.

In another embodiment of the method, the method includes the computer server continuously determining the presence or absence of a human body within a detection area, the determination being continuously received at the computer server from the baseline signal profile and the first transceiver. based at least in part on a comparison with signal data comprising data relating to characteristics of the first set of radio signals; and the computer continuously updating the baseline signal profile based on the continuously received signal data when the continuously received signal data indicates that there is no human body in the detection area.

In another embodiment of the method, the method further comprises the computer server determining whether the number of human bodies is within a detection zone, the determining based on a comparison of the received second set of signal characteristics to the baseline signal profile. based at least in part on

In another embodiment of the method, the method further comprises the computer server determining the position of one or more human bodies within the detection area, the determining based on a comparison of the received second set of signal characteristics with at least a baseline signal. partially based on

In another embodiment of the method, the method further comprises a computer server being operatively coupled to the second system, the computer operating the second system only after the computer server detects the presence of a human body in the detection zone. .

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

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

In another embodiment of the method, the second system is a lighting system.

In another embodiment of the method, the second system is a heating, exhaust, and cooling (HVAC) system.

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

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

In another embodiment of the method, the wireless communication protocol is selected from the group consisting of Bluetooth (TM), Bluetooth (TM) Low Energy, ANT, ANT+, WiFi, ZigBee, Thread and Z-Wave.

In another embodiment of the method, the wireless communication network has a carrier frequency range covering 850 MHz and 17.5 GHz.

In another embodiment of the method, the determination of whether the human body is within the detection area comprises determining a first sample location of the human body having a fiducial element in the detection area, wherein the first sample location is the fiducial element. determining the first sample location, determined based on the detection of the element; determining a second sample position of the human body in the detection region, the second sample position being at least partially proportional to a comparison of the received second set of signal data and the baseline signal profile without using the fiducial element. Determining the second sample position, which is determined based on; comparing the first sample position and the second sample position; and adjusting the determining step based on non-fiducial element positions to enhance the position computation capability of the system, wherein the adjusting is based on the comparing step. Adjusted based on learning.

In another embodiment of the method, determining whether a human body is present in the detection region comprises determining that a human body is present in the region based on a user input or action, wherein the sample signal characteristic is at least partially different from a baseline signal characteristic of an empty space. When corresponding to , at least partially modifying the baseline signal characteristic for the empty space; at least partially modifying a signal characteristic associated with the occupied space; and adjusting how the sample signal characteristics are compared to the baseline and other comparison signal characteristics to improve the accuracy of the system over time.

In embodiments of the present system, user inputs or actions that provide presence data are provided directly to the system in some form, including but not limited to physical switches, smart phone inputs, or auditory cues.

In an embodiment of the present system, user input or action providing presence data is, for example, intentionally changing the signal profile to correspond to a decision made by the system, such as providing such a change during a dimming step in a lighting system. provided indirectly to the system in some form, such as

In another embodiment of the method, the method further includes the computer server storing a plurality of historical data records indicating whether the human body has been present in the detection zone for a period of time, each historical data record indicating whether the human body has been present in the detected zone. includes the number of human bodies and the date and time at which the number of human bodies was detected in the detection area; and the computer server makes the historical data records available to one or more external computer systems through an interface.

Among other things, the present application also describes a method of detecting the presence of a human body, the method comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within the detection area; a computer server communicatively coupled to the first transceiver; providing a first external system operably coupled with the computer server; providing a second external system operably coupled with the computer server; The computer server sends a baseline signal data set comprising characteristic data relating to signal characteristics of a first set of radio signals received by the first transceiver from the second transceiver when a human body is not present within the detection area. receive from a first transceiver, wherein the characteristic data is generated as part of normal operation of the first transceiver on the communication network; The computer server generates a baseline signal profile for communication from the second transceiver to the first transceiver when a human body is not present in the detection area, the baseline signal profile being the baseline signal profile when a human body is not present in the detection area. based at least in part on characterization data that characterizes a wireless transmission from the second transceiver to the first transceiver when not in use; The computer server receives a first set of baseline signal data including characteristic data relating to signal characteristics of a second set of radio signals received by the first transceiver from the second transceiver when a human body is present within the detection area. receive from the first transceiver, wherein the characteristic data is generated as part of normal operation of the first transceiver on the communication network; The computer server generates a first sample baseline signal profile for communication from the second transceiver to the first transceiver when a human body is present in the detection area, the first sample baseline signal profile in the detection area. based at least in part on characteristic data in the first set of sample baseline signal data representing characteristics of a wireless transmission from the second transceiver to the first transceiver when a human body is present; The computer server receives a second set of baseline signal data including characteristic data regarding signal characteristics of a third set of radio signals received by the first transceiver from the second transceiver when a human body is present within the detection area. receive from the first transceiver, wherein the characteristic data is generated as part of normal operation of the first transceiver on the communication network; The computer server generates a second sample baseline signal profile for communication from the second transceiver to the first transceiver when a human body is present in the detection area, the second sample baseline signal profile in the detection area. based at least in part on characteristic data in the second set of sample baseline signal data representing characteristics of a wireless transmission from the second transceiver to the first transceiver when a human body is present; The computer server receives a third set of baseline signal data including characteristic data regarding signal characteristics of a fourth set of radio signals received by the first transceiver from the second transceiver when a human body is present within the detection area. receive from the first transceiver, wherein the characteristic data is generated as part of normal operation of the first transceiver on the communication network; based on the computer server determining that characteristic data of the third set of sample baseline signal data corresponds to the first sample baseline signal profile, the computer server determines to operate the first external system; The computer server determines not to operate the second external system based on the computer server determining that characteristic data of the third set of sample baseline signal data corresponds to the second sample baseline signal profile. include

In an embodiment of the method, the decision to operate the first external system and the decision not to operate the second external system are the steps of determining a location of a first sample of the human body having a fiducial element in the detection area. , determining the first sample position, wherein the first sample position is determined based on the detection of the fiducial element; determining a second sample position of the human body in the detection region, the second sample position being at least partially proportional to a comparison of the received second set of signal data and the baseline signal profile without using the fiducial element. Determining the second sample position, which is determined based on; comparing the first sample position and the second sample position; and adjusting the determining step based on the non-fiducial element position to improve the position calculation capability of the system, wherein the adjusting is based on the comparing step. Adjusted based on machine learning.

In another embodiment of the method, the decision to operate the first external system and the decision not to operate the second external system include determining a location of a first sample of the human body in a detection region using inference, wherein the first external system determining a first sample location, wherein the sample location is determined based on detecting a human body interacting with the system in some known way; determining a second sample position of the human body in the detection region, wherein the second sample position is at least in comparison with the received second set of signal data and the baseline signal profile without using the estimated position; determining the second sample location, which is determined based in part on the basis; comparing the first sample position and the second sample position; and adjusting a determining step based on the inferred position to improve a system's ability to calculate position, wherein the adjustment is adjusted based on machine learning comprising the adjusting step based on the comparing step.

In another embodiment of the method, the characteristic data relating to the wireless signal includes data relating to a signal characteristic selected from the group consisting of received signal strength, latency and bit error rate.

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

In another embodiment of the method, the method further comprises the computer server from the second transceiver an additional set of baseline signals comprising characteristic data relating to signal characteristics of a radio signal of 2V received by the first transceiver. receive data from the first transceiver, the characteristic data being generated by the first transceiver as part of normal operation of the first transceiver on a communication network, the computer server continuously receiving the received set of baseline signal data and updating the baseline signal profile based on the continuously received additional set of baseline signal data when ? indicates that there is no human body in the detection area.

In another embodiment of the method, the method provides the computer server with characteristic data relating to signal characteristics of a second set of radio signals received by the first transceiver from the second transceiver when one or more human bodies are present within the detection area. receive from the first transceiver a signal data set comprising: wherein the characteristic data is generated as part of normal operation of the first transceiver on the communication network; The computer server further comprises determining a quantity of people present in the detection area based at least in part on the comparison of the signal data set and the baseline signal profile.

In another embodiment of the method, the method further comprises the computer server determining a position of each of the one or more human bodies present in the detection area, the determining comprising at least a comparison of the set of signal data and a baseline signal profile. partially based on

In another embodiment of the method, when the human body is present in the detection region, the computer server determines that the human body is present in the detection region and the characteristic data of the third set of sample baseline signal data corresponds to the second sample baseline signal profile. Even if it does, the first external system is operated.

In another embodiment of the method, when the human body is present in the detection region, the computer server determines that the human body is present in the detection region and the characteristic data of the third set of sample baseline signal data corresponds to the second sample baseline signal profile. The second external system is operated only in the case of

In another embodiment of the method, the wireless communication network has a carrier frequency range covering 850 MHz and 17.5 GHz.

In another embodiment of the method, the method includes: the computer server stores a plurality of history data records indicating whether or not a human body has been present in the detection zone for a period of time, each of the history data records representing a human body detected in the detection zone. each of the number and the number of the human body includes an indication of the date and time detected in the detection area; and the computer server making the historical data record available to one or more external computer systems through an interface.

According to another embodiment of the method, a method for correlating the detection of human activity in space with a desired system action, comprising: a system input and a human body a training phase in which an overall training data set of human activities is provided to the system; model building phase; and an action phase, wherein the human body activity includes a change in the position of one or more human bodies, the presence of one or more human bodies, and a count of human bodies in a physical space. , and/or positions of human bodies in physical space, wherein in the model building step, the system calculates a best fit relationship between the system input and the human body activity; A method is provided wherein the system predicts an action to take based on the optimal relationship, and in the action step, the system performs the predicted action.

The training step and the model building step may be repeated before the operation step.

The system input may include at least one of time of day, calendar date, day of the week, current weather, or predicted weather. The system input may include a comparison of new system input to previous system input. The system input may include an output from a sensor.

The sensor may be selected from the group consisting of a light sensor, a temperature sensor, a carbon dioxide sensor or a location beacon.

According to another embodiment of the method, a method of estimating the number of people in a space, comprising providing a plurality of presence sensing networks in the space - the presence sensing network. each of which may provide at least one data element for a detection area within the space that is specific to that network, and an overall estimate of people within the space ), aggregating all of the data elements from all the presence sensing networks, each of the data elements indicating the presence of at least one person in the specific detection area. selected from the group consisting of detecting, determining the number of people in the detection area, and calculating a metric correlated with the average number of people in the particular detection area within a particular time period. A method is provided.

The result of the aggregation may be periodically recorded and timestamped. The aggregation result may be provided to a requesting party. The requesting party may include a first responder for an emergency in the space. The requesting party may include a robot.

The data element may be a map, a real-world audible or visual signal, an overlay on a display, or directional information in a virtual reality display. information) may be provided as one or more.

