KR20210099130A - Apparatus, system and method for determining geographic location - Google Patents

Abstract

An apparatus, system, and method are provided for determining a geographic location. The apparatus includes a receiver, a sensor, a processor and a transmitter. The receiver is configured to receive the first geographic location. The sensor is configured to determine a change in pose of the device. The processor is operatively coupled to the memory, the receiver, and the sensor. The processor is configured to determine the second geographic location based on the first geographic location and the sensor using the neural network. The first transmitter is configured to output a second geographic location of the device.

Description

Apparatus, system and method for determining geographic location

Cross-references to related applications

This application claims priority to U.S. Provisional Application No. 62/777,782, U.S. Provisional Application No. 62/798,754, filed January 30, 2001, entitled "Location-Estimating Device", "Location Broadcast Beacon", 2019 U.S. Provisional Application No. 62/872,262, filed July 10, 2019, and U.S. Provisional Application No. 61/872,262, filed July 10, 2019. ngps (Network Terrestrial Positioning System) for estimating geo-location (geographical location), filed December 2, 2019 & Sensor-actuated neural network to estimate sensor-actuated neural network (sensor-actuated neural network) 2019 for estimating geographic location.

Global Positioning System (GPS) may be used to determine the geographic location of a GPS-enabled device. For example, a GPS-enabled device may receive GPS broadcasts from satellite orbit (satellite) for 12,000 miles above the Earth's surface.

There are power requirements and accuracy of GPS-enabled devices.

In one example, an apparatus for determining a geolocation (geographic location) is provided. The apparatus includes a receiver, a sensor, a processor, and a transmitter. The receiver is configured to receive a first geolocation (geographic location). The sensor is configured to determine a change in a pose of the device. The processor is operatively coupled to a memory, a receiver, and a sensor. The processor is configured to determine a second geographic location based on the first geolocation and the sensor using the neural network. The first transmitter is configured to output a second geographic location of the device.

In another example, a network for determining a geographic location is provided. The network includes nodes and mobile devices. The node includes a transmitter configured to output a current geographic location of the node via a wireless communication protocol. The wireless communication protocol includes a short-range communication protocol, a Bluetooth low energy protocol, a Wi-Fi protocol, or a Zigbee protocol, or a combination thereof. A mobile device includes a receiver, a sensor, and a processor. The receiver is configured to receive a current geographic location of the node via a wireless communication protocol. The sensor is configured to determine a change in a pose of the mobile device. The processor is operatively coupled to a memory, a receiver, and a sensor. The processor is configured to determine a current geographic location of the mobile device based on a current geographic location of the node and the sensor using the neural network.

The novel features of the various aspects described herein are set forth with particularity in the appended claims. However, the various aspects may be better understood with reference to the following description taken in connection with the accompanying drawings in which:
1 shows an example of a system diagram of a location-enabled device for determining a geographic location according to the present disclosure;
2 shows an example of a process diagram for determining a second geolocation according to the present disclosure;
3 shows an example of a process diagram for training a neural network according to the present disclosure.
4 shows an example of a process diagram for fine-tuning a neural network according to the present disclosure.
5 shows an example of a system diagram of a location enabling apparatus for determining a geographic location in accordance with this disclosure capable of receiving an observed geographic location from a device and transmitting a second geographic location to the device;
6 is a system diagram of a location capable apparatus for determining a geographic location in accordance with the present disclosure for transmitting a second geolocation (geographic location) to a first device and receiving an observed geolocation (geographic location) from a second device; shows an example of
7 shows an example of a process diagram for a mobile device including a location-enabled battery and the functionality of a location-enabled device according to the present disclosure incorporated within a location-enabler application.
8 illustrates an example of a process diagram for a mobile device including a location-enabled application and functionality of a location-enabled apparatus in accordance with this disclosure.
9 shows an example of a system diagram of a network of nodes for determining a geographic location according to the present disclosure;

Various examples are described and illustrated herein to provide a thorough understanding of the structure, function, and use of the disclosed articles and methods. The various examples described and illustrated herein are non-limiting (non-limiting) and non-inclusive (not limiting). Accordingly, the present invention is not limited by the description of the various non-limiting and non-exhaustive examples disclosed herein. Rather, the invention is defined solely by the claims. Features and features shown and/or described in connection with various examples may be combined with features and features of other examples. Such modifications and variations are intended to be included within the scope of this specification. As such, the claims may be amended to reconsider any feature or characteristic expressly or inherently set forth herein, or otherwise expressly or inherently supported by this specification. In addition, Applicant definitively discovers features or characteristics that may exist in the prior art by reserving the claims for the purpose of advancing them. The various examples disclosed and described herein may consist of, consist essentially of, or consist of the features and features as variously described herein.

Any references to various examples herein, in some instances, for example, or similar phrases, mean that a particular feature, structure, or characteristic described in connection with the example is included in at least one example. Thus, appearances of phrases in various examples, in some instances, in one example herein, are not necessarily referring to the same example. Also, a particular described feature, structure, or characteristic may be in one or more examples. They may be combined in any suitable manner. Accordingly, particular features, structures, or characteristics illustrated or described in connection with one example may be combined in whole or in part with the features, structures, or characteristics of one or more other examples without limitation. Such modifications and variations are intended to be included within the scope of this embodiment.

In the present specification, unless otherwise indicated, all numerical parameters are prefaced in all cases by the term "about", which numerical parameters have the inherent variability characteristics of the basic measurement techniques used to determine the numerical value of the parameter. It must be understood that transformation Each numerical parameter described herein should at least be construed as a number of reported significant digits and, by applying ordinary rounding techniques, each numerical parameter described herein should at least be construed as a number of reported significant digits.

Also, any numerical range recited herein includes all sub-ranges subsumed within the recited range. For example, a range from 1 to 10 includes all subranges between the recited minimum value (1) and the recited maximum value (10), ie, all subranges having a minimum value of 1 or more and a maximum value of 10 or less. Any maximum numerical limitation recited herein is intended to include all lower numerical limitations subsumed therein, and any minimum numerical limitation recited herein is intended to include all higher numerical limitations subsumed therein. It is intended

Applicants, therefore, reserve the right to recite this specification, including the claims, to expressly recite any sub-range falling within the expressly recited scope, including the claims. All such ranges are uniquely set forth herein.

