Method and apparatus implementing an optimized network reselection setting based on biometric information of a user and status information of a wearable computing device

Abstract

A wearable computing device includes at least one memory to store instructions and at least one processor to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

Description

METHOD AND APPARATUS IMPLEMENTING AN OPTIMIZED NETWORK RESELECTION SETTING BASED ON BIOMETRIC INFORMATION OF A USER AND STATUS INFORMATION OF A WEARABLE COMPUTING DEVICEFIELD

[0001] The disclosure relates generally to wearable computing devices. More particularly, the disclosure relates to wearable computing devices which can implement an optimized network reselection setting which is determined based on biometric information associated with a user and status information associated with the wearable computing device, to perform a network reselection operation.BACKGROUND

[0002] Wearable computing devices can lose connectivity with a wireless network when the wearable computing device is placed under an object such as a blanket or body part of a user. According to some existing methods, when the wearable computing device signal strength falls below a threshold level, the wearable computing device can enter a loop attempting to search all frequency bands or wireless carriers to find a suitable carrier.SUMMARY

[0003] Aspects and advantages of embodiments of the disclosure will be set forth in part in the following description, or can be learned from the description, or can be learned through practice of the example embodiments.

[0004] In an example embodiment, a wearable computing device (e.g., a biometric computing device, a smartwatch, a tracker, wearable jewelry, for example, having long-term evolution (LTE) capabilities, and the like) is provided. The wearable computing device includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a networkreselection operation.

[0005] In some implementations, the at least one processor is further configured to: when the biometric information indicates the user is asleep and the status information indicates movement of the wearable computing device is less than a threshold movement level, increase a default signal strength threshold value to an optimized signal strength threshold value which is set as the network signal strength threshold value, and when the biometric information indicates the user is awake or the status infomiation indicates movement of the wearable computing device exceeds the threshold movement level, maintain the default signal strength threshold value as the network signal strength threshold value.

[0006] In some implementations, the optimized network reselection setting includes a time associated with triggering the network reselection operation and the at least one processor being further configured to: when the biometric information indicates the user is asleep and the status infomiation indicates movement of the wearable computing device is less than a threshold movement level, change the time associated with triggering the network reselection operation, and when the biometric information indicates the user is awake or the status information indicates movement of the wearable computing device exceeds the threshold movement level, maintain the time associated with triggering the network reselection operation.

[0007] In some implementations, the at least one processor is configured to change the time associated with triggering the network reselection operation by increasing a period of time for triggering the network reselection operation subsequent to the signal strength being less than the network signal strength threshold value.

[0008] In some implementations, the network reselection operation includes switching the wearable computing device between a Wi-Fi network and a Long-Term Evolution network.

[0009] In some implementations, the at least one processor is configured to implement a machine-learned model trained to determine the optimized network reselection setting based on the biometric information indicating whether the user is asleep and the status information.

[0010] In some implementations, the optimized network reselection setting includes an optimal frequency band among a plurality of frequency bands, and the at least one processor being further configured to switch to the optimal frequency band to perform the network reselection operation.

[0011] In some implementations, the optimized network reselection setting includes anoptimal network carrier among a plurality of network carriers, and the at least one processor being further configured to switch to the optimal network carrier to perform the network reselection operation.

[0012] In some implementations, the optimized network reselection setting includes the network signal strength threshold value, and the at least one processor being further configured to perform the network reselection operation based on the network signal strength threshold value determined by the machine-learned model.

[0013] In some implementations, the optimized network reselection setting includes an optimal wireless network platform among a plurality of wireless network platforms, and the at least one processor being further configured to switch to the optimal wireless network platform to perform the network reselection operation.

[0014] In some implementations, the plurality of wireless network platforms includes a Wi-Fi wireless network platform and a Long-Term Evolution wireless network platform.

[0015] In some implementations, the status information includes at least one of movement information associated with the wearable computing device, location information associated with the wearable computing device, or an operating mode of the wearable computing device.