The result may be periodically updated by new information from the plurality of presence sensing networks. The result may indicate when one of the presence sensing networks is no longer transmitting data elements. The result may also include information provided from other sensors within the space and information from sensors outside the space.

1 is a schematic diagram of an embodiment of a system according to the present disclosure.
2 is a flowchart of an embodiment of a method according to the present disclosure.
3A shows a schematic diagram of a system for detecting changes in a detection network over time according to the present disclosure.
3B shows a schematic diagram of a system for detecting a change in position of a human body in a detection network over time according to the present disclosure.

The following detailed description and disclosure are exemplified by way of example and not limitation. This description will enable those skilled in the art to make and use the disclosed systems and methods, and will describe several embodiments, adaptations, variations, alternatives, and uses of the disclosed systems and methods. As various changes could be made in the above constructions without departing from the scope of the present disclosure, everything contained in the description or shown in the accompanying drawings is to be interpreted as illustrative and not in a limiting sense.

Generally speaking, described in this application are systems and methods for detecting the presence of a body in a fiducial element-free network. In general, the systems and methods described herein utilize signal absorption of RF communications, and signal forward scatter and reflected backscatter, caused by the presence of a biological mass in a communications network, typically a mesh network. .

Throughout this disclosure, the term "computer" describes hardware that implements the functionality provided by digital computing technology in general, and particularly computing functionality associated with a microprocessor. The term “computer” is not limited to any particular type of computing device, and is intended to include all computing devices, including but not limited to: processing devices, microprocessors, personal computers, desktop computers, laptop computers, workpieces. Stations, terminals, servers, clients, portable computers, handheld computers, smart phones, tablet computers, mobile devices, server farms, hardware appliances, mini computers, mainframe computers, video game consoles, handheld video game products , and wearable computing devices including, but not limited to, eyewear, wrist worn, pendant, and clip-on devices.

As used in this application, "computer" is an abstract concept of functionality provided by a single computer device with hardware and accessories typical of a computer in a specific role. By way of example, and not limitation, the term "computer" in reference to a laptop computer will be understood by those skilled in the art to include functionality provided by a pointer-based input device such as a mouse or track pad, whereas enterprise-class servers and It will be understood by those skilled in the art that the term "computer" when used in connection includes functions provided by redundant systems such as RAID drives and dual power supplies.

It is also well known to those skilled in the art that the functionality of a single computer can be distributed across multiple separate machines. This distribution may function where specific machines perform specific tasks; Or balance where each machine can perform most or all of the functions of any other machine and tasks are assigned based on the resources available at any given point in time. Accordingly, as used in this application, the term “computer” refers to a single, but not limited to, networked server farm, “cloud” computing system, software-as-a-service, or other distributed or collaborative computer network. It may refer to a stand-alone self-contained device or multiple machines operating together or independently.

Those skilled in the art also recognize that some devices that are not commonly thought of as "computers" may exhibit "computer" characteristics in certain contexts. Where such a device performs the functions of a "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 SANs, load balancers, and any other hardware that can interact with the systems and methods described herein in the context of conventional "computers". not limited."

Throughout this disclosure, the term "software" may be executed by a computer processor, including but not limited to a virtual processor or by use of a runtime environment, virtual machine, and/or interpreter. code objects, program logic, instruction structures, data structures and definitions, source code, executable and/or binary files, machine code, object code, compiled libraries, implementations, algorithms, libraries, or any Refers to a set of instructions or instructions. One skilled in the art recognizes that software is not limited to a microchip and may be hard-wired or embedded in hardware and is still considered "software" within the meaning of this disclosure. For purposes of this disclosure, software includes, but is not limited to: RAM, ROM, flash memory BIOS, CMOS, motherboard and daughter board circuitry, hardware controllers, USB controllers or hosts, peripherals and controllers, video cards, audio controllers. , network cards, Bluetooth and other wireless communication devices, virtual memories, storage devices, and associated controllers, firmware, and device drivers. The systems and methods described in this application are typically contemplated using a computer and computer software stored on a computer or machine readable storage medium or memory.

Throughout this disclosure, terms used in this application to describe or refer to software bearing media, including but not limited to terms such as “medium,” “storage medium,” and “memory,” are temporary, such as signals and carrier waves. Media can be included or excluded.

Throughout this disclosure, the term "network" generally refers to a voice, data or other telecommunications network through which computers communicate with each other. The term "server" generally refers to a computer that provides services over a network, and "client" generally refers to a computer that accesses or uses services provided by a server over a network. Those skilled in the art will understand that the terms "server" and "client" may refer to hardware, software, or a combination of hardware and software, depending on the context. One skilled in the art will further understand that the terms "server" and "client" may refer to an endpoint of a network communication or network connection, including but not necessarily limited to a network socket connection. Those skilled in the art will further understand that a "server" may include a plurality of software and/or hardware servers that deliver a service or set of services. Those skilled in the art will understand that the term "host" in noun form can refer to a network communication or endpoint in a network (e.g., "remote host"), or in verb form to refer to a server providing services over a network ("website hosting"). ) or an access point of service over a network.

Throughout this disclosure, the term “real time” refers to software that is capable of starting or completing a given event or operating within an operating deadline for a given module, software, or system to respond, typically responding or Performance times are within normal user perception and, given the technical context, in fact are generally referred to as coincident with the reference event. Those skilled in the art will understand that "real-time" does not literally mean that the system processes and/or responds immediately to input, but that the system processes sufficiently fast that the processing or response times are within normal human perception for real-time delivery in the program's operating environment. and/or respond. One skilled in the art understands that when the operating environment is a graphical user interface, "real-time" generally means a real-time response time of one second or less, with milliseconds or microseconds being preferred. However, one skilled in the art understands that systems operating in "real time" in other operating environments may exhibit delays greater than one second, especially when network operations are involved.

Throughout this disclosure, the term “transmitter” refers to equipment or set of equipment having hardware, circuitry and/or software for generating and transmitting electromagnetic waves that carry messages, signals, data or other information. The transmitter may also include components that receive electrical signals containing such messages, signals, data or other information and convert them into electromagnetic waves. The term “receiver” means a device or set of devices having hardware, circuitry and/or software that receives such transmitted electromagnetic waves and converts them into generally electrical signals from which messages, signals, data or other information can be extracted. . The term "transceiver" generally refers to a device or system that includes both a transmitter and a receiver, such as a two-way radio, or a wireless networking router or access point. For purposes of this disclosure, all three terms are to be understood as interchangeable unless otherwise indicated; For example, the term "transmitter" should be understood to mean the presence of a receiver, and the term "receiver" to mean the presence of a transmitter.

Throughout this disclosure, the term “detection network” refers to a wireless network used in the systems and methods of this disclosure to detect the presence of a biological mass intervening within the communication area of the network. The detection network may use common networking protocols and standards and need not necessarily be a special purpose network. That is, although nodes of the network may be deployed for the specific purpose of establishing a wireless detection network in accordance with the present invention, they do not need to and generally will not. Normal wireless networks established for other purposes may be used to implement the systems and methods described herein. In the preferred embodiment, the detection network uses a plurality of Bluetooth (TM) low energy nodes, although the present disclosure is not limited to such nodes. Each node acts as a computer with appropriate transmitters and receivers to communicate over the network. Each computer that sends a message provides a unique identifier within the network that allows the receiving computer to identify where the message originated. This message origination information will generally be important to the functionality of the present invention described in the detailed description. The receiving computer then analyzes the incoming signal properties including signal strength, bit error rate and message delay. The detection network may be a mesh network, which means a network topology in which each node relays data from the network.

Throughout this disclosure, the term “node” means the start point or end point of a device that communicates over a network, typically a device that has a wireless transceiver and is part of a detection network. Nodes are typically standalone, self-contained networking devices such as wireless routers, wireless access points, short-range beacons, and the like. A node may be a general purpose device or a special purpose device configured for use in a detection network as described herein. By way of example, and not limitation, a node is a device having the wireless transmit functionality of an off-the-shelf wireless networking device with the addition of specialized hardware, circuitry, components, or programming to implement the systems and methods described herein. can; That is, it detects significant changes to signal properties including but not limited to signal strength, bit error rate and message delay. Within a detection network, each node can act as a transmitter of signals into the network as well as a receiver for other nodes to push information. In a preferred embodiment, the node uses Bluetooth Low Energy (BLE) as its wireless networking system.

Throughout this disclosure, the term “continuous” refers to events occurring on an ongoing basis over time, whether mathematically continuous or discontinuous. The commonly accepted mathematical definition of a "continuous function" describes a function without holes or jumps, usually described by a two-sided limit. The techniques described in this application are based on disturbance to telecommunication systems, where transceivers transmit at discrete intervals and received raw data is taken discretely, i.e. at discrete time intervals. The resulting data itself may be discrete in that it captures characteristics of the system over a specific observation window (ie, time interval). In a physical or mathematical sense, this mechanism is a set of discrete data points implying an inherently discrete function. However, in the context of technology, one skilled in the art will understand that a system exhibiting this type of behavior is “continuous” if such measurements are taken on an ongoing basis over time.

The measurable energy density signature of an RF signal is affected by environmental absorbers and reflectors. Many biological masses, such as the human body, are mostly water and serve as important energy absorbers. Other attributes of the human body, such as clothing, jewelry, internal organs, etc., all further influence the measurable RF energy density. This is especially true when RF communication devices transmit over relatively short distances (eg less than 50 meters) such as Bluetooth, WiFi, 802.15.4 (Zigbee, Thread) and Z-Wave transceivers. A human body passing through the network's physical space can cause signal absorption and disruption. Due to the relative uniformity of size, density and mass composition, the human body can give rise to characteristic signal absorption, scattering and measurable reflections. Changes in signal behavior and/or characteristics are generally referred to herein as "Artifacts". This phenomenon is particularly useful in the Industrial, Scientific, and Medical (ISM) band of the RF spectrum, but is typically observed at bands beyond that range.

In an RF communication system that includes a transmitter and receiver separated in space, a signal received by a receiver from a given transmitter is composed of energy from the original transmitted message arriving at the receiver. In general, objects in the transmission path affect the characteristics of the final signal reaching the receiver.

Communication systems are generally designed to address this issue and also faithfully reproduce the message from the sender. Since the human body is usually present, as a large amount of water, as far as RF communication is affected, one of the observable differences between the presence and absence of the human body in the detection network is signal absorption by the human body. In general, the closer to the transmitter or receiver the more significant the absorption can be.

In general, human bodies are expected to generate artifacts in detection networks in a somewhat predictable way that can be programmatically detected or identified by detection algorithms. Artifacts can also be cross-correlated across the network to determine the estimated location of the object causing the artifact. The accuracy of this estimate may vary depending on the algorithm chosen/configured and the equipment used in the individual system.