As used herein, the grammatical articles "a,", "and", unless otherwise indicated, include at least one or more, or Unless otherwise stated, it is intended to include at least one or more grammatical items. Accordingly, the foregoing grammatical articles are used herein to refer to one or more (ie, at least one) of a particular identified element. Also, the use of a single noun includes the plural and the use of the plural noun includes the singular, unless the context of use requires otherwise.

A location-enabled device may include a Global Positioning System (GPS) receiver to determine its geographic location. However, a GPS receiver may require a large amount of power (eg, 100 milliamperes (mA) or more) to process GPS broadcasts from satellites and determine the geographic location of a location-enabled device. Also, the GPS receiver maintains polling after a certain interval so that geo-location updates are maintained, consuming additional power. Also, since GPS typically receives and operates for a long time (eg, 1 minute or more), GPS is typically kept "ON". For example, many location-enabled devices, such as cellular phones, have other energy-intensive functionality such as, for example, screens, speakers, and indicators (eg, LEDs). Reducing energy consumption may be beneficial in enabling increased battery life.

The inventors of the present invention have determined that limiting the use of GPS receivers can reduce the energy consumption of location-enabled devices. For example, it may be advantageous to use a sensor configured to determine a change in geographic location of a location-enabled device that requires less current than a GPS receiver. For example, low-power sensors for determining geolocation (geographical location), such as microelectromechanical systems (MEMS) accelerometers, use low currents (e.g., less than or equal to tens or less micro-amperes (mA)). may need Thus, by using a low-power sensor for determining the geographic location of a location-enabled device instead of a GPS receiver, energy consumption of the location-enabled device can be reduced. However, typical accelerometer-only geo-location approaches can be inaccurate.

Accordingly, the present disclosure provides a location-enabled device comprising a neural network and a sensor configured to determine a change in pose of the location-enabled device while reducing power consumption. A location-capable device may have a geographic location initialized (eg, by a GPS receiver, a node in a network, another device). After initialization of the geo-location, the neural network may determine a change in the pose of the location-enabled device from the initialized geolocation using the sensor. The change in pose can be used to determine the current location of the location-enabled device without using a GPS receiver. Accordingly, a reduction in energy required to determine the geographic location of the location-enabled device can be achieved.

Additionally, a location-enabled device in accordance with the present disclosure may use a GPS receiver, a node in a network, and/or another observed geolocation providing device to obtain an observed geolocation (eg, accurate, accurate, actual) It can be trained by providing it periodically. The accuracy of geolocation of a location-capable device according to the present disclosure may be increased (eg, fine-tune an algorithm within the neural network) by providing the neural network with more observed geolocations during training.

1 shows an example of a system diagram of a location-enabled device 100 for determining a geographic location according to the present disclosure. The device 100 includes a processor 102 (eg, a microcontroller unit (MCU)), a memory 104 , a receiver 106 , a transmitter 108 , a sensor 1 10 , and a neural network 1 ( 16) may be included. The processor 102 may be operatively coupled to a memory 104 , a receiver 106 , a transmitter 108 , and a sensor 110 .

Memory 104 may be non-transitory memory, which, when executed by processor 102 , causes processor 102 to perform the functions of neural network 1 16 , various algorithms, and other innovations described herein. may contain machine-executable instructions that may Memory 104 may include any machine-readable or computer-readable medium capable of storing data, including both volatile and non-volatile memory. For example, memory 104 may include gypsy man (read-only memory), small amount (dynamic), DDR-ram (double the data rate less amount), SDRAM, SRAM, PROM, EPROM, EEPROM , flash memory (eg NOR or NAND flash memory), content addressable memory (CAM), polymer memory (eg ferroelectric polymer memory), phase-change memory (eg ovonic memory), ferroelectric memory, silicon-oxide-nitride-oxide-silicon (SONOS) memory, disk memory (eg, floppy disk, hard drive, optical disk, magnetic disk), or card (eg, magnetic card, optical card); or any other type of medium suitable for storing information. In various examples, the memory 104 may be a secure memory, such as, for example, a write-once (WORM) memory, a blockchain enabled memory, or other secure storage memory, or combinations thereof.

The receiver 106 may be configured to receive the first geographic location. As used herein, a “geo-position” is the position (eg, longitude, latitude, altitude) and/or orientation (orientation) of an object relative to the Earth. The first geolocation may be an initial geographic location, a current geographic location, a recent geographic location, an observed geographic location, or combinations thereof. The first geographic location may then be stored in the memory 104 . The receiver 106 may be configured to receive the first geographic location via a first wireless communication protocol or a wired communication protocol, or a combination thereof. The wireless communication protocol may include a short-range communication protocol, a Bluetooth low energy protocol (eg, 2.4 MHz), a Wi-Fi protocol (eg, 800 MHz), or a ZigBee protocol, or a combination thereof.

Sensor 110 may be configured to measure a change in pose (eg, position and/or orientation) of device 100 . The change in pose may be within at least 2 degrees of freedom, for example at least 3 degrees of freedom, at least 4 degrees of freedom, or at least 5 degrees of freedom. In various examples, the change in pose can be 6 degrees of freedom. The sensor 110 may include an accelerometer, an inertial measurement unit, a gyroscope, or a magnetometer, or a combination thereof. The sensor 110 may output the measured change in pose as a pause signal to the processor 102 for processing using the neural network 1 ( 16 ). In various examples, sensor 1 10 may output a pause signal to processor 102 indicating that device 100 has not moved.

The processor 102 may process the pose signals from the sensor 110 using the neural network 1 16 , and may determine a second geographic location of the device 100 based on the first geolocation. The second geographic location may be a current geographic location, a recent geolocation, or an estimated geographic location, or combinations thereof.