[0016] In some implementations, the movement information including movement information which indicates whether movement of the wearable computing device is less than a threshold movement level, the location information including location information which indicates a particular room in a building in which the wearable computing device is located, and the operating mode of the wearable computing device including an operating mode associated with the user being asleep.

[0017] In some implementations, the at least one processor is further configured to: implement a machine-learned model, trained based on reinforcement learning and observations of network conditions associated with the wearable computing device in a particular environment, to determine the optimized network reselection setting based on the biometric information indicating whether the user is asleep and a current environment of wearable computing device as indicated by the status information.

[0018] In an example embodiment, a computer-implemented method for a wearable computing device is provided. The computer-implemented method includes: receiving biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receiving status information indicating a state of the w earablecomputing device, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, implementing an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

[0019] The computer-implemented method for the wearable computing device may include further operations to execute other aspects and operations of the wearable computing device as described herein.

[0020] In an example embodiment, a wearable computing device (e.g., a biometric computing device, a smartwatch, a tracker, wearable jewelry, for example, having long-term evolution (LTE) capabilities, and the like) is provided. The wearable computing device includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, implement a machine-learned model trained to output an optimized network reselection setting based on the biometric information and the status information, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, perform a network reselection operation according to the optimized network reselection setting output by the machine- learned model.

[0021] In some implementations, the optimized network reselection setting includes an optimal frequency band among a plurality of frequency bands, and the at least one processor being further configured to switch to the optimal frequency band to perform the network reselection operation.

[0022] In some implementations, the optimized network reselection setting includes an optimal public land mobile network (PLMN) component among a plurality of PLMN components, and the at least one processor being further configured to utilize the optimal PLMN component to perform the network reselection operation.

[0023] In some implementations, the optimized network reselection setting includes thenetwork signal strength threshold value, and the at least one processor being further configured to perform the network reselection operation based on the network signal strength threshold value output by the machine-learned model.

[0024] In some implementations, the optimized network reselection setting includes a time associated with triggering the network reselection operation and the at least one processor being further configured to perform the network reselection operation based on the time output by the machine-learned model.

[0025] In some implementations, the optimized network reselection setting includes an optimal wireless network platform among a plurality of wireless network platforms, and the at least one processor being further configured to switch to the optimal wireless network platform to perform the network reselection operation.

[0026] In an example embodiment, a computer-implemented method for a wearable computing device is provided. The computer-implemented method includes: receiving biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receiving status information indicating a state of the wearable computing device, implementing a machine-learned model trained to output an optimized network reselection setting based on the biometric information and the status information, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, performing a network reselection operation according to the optimized network reselection setting output by the machine-learned model.

[0027] The computer-implemented method for the wearable computing device may include further operations to execute other aspects and operations of the wearable computing device as described herein.

[0028] In an example embodiment, a server computing system is provided. The server computing system includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing a wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computingdevice is connected being less than a network signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

[0029] Tn an example embodiment, a server computing system is provided. The server computing system includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, implement a machine-learned model trained to output an optimized network reselection setting based on the biometric information and the status information, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a netw ork signal strength threshold value used to trigger reselection, perform a network reselection operation according to the optimized network reselection setting output by the machine-learned model.

[0030] In an example embodiment, a non-transitory computer-readable medium which stores instructions that are executable by at least one processor of a computing device is provided. The non-transitory computer-readable medium stores instructions which are executable by at least one processor of the computing device. The instructions include instructions to cause the at least one processor to: receive biometric information relating to a user wearing the wearable computing device indicating whether a user is asleep; receive status information indicating a state of the wearable computing device; and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

[0031] In an example embodiment, a non-transitory computer-readable medium which stores instructions that are executable by at least one processor of a computing device is provided. The non-transitory computer-readable medium stores instructions which are executable by at least one processor of the computing device. The instructions include instructions to cause the at least one processor to: receive biometric information relating to a user wearing thewearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, implement a machine-learned model trained to output an optimized network reselection setting based on the biometric information and the status information, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, perform a network reselection operation according to the optimized network reselection setting output by the machine-learned model.