For each given algorithm selected/configured, the system can build a detection such as a combination of a baseline signal profile with no human body present in the detection region and baseline signal data with a human body present in the detection region. The new incoming sample baseline signal data is compared to the known sample baseline signal data and the baseline signal profile to determine the presence or absence of a human body in space.

Short-range, low-power communication networks typically operate using signals in the 2.4 GHz frequency band, which is notable for being significant within the energy frequencies observed to be absorbed by the human body. As indicated, the human body physically intervened in the detection network absorbs and/or reflects at least some of the signals transmitted between and among the nodes. However, other effects such as forward and back scattering may also occur. Utilize data collection from the detection network without human presence to establish a baseline, and future elements of the data for statistically significant differences typically exhibited by the physical presence of one or more human bodies, regardless of whether one or more human bodies are moving. , the detection network makes a decision regarding the presence or absence of a human body within the network.

Depending on the communication network itself, the hardware used and the human body, these changes may register in the network in different ways and produce different results; However, such changes are detectable. It differs from radar technology in that the detection of an object does not depend or need not rely solely on signal reflection, but on the opposite principle, signal absorption, which is often detected through measurable changes in signal characteristics between transmitter and receiver at different physical locations. .

By analyzing changes in signal characteristics between nodes in the network, the location of disruptors and, for example, human bodies can be calculated for the network. Since the mere existence of the body suffices, the system need not necessarily include fiducial elements, and need not rely on motion or movement. Because fiduciary elements are not required, the systems and methods described herein can provide anonymous location data reporting services, information about traffic, travel routes and occupancy without the need for additional components or devices to be associated with the body being tracked. data can be collected. Generally speaking, the systems and methods described herein operate in real time.

1 is a schematic diagram of a system and method according to the present disclosure. In the illustrated embodiment 101 of FIG. 1 , a detection network 103 comprising a plurality of nodes 107 is disposed within a physical space 102 such as a room, corridor, hallway, or doorway. In the illustrated embodiment of FIG. 1 , indoor space 102 is used, but the systems and methods described herein are capable of operating in an outdoor environment as well. In the illustrated embodiment, node 107A is communicatively coupled (111) to a telecommunications network 115, such as an intranet, the Internet or the Internet. The server computer 109 may also be communicatively coupled to the telecommunications network 115 and to a node 107A connected thereby (113). The illustrated server 109 includes programming instructions for implementing the systems described herein and performing the method steps described herein. However, in one embodiment, functions performed by the server may be performed by one or more nodes 107 having appropriate software/programming instructions or modified as appropriate.

In the illustrated embodiment of FIG. 1 , each node 107 is communicatively coupled to at least one other node 107 in the detection network 103, and two or more or all other nodes in the detection network 103 (107) can be communicatively connected. For example, in a typical wireless network deployment strategy, multiple wireless access points are deployed throughout the physical space 102 to generally ensure that a high quality signal is available everywhere. These nodes 107 collectively form the detection network 103 and may transmit data to each other or only to a router or set of routers. In the illustrated embodiment of Figure 1, node 107A is a wireless router, and other nodes 107B, 107C and 107D are wireless access points. However, this is one possible configuration. Also, any given node 107 need not be a particular type of wireless device. Any number of nodes 107 may include routers, access points, beacons, or other types of wireless transceivers. Additionally, although any number of nodes 107 may be present in one embodiment, a minimum of two is preferred. More nodes 107 in space 102 increase the amount of data collected (as described elsewhere in this application), and improve the likelihood that a human body will normally be sandwiched between at least two nodes 107. to improve location resolution.

In the course of normal operation, node 107 frequently transmits and receives radio transmissions. For example, when wireless router 107A receives a data packet, wireless router 107A typically broadcasts a wireless transmission containing the packet. This means that any receiver within the broadcast radius of router 107A can receive the signal whether intended or not. Likewise, when an access point receives local data, this data is broadcast as well and can be detected by other access points and routers. Even if user data is not actively transmitted in the network, other data is frequently transmitted. These other transmissions may include data exchanges for status data, service scans, and functions of lower-level layers of the network stack.

Thus, each node 107 in a typical detection network 103 receives transmissions on a consistent basis, and in a busy network this may be a substantially continuous basis. Accordingly, detection network 103 may be used to calculate the presence and/or location of biological masses 104 or 105 physically intervening within transmission range of network 103 . Since the presence of a human body affects the characteristics of signals transmitted between or among nodes 107 in the network 103, such presence can be detected by monitoring changes in those characteristics. This detection can also be performed while the data of the transmitted and received data packets is still being transmitted and received; That is, detection occurs in normal data exchange between or among two or more nodes, which continues regardless of detection. Specifically, a wireless network operates to transmit data between nodes while detecting and locating an object using characteristics of the manner in which data packets incorporating that data are affected by the presence of the object within the transmission path. can do.

In the illustrated embodiment of FIG. 1, at least one node 107 is sensitive to statistically significant changes in signal characteristics even while waiting for, receiving, and/or transmitting communications between itself and other nodes 107. Monitoring the communication signature between (107) and at least one other node (107). Certain geometries of the physical space 102, including the presence and location of fixtures in the physical environment, generally do not affect the system, and monitoring detects statistically significant changes in signal characteristics representing or demonstrating characteristics of the human body. because it is about That is, changes in signal characteristics are due to changes in an absorber or reflector such as a human body in a physical environment covered by the detection network 103 or in a communication space. Detection of the presence of a human body within the detection network 103 may be performed using statistical analysis methods for the signals, such as using sensing algorithms, as described elsewhere in this application. Again, this does not require the human body to be associated with a fiducial element or motion. Instead, detection network 103 detects that a new object (typically a human body object) has been introduced into the communication space and that object's presence has caused a change in the nature of the network communication between nodes 107, typically a data packet. Detect that characteristics of network communication have changed.

To detect changes, a baseline of signal characteristics is usually developed against which recently transmitted signals are compared. These properties are derived from typical wireless communication network diagnostic information. This baseline of signal characteristics between nodes 107 is typically established prior to using detection network 103 as a detector. This can be done by operating the detection network 103 in a typical or normal environment, i.e. the detection network 103 communicates data packets and does not have significant biological mass intervening in the physical broadcast space of the detection network 103. . For a period of time during such operation, signal characteristics between and/or among nodes 107 are monitored, collected, and stored in a database. In one embodiment, server 109 receives and stores such data, but in one embodiment, one or more nodes 107 may comprise a hardware system configured to receive and/or store such data.

For example, where a node 107 includes special purpose hardware and programming for use in accordance with the present disclosure, such node 107 may store its own signal characteristic data. Such signal characteristic data may be data related to received energy characteristics of a signal received by a particular node 107 from one or more other nodes 107 . The baseline data establishes a signature characteristic profile for each node 107, which is essentially typical of a signal received by a node 107 under normal operating conditions with no significant biological mass intervening in the detection network 103. and/or a set of data defining general characteristics. A node 107 may have one or more such profiles for different nodes 107 receiving data.

In one embodiment, after the baseline signature has been detected and collected, the detection network 103 will continue to operate in a generally the same or similar manner, but may now detect the presence of a biological mass. This is done by detecting and collecting additional signal characteristics, typically in real time, when the detection network 103 operates in a normal mode of transmitting and receiving data packets. Since these newly generated real-time signal characteristic profiles are also generally characteristic of the signal between two specific nodes 107 in the detection network 103, the corresponding baseline signal characteristic profiles for the same two specific nodes 107 and can be compared Statistically significant differences in certain characteristics between the two profiles can be interpreted as being caused by the presence of significant biological mass, such as the human body.

The comparison operation may be performed by appropriate hardware at a given node 107 or the real-time signal characteristic profile may be transmitted to server 109 for processing and comparison. In a further embodiment, both are performed so that a copy of the real-time data can also be stored and accessed via the server, effectively providing a history of the signal characteristic profile.

This is because, as described herein, a biological mass intervening in a network generally intercepts and/or generally interacts with a biological mass, and at least some signal characteristics between at least two nodes are changed when a data packet is transmitted. because it makes The extent and nature of the change will generally be related to the nature of the particular biological mass intervening (eg, size, shape and composition) and its location 103 in the network. For example, when a housefly flies through the detection network 103, the amount of change in the signal may be so small that it is indistinguishable from natural fluctuations in the signal characteristics. However, larger masses such as the human body may result in more substantial and statistically significant changes in signal characteristics.

These changes need not necessarily be present in every signal characteristic profile for the detection network 103. For example, if a mass intervenes on an edge of the detection network 103, the node 107 closest to that edge is likely to experience a statistically significant signal characteristic change, while the node on the opposite side of the detection network 103 Nodes will have little or no statistically significant change (where each other's signals pass through the biomass or not through the periphery). Thus, if the physical location of node 107 is also known, the system not only determines whether a biological mass is present in detection network 103, but also which node 107 is experiencing a change and is calculating the magnitude of that change. By determining it, you can calculate an estimate of where it is located.

This can be seen in the illustrated embodiment of FIG. 1 . 1 , assuming that there is only one human body (A 104 or B 105) exists for simplicity, A 104 is generally at node 107C rather than between nodes 107A and 107C. ) and the signal characteristics between node 107A. Moreover, A 104 also typically has a small bi-directional effect on the signal characteristics between nodes 107B and 107D. Conversely, B 105 will bidirectionally affect the signal characteristics between nodes 107A and 107C as well as the signal characteristics between nodes 107B and 107D.

Although all nodes can communicate with each other, the influence of A 104 and B 105 is usually greater in communications where A 104 and/or B 105 are not normally aligned with the communication path between nodes. can be ignored For example, none of the human bodies 104 or 105 may significantly affect the transmission between nodes 107A and 107B because the human body 104 or 105 is not in the transmission path between those nodes. However, A 104 may affect the transmission between nodes 107C and 107D.

It should be noted that the presence or absence of a biological mass within the communication area of the detection network 103 will not necessarily result in any change to the data communication. Detection network 103 is expected to use its standard existing protocols, means and methods (including all forms of retransmission and error checking) to ensure that data in transmitted data packets is correctly received, processed and operated on. In practice, the detection process of the detection network 103 is performed in addition to the standard data communication of the detection network.

From this it should be appreciated that data in data packets communicated by nodes 107 in detection network 103 will not generally be used directly to detect biological masses within the communication area of detection network 103. Instead, the data will simply be data communicated through the detection network 103 for whatever reason, often unrelated to the detection of a biological mass. Moreover, while this disclosure generally contemplates packetized communication in the form of data packets, in alternative embodiments, data may be communicated continuously in unpacked form.