Neural network 1 16 may be stored in memory 104 or in a remote device (not shown) as shown in FIG. 1 . Neural network 1 16 receives pose data from sensor 1 10 and, together with processor 102 , transforms the pose data into a change vector (eg, change in direction and magnitude in pose). For example, neural network 1 ( 16 ) may include artificial neurons that may be connected together using edges. Artificial neurons may be arranged in at least two layers. For example, one of the layers may be an input layer capable of receiving pause data, and a different one of the layers may be an output layer capable of providing an output. The propagation function in each artificial neuron may compute an output based on a predefined weight associated with each input to the artificial neuron (eg, pose data, a predecessor artificial neuron output), and the bias is the artificial neuron's output. It can be used to make adjustments to the resulting output. The resulting output of neural network 1 ( 16 ) may be a change vector. Thereafter, the processor 102 may receive the change vector and may determine a second geographic location based on the first geographic location (eg, a previous location).

The processor 102 may be a central processing unit (CPU). Processor 102 is a general purpose processor, chip multiprocessor (CMP), dedicated processor, embedded processor, digital signal processor (DSP), network processor, media processor, input/output (I/O) processor, media access control (MAC) processor, radio baseband processor, vector co-processor, complex instruction set computer (CISC) microprocessor, reduced instruction set computing (RISC) microprocessor, and/or very long directive (VLIW) microprocessor, or other processing device. can A processor may also be implemented by a controller, microcontroller, application specific integrated circuit (ASIC), field programmable gate array (FPGA), programmable logic device (PLD), or the like. The processor 102 may be configured to execute an operating system (OS) and various other applications.

The processor 102 may be arranged to receive information via a communication interface. The communication interface may include any suitable hardware, software, or combination of hardware and software that may couple processor 102 to another component, network, or other device of apparatus 100 , or combinations thereof. . For example, the processor 102 may receive, for example, the first geolocation via the receiver 106 and the pause signals from the sensor 1 . As described herein, the processor 102 is configured to use neural network 1 16 , based on a first geolocation and sensor 1 10 (eg, pause signals from sensor 110 ). A second geographic location of the device 100 may be determined. For example, the processor 102 in conjunction with the sensor 110 may measure a change in the pose of the device 100 relative to the first geographic location, whereby based on the change from the first geographic location, the second geographic location may be used. location can be determined.

The processor 102 may store the first geographic location, the second geographic location, or pause signals or combinations thereof in the memory 104 . For example, the processor 102 may be configured to store a first geographic location in the memory 104 , and the processor 102 may be configured to overwrite the first geographic location with a second geographic location in the memory 104 . can be

A process diagram 200 of the processor 102 for determining a second geographic location is shown in FIG. 2 as shown, and the recent geographic location may be retrieved from memory ( 202 ). In various examples, the recent geographic location may be a first geographic location received by the receiver 106 or a recently determined second geographic location. When the device 100 is moved, the sensors 1 and 10 may output a pause signal that may be received by the processor 102 . The processor 102 may then process the pause signals using the neural network 116 (206). In various examples, neural network 1 16 may be pre-trained as illustrated in FIG. 3 and/or fine-tuned as illustrated in FIG. 4 and/or as combinations thereof.

The processor may use neural network 1 ( 16 ) to determine a change vector of device 100 using neural network 1 ( 16 ) for the most recent geo-location stored in memory ( 208 ).

Processed (206) pose signal. To enable the processor 102 to accurately calculate the change vector, the pause signals 206 processed by the processor 102 can be generated at any point between the current location of the device 100 and the most recent geo-location stored in the memory 104 . movement should be considered. Processor 102 may then determine 210 a second geo-location based on the most recent geo-location retrieved from memory 104 and the determined change vector. The processor 102 may output 212 the second geo-location and update 214 the memory with the second geo-location in step 21414 . For example, processor 102 becomes the most recent geographic location for another iteration of process diagram 200 as shown in FIG. 2 for another iteration of process diagram 200 as shown in FIG. 2 2 It may be performed based on a desired frequency, a triggering event (eg, activation of an energy harvesting device as described herein), or other parameter, or combinations thereof.

The neural network 1 16 of the device 100 may be trained as the process diagram 300 shown in FIG. 3 , such that the second geolocation output may be accurate (eg, the observation of the device 100 ). can be trained substantially similarly to a given geolocation). In various examples, the receiver 106 may be configured to receive an observed geolocation (geographic location) and the processor 102 to train the neural network 1 ( 16 ) with the observed geolocation (geographic location). can be configured. For example, the processor 102 may be configured to train the neural network 116 by adjusting the weights and biases in the neural network 1 , 16 .

For example, a process diagram 300 of the processor 102 for training the neural network 116 is shown in FIG. 3 as shown, and a recent geo-location can be retrieved from memory (eg, correct Observed geolocation) An observed geolocation (eg, a correct observed geolocation) may be received 302 , the current geolocation and the observed geolocation (eg, the current geolocation) and the observed geolocation. The most recent geo-location and the retrieved geolocation are provided to the processor 102 for processing ( 306 , by comparison) to determine a difference between the locations. Processor 102 may then propagate back any observed errors through neural network 1 16 . For example, the processor 102 may determine 308 a derivative of an error function (eg, a loss function) of the determined difference. The processor 102 may then propagate the neural network 310 back to the neural network using a gradient descent algorithm to adjust the weights and biases in the neural network 1 16 ( 310 ). Weights and biases Adjustment of these may be an initial training of neural network 1 ( 16 ) or retraining (retraining) of neural network 1 ( 16 ).

The trained neural network 1 16 may then process 314 the sensor signal from the sensor 1 10 (eg, reprocess) from the received 312 sensor signals and , determine a change in the geo-location relative to a previous geo-location (eg, a recent geo-location) stored in the memory. The processor 102 may output 316 the second geo-location and update 318 the memory with the second geo-location in memory. Another iteration of the process diagram 300 is shown in FIG. 3 , calculated between the output second geolocation and the observed geolocation, or other parameter, or combinations thereof, based on a desired number of iterations. It can be performed based on errors. After training in FIG. 3 , neural network 1 ( 16 ) may be trained, and neural network 1 ( 16 ) may be coded with another device.

After neural network 1(16) is trained, neural network 1(16) can be fine-tuned on the desired device. Fine-tuning can also occur at the desired frequency in each device. Although a process diagram 400 of the processor 102 fine-tuning the neural network 116 in the device 100 is shown in FIG. 4 as shown, the most recent geo-location is retrieved from memory in step 402 . and an observed geo-location may be received. The recent geolocation and retrieved geolocation are provided 406 to the processor 102 for processing. For example, the processor 102 may determine a derivative of the error function for the observed geolocation and may backpropagate the derivative of the error function via the neural network 1 ( 16 ).