[0032] In some implementations, a non-transitory computer-readable medium may store additional instructions to execute other aspects and operations of the computing device, the server computing system, and computer-implemented methods as described herein.

[0033] These and other features, aspects, and advantages of various embodiments of the disclosure will become better understood with reference to the following description, drawings, and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate examples of the disclosure and, together with the description, serve to explain the related principles.BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Detailed discussion of example embodiments directed to one of ordinary skill in the art is set forth in the specification, which makes reference to the appended drawings, in which:

[0035] FIG. 1 A is an example system including block diagrams of a wearable computing device, a server computing system, and an external computing device, according to one or more examples of the disclosure;

[0036] FIG. IB is an example block diagram of a network reselection optimizer application, according to one or more examples of the disclosure;

[0037] FIGS. 2A-2B are example tables depicting example optimized network reselection settings, according to one or more examples of the disclosure; and

[0038] FIG. 3 is a flow diagram of an example, non-limiting computer-implemented method according to one or more examples of the disclosure.DETAILED DESCRIPTION

[0039] Reference now will be made to embodiments of the disclosure, one or more examplesof which are illustrated in the drawings. Each example is provided by way of explanation of the disclosure and is not intended to limit the disclosure. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made to the disclosure without departing from the scope or spirit of the disclosure. For instance, features illustrated or described as part of one embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the disclosure covers such modifications and variations as come within the scope of the appended claims and their equivalents.

[0040] Terms used herein are used to describe the example embodiments and are not intended to limit and / or restrict the disclosure. The singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. In this disclosure, terms such as "including", "having", “comprising”, and the like are used to specify features, numbers, steps, operations, elements, components, or combinations thereof, but do not preclude the presence or addition of one or more of the features, elements, steps, operations, elements, components, or combinations thereof.

[0041] It will be understood that, although the terms first, second, third, etc., may be used herein to describe various elements, the elements are not limited by these terms. Instead, these terms are used to distinguish one element from another element. For example, without departing from the scope of the disclosure, a first element may be termed as a second element, and a second element may be termed as a first element.

[0042] The term "and I or" includes a combination of a plurality of related listed items or any item of the plurality of related listed items. For example, the scope of the expression or phrase "A and / or B" includes the item "A", the item "B", and the combination of items "A and B”.

[0043] In addition, the scope of the expression or phrase "at least one of A or B" is intended to include all of the following: (1) at least one of A, (2) at least one of B, and (3) at least one of A and at least one of B. Likewise, the scope of the expression or phrase "at least one of A, B, or C" is intended to include all of the following: (1) at least one of A, (2) at least one of B, (3) at least one of C, (4) at least one of A and at least one of B, (5) at least one of A and at least one of C, (6) at least one of B and at least one of C, and (7) at least one of A, at least one of B, and at least one of C.

[0044] Example aspects of the disclosure are directed to a computing device, for example, a wearable computing device such as a smartwatch, fitness tracker, earbuds, and the like, whichcan connect to a network (e.g., via long-term evolution (LTE) technology).

[0045] Power consumption is a difficult problem for wearable computing devices. For example, while a user is sleeping and moves around and tucks their arm under a blanket / body, the wearable computing device may lose network connectivity (e.g., with a cellular tower) as a signal path associated with the wearable computing device is blocked and a signal strength value (e.g., a reference signal received power (RSRP) value, a reference signal received quality (RSRQ) value, etc.) drops below a network signal strength threshold value (e.g., a QRXLEV-MIN) specified by the network. The wearable computing device can enter a loop of trying to search all frequency bands / network carriers to find a suitable carrier to camp on, thus losing a large amount of battery life in this continuous search stage.