In one embodiment, to enable detection network 103 to detect the presence or absence of a particular biological mass, the system includes a training aspect or step. This aspect may include, after a baseline is established, one or more persons are intentionally intervened in the network at one or more locations in the network, and one or more additional baseline data sets are collected and stored. This second baseline can be used for comparative purposes to improve the accuracy of detecting the size, shape and/or other characteristics of the biological mass intervening in the network and/or to improve the accuracy of location determination. Such training may use supervised learning or unsupervised learning and/or may utilize techniques known to those skilled in the art of machine learning.

In one embodiment, detection network 103 may use a specialized protocol that includes a controlled messaging structure and/or format that can be controlled from one node 107 to another node 107, such that any node 107 ) from which the message originated is simpler and easier, allowing control of aspects such as composition of the transmitted signal, transmitted signal strength and signal duration. Such control further facilitates certain improvements in processing, identifying and using certain signal qualities and/or characteristics specific to the detection aspects of the network 103 that may differ from the general networking aspects that share the same network 103. enable the receiver. There is no need to scan a signal or sweep an area in space when controlling messages sent or received on opposite sides of a positioned mass, such functions far beyond those required for typical broadcast or directional transmission between nodes 107. This is because they tend to require more expensive equipment. Messages are generally structured in a way that best produces usable data for detection algorithms that are configured to work best with the communication network in use. In general, such an arrangement still avoids the need for waveform level analysis of signals transmitted by the network.

In the illustrated embodiment, each node 107 can generally determine the originating node 107 of packets received by that node 107 . Such message origin information is typically encoded within the message itself, as is known to those skilled in the art of communication networks. By way of example, and not limitation, this may be done by examining data embedded in established protocols in the networking stack, or by examining data transmitted by the originating node 107 for the specific purpose of implementing the systems and methods described herein. can be performed Typically, each node 107 has appropriate hardware and processing capabilities to analyze received messages. Many different topologies and messaging protocols allow for the functionality described herein, but generally mesh networking topologies and communication methods will produce useful results.

FIG. 2 illustrates an 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 the establishment ( 203 ) of a detection network ( 103 ) comprising a plurality of communication nodes ( 107 ) according to the present disclosure. As is known to those skilled in the art of establishing communication systems, many different approaches to the setup of such a network 103 exist, and within this framework many other network 103 topologies may be feasible.

Next, a digital map in memory representing the physical node 107 geometry of detection network 103 may be created (205). The detection algorithms described herein generally use information about where nodes 107 are placed in the physical environment 102 . Data regarding these physical locations of nodes 107 can be manually fed into an accurate diagram of the physical network environment 102 and/or software creates a map of the relative locations of one or more nodes 107 within the detection network 103. used to automatically generate, facilitating easier placement of nodes 107 into such environment maps or diagrams.

Alternatively, node 107 may be placed in an empty map or empty map or diagram using relational (as opposed to absolute) distances for detection. In such a dimensionless system, messages can still be generated from algorithms related to the detection of human bodies in the system (101), and within the network (103) users about which human body movement and/or presence related messages are being sent. Additional manual processing such as typing may be involved.

In embodiments with automatic node 107 location detection, node 107 locations may include, but are not necessarily limited to: the physical location of a particular hardware component, such as node 107, and relative to one or more other nodes 107, respectively. setup and configuration of detection network 103, including location of node 107 in; signal strength indicator; and algorithmically and/or programmatically detected by one or more nodes 107 and/or computer server 109 based on factors such as transmission delay. In the illustrated embodiment, this step 205 includes overlaying a map created on a digital map of the physical space 102 or environment (referred to herein as an “environment map”); , the detection network 103 occupies the floor plan of the building. This step 205 may additionally and optionally include a scaling element to align the scale of the generated map to the environment map, and a user operable and/or modifiable input element to adjust the generated map for fine-tuning. , so that it more closely conforms to the actual node 107 placement geometry, as would be appreciated by those skilled in the art. In an alternative embodiment, each node 107 may be manually placed in an appropriate location on the environment map without using a relative positioning algorithm.

Either way, this step 205 establishes the physical location of node 107 in detection network 103, which enables determination of the location of the intervening biological mass due to the presence of a human body within detection network 103. will make By placing nodes 107 on the map (either manually or via automatic means), nodes 107 are mapped to the human body in the network 103 based on how the baseline signals affect communication between the various nodes 107. existence can be traced. System 101 then uses the collected information about the signal reaching the receiver, given the set of transmitted information known to the data processing algorithms. The data processing algorithm is ultimately to determine whether a human body exists within network 103 and/or where a human body is located within network 103 .

Next, messages are constructed and exchanged according to a protocol in a format determined to be suitable for detecting the presence of a biological mass within the network 103 (207). This can be done using general-purpose networking protocols known in the art, such as those of the OSI network model, or special-purpose protocols that replace or supplement such general-purpose protocols.

Generally, this step preferably further includes controlling and/or modifying 207 messages passed within the detection network 103 for the specific purpose of detecting human presence and enabling simplified statistical analysis. Do. By controlling the message exchange (207), the system 101 adjusts for common content sent over the detection network 103, including but not limited to transmission intervals; transmit power; message length and/or content; and enable adjustment of parameters including the intended message recipient(s). Again, the system does not have to rely on waveform level analysis, so it can operate within the scope of wireless communication standards.

Controlling these parameters 207 allows for the development of statistics and/or analytics, which may be based at least in part on predefined or expected message content or characteristics. Such content and/or characteristics may include, but are not limited to, transmit time stamps and/or transmit power levels. By controlling and modifying these aspects, detection network 103 according to present disclosure 207, such as, but not necessarily limited to, automatic gain control (AGC) circuitry that may be incorporated into specific receiver hardware at node 107. It can overcome hardware limitations, including hardware features that cause undesirable results when used in

In the next illustrated embodiment (201), the space (102) clears (209) significant biological mass, in particular the human body (205). A statistical baseline of signal strength is then developed locally by each node 107 (211). Again, by placing node 107 on the map via manual and/or automatic means in step 205, node 107 is able to determine based on how the baseline signal affects communication between nodes 107. The presence of a human body can be tracked in the network 103 .

Next, the biological mass enters the detection network 103 (213), causing signal absorption and other distortions, which manifest in changes in signal characteristics between nodes (107). Such changes are detected (215) and analyzed (217) to determine whether the changes are indicative of the presence of a human body or other type of biological mass that the detection network (103) is configured to detect. This detection is more limited to regions between nodes, such as within an internal region between at least three nodes on the network, but is possible with greater accuracy depending on the algorithms and hardware in use at the time.

Generally, this is done using a detection algorithm executed by one or more nodes 107 or server computers 109. Nodes 107 and/or servers 109 use software to determine the location of biological masses detected in detection network 103 using one or more detection algorithms. These algorithms generally compare a baseline profile to newly detected signals, and also, for example and without limitation: the physical location of a particular hardware component, such as node 107, and each node 107 relative to one or more other nodes 107. ) setup and configuration of the detection network 103, including the location of; signal strength indicator; and various data and other aspects such as transmission delay.

Generally speaking, as described elsewhere in this application, these algorithms compare a newly collected signal characteristic profile 215 to a baseline signal characteristic profile 211 to identify a change and, based on the nature of the change, identify the change. Including determining whether it indicates the presence of a human body. This determination may be performed at least in part using training data developed through machine learning as described elsewhere in this application.

In one embodiment, the detection algorithm may further include the use of the observed signal characteristic change(s) between one or more pairs of nodes 107 in the detection network 103, correlated in time and relative effect. These factors enable identification of the physical location in the detection network 103 where such a signal change occurred, allowing estimation of the physical location of the human body causing this signal characteristic change(s), which in turn allows the biological mass to It can be used to estimate a physical location in an intervening detection network 103 environment. This physical location can be given as simple x, y, z coordinates according to a coordinate system or can be displayed visually on a map, for example.

When multiple human bodies are present in the detection network 103, it is more difficult to separate the influences of the various individuals from each other, and accuracy will generally be improved by adding more nodes 107. In one embodiment, techniques such as advanced filtering and predictive path algorithms may be used to individually determine an individual's location within the network 103 . Although motion of the human body in the network 103 is not required for the systems and methods to operate correctly, motion or lack of motion can be used to improve detection accuracy by predicting the path of a single person. This can help identify instances where an individual has statistically “disappeared” from detection network 103, but the system has enough data to infer that the individual still exists in network 103.

For example, if an individual's movement path is predicted and ends next to another detected individual, system 101 may determine that the two individuals are too close for signal characteristic profile changes to individually identify them, but because of the individual's movement, the system 101 may determine that the path has not determined the individual to be out of network 103 detection range, and the algorithm determines that the individual is in close proximity to another detected body and does not move. Thus, when one of the two adjacent stationary bodies moves, the algorithm can individually identify each again and resume path prediction based on the observed signal characteristic profile change.

In this way, systems and methods according to the present disclosure can track whether one or more individual human bodies within the network 103 are moving, and whether those human bodies are associated with fiducial elements. Specific individual identification may further be performed using other path prediction and sensing algorithms, such as those used in body tracking technology in the robotics industry, to estimate who the specific individual is. It should be noted that individuals can impart specific and unique influences on various signal properties that allow identification of particular individuals and also allow one particular individual to be distinguished from other individuals. This influence can be used to further determine the location of a particular individual within the detection network.

The detection algorithm(s) are generally configured to take advantage of characteristics of the communication signal taking into account factors such as, but not necessarily limited to, the frequency of the signal(s) and the transmitted power level of the signal(s). In one embodiment, an algorithm determines the effect of the presence of a human body on signal characteristics in an RF environment within a communications network, and then uses a data-driven method to identify when that effect is later observed. detect the presence

For example, in one embodiment, the signal characteristic that changes with the presence of a human body is the signal strength registered between nodes 107 . This is especially the case within a BLE network, where statistics related to signal strength over time can indicate the presence of a human body within the network. These artifacts can be used by detection algorithm(s) to provide information about the physical location of the object causing the artifact. That is, by combining various statistics about artifacts captured over network 103, the system determines where the artifact is in physical space 102 and, therefore, where the human body is within network 103.

In the simplest use case, the algorithm can simply identify changes in signal characteristics that are similar to changes known to be caused by the presence of the human body (e.g., from training), and whenever such changes are detected relative to baseline A detection event 219 can be triggered. This may look like an adjustment of the average, standard deviation, skewness or variance of the signal strength depending on the system 101 used. When the detected signal characteristic profile returns to a profile similar to the baseline, it can be assumed that the physical environment 102 has returned to an empty state with respect to the presence or absence of a human body.

Elaborating the simplest use case, in this case the baseline profile consists of some or all of the baseline profiles that exist when the space does not contain any human bodies and may vary depending on physical adjustments to that space. . A simpler algorithm that can account for changes associated with newly detected anatomical changes relative to a recent baseline can be used to handle such situations; However, when the baseline is changed, it is desirable for the system to accurately determine whether one or more current signal profiles match an empty baseline profile or a profile representing some degree of occupancy. Although this determination may be made in response to motion, it is preferably not made in response to motion, but rather based on whether characteristics of such a signal can be correlated with one or more bin baselines or one or more presence signal profiles.