Thereafter, the trained layers of the neural network 1 ( 16 ) can be retrieved and fine-tuned with the adjusted weights and biases ( 408 ). The processor 102 may process 410 the signal from the sensor 1 , 10 (eg, reprocess). For example, the processor may determine a change vector for a current geolocation stored in the memory using the fine-tuned neural network, and may determine a second geographic location of the device 100 . The processor 102 may output 412 the second geo-location and update the memory with the second geo-location. In various examples, processor 102 may determine an error-level in a second geolocation relative to a previous recent geo-location, and output the observed geolocation if the error-level is greater than or equal to a threshold. In various other examples, if the error-level at the second geolocation relative to the current geolocation is less than a threshold, the processor 102 may output the second geolocation.

Another iteration of the process diagram as shown in FIG. 4 may be performed based on the desired number of iterations, the calculated error between the recent geo-location and the observed geo-location, the desired frequency, or other parameter, or combinations thereof. can

Referring again to FIG. 1 , in various examples, the transmitter 108 may be configured to output a second geographic location of the apparatus 100 . The second geographic location may be the same as the first geographic location or a different geographic location. For example, if device 100 did not move when device 100 received the first geographic location, the second geographic location may be the same as the first geographic location. The transmitter 108 may be configured to output the second geographic location via a first wireless communication protocol or a wired communication protocol, or a combination thereof. Wireless communication protocols may include short-range (near) field communication (NFC) protocols, Bluetooth low energy (BLE) protocols (eg, 2.4 MHz), Wi-Fi protocols (eg, 800 MHz), or the ZigBee protocol, or combinations thereof. The transmission of the second geolocation (geographic location) may or may not be fixed depending on the application.

Receiver 106 and/or transmitter 108 may include mobile chipset radio frequency (RF) radio circuitry, or radio communication circuitry, which may simply be a cellular radio. The wireless communication circuitry may be a low-power chipset and may be configured to connect to a network as well as other devices 120 (eg, cell phones, smartphones, tablet computers, laptop computers, gateway devices, etc.). The wireless communication circuitry may include an antenna for receiving and transmitting wireless signals, transmitter circuitry, or receiver circuitry, or combinations thereof.

As shown in FIG. 1 , device 120 may communicate with device 100 via link 12.2 . Device 120 may receive a second geo-location from device 100 , and may transmit the observed geolocation (eg, training data) to device 100 as shown in FIG. 5 . 6, the plurality of devices may communicate with the apparatus, the first device 620a may receive a second geolocation, and the second device 620b may transmit the observed geographic location to the apparatus 100 there is.

Device 100 may be configured as an NFC-BLE beacon. For example, the receiver 106 may communicate wirelessly via NFC, and the transmitter 108 may communicate wirelessly via BLE.

The apparatus 100 may include an energy harvesting device 1 , 12 , which may include a piezoelectric energy harvesting device, an electrostatic energy harvesting device, an electromagnetic energy harvesting device, a photovoltaic cell, or a combination thereof. For example, if the device 100 is located adjacent to a road, traffic on the road can generate vibrations that can convert electricity into electrical power by the energy harvesting device 1 . In various other examples, devices may be attached to vehicles and vehicles, and vibrations (eg, movement, engine vibrations) and vibrations may be converted into electricity by an energy harvesting device. The amount of power generated by the energy harvesting device 1 12 may be suitable for powering the apparatus 100 to determine a second geographic location (eg, longitude and latitude).

In various examples, the apparatus 100 receives a vibration from the road whenever the energy harvesting device 1 12 provides power to the apparatus 100 (eg, it receives a vibration from the road. Other times , the device 100 may not output the second geographic location to conserve power.

In various examples where device 100 is battery-less, device 100 is configured to transmit a second geolocation (geolocation) via BLE, and device 100 is configured to, for example, a house It may be used in fixed locations such as numbers, door bells, poles, walls, traffic signals, sidewalks, transit stations, or public places, or a combination thereof.

The device 100 may include a GPS receiver 1 , 18 . The GPS receiver 1 18 may be configured to provide the observed geographic location to the device 100 for training the neural network 1 16 as shown in FIG. 3 . For example, the GPS receiver 1 18 may provide the observed geographic location for processing by the processor 10.2. In various examples, it may be desirable to limit the operation of the GPS receiver 1 18 to reduce the power consumption of the device 100 .

Device 100 may include circuits designed to interface with various sensors and combinations of components of device 100 . For example, apparatus 100 may include, for example, an analog front-end in a low-power ASIC/chip that may include a number of functions such as geo-location, neural network training, neural network fining tuning, etc. , a combination of vector/digital signal processing, microprocessor and memory. Apparatus 100 includes, for example, a printed circuit board assembly, universal serial bus (USB), connection ports to external devices and/or sensors, and a hardware accelerator, data memory, such as SPI, universal asynchronous receiver. To support the functionality of the device 100 , such as hardware accelerators, data memory, serial interfaces, such as a transmitter (UART), a two-wire multi-master serial single-ended bus interface (I2C), general-purpose input/output (GPIO) It may include various components and modules for It may include one or more of a real-time clock, control circuitry, analog-to-digital converter (ADC), gain and adjustment circuitry, drivers, or other components.

In various examples, the device 100 may include a battery 1 , 14 , and the neural network 1 , 16 may be embedded in the battery 1 , 14 (not shown). In various examples, the memory 104 , the processor 102 , and the sensor 1 , 10 may be embedded within the battery 1 . Thus, the device 100 can remain ON and thus keep updating the geolocation of the device 100 whenever the device 100 comprising the battery 1 , 14 is moved. In various examples, the initial position of the device 100 including the battery 1 14 (eg, received by the receiver 106 during manufacture and stored in the memory 104 ) may be determined at the time of manufacture or at a later seeding time. can be

Neural network 1 ( 16 ) may be embedded in a battery management system (BMS) of battery 1 ( 14 ). Sensor 1 ( 10 ) can track the movement of battery 1 ( 14 ), and using neural network 1 ( 16 ), the processor ( 102 ) continuously tracks the geo-position based on the pose signal from sensor 1 ( 10 ). can be updated with Thus, any device comprising a location-enabled apparatus according to the present disclosure that includes a battery can utilize the location-enabled apparatus for power and current geo-location.