[0046] According to example embodiments of the disclosure, a network reselection optimizer application receives various inputs (e.g., operation mode data including bedtime mode sensor data, motion data including body movement data, biometric data associated with the user, etc.). The network reselection optimizer application can implement one or more machine- learned models to learn which particular frequency bands, network carriers, and the like are optimal given particular conditions. For example, the one or more machine-learned models can leam a particular frequency band or a network carrier which is optimal for the wearable computing device to switch to when a signal strength associated with the wearable computing device falls below a network signal strength threshold value given that a user is located in a particular room at a particular time and is asleep.

[0047] The network reselection optimizer application can implement one or more machine- learned models to leam to increase a default signal strength threshold value to an optimized signal strength threshold value which is set as the network signal strength threshold value. For example, the one or more machine-learned models can be trained to preemptively increase the default signal strength threshold value to the optimized signal strength threshold value, given certain conditions (e.g., that a user is located in a particular room at a particular time and is asleep). For example, the one or more machine-learned models can be trained to reactively increase the default signal strength threshold value to the optimized signal strength threshold value as the signal strength worsens and approaches or crosses a currently set network signal strength threshold value (e g., the default signal strength threshold value), given certain conditions (e.g., that a user is located in a particular room at a particular time and is asleep).

[0048] As an example, if the wearable computing device operates in a bedtime mode (which is indicative of a user being asleep), but the user is on a bus or train, the network reselection optimizer application can implement one or more machine-learned models which may be trained to recognize that the loss in signal strength may be due to movement of the vehicle, and thus a network reselection operation may not include increasing the default signal strength threshold value, but instead may include allowing the wearable computing device to search for frequency bands / network carriers to find a suitable carrier to camp on.

[0049] For example, the one or more machine-learned models may be trained to limit (bound) the search window of frequency bands / network carriers according to a location of the user. For example, in the same building (e.g., a house) different floors or rooms may have different frequency bands / network carriers. For example, a room on the top floor compared to a room on a bottom floor may have different frequency bands / network carriers which are optimal (e.g., which have a higher quality signal, a greatest signal strength, etc.). The one or more machine-learned models may be trained to determine in advance the set of the frequency bands / network carriers in the building which are optimal for searching in a reselection process. This set may be much less than the entire set of frequency bands / network carriers the wearable computing device might otherwise search.

[0050] According to existing methods, if a signal strength associated with a wearable computing device falls below a network signal strength threshold value (e.g., QRXLEV mm), the wearable computing device may begin a reselection process and scan around for all other networks or cells (from the same and other network carriers), to find the next most suitable network and then camp on this network.

[0051] Examples of the disclosure modify the behavior of the wearable computing device, leading to computer resource savings (e.g., reduced power consumption), reduced time spent searching for a network to camp on, increased connectivity to a network, etc. The behavior of the wearable computing device can be modified using the network reselection optimizer application described herein, the one or more machine-learned models described herein, and in view of the biometric information of the user and the status information of the wearable computing device described herein.

[0052] In some implementations, the wearable computing device can determine whether a user is sleeping, determine an operating mode of the wearable computing device, anddetermine motion information associated with the wearable computing device (which, when worn by the user is indicative of motion of the user).

[0053] The wearable computing device can be configured to detect or determine when the user is sleeping (e.g., using known sleep detection algorithms pertaining to sleep tracking). Although the user may move around and activate a motion sensor, the user could still be asleep. For example, operation of a bedtime mode may also be indicative of a user being asleep. However, in some cases a bedtime operating mode may be enabled and the user may not be sleeping.