Compared to other technologies (typically Passive Infrared (PIR) sensors) used to make such determinations that motion is required to perform a function, the systems and methods described in this application can be compared to the presence of a static human body within space 102, the presence of a moving human body, It is possible to detect whether or not, more precisely, when the human body is no longer in the space 102 . For applications such as security and occupancy sensing, this system can be more difficult to fool. Some examples of tricks that can trick PIR and other similar motion-based technologies are moving very slowly with a sheet while the human body enters the space, or generally remaining motionless in an area after entering. Another advantage is that the system does not require any additional hardware other than the one used for normal network communication. This is because additional software and processing functions can be provided through external components or modifications to existing hardware, such as implementing appropriate software such as System On a Chip (SOC) attached to off-the-shelf communication modules. If additional processing power is required, additional processing node(s) can be added to analyze the signals propagated between nodes 107, or the workload is transferred to a dedicated server machine 109 and attached to it. can be processed by

Determining the presence and/or location of the human body may involve specifying the specific types of signals to be analyzed, and controlling the signals transmitted between nodes 107 on the network 103 to best achieve such detection. By sending controlled communication pulses through the network 103 where the original signal is known and the transmitted power can be modulated, an exemplary implementation related to signal absorption, reflection, backscattering, etc. due to additional human bodies between the nodes 107. data can be developed. Since it is generally assumed that a baseline system can be configured without the presence of a human body and that such a baseline will look statistically different from the presence of a human body, signal characteristic changes can further be assumed to be due to the presence of a human body in the network. By configuring the system to allow entry of a timer when space 102 is empty and generally improve the baseline definition, the system can be periodically recalibrated to achieve improved accuracy. Generally speaking, the tracking algorithm uses best available triangulation calculations combined with statistical methods known to those skilled in the art of location, combined with detection algorithms for detecting human bodies within network 103.

The present invention does not require a fiducial element associated with the detected human body, nor does the human body need to have any device capable of communicating with the network; However, such techniques utilize such elements when deployed within a system. Adding these elements can reduce the computational burden on the system and increase accuracy. The systems and methods described herein do not preclude such additional functionality, and may be enhanced thereby. Augmenting detection with an inference engine makes the system more robust as the sensing hardware can recover from false alarm conditions or other edge cases. Such an inference engine may further feed information into the machine learning system, which may further modify one or more baseline signal profiles or one or more presence signal profiles to improve the performance of the system.

In one embodiment, detection network 103 implementing the systems and methods described herein may further include an element 219 that takes action based on the presence and/or location of a detected human body. This may be done, for example, by first determining the presence and/or location of a human body on the network via the network, then determining an action to perform based on the presence and/or location of the human body on the network, and then using the network to take that action. This can be done by sending control signals over a network using a computer to send messages through. Because the communication network and the network performing the detection can be the same network, the invention described in this application extends the traditional functionality of the communication network to include human body detection and/or position sensing without requiring additional sensing hardware.

The computer elements of the network must perform additional calculations and may generate communication signals. This can reduce the computational burden on the computer; However, the network may still function as a command and control network independent of the network as a detection network.

Systems as a whole range from occupant sensing that can be used for lighting control and/or security, to counting the number of people in a space needed for heat and/or traffic maps to systems that track individual human bodies as they move through a space. Can be used for applications. The technology may be integrated into the network node itself, or it may be a combination of nodes that transmit information to processing elements (either directly on the network or in the cloud) to perform calculations to determine the desired information. The resulting integrated suite can be tailored to the application and can be used in a variety of ways.

No additional sensors are required (but in one embodiment, sensors may be present), but detection is effectively achieved by calculating statistics from the traditional RF communication stack. Such a system avoids collecting personal data from people walking through the space, since the system knows that an approximately human-sized mass of water, organs, clothing, etc. has been passed over, requiring any separate device to act as a fiducial element. don't As such, the technique is a major departure from traditional methods of tracking a human body as it moves through space.

A logical extension of the systems and methods described herein includes dynamically processing functional network messages within statistical analysis to avoid or reduce additional messaging overhead for the system. Further, in one embodiment, the systems and methods described herein are extended to include dynamic adjustments to network and/or message structure, configuration and/or operating parameters based at least in part on functionality messages transmitted within the network. is considered to be

Moreover, since tracking is usually based on signals affected by the body mass, the system does not rely on a human body moving around for detection. Because it does not rely on motion, it overcomes many of the drawbacks associated with traditional presence sensing technologies such as passive infrared and ultrasonic sensing technologies.

In a network where the human body does not have a fiducial element, the use of communication network signals between nodes to detect the presence of a human body is a radical departure from current non-fiducial element detection methods and a completely new way to perform presence sensing. use a communication network for The combination of detection technology and the use of network nodes as a transmitter-receiver combination to perform human presence detection presented in this application provides a new type of human presence detection system that does not require additional equipment beyond that required to form the communication network itself. make up

The systems and methods described in this application can be implemented in a communication network for normal communication purposes without affecting the operation of the network itself. The network continues to operate as a communication network as its main function, but in this case some communication is used to calculate the position of the human body present in the network. Because the systems and methods described herein utilize the basic operation of the network, a human body within a network that additionally carries a transceiver device known to the network can be detected and located with increased accuracy. Such transceiver devices, which may include, for example, mobile computing devices having wireless transceivers, such as cell phones, cell phones, smart phones, tablet computers, wearable computer technology, etc., may be connected to a network and employ traditional triangulation methods known to those skilled in the art. It can be located by network using When a person carries such a transceiver, machine learning algorithms can be applied, which in turn can further improve performance.

The calculated position of a known transceiver device can be compared to the position of a person determined by the non-transceiver aspects described herein. If the communication network reports both the position of the fiducial element and the human body within the network, these two positions can be compared. In general, since the detected position of the fiducial element has a higher accuracy than the estimated position of the human body based on network communication alone, the position calculation of the position of the human body in the network is the position calculation of the system relative to the next human body entering the network. It can be tuned using machine learning algorithms to improve performance.

Using a machine learning algorithm, the system can improve the accuracy of the position prediction algorithm based on the known position from the transceiver. This allows you to check your prior decisions and refine your future decisions. For example, if previous decisions are found to be consistent by approximately the same amount, that amount may be applied to future decisions as an adjustment. In this way, the system can be continuously improved and trained to better locate the human body within the network. Likewise, machine learning can continuously improve detection and false alarm rates. By way of example and without limitation, data regarding previous traffic patterns at a facility may be used to establish defaults, estimates or expectations regarding the range of times or days during which a particular facility is generally occupied or generally unoccupied. The system can use this data to improve performance.

Additionally, the system includes a network element; That is, making inferences based on physical interaction with a device or component communicating with or attached to a network that is or is operable based on the presence of a human body, such as a network-operable electrical switch, door, motion sensor, infrared sensor, or the like. configured to derive These physical interactions can be considered fiducial elements at the point of interaction for the purposes of the system. As an example, if a light switch that is part of a network is actuated, the system may infer that a human body was present at or near the physical location of the switch when the switch was actuated. As such, the system translates that information into a known data point to which machine learning can be applied to better predict the presence of a human body in the future (i.e. the inferred knowledge that the characteristic reflects the human body at a specific location near the switch). It can be used as an inspection of the signal characteristics of various network devices at a point). Additionally, these events can be used as presence triggers for other purposes, such as security alerts. As an example, suppose the system is in secure mode and someone has found a way to hide their presence but still interacts with the switch, the system can determine that someone is present and send an alert based on their interaction with the switch. Generally speaking, interactions with a system are physically and logically defined, and logical interactions will include typical usage patterns based on time, external inputs, etc. These systems serve as a backup to RF presence sensing and provide additional machine learning capabilities to the system.

Additionally, the system can infer whether a mobile transceiver in the network is actually being carried by a human body, eg where the human body has left the device at a location within the network. Since the system can detect the human body as biomass through changes in signal characteristics, it can detect whether a transceiver is present in the network while there is no human biomass. This prevents erroneous training of the system and prevents the baseline and presence signal profiles from being corrupted by data not correlated with these profiles.

In one embodiment, as an additional input to the inference engine, if some representation of the system changes state, and the human body within the detection area behaves in a way that corrects the system state, the system better reflects user preferences. It can be inferred that the baseline and premise profiles for For example, if the lights in a room are to be turned off along with a human body in the room, the human body may physically move or reflect its presence, such as waving an arm, or simply perform an action such as looking for a wall switch or walking towards it. . This movement can be detected within a reasonable amount of time and the system can determine that it has mistakenly determined that the space is empty and adjust the baseline and presence profiles accordingly. This activity may be referred to as inferring the presence of one or more human bodies in space.

As a side effect of being able to collect different signal characteristics and run them through different algorithms, the system can run multiple detection calculations simultaneously to achieve different performance criteria in the same system. By way of example, the same communications network may be used for detection related to lighting and security; However, the collected statistics may be processed differently for the two applications, but concurrently. In this way, lighting applications can still provide shorter detection times to detect but potentially higher false alarm rates, while security applications can trade slightly longer times to detect while reducing false detection rates. there is. The characteristics of the signals processed by the system may vary depending on the application, but they are all captured in the communication network and can be processed simultaneously in several ways. This processing method may be encapsulated with several sets of different sample baseline signal data to determine detection relative to the baseline signal profile.

In one embodiment of the system according to the present invention, the system comprises a communication system capable of determining the presence of one or more human bodies from information about radio signals between two or more computers on a network, each computer having a transceiver for communication. ; and computing elements for performing calculations, each computer sending a signal to one or more other computers on the network, the signal including a unique identifier of the computer sending the signal; Each computer processes received signals for the purpose of determining the presence of one or more human bodies; and the one or more human bodies do not require the person to have any device capable of communicating with the network.

In one embodiment of such a system, an algorithm determines the presence of one or more human bodies using statistical methods. In a further embodiment of such a system, a statistical method determines the number of persons present. In yet further embodiments of such a system, the system may determine the physical location of one or more human bodies on the network. In another embodiment of such a system, the system may track the physical location of one or more human bodies over time. In another further embodiment of such a system, the system uses information about the presence of one or more human bodies to control devices on the network. In one embodiment, the network is a mesh network.

In one embodiment, the computers determine their relative physical locations and further determine the relative physical locations of one or more human bodies on the network. In a further embodiment, statistical methods are applied to measurements of signal strength to determine the presence of a human body. In a further embodiment, the transmitted signal is controlled to more easily detect the presence of a human body. In another embodiment, the power level of the transmitted signal is controlled to facilitate the presence of a human body. In a further embodiment, the system functions as an occupancy sensing system. In a further embodiment, the occupancy sensing system controls the lighting system. In a further embodiment, the network for controlling the lighting system and the network used for occupancy sensing use the same communication technology and hardware. In a further embodiment, the communication technology employed by the computer is selected from a list of Bluetooth low energy, Wi-Fi, ZigBee, Thread and Z-Wave.