In various examples where neural network 1 16 is embedded in battery 1 14 , receiver 106 may sniff a node (eg, a location-beacon) as described herein, and neural network 1 (16) may receive the observed geographic location from the node to train (eg, back-propagation). Thus, the battery 1 ( 14 ) may comprise circuitry for training the neural network ( 1 ) 16 , such that the battery 114 may be a self-training, standalone, localization-estimating unit, and the neural network (1) may not require communication with a mobile device to train (16).

A location-enabled apparatus according to the present disclosure may be integrated into a mobile device. For example, as shown in the application diagram 700 shown in FIG. 7 , a mobile device comprising the functionality of a location-enabled apparatus according to the present disclosure may include a location-enabled battery for execution by the mobile device and It can be integrated with location-enabler applications. As shown in the application diagram 700 , the location enabler application 702 uses the observed geolocation 704 for fine tuning from the location enable device 706 or GPS satellites 708 (up in the sky). ) can be received. The location-enabler application 702 may also receive the estimated location 710 from the location-enabled battery 7124 . Additionally, the location-enabler application 702 may provide a back wave 714 to the location-enabled battery 712 . The location enabler application 702 may also receive motion data 716 from the smartphone 718 and provide the estimated location 720 to the smartphone 718 . The location enabler application 702 provides an estimated location 720 using the neural network within the location enabler application 702 and the processor of the smartphone 718 . In various examples, location enabler application 702 may be located on smartphone 718 .

In certain examples, if the smartphone 718 uses the Android OS, the location-enabler application 702 may act as a virtual background service that may not be visible to the end user. In various examples, when the smartphone 718 uses an OS other than Android, multitasking (multitasking) may be allowed, and the location-enabler application 702 may be configured as a local server. In certain examples, phone manufacturers may provide a location-enabler application 702 bundled with their respective OSes.

In various examples, as illustrated in application diagram 800 shown in FIG. 8 , a location-enabled application for execution by a mobile device and a mobile device that includes the functionality of a location-enabled apparatus in accordance with the present disclosure. (816) is provided. A location-enabled apparatus according to the present disclosure may be performed by a service running in the background of a mobile device. The mobile device may include an Android operating system, iOS, or another operating system, or a combination thereof. The location-based application 816 may receive the current geolocation 802 forming the smartphone 718 , and when necessary, a second geolocation 804 to the smartphone 718 along with a back wave 806 . can provide The smartphone 718 is an in-memory neuron that receives information from the location-aware application 808 as well as the motion sensor 810 on the smartphone 718 and the memorization-memorization fine-tuning" layer (n+1) 814 network 810 .

A location-enabler application 702 (eg, a NOGPS app) may be a link between a fixed location beacon and a neural network in accordance with this disclosure. The NOGPS app may provide location information to other applications on the mobile device (eg, location capable application 816 ), such as, for example, a navigation application (eg, navigation application), map, Waze ), location services, or SOS services, gaming applications, or combinations thereof that may require geolocation (geographic location) of the mobile device. The NOGPS app may obtain a trained neural network according to the present disclosure from a mobile device, battery, and/or secondary device (eg, cloud). For example, cloud storage may be used to maintain a copy of a trained neural network in accordance with the present disclosure. The mobile device may be configured to receive an observed geographic location from a location-enabled battery, a fixed location beacon, or GPS, or combinations thereof.

In various examples, the NOGPS app may periodically determine whether further fine-tuning of the neural network according to the present disclosure should be performed by comparing the second geolocation (geographical location) to the observed geolocation (geographical location). The function of the NOGPS app of FIG. 7 is substantially similar to that of the gps app of FIG. 7 , but the geo-location of FIG. 7 allows the location-enabled battery to remain ON even when the mobile device is switched ON-OFF. It is substantially similar to the function of the NOGPS app of FIG. 8 , except that it can be constantly updated.

A location-enabled apparatus according to the present disclosure may be a component or part of a variety of other devices. For example, a mobile device, fastener, marker, doorbell, or combination thereof may include a position-enabled device according to the present disclosure. For example, an anti-theft device may include a location-enabled device in accordance with the present disclosure and a secure memory for storing a current geographic location. For example, various devices, such as a cellular phone, can sniff the BLE transmission of a geolocation (geolocation), and compare the transmitted geolocation (geolocation) of the anti-theft device to the current geolocation (geolocation) of the cellular phone. can be compared with Thus, if the theft is outside the designated area (or inside the restricted area), the cell phone can send an alert. Alternatively, the anti-theft device may transmit an alert using the sensor and neural network of the location-enabled device according to the present disclosure when the anti-theft device is outside a designated area or within a restricted area. Anti-theft devices may be battery-free (which may include, for example, energy harvesting devices (energy harvesting devices)) and deep (deep) hidden inside objects that need to be secured against theft.

In various examples, an apparatus according to the present disclosure may be securely attached to a wall, roadway, pathway, store, office, counter, building, or desk, or combinations thereof. A securely attached device may transmit its current geographic location to another device or device or a combination thereof. The marker may include a cat-eye, bumper sticker, sign post, house number, name plate, or street sign, or a combination thereof. For example, a house number or name plate or combination thereof may be issued by a designated formula (eg, a city office), sending the specific geographic location of the location where the house number or name plate or combination thereof will be installed pre-programmed to

The location enabling device according to the present invention can be installed on a road similar to the way cat's eyes are installed on the road. For example, a position-enabled device according to the present invention may be installed over fasteners (eg nails, screws) that are driven into the roadway. The fastener may define a cavity within the head of the fastener, such that a positionable device according to the present disclosure may be securely attached within the cavity. A position-enabled device according to the present disclosure may be attached within the cavity after installing the fastener.

In examples where a position-enabled device according to the present disclosure can convert vibration into electrical power, the device can be installed in a roadway by drilling a hole and introducing the device into the hole. The hole can then be sealed with a quick-setting durable epoxy. Then, when the vehicle approaches the location-enabled device according to the present disclosure installed on the road, the vibrating road may power the device that in turn broadcasts the second geo-location.