[0054] For example, the one or more machine-learned models may be trained (e.g., based on using reinforcement learning) to learn the user’s movement pattern while the user is asleep. The one or more machine-learned models may be trained using a reward system that rewards a model which conserves power, maintains connectivity, establishes connectivity quickly, etc. On the other hand, the reward system may penalize a model which results in power being drained, has a lack of connectivity (unintentionally), takes too long to establish connectivity, etc. With a fingerprint of the user’s behavior, knowledge of a sleep or bedtime mode, knowledge of the user’s sleep pattern, and the like, the one or more machine-learned models may be configured to: attempt to connect to one or more particular frequency bands and / or network carriers if a signal strength drops below a network signal strength threshold value (e.g., QRXLEV-MIN); adjust a default network signal strength threshold value; delay a time for attempting to reconnect to another network and allow the wearable computing device to be disconnected from the network (or experience poor signal quality) for a time greater than a default period of time; blacklist certain frequency bands, in a given context, for a period of time greater than a default period of time so that the wearable computing device does not attempt to reconnect to certain frequency bands in that context (e.g., changing the blacklist period of time from 300 seconds to 24 hours, 1 week, etc.).

[0055] For example, if a user sleeps in the same bedroom at generally the same time of day, in some instances the network reselection optimizer application may be configured to prioritize attempting to connect to a particular frequency band (or top frequency bands) which has (have) been identified by the one or more machine-learned models as most likely for the wearable computing device to successfully connect to, when the signal strength associated with the wearable computing device drops below a network signal strength threshold value. For example, in some instances the network reselection optimizer application may be configured to instead delay the reselection process for a few seconds or afew minutes because the one or more machine-learned models has determined the user’s movement patterns and predicts that the original signal (and signal strength) will be restored shortly. For example, in some instances the network reselection optimizer application may be configured to instead change the network signal strength threshold value (e.g., by increasing the threshold some amount such as 6 dB or 10 dBm) so that the reselection process does not begin until the signal quality is lower than in other circumstances where the reselection process would begin earlier in time.

[0056] Example aspects of the disclosure provide several technical effects, benefits, and / or improvements in computing technology and the technology of computing devices including wearable computing devices. For example, according to one or more examples of the disclosure, computing resources (e.g., battery resources, processing resources, etc.) may be saved or conserved by modifying the behavior of the wearable computing device under certain conditions.

[0057] Furthermore, implementation of the disclosed method and wearable computing device can improve the function of the wearable computing device itself by maintaining network connectivity, decreasing a time for a reselection process to be performed by preemptively identify ing optimal frequency bands and / or network carriers, etc.

[0058] For example, according to one or more examples of the disclosure, additional aspects described herein may conserve computing resources (e.g., processing resources, battery resources, etc.) of the wearable computing device. For example, computing resources may be saved or conserved by not searching all frequency bands and / or network carriers, by delaying a time to perform the reselection operation, by increasing a network signal strength threshold value, etc.

[0059] Referring now to the drawings, FIG. 1 A illustrates an example system including block diagrams of a wearable computing device, a server computing system, and an external computing device, according to one or more examples of the disclosure.

[0060] In FIG. 1A, the example system 1000 includes a wearable computing device 1100, a server computing system 1300, and an external computing device 1400. For example, the wearable computing device 1100, server computing system 1300, and external computing device 1400 may be connected with one another over a network 1200. Any communications interfaces suitable for communicating via the network 1200 (such as a network interface card) may be utilized as appropriate or desired by the wearable computing device 1100,server computing system 1300, and external computing device 1400.

[0061] The wearable computing device 1100 may include wearable computing devices (e.g., a smartwatch, a tracker, earbuds, jewelry, and the like). For example, the wearable computing device may be capable of measuring biometric information of a user associated with the wearable computing device. In example embodiments described herein, the wearable computing device 1100 can connect to a network wirelessly, for example, via WiFi, via a cellular network utilizing long temi evolution (LTE) technology, etc.

[0062] The server computing system 1300 may include a server, or a combination of servers (e.g., a web server, application server, etc.) in communication with one another, for example in a distributed fashion. The external computing device 1400 may include any computing device including a personal computer, a smartphone, a laptop, a tablet computer, a wearable computing device, and the like. In example embodiments described herein, the external computing device 1400 may be a computing device that can communicate with the wearable computing device 1100 via a wireless network, for example, via Wi-Fi, via a cellular network utilizing long term evolution (LTE) technology, etc.