In a further embodiment, the system functions as a sensing system for security applications. In a further embodiment, the security sensing system controls the security system. In a further embodiment, the network for controlling the security system and the network used for security sensing use the same communication technology and hardware. In a further embodiment, the system functions as a human body detector for a robotic system. In a further embodiment, the robotic system has a computer that dynamically positions the various elements of the robotic system relative to each other. In a further embodiment, the network for controlling the robotic system and the network for functioning as a human body detector for the system use the same communication technology and hardware.

In a further embodiment, the system functions as a sensing system for HVAC applications. In a further embodiment, the HVAC sensing system controls the HVAC system. In a further embodiment, the network for controlling the HVAC system and the network used for HVAC sensing use the same communication technology and hardware.

In another embodiment, the system uses machine learning to improve detection capabilities and allows a person with their fiducial element to: (1) use known location techniques to determine the location of the fiducial element; (2) using the system described above to locate a person; (3) comparing the position calculated by the method (1) of this paragraph with the method (2) of this paragraph; (4) Train the system by adjusting the positioning method using a machine learning algorithm to improve the system's position calculation ability.

In another embodiment, the system may infer the presence of a human body in the network based on the human bodies interacting in some way with one or more computers on the network. In a further embodiment, the system may use the estimated presence of the human body as an input for machine learning to improve detection capabilities.

In one embodiment of the system according to the present invention, the system includes a communication system capable of determining the presence of one or more human bodies, both stationary and moving, from information about signals between two or more computers on a network, each computer communicating transceiver for; and computing elements for performing calculations, each computer sending a signal to one or more other computers on the network, the signal including a unique identifier of the computer sending the signal; Each computer processes received signals for the purpose of determining the presence of one or more human bodies; The one or more human bodies do not require the person to have any device that can communicate with the network.

In one embodiment, the algorithm determines the presence of one or more human bodies using statistical methods. In another embodiment, a statistical method determines the number of human bodies present. In another embodiment, the system may determine the physical location of one or more human bodies on the network. In other embodiments, the system may track the physical location of one or more human bodies over time. In another embodiment, the system uses information about the presence of one or more human bodies to control devices on the network. In another embodiment, information regarding the presence of one or more human bodies is available to one or more systems not directly involved in determining the presence. In other embodiments, the system has the ability to self-optimize to achieve a given performance according to one or more preset criteria.

In a further embodiment, communication protocols or networks are generally defined by standards committees, including but not limited to protocols such as Bluetooth low energy, Wi-Fi, ZigBee, Thread, and Z-Wave. In another embodiment, a statistical method is applied to measurements of received signal strength to determine the presence of a human body. In another embodiment, transmitting and receiving devices on the network may be selected and actuated by the system to facilitate human body detection. In another embodiment, the power level of the transmitted signal may be controlled to facilitate the presence of a human body. 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 for controlling the lighting system and the network used for occupancy sensing use the same communication technology and hardware.

In another embodiment, the system functions as a sensing system for security applications. In another embodiment, the security detection system controls the security system. In another embodiment, the network for controlling the security system and the network used for security sensing use the same communication technology and hardware. In another embodiment, the system functions as an occupancy sensor for a heating, exhaust, and cooling (HVAC) system. In another embodiment, the occupancy sensing system controls the HVAC system. In another embodiment, the network for controlling the HVAC system and the network used for occupancy sensing use the same communication technology and hardware.

In another embodiment, the system uses machine learning to improve detection capabilities and allows a person with their fiducial element to: (1) use known location techniques to determine the location of the fiducial element; (2) using the system to locate people; (3) comparing the position calculated by (1) of this paragraph with (2) of this paragraph; (4) Train the system by adjusting the positioning method using a machine learning algorithm to improve the system's position calculation ability.

In another embodiment, the system may infer the presence of a person in the network based on the persons interacting in some way with one of the computers on the network. The interaction may be a direct physical interaction or an indirect interaction in response to a state change in the system (eg waving an arm in response to a light being turned off). In another embodiment, the system may use the estimated presence of the human body as an input for machine learning to improve detection capabilities.

Also described herein is a communication system capable of determining the presence of one or more human bodies, both stationary and moving, in a detection network from information about signals between two or more computers on the network, each computer comprising: a transceiver for communication; and computing elements for performing calculations, each computer sending a signal to one or more other computers on the network, the signal including a unique identifier of the computer sending the signal; Each computer processes received signals to determine the presence of one or more human bodies in two or more ways to achieve different performance criteria required to function simultaneously for two or more purposes; The one or more human bodies do not require the person to have any device that can communicate with the network.

In one embodiment, the algorithm uses two or more statistical methods to determine the presence of one or more anatomy according to two or more sets of performance criteria. In other embodiments, the system has the ability to self-optimize to achieve two or more performance sets according to two or more pre-established criteria. In a further embodiment, communication protocols or networks are generally defined by standards committees, including but not limited to protocols such as Bluetooth low energy, Wi-Fi, ZigBee, Thread, and Z-Wave. In another embodiment, two or more statistical methods are applied to the measurement of received signal strength to determine the presence of a human body according to two or more sets of performance criteria. In another embodiment, the system uses machine learning to enhance the detection capability of two or more methods for determining presence and allows a person with their fiducial element to: (1) use a known location description to determine the location of the fiducial element. what to use; (2) using the system to locate people; (3) comparing the position calculated by (1) of this paragraph with (2) of this paragraph; (4) Train the system by adjusting the positioning method using a machine learning algorithm to improve the system's position calculation ability.

In one embodiment, the systems and methods described herein include tamper detection. By way of example and not limitation, change detection may or may use a rolling baseline approach. In this embodiment, a first baseline is established and compared to a second baseline, and any difference between the first baseline and the second baseline caused by the presence of a human body in the detection network will be recognized by the system. can It receives a set of radio signal characteristic data from one or more nodes in the detection network, and based on this data, when a first baseline is established compared to a second baseline, the RF environment caused by the presence of the human body in a different position. It can be performed by software programming to detect a change in . These methods can be used when the system is first set up in a location to establish a minimum performance level without requiring free space at startup. Such systems with change detection can improve overtime to the state between presence and change that limited aspects of presence detection can exist in such systems.

A representative example of change detection is shown in FIG. 3A. In the illustrated embodiment of FIG. 3A , the RF environment of FIG. 1 is shown with a human body 301 present in environment 103 at discrete locations 303 . As described elsewhere in this disclosure, the characteristics of wireless signal transmission between nodes 107A-107D are affected by the presence of human body 301 . In this particular example, the transmission between node A 107A and node D 107D is affected by the presence of human body 301 . Accordingly, when the baseline is established (211) as shown in the method of FIG. 2, the baseline represents the radio signal characteristics and the human body 301 is present at discrete positions 303. When the human body 301 moves to a new location 305, the characteristics of the radio signal between nodes 107A to 107D will change, as shown in FIG. 3A.

In this particular exemplary embodiment, there will be little interference between nodes A 107A and D 107D when the human body is in position 305. However, there will be more interference between nodes B 107B and C 107C since location 305 is placed between these two nodes. Accordingly, when a difference is detected (205), as shown in FIG. 2, a change in position of the human body can be detected.

This is less difficult to implement than presence sensing because the human body is not present and the need to establish a baseline in the detection network 103 is reduced. Such a system can detect changes primarily based on when the human body changes position and within the detection network 103, and update the motion baseline profile on a rolling basis. That is, baseline 211 in this embodiment is updated to be the same as baseline when human body 301 is at position 305 . Thus, when the human body 301 moves to the third position 307, the detected difference 215 is the difference between the second baseline taken at the position 305 and the detection network 103 when the human body is at the position 307. It is the same as that between radio signal characteristics. Similarly, baseline 211 is updated to equal the baseline of location 307 , which can then be used to detect further changes in the location of human body 201 . This detection method uses a change in the radio signal baseline caused by a change in the position of the human body 301 in the detection network 103. This system has many advantages over conventional motion detection techniques such as passive infrared in that it is not obscured by objects and can detect slow or gradual changes in position, which may be overlooked by conventional systems. has In embodiments using this method, the baseline may be continuously updated.

In another embodiment, a system or method includes reliability determination. This aspect may determine a confidence level that the third baseline corresponds to the first or second baseline set. Reliability determination may use any number of techniques including those known in the art, such as supervised training or the use of statistical methods to determine the degree of similarity or difference between data sets. Confidence can increase or decrease over time and can automatically make decisions regarding baseline differences with minimal differences but still indicate the presence of a human body in the detection network 103 . Confidence in determining the presence or absence of a human body in the detection network 103 may be determined based on how similar the third baseline is to the first baseline or the second baseline. For example, if the third baseline is known to indicate the presence of masses affecting the signal characteristics, comparing the first baseline or the second baseline with the third baseline will result in the identified masses at the third baseline. The confidence level of being identical to the identified mass may be improved (or decreased). Depending on the reliability, the system can be configured to use different reliability thresholds in different operating contexts (eg, HVAC, security, lighting, safety, etc.). A system or method involving reliability determination may operate across multiple systems using a common communication system, and a system may include disparate nodes that communicate with each other. A given node operates in multiple detection networks (103), allowing for better system scaling when deploying systems and methods in multiple adjacent detection networks (103).

In another embodiment, the baseline difference may be used to count or estimate the number of human bodies present in the detection network. In one embodiment, this may be done by estimating the amount of body mass in the detection network and dividing by the average mass per person. This may be done by establishing a first, empty baseline when there are no human bodies in the detection network 103, and establishing a second, occupied baseline when a known number of human bodies are present in the detection network 103. Next, the third baseline is taken and compared to the first empty baseline and the second occupied baseline. The system software then interprets the location where the third baseline radio signal characteristic fits the spectrum of the profile between the first empty baseline and the second occupied baseline, and from that determination determines the total Estimate body mass. This estimate may be based on the total mass of the human body in the detection network when a second occupied baseline is established.

As a non-limiting example, if the signal distortion at the third baseline is moderate compared to the first empty baseline, the system may infer that the amount of human body mass present is relatively low. However, if the amount of signal distortion is closer to that shown in the second occupied baseline, the system will determine that the amount of estimated human body mass present in the detection network 103 is closer to the amount that existed when the second baseline was taken. can Similarly, if the amount of distortion is determined to be much more extreme than reflected in the second baseline, the system determines that the amount of total body mass present when the third baseline is taken exceeds the amount present when the second baseline is taken. can decide to do it. Estimation of body mass may be based broadly on the algorithms and methods described herein, and may generally be adapted to estimate multiple bodies in a space, as described above.