In various examples, a toy may be configured with a position-enabled device according to the present disclosure, and the toy may behave differently depending on its geolocation. For example, a toy can be considered intelligent, a toy can speak French when the toy's current geographic location is France, and a toy can say that the toy's current geolocation is England When you can speak English.

Referring again to FIG. 1 , in various examples, device 100 may also transmit a message. For example, receiver 106 may receive a message that may be stored in memory 104 , and the message may be transmitted by transmitter 108 . For example, around a desk, the transmitter 108 may transmit a message that does not create noise around such desk. The message may be sent to the receiver 106 using a mobile device or other device. The device 100 may be used in a variety of applications, such as, for example, navigation, proximity applications, or gaming applications, or combinations thereof.

A smart bumper sticker comprising a location-enabled device according to the present invention may be initialized by a companion app on the smartphone that can transfer (eg, seed) the initial geographic location to the memory of the smart bumper sticker. can When the sensor in the smart bumper sticker detects any movement, the processor of the smart bumper sticker may update the geographic location of the smart bumper sticker using a neural network. Updating the geographic location of the device may utilize Newton's law. can

After seeding (deep) the initial geolocation (geolocation) into the memory of the smart bumper sticker, periodic reseeding (reseed) of the observed geolocation (geolocation) different from the initial geolocation (reseed) is sticker) and can be used to train neural networks on smart bumper stickers (smart bumper stickers, for example, to make neural networks more accurate in geo-location estimates (geo-location estimates)). For example, a person may initialize a smart bumper sticker at the location of their primary residence (eg, home), , then the location of where they operate, the location of a friend's home, or another person's home (eg, home). For example, relatives) or in a different location (location). If the observed geolocation (geographical location) is provided to the smart bumper sticker, the smart bumper sticker may be smarter and more accurate in determining the second geolocation (geographical location).

A location-enabled device according to the present disclosure may be configured as a fixed-location beacon (eg, the second geo-location is the same as the first geo-location) and is not changed because the beacon is in a fixed pose. not) may include a battery or may be a battery-free energy harvesting device or a moving-location beacon (eg second geo-location changes as a beacon), which may include a battery or be a battery-free energy harvesting device. device or combinations thereof.

A mobile device may use fixed-location beacons to obtain an observed geographic location to fine-tune a neural network of a location-enabled device embedded in the mobile device. A mobile device may obtain training data and/or an observed geographic location using various wireless communication protocols.

A location-enabled device according to the present disclosure may be configured in a network of at least two nodes or at least three nodes. For example, a network 900 of nodes is provided in FIG. 9 , wherein the nodes may be configured to form a mesh network, whereby each node may negotiate its current geographic location with respect to its neighbors. can Nodes can negotiate their current geographic location using a two-factor authentication, mutually negotiated (dampn) protocol. Once a node has successfully negotiated its current geolocation, it can be an Authorized Location Server (ALS). Nodes may be located within the network based on their demand for specific functions (eg, routing, messaging). In various examples, the network may also include a server.

A location-enabled device according to the present disclosure may be configured as a node of the network 900 , such as, for example, a router node, a base node, a service provider node, or a service requestor node, or a combination thereof. Each node may include a receiver configured to receive the geographic location of each node and/or neighboring nodes. Each node may include a transmitter configured to output the geographic location of each node.

A router node may be configured to route communications from one of the nodes to the other. The primary node may transmit a second geographic location (eg, the primary node's current location). The base node may be a low power node and may not include a GPS receiver. The service requestor node may be a mobile device including a receiver, a sensor, and a processor. The service requestor node may be configured to determine a current geographic location of the service requestor node based on a second geographic location output from at least one of respective nodes in the network and a sensor of the service requestor node using the neural network.

Each node may include class 1, class 2, class 3, or class 4 transmit power as shown in Table 1 below.

For example, each node may have a communication range of 1,000 meters or less, such as 500 meters or less, 100 meters or less, 10 meters or less, 1 meter or less, or 0.5 meters or less. In various examples, each node may have a communication range of at least 0.1 meters, such as at least 0.5 meters, at least 1 meter, at least 10 meters, at least 100 meters, or at least 500 meters. Nodes may not communicate with global positioning satellites or other objects more than 100 miles from the Earth's surface to determine their current geographic location.

The service provider node may send the message in addition to the second geolocation. The message may be a short message service or a very short message service. Messages may include advertisements. For example, a service provider node may be used to advertise a desired service via the network 900 of FIG. 9 neighboring the service provider node, and the service provider node may route this advertisement to the desired node.

As shown in Fig. 9, node (Q, R, S) is a router node, and node (a, B, C, D, E, F, G, H, I, J, K, L, M) is It is a basic node, node (O,P) is a service provider node, and node (N) is a service requestor node.

Physical objects cannot know their physical location. The present inventor provides a location-enabled (location assisting) device, which can provide geo-location to a physical object with minimal power consumption and low energy requirements, thereby performing a location aware function. These objects are smart objects because they can perform intelligent functions based on their context (eg pose).

Powered location-capable devices according to the present invention may store their current geographic location in available memory and may update their geographic location as desired. A non-powered object may use an energy harvesting device to provide power to a location-enabled device according to the present disclosure. However, non-motorized objects do not know their current geographic location because they do not have memory for receiving and storing the geographic location. However, the powered location-enabled device or other location-aware device according to the present disclosure may store the relative geographic location of non-powered objects with reference to its current geographic location. Accordingly, a non-powered object may receive its current geographic location from a powered location-capable device according to the present disclosure and may perform intelligent functions based on their context.

While several forms have been shown and described, it is the applicant's intention not to limit or limit the scope of the appended claims to these details. Numerous modifications, variations, alterations, substitutions, combinations, and equivalents to such forms can be embodied and will occur to those skilled in the art without departing from the scope of the invention. Also, each element associated with the described forms The structure of may alternatively be described as a means for providing the function performed by the element. Also, where materials are disclosed for a component, other materials may be used. Accordingly, it is to be understood that the foregoing description and appended claims embrace all such modifications, combinations and variations that fall within the scope of the form disclosed. The appended claims are intended to cover all such modifications, variations, alterations, substitutions, modifications, and equivalents.