[0063] For example, the network 1200 may include any type of communications network such as a local area network (LAN), wireless local area network (WLAN), wide area network (WAN), personal area network (PAN), virtual private network (VPN), and the like. For example, wireless communication between elements of the examples described herein may be performed via a wireless LAN, Wi-Fi, Bluetooth, ZigBee, Wi-Fi direct (WFD), ultra wideband (UWB), infrared data association (IrDA), Bluetooth low energy (BLE), near field communication (NFC), a radio frequency (RF) signal, cellular networks (e.g., using protocols including Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), or LTE), and the like. For example, wired communication between elements of the examples descnbed herein may be performed via a pair cable, a coaxial cable, an optical fiber cable, an Ethernet cable, and the like. Communication over the network can use a wide variety of communication protocols (e.g., TCP / IP, HTTP, SMTP, FTP), encodings or formats (e.g., HTML, XML), and / or protection schemes (e.g., VPN, secure HTTP, SSL).

[0064] The wearable computing device 1100 may include one or more processors 1110, one or more memory devices 1120, a network reselection optimizer application 1130, an input device 1140, a display device 1150, an output device 1160, a communication interface 1170, one or more sensors 1180, and an operating mode selector 1190. The wearable computingdevice 1100 depicted in FIG. 1A is only an example, and the wearable computing device 1100 described herein may include more features or less features than those shown in FIG.1 A. Each of the components of the wearable computing device 1100 may be operatively connected with one another via a system bus. For example, the system bus may be any of several types of bus structures that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and / or a local bus using any of a variety of commercially available bus architectures.

[0065] The server computing system 1300 may include one or more processors 1310, one or more memory devices 1320, and a network reselection optimizer application 1330. Each of the features of the server computing system 1300 may be operatively connected with one another via a system bus. For example, the system bus may be any of several types of bus structures that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and / or a local bus using any of a variety of commercially available bus architectures.

[0066] The external computing device 1400 may include a personal computer, a smartphone, a laptop, a tablet computer, a wearable computing device, and the like. In example embodiments described herein, the external computing device 1400 may be any computing device that can communicate with the wearable computing device 1100 via a wireless network. The external computing device 1400 can include some or all of the components described with respect to the wearable computing device 1100 including the network reselection optimizer application 1130. Therefore, descriptions of these components in the context of the wearable computing device 1100 are also applicable to the external computing device 1400 and will not be repeated for the sake of brevity. Each of the features of the external computing device 1400 may be operatively connected with one another via a system bus. For example, the system bus may be any of several types of bus structures that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and / or a local bus using any of a variety of commercially available bus architectures.

[0067] For example, the one or more processors 1110, 1310 can be any suitable processing device that can be included in a wearable computing device 1100 or server computing system 1300. For example, such a processor 1110, 1310 may include one or more of a processor, processor cores, a controller and an arithmetic logic unit, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an image processor, a microcomputer, a field programmable array, a programmable logic unit, an application-specific integrated circuit (ASIC), a microprocessor, a microcontroller, etc., and combinations thereof, including any other device capable of responding to and executing instructions in a defined manner. The one or more processors 1110, 1310 can be a single processor or a plurality of processors that are operatively connected, for example in parallel.

[0068] The one or more memory' devices 1 120, 1320 can include one or more non-transitory computer-readable storage mediums, such as such as a Read Only Memory (ROM), Programmable Read Only Memory (PROM), Erasable Programmable Read Only Memory (EPROM), and flash memory, a USB drive, a volatile memory device such as a Random Access Memory (RAM), an internal or external hard disk drive (HDD), floppy disks, a blueray disk, or optical media such as CD ROM discs and DVDs, and combinations thereof. However, examples of the one or more memory devices 1120, 1320 are not limited to the above description, and the one or more memory devices 1120, 1320 may be realized by other various devices and structures as would be understood by those skilled in the art.