In another embodiment, the system uses the entrance and exit signatures in the network diagnostic information to estimate the number of human bodies present in the space based on those signatures.

In this method, an entrance profile is established by a human body entering a space, an exit profile is established by a human body leaving the same space, and later captured other profiles are compared with the entrance and exit profiles to determine whether a human body entered or exited the space. decide whether The entry and exit profiles are learned through normal system operation based on estimations from presence detection techniques and decisions based on state changes. As a non-limiting example, if the system detects a change and the presence goes from undetected to detected, such an event may be classified as an entry. Similarly, by way of example and not limitation, if the system detects a change and determines that the space has gone from occupied to unoccupied, that event may be classified as an exit. The difference between the entry count and exit count can be used to estimate the number of human bodies present in the space.

In another embodiment, the system uses the entry and exit signatures in the network diagnostic information in combination with a person count estimate derived by comparing the presence profile of the various person counts with the sample profile.

Each of these methods can be used in conjunction with one or more counting methods to improve accuracy.

In one embodiment, the number or estimate of the number of human bodies present in the detection network 103 may be used to operate other systems, such as, but not necessarily limited to, HVAC systems.

In one embodiment, the location or position of the human body in the detection network is estimated. It estimates the range between various devices to determine the position of the human body, examines a subset detection area composed of a larger number of nodes, uses different position baselines, and additionally estimates the velocity and the velocity of the human body in the detection network. It can be done by further extending the location system's ability to analyze position over time to estimate direction. In one embodiment of this method, the system may use various pairs of nodes, estimate the position of the body between those pairs using nested estimates within pairs of nodes based on the baseline information, and then determine the actual position of the body. In order to determine the highest probability location for the human body in the detection network based on the overlap estimate.

In other embodiments, a system with a larger number of nodes may use a larger subset of detection areas, typically systems with three or more nodes each, to determine the presence or absence of a human body in each space; The location of the commonly occupied space can be estimated based on overlapping occupied areas that can be assumed to be the most specified location of the human body in the detection network. By way of example and not limitation, a set of four nodes may be subdivided into four sets of three nodes, where a subset of three node presences may be located based on where they are detected. This sub-region creation allows detection within sub-regions where these sub-shapes are defined by overlapping regions created by sets of three or more nodes. Alternatively, multiple baselines can be established for the human body at different locations within the detection network, and subsequent baselines are compared to the baselines to determine the location of the human body within the detection network. As a non-limiting example, detection profiles can be created for various locations within a detection area where a given detection profile corresponds to a human body at a given location in the network, the sample profile is compared to a set of detection profiles corresponding to the different locations, The system determines which detection profile correlates best with the sample profile, and the system determines the location of the body based on the location of the detection profile considered most similar to the sample profile.

Also, based on the detected change in the position of the human body in the detection network over time, the moving speed and direction of the human body in the detection network can be estimated. This can be done, for example, using interpolation and dead reckoning (or direct reconnaissance). An exemplary embodiment of such a system and method is shown in FIG. 3B. In the depicted embodiment, The human body is located in the detection network 103 at location 401 at Time0. At a later point in time at Time1, the human body is detected at another location 403. The location 401 and the location ( Since 403) is known, the distance 1 between them can be computed In addition, the time from time 0 to time 1 can be determined or known. The moving speed of the human body from 1 to the position 403 may be determined. Additionally, a vector representing the motion of the human body by embodying both direction and magnitude (velocity) may be determined.

However, with only two sample points, the possibility of a high error rate increases and more than two sample points are required. For example, in the illustrated embodiment, a third profile taken at Time2 places the body at position 405 . Again, the distance 2 from location 403 to location 405 can be determined, and the ratio of velocities between these locations can also be determined. In the illustrated embodiment, these positions are generally linear, suggesting that the human body is moving in a nearly straight line in a given direction defined by a vector. Accordingly, the system may further estimate the future or expected position of the human body based on this data. That is, at Time3, the estimated position 407 of the human body may be determined based on the previously detected position. This estimate can place the human body outside of the detection network 103 and can be further used to estimate the arrival or departure of the human body in or into the detection network 103 . Additionally, this information could potentially be used to alert entire other detection networks or other segments of detection networks that a person is about to arrive. This may be performed, for example, by communication using computer server 109 over network 115 .

Continuing the above exemplary embodiment, in the illustrated embodiment, the detected change in position of the human body from time 0 to time 1 is 0.8 meters per second, at a rate of 0.8 meters per second. The change detected in the distance from time 1 to time 2 is 1.2 meters for each additional elapsed second at an average rate of 1 meter per second, or 2.0 meters total for the two total elapsed seconds. Thus, at time 3 after 1 second, an additional 1 meter movement can be expected, making the estimated future position 407 further along the vector than position 405 by 1 meter.

In one embodiment, the systems and methods use machine learning to further train the system over time. By way of example and not limitation, the system may derive from one or more of the change detection techniques described above using known feedback and/or combinations of feedback from third party systems such as, but not limited to, interactions with other smart devices. It can accumulate data (thermostats, voice recognition systems, etc.) and/or use inference over time to improve behavior based on expected or anticipated system behavior. Such inferences may be based on normal behavior in space, direct human interaction with elements of the system, or sample profile changes from human body responses to system decisions. As a non-limiting example, in a system that implements change detection to operate a lighting or HVAC system, user feedback as supervised training data indicating whether a given action is correct (i.e., whether a change has been made in the lighting or HVAC system). system can be provided.

Similarly, in systems that implement presence detection, a user can forcibly trigger change detection while in the detection network, resulting in an automated system that establishes a baseline run for the occupancy based on the time a change trigger event occurs. Means may be provided, allowing when away from the change triggering event to be detected as generally empty. When combined with inferred occupancy based on room type, this method can facilitate system training itself, improving functionality over time from change detection to presence detection level functionality. Effectively, by using a system based on change detection, the system can infer presence and absence, allowing it to establish a baseline profile for when the human body is not present and a detection profile based on when the human body is present. In this way, the system may train itself to move from operating as a change detection system to operating as a presence detection system.

In embodiments that implement counting, a combination of change detection and presence detection can determine an estimated count of the human body within the detection network, estimating such a counting baseline profile and improving it over time. Such a system can count the number of human bodies in the detection network, facilitating the training of the system itself over time.

In embodiments implementing person locating, a combination of change detection, presence detection, and body counting determines a location estimate based on overlapping area and occupancy counts and ultimately establishes a more accurate baseline estimate to determine time Over time, this allows the system to improve locating the human body within the detection network. Such systems may include an inference engine, such as computer software running on a server, and/or build inferences of expected system behavior from normal operation and adjust operating parameters according to expected behavior. For example, if a detection area is typically empty from 10 AM to 3 PM, and occupied from 3 PM to 6 PM, the parameter expects an empty state from 10 AM to 3 PM and occupies 3 PM. may be adjusted to anticipate a presence state from 12:00 to 6:00 PM). This heuristic can be developed over time and maintain overall flexibility while improving performance over time.

Nodes can be placed in various location combinations to improve system operation. The system may operate with nodes positioned on walls, ceilings, stationary nodes, mobile nodes, and/or mixed configurations. Because space is three-dimensional, detection areas can be defined by nodes on different floors of a building. Nodes can be placed on walls at locations such as switches and exits. The broadcast range generally defines the perimeter of the detection area, and the system can be configured to assume that the human body is within the perimeter and examine network diagnostics.

In one embodiment, one or more nodes may be placed in the ceiling. By way of example and not limitation, this may occur when the node is incorporated into a fixture and/or lighting system. In such an embodiment, the node may generally radiate downward into the detection area, and the system may be configured to examine network diagnostics based on radiation and multipath patterns different from those seen in switch and egress based systems. In this embodiment, the nodes generate communication generally in a downward direction, where reflections from walls, objects, and floors generally ensure that RF energy travels multiple paths to reach other nodes. Multipath also generally provides coverage of the detection area. This coverage due to multipath means that ceiling mount nodes behave similarly to wall mount nodes with respect to the human body's influence on network diagnostic information.

other stationary nodes, e.g. televisions; Also contemplated are monitors and smart home hubs, but are not limited thereto. These nodes can be mounted on walls, ceilings or fixed locations. Other nodes such as smart phones, tablets and laptop computers can be used as mobile nodes in the detection network. However, in this embodiment, the mobile node may first locate itself relative to the stationary node in the system. Establishing a location within the network can further improve the accuracy of the system.

In one embodiment, a combination of nodes may be used in the detection domain. When combining a larger number of nodes, the system can determine the best node for operation. The optimal node can be determined by, among other things, determining the most efficient node for the selected functional level. As the number of nodes increases, the accuracy of the decision generally increases, as does the functional level.

In one embodiment, one or more nodes may operate in multiple detection areas. This enables improved system scaling, especially for adjacent detection areas. This scaling can also cause inference within a larger network of nodes that include multiple detection areas, making it easier to track human detection from one detection area to the next. For example, nodes can be shared between detection areas. A given node within the first detection network may have network diagnostic information based on communications within the first detection domain, and may also be part of a second detection network and may have network diagnostic information based on communications within the second detection network. The system may make independent decisions on how to operate third party systems in each of the two detection domains. Examining the inference about detection areas can improve the determination of the presence or absence of a human body within a detection area, particularly where a person leaves one detection area and enters another. The detected change in the signal characteristic can be used to determine the presence or absence of a human body in the respective region based on information shared between the first and second detection regions.

In one embodiment, the systems and methods may operate through the use of mass body identification techniques. In this embodiment, a "mass" is identified and tracked. A unique identity can be assigned to a mass by a computer system and can be tracked based on changes in radio signal characteristics. By way of example and not limitation, if a mass is first detected near the center of the room and then is detected several feet from the center of the room, the system has not detected any other masses entering the room, and the system does not detect any other mass entering the room. 2 It can be assumed that the detected mass is the same mass as the first detected mass, but has been relocated to a new location. Based on differences in signal characteristics caused by interference of masses in the network, the system can infer, for example, that other masses exhibiting similar motions will have a similar effect on signal characteristics. In this way, the system can "learn" how to identify and track masses.

Each body mass in the system will cause different interference characteristics when placed anywhere for most indoor locations, but the total set of human bodies likely to be present in a room is generally finite. In other words, most indoor spaces are occupied most of the time by the same basic set of people, with minor and infrequent changes. For example, the same set of people show up every day in public places like work, school and even restaurants. Because most indoor spaces can only be entered through a limited number of entry points, such as entrances, the system can detect who enters and exits the entry points and determine specific interference patterns due to the presence of specific human bodies when entering or exiting the space. Based on the characteristics of the signal (interference) and the way these characteristics change compared to other human bodies in the space, it is possible to determine where and how each human body moves through the room.