The foregoing detailed description describes various forms of devices and/or processes through the use of block diagrams, flow diagrams, and/or examples. Although such block diagrams, flow diagrams, and/or examples include functions and/or operations, each function and/or operation within such block diagrams, flow diagrams, and/or examples may extend to a wide variety of hardware, software, and/or software. It will be understood by those skilled in the art that it may be individually and/or collectively implemented by One of ordinary skill in the art will recognize that some examples of the forms disclosed herein, in whole or in part, are computer programs running on a computer (eg, programs running on a computer system) as a program running on a processor (eg, a computer It will be appreciated that they may be implemented equivalently in integrated circuits (programs running on a system), as firmware (programs running on a microprocessor), as firmware, or substantially any combination thereof, in software and/or Designing code and/or designing circuitry for firmware will be well known to those skilled in the art in view of this disclosure. Also, those skilled in the art will appreciate that the mechanisms of the subject matter described herein may be distributed as a program product in various forms, and It will be understood that the exemplary form of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually perform the distribution.

The instructions used to program the logic to perform the various disclosed examples may be stored in memory within the system, such as dynamic random access memory (DRAM), cache, flash memory, or other storage. Also, the instructions may be distributed over a network or by other computer-readable media. Accordingly, a machine-readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (eg, a machine), a floppy diskette, an optical disk, a compact disk read-only memory ( CD-ROM), magneto-optical disk, read only memory (ROM), random access memory (RAM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), magnetic or including, but not limited to, optical cards, flash memory, or tangible machine-readable storage media used for the transmission of information over the Internet via electrical, optical, acoustical, etc., or other forms of propagated signals (such as For example, carrier waves, infrared signals, digital signals, etc.). Accordingly, non-transitory computer-readable media includes any tangible machine-readable medium suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, a computer).

As used herein, the term “control circuitry” includes, for example, hardwired circuitry, programmable circuitry (eg, one or more discrete instruction processing cores, processing unit, processor, microcontroller, microcontroller unit). , controller, digital signal processor (DSP), programmable logic device (PLD), programmable logic array (PLA), or FPGA), state machine circuitry, firmware that stores instructions to be executed by programmable circuitry , and any combination thereof. The control circuitry may be implemented, collectively or individually, as circuitry forming a larger system such as an IC, ASIC, SoC, desktop computer, laptop computer, tablet computer, server, smart phone, and the like. Thus, as used herein, a control circuit is an electrical circuit having at least one discrete electrical circuit, an electrical circuit having at least one IC, an electrical circuit having at least one application-specific IC, configured by a computer program An electrical circuit forming a general-purpose computing device (eg, a general-purpose computer configured by a computer program at least in part to execute the processes and/or devices described herein, or at least in part the processes and/or devices described herein, and A microprocessor configured by a computer program to perform the devices, an electrical circuit forming a memory device (eg, forms of RAM), and/or a communication device (eg, a modem, communication switch, or optical- electrical circuits forming electrical equipment.) Those skilled in the art will recognize that the subject matter described herein may be implemented in an analog or digital manner, or some combination thereof.

As used herein, the term “logic” may refer to an app, software, firmware, and/or circuitry configured to perform any of the operations described above. Software may be implemented as a software package, code, instructions, instruction sets, and/or data recorded on a non-transitory computer-readable storage medium. Firmware may be implemented as code, instructions or instruction sets, and/or hard-coded (eg, non-volatile) data in memory devices.

As used herein, the terms “component,” “system,” “software module,” and the like may refer to a computer-related entity, hardware, a combination of hardware and software, software, or software in execution.

As used herein, "algorithm" refers to a self-consistent sequence of steps leading to a desired result, wherein the steps are not required, but store, transfer, combine, compare, and otherwise refers to the manipulation of physical quantities and/or logical states that may take the form of electrical or magnetic signals that may otherwise be manipulated. It is common to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, and the like. These and similar terms may be associated with the appropriate physical quantities, and may merely be convenient labels applied to such quantities and/or states.

The network may include a packet switched network. The communication devices may communicate with each other using a selected packet switched network communication protocol. One example communication protocol may include an Ethernet communication protocol, which may allow communication using Transmission Control Protocol/Internet Protocol (TCP/IP). Ethernet protocol can be compliant

Alternatively, it may be compatible with the Ethernet standard published in the IEEE 802.3 standard, which is the IEEE 802.3 standard, and/or may be compatible with the Ethernet standard published by later versions of this standard. Alternatively or additionally, communication devices may communicate with each other using an X.25 communication protocol. < x > 25 The communication protocol may conform or be compatible with the standard promulgated by ITU-T (International Telecommunication Union - Telecommunication Standardization Sector). Alternatively or additionally, communication devices may communicate with each other using a frame relay communication protocol. The Frame Relay communication protocol may conform or be compatible with standards promulgated by the International Telegraph (International Telegraph) and Telephone (CIT) and/or the Presumptive Committee (Advisory Board) for the American National Standards Institute (ANSI). Alternatively or additionally, the transceivers may communicate with each other using an asynchronous transfer mode (ATM) communication protocol. The ATM communication protocol is compatible or may be compatible with the ATM standard promulgated by the ATM Forum, which may be compatible with ATM-MPLS Network Interworking 2.0 published August, 2001, and/or a later version of this standard. there is. Of course, different and/or later developed connection-oriented network communication protocols are considered equally herein.

As will be apparent from this disclosure, it is recognized that throughout this disclosure, unless specifically set forth, discussions are discussed using terms such as referring to the operations and processes of a computer system, or similar electronic computing device. That is, it converts and converts data expressed as physical (electronic) quantities in registers and memories of a computer system into other data similarly expressed as physical quantities in computer system memory or registers or other information storage, transmission, or display devices.

A component may generally include active-state components, inactive-state components, and/or standby-state components, unless the context requires otherwise.