In particular, it is contemplated that the system can automate various aspects of setup, particularly with respect to grouping nodes into detection regions and building nominal functional levels based on the machine learning methods described in this application. The system that determines the nearest node and estimates the detection area through inference does not require user setup. Based on the best estimate, users can simply place nodes throughout the building, and the nodes will automatically group into detection areas using unsupervised machine learning, ultimately allowing the building system to learn how to detect occupants. . Occupancy can be related to actions taken by occupants, and automated systems can be developed that can reduce or eliminate the need for human input for normal system operation.

In one embodiment, the method is a method for detecting the presence of a human body, the method comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within the detection area; a computer server communicatively coupled to the first transceiver; the first transceiver receives a first set of radio signals from the second transceiver; The computer server: receiving a first set of signal data from the first transceiver, the first set of signal data comprising data relating to characteristics of the first set of radio signals. ; estimating that the first set of signal data indicates the presence of a human body in the detection area; wireless communication from the second transceiver to the first transceiver based at least in part on a characteristic of the first set of radio signals in the first set of signal data when a human body is estimated to be present in the detection region. generating a detection signal profile; receiving, by the first transceiver, a second set of radio signals from the second transceiver; the computer server comprising: receiving from the first transceiver a second set of signal data comprising data relating to characteristics of the second set of radio signals; estimating that the second set of signal data indicates that no human body is present in the detection area; wireless communication from the second transceiver to the first transceiver based at least in part on characteristics of the second set of radio signals in the second set of signal data when the absence of any human body within the detection area is inferred. generating a baseline signal profile for receiving, by the first transceiver, a third set of radio signals from the second transceiver; the computer server receives a third set of signal data from the first transceiver, the third set of signal data including data relating to characteristics of the third set of radio signals; determining whether the third set of signal data indicates the presence of a human body or the absence of any human body in the detection area, wherein the detection signal profile and the baseline signal profile and the third set of signal data and determining, based at least in part on the comparison.

In a further embodiment, the method further comprises inferring that the first set of signal data indicates the presence of a human body in the detection area, wherein the inference is received by the first transceiver from other transceivers in the detection area. based at least in part on an additional set of signal data for the detected signals; and inferring that the second set of signal data is indicative of the absence of any human body in the detection area, wherein the inference is based on additional information about signals received by the first transceiver from other transceivers in the detection area. based at least in part on the set of signal data.

In a further embodiment, the method may further include storing a plurality of historical data records indicating whether a human body was determined to be present in the detection zone for a period of time, each historical data record present in the detection zone. includes an indication of the number of human bodies determined to be present and the date and time each of the number of human bodies was determined to be present in the detection area; and making the computer server available at least some of the plurality of historical data records to one or more external computer systems through an interface.

In a further embodiment, the method further includes the computer server being operatively coupled to a second system; Only after the computer server determines that a human body is present in the detection area, the computer server includes operating the second system.

In a further embodiment, the method includes causing the first transceiver and the second system to be configured to communicate using the same communication protocol.

In a further embodiment, the method may further include the second system comprising: an electrical system; lighting system; heating, exhaust, and cooling (HVAC) systems; security system; and being selected from the group consisting of industrial automation systems and electrical systems.

In a further embodiment, the method includes the wireless communication using a protocol selected from the group consisting of Bluetooth, Bluetooth low energy, ANT, ANT+, WiFi, ZigBee, Thread, and Z-Eve.

In a further embodiment, the method includes wireless communication from the second transceiver to the first transceiver having a carrier frequency ranging from 850 MHz to 17.5 GHz.

In a further embodiment, the method includes causing the computer server to determine whether the third set of signal data indicates the presence of a human body includes a confidence metric.

In a further embodiment, the method includes the first transceiver and the second transceiver being configured to automatically calculate relative positions within the detection area.

In another embodiment, the method includes a method for estimating the number of human bodies present in an area, the method comprising: providing a first transceiver disposed at a first location within a detection area; providing a second transceiver disposed at a second location within the detection area; a computer server communicatively coupled to the first transceiver; receiving a first set of radio signals from the second transceiver when the first transceiver does not exist within the detection area; the computer server receives a first set of signal data from the first transceiver, the first set of signal data including data relating to characteristics of the first set of radio signals; The computer server generates a baseline signal profile for wireless communication from the second transceiver to the first transceiver, the baseline signal profile when the human body is not present in the detection area, the first set of signal data based at least in part on characteristics of the first set of radio signals in ; the first transceiver receives a second set of radio signals from the second transceiver when a first plurality of human bodies are present in the detection area, and the first plurality of human bodies has a total mass; the computer server receives a second set of signal data from the first transceiver, the second set of signal data including data relating to characteristics of the second set of radio signals; The computer server generates a second baseline signal profile for wireless communication from the second transceiver to the first transceiver, the second baseline signal profile when the first plurality of human bodies are present in the detection area. based at least in part on characteristics of the second set of radio signals in the second set of signal data; the first transceiver receives a third set of radio signals from the second transceiver when a second plurality of human bodies are present in the detection area; the computer server receives a third set of signal data from the first transceiver, the third set of signal data including data relating to characteristics of the third set of radio signals; The computer server estimates the total mass of the second plurality of human bodies, the estimation based on characteristics of the third set of radio signals in the signal data of the third radio set, the first baseline signal profile and the first 2 based at least in part on a comparison to the baseline signal profile; The computer server estimates the total number of bodies in the plurality of bodies based at least in part on dividing the estimated total mass of the plurality of bodies by the average mass per body.

In a further embodiment, the method may further include the computer server estimating the total mass of the second plurality of human bodies based on characteristics of the third set of radio signals in the signal data of the third radio set and the second set of radio signals. and based at least in part on a comparison of characteristics of the second set of radio signals in the radio signal data of the .

In a further embodiment, the method further comprises wherein the characteristics of the first set of radio signals, the second set of radio signals, and the third set of radio signals include radio network signal protocol characteristics determined by the first transceiver. .

In a further embodiment, the method comprises wherein each of the wireless network signal protocol characteristics is selected from the group consisting of received signal strength, latency and bit error rate.

In a further embodiment, the method includes interpolating the estimate by the computer server of the total mass of an anatomical body in the second plurality of anatoms.

In a further embodiment of the method, the interpolating step uses a assumed mass of zero for the baseline signal profile and a total mass of the first plurality of anatomy for the second baseline signal profile.

In a further embodiment, the method includes wherein the total mass is a discrete user-supplied quantity.

In a further embodiment, the method includes wherein the average mass per body is a discrete user supply.

In a further embodiment, the method may further include the computer server storing a plurality of historical data records indicating whether a human body has been present in the detection zone for a period of time, each record of historical data indicating a number of human bodies detected in the detection zone and each of the numbers of the human body includes an indication of the date and time detected in the detection area; and the computer server making available at least some of the plurality of historical data records to one or more external computer systems through an interface.

In a further embodiment, the method wherein the computer server estimating the total mass of the second plurality of anatomy is adjusted based on machine learning comprising: having a fiducial element in the detection region. determining a first sample total mass of a plurality of human bodies, wherein the first sample mass is determined based on the detection of the fiducial element; determining a second sample total mass of the plurality of anatoms in the detection region, wherein the second sample mass is determined based at least in part on a comparison of the received second set of signal data and the baseline signal profile. , determining the second sample total mass; comparing the first sample mass and the second sample mass; and adjusting the estimate of the total mass of the second plurality of anatoms based on the comparison.

In a further embodiment, the method wherein the computer server estimating the total mass of the second plurality of anatomy is adjusted based on machine learning comprising: determining a first sample total mass; determining a second sample total mass of the plurality of anatoms in the detection region, the second sample mass determined based at least in part on a comparison of the received second set of signal data to the baseline signal profile; determining the second sample total mass; comparing the first sample mass and the second sample mass; and adjusting the determination of the second sample mass based on the comparison.

In a further embodiment, the method may further include determining a first sample position of the human body based on the inference in the detection zone, wherein the computer server determines from the detected motion of the network element in the detection zone that the human body is proximate to the network element. Including inferring that it exists within the detection region of

In a further embodiment, the method includes the network component being a component of an electrical system, a lighting system, a heating, ventilation and cooling (HVAC) system, a security system or an industrial automation system.

In a further embodiment, in the method, estimating the total number of anatomy in the plurality of anatomy includes a reliability metric.

In a further embodiment, the method includes the first transceiver and the second transceiver being configured to automatically calculate relative positions within the detection area.

In a further embodiment, the method includes the wireless communication using a protocol selected from the group consisting of Bluetooth, Bluetooth low energy, ANT, ANT+, WiFi, ZigBee, Thread, and Z-Eve.

In a further embodiment, the method includes wireless communication from the second transceiver to the first transceiver having a carrier frequency ranging from 850 MHz to 17.5 GHz.

Although the present invention has been disclosed with description of specific embodiments, including those presently preferred, the detailed description is for the purpose of explanation and should not be construed as limiting the scope of the present disclosure. As will be appreciated by those skilled in the art, embodiments other than those detailed in this application are encompassed by the present invention. Modifications and variations of the described embodiments may be made without departing from the spirit and scope of the invention.

Claims (15)

delete delete delete delete delete delete A method for estimating the number of people in a space,
providing a plurality of presence sensing networks within the space, each of the presence sensing networks capable of providing at least one data element for a detection area within the space specific to that network; and
Aggregating all of the data elements from all of the presence sensing networks to provide an overall estimate of people in the space.
including,
Each of the data elements,
detecting the presence of at least one person in the specific detection area;
determining the number of people in the detection area; and
Calculating a metric correlated with the average number of people within the specific detection area within a specific time period.
Selected from the group consisting of
How to estimate the number of people in a space.
According to claim 7,
The result of the aggregation is,
Periodically recorded and timestamped,
How to estimate the number of people in a space.
According to claim 7,
The aggregation result is,
provided to the requesting party;
How to estimate the number of people in a space.
According to claim 9,
The requesting party,
Including a first responder to an emergency in the space,
How to estimate the number of people in a space.
According to claim 9,
The data element is
provided as one or more of a map, real-world audio or visual cues, an overlay on a display, or directional information in a virtual reality display;
How to estimate the number of people in a space.
According to claim 9,
The result is,
Periodically updated by new information from the plurality of presence sensing networks,
How to estimate the number of people in a space.
According to claim 12,
The result is,
indicating when one of the presence sensing networks is no longer transmitting data elements;
How to estimate the number of people in a space.
According to claim 9,
The requesting party,
including robots,
How to estimate the number of people in a space.
According to claim 9,
The result is,
Also including information provided from other sensors in the space and information from sensors outside the space,
How to estimate the number of people in a space.

Images