One of ordinary skill in the art will generally recognize that terms used herein, in particular the appended claims (eg, the bodies of the appended claims), generally refer to the term (eg, the bodies of the appended claims) in general. It will be appreciated that it should not be construed as a term (eg, the bodies of the appended claims). A person of ordinary skill in the art will understand that where a certain number of introduced claim recitations are intended, such intent is expressly recited in claim 1, and in the absence of such recitation, no such intent exists. will be. For example, as an aid to understanding, the following appended claims may include an introduction to claim 1 and an introduction to one or more claims. However, the use of such phrases includes one or more of the introductory phrases of the same claim, or at least one or more locations and indeterminate articles such as indeterminate articles (e.g.

Furthermore, even if a particular number of introduced claim recitations are expressly recited, one of ordinary skill in the art will recognize that such recitations are at least the recited number (e.g., without other modifiers, typically at least two recesses, or two or more recesses). ) should be construed to mean Also, in these cases, there is a rule similar to at least one of a, B, and C. In general, such a configuration would be appreciated by those of ordinary skill in the art that a system having at least one of a, B and C alone, B alone, C alone, a system having a and B together, a and C together, B and with C, and/or systems comprising a, B, and C together). Generally, in separate words and/or phrases, descriptions, claims, or drawings providing two or more alternative terms, terms, one of the terms, or one of the two terms, unless the context dictates otherwise. It should be understood as considering the possibilities including For example, the phrase a or B will typically be understood to include the possibilities of a, B, or a and B.

With reference to the appended claims, one of ordinary skill in the art will understand that the operations recited herein may be performed in any order. Also, although various operational flow diagrams are presented in sequence(s), it should be understood that various operations may be performed in an order other than those shown, or may be performed concurrently. Examples of such alternative orderings may include overlapping, interleaved, interrupted, reordered, incremental, prepared, supplemental, simultaneous, inverse, or other variant ordering, unless the context dictates otherwise. Also, terms such as context are generally not intended to exclude such variations, unless the context dictates otherwise.

Any patent application, patent, non-patent publication, or other disclosing material mentioned herein is incorporated herein by reference to the extent that the incorporated material is inconsistent with this application. As such, and to the extent necessary, as expressly set forth herein, this specification is incorporated herein by reference. Any material, or portion thereof, which may be incorporated by reference herein conflicts with existing definitions, statements, or other disclosing materials set forth herein, but between the materials disclosed herein and pre-existing starting materials. They will coalesce only to the extent that no collisions occur.

Various aspects of the invention in accordance with this disclosure include, but are not limited to, those listed in the following numbered clauses.

100: device 102: processor
104: memory 106: receiver
108: transmitter 110: sensor

Claims (22)

A device for determining a geolocation (geographic location), comprising:
a receiver configured to receive a first geolocation (geographic location);
a sensor configured to determine a change in pose of the device;
a processor operatively coupled to a memory, the receiver, and the sensor, the processor configured to determine a second geographic location based on the first geolocation and the sensor using a neural network;
and a first transmitter configured to output the second geographic location of the device.
According to claim 1,
The apparatus of claim 1, further comprising an energy harvesting device comprising a piezoelectric energy harvesting device, an electrostatic energy harvesting device, an electromagnetic energy harvesting device, a photovoltaic cell, or a radio frequency energy harvesting device, or combinations thereof.
According to claim 1,
The apparatus further comprising a battery, wherein the neural network is embedded in the battery.
According to claim 1,
wherein the receiver is configured to receive the first geolocation via a first wireless communication protocol, and the first transmitter is configured to output the second geographic location via a second wireless communication protocol.
5. The method of claim 4,
wherein each wireless communication protocol comprises a short-range communication protocol, a Bluetooth low energy protocol, a Wi-Fi protocol, or a Zigbee protocol, or a combination thereof.
5. The method of claim 4,
wherein the first wireless communication protocol includes a short-range communication protocol and the second wireless communication protocol includes a Bluetooth low energy protocol.
According to claim 1,
wherein the sensor comprises an accelerometer, an inertial measurement unit, a gyroscope, or a magnetometer, or a combination thereof.
According to claim 1,
wherein the memory is secure memory.
A mobile device comprising the apparatus of claim 1 , comprising a fastener, a marker, a doorbell, or combinations thereof.
According to claim 1,
and the processor is configured to store the second location in the memory.
According to claim 1,
and the first transmitter is configured to transmit a message.
According to claim 1,
wherein the first geo-location is stored in the memory and the processor is configured to overwrite the first geo-location with the second geo-location.
According to claim 1,
wherein the receiver is further configured to receive an observed geolocation (geographic location), and the processor is configured to train the neural network with the observed geolocation (geographic location).
14. The method of claim 13,
wherein the processor configured to train the neural network comprises a processor configured to adjust weights and biases in the neural network.
14. The method of claim 13,
wherein the receiver is configured to receive the observed geographic location from a node:
a second transmitter configured to output a current geographic location of the node as an observed geolocation via a wireless communication protocol, wherein the wireless communication protocol is a short-range communication protocol, a Bluetooth low energy protocol, a Wi-Fi protocol, or a Zigbee protocol, or these An apparatus for wireless communication comprising combinations of
According to claim 1,
and a global positioning system configured to provide the observed geo-location to the processor for training the neural network.
A network for determining a geolocation (geographic location), comprising:
As a node (node),
a first transmitter configured to output a current geographic location of the node via a wireless communication protocol, the wireless communication protocol comprising a short-range communication protocol, a Bluetooth low energy protocol, a Wi-Fi protocol, or a Zigbee protocol, or combinations thereof; and
A mobile device comprising:
a receiver configured to receive a current geographic location of the node via the wireless communication protocol;
a sensor configured to determine a change in pose of the mobile device; and
a processor operatively coupled to a memory, the receiver, and the sensor, wherein the processor is configured to determine a current geographic location of the mobile device based on a current geographic location of the node and the sensor using a neural network. Consisting of a mobile device.
18. The method of claim 17,
A system further comprising at least two nodes.
The system of claim 18 , wherein the at least two nodes form a mesh network.
19. The method of claim 18,
at least one of the nodes is configured to send a message.
19. The method of claim 18,
and at least one of the nodes is configured to route communication from one of the nodes to a different one of the nodes or the mobile device, or combinations thereof.
19. The method of claim 18,
at least one of the nodes configured to determine the geographic location of the node using a mutually negotiated protocol negotiated with each other.

Images