[0069] For example, the one or more memory devices 1120 can store instructions, that when executed, cause the one or more processors 1110 to: receive biometric information relating to a user wearing the wearable computing device 1100 indicating whether the user is asleep, receive status information indicating a state of the wearable computing device 1100, and in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a network signal strength threshold value, implement an optimized network reselection setting determined based on the biometric information indicating the user is asleep and the status information, to perform a network reselection operation, as described according to examples of the disclosure.

[0070] For example, the one or more memory devices 1320 can store instructions, that when executed, cause the one or more processors 1310 to: receive biometric information relating to a user wearing the wearable computing device 1100 indicating whether the user is asleep, receive status information indicating a state of the wearable computing device 1100, and in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a network signal strength threshold value, implement an optimized network reselection setting determined based on the biometric information indicating the user is asleep and the status information, to perform a network reselection operation, as described according to examples of the disclosure.

[0071] The one or more memory devices 1120 can also include data 1122 and instructions 1124 that can be retrieved, manipulated, created, or stored by the one or more processors 1110. In some examples, such data can be accessed and used as input to implement an optimized network reselection setting determined based on biometric information indicating whether the user is asleep and status information indicating a state of the wearable computing device 1100, to perform a network reselection operation, as described according to examples of the disclosure.

[0072] The one or more memory' devices 1320 can also include data 1322 and instructions 1324 that can be retrieved, manipulated, created, or stored by the one or more processors 1310. In some examples, such data can be accessed and used as input to implement an optimized network reselection setting determined based on biometric information indicating whether the user is asleep and status information indicating a state of the wearable computing device 1100, to perform a network reselection operation, as described according to examples of the disclosure.

[0073] The wearable computing device 1100 can include a network reselection optimizer application 1130. The network reselection optimizer application 1130 can include an application which is configured to implement an optimized network reselection setting determined based on biometric information indicating whether the user is asleep and status information indicating a state of the wearable computing device 1100, to perform a network reselection operation. Operations of the network reselection optimizer application 1130 are explained in more detail with reference to FIG. IB. In some implementations, the network reselection optimizer application 1130 can include a motion determiner 1132, a location determiner 1134, a sleep determiner 1136, one or more machine-learned models 1138, and an optimized network reselection setting determiner 1139.

[0074] The server computing system 1300 can include a network reselection optimizer application 1330. The network reselection optimizer application 1330 can also include similar features as the network reselection optimizer application 1130 (e.g., as shown in FIG. IB) which perform similar functions and operations, and therefore a description of those features will not be repeated for the sake of brevity.

[0075] The wearable computing device 1100 may include an input device 1140 configured to receive an input from a user and may include, for example, one or more of a keyboard (e.g., a physical keyboard, virtual keyboard, etc.), a mouse, a joystick, a button, a switch, anelectronic pen or stylus, a gesture recognition sensor (e.g., to recognize gestures of a user including movements of a body part), an input sound device or voice recognition sensor (e.g., a microphone to receive a voice command), a track ball, a remote controller, a portable (e.g., a cellular or smart) phone, and so on. The input device 1140 may also be embodied by a touch-sensitive display device having a touchscreen capability, for example. For example, the input may be a voice input, a touch input, a gesture input, a click via a mouse, a remote controller, and so on.

[0076] The wearable computing device 1100 may include a display device 1150 which presents information viewable by the user, for example on a user interface (e.g., a graphical user interface). For example, the display device 1150 may be a touch sensitive display or a non-touch sensitive display. The display device 1150 may include a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, active matrix organic light emitting diode (AMOLED), flexible display, 3D display, a plasma display panel (PDP), a cathode ray tube (CRT) display, and the like, for example. However, the disclosure is not limited to these example display devices and may include other types of display devices.

[0077] The wearable computing device 1100 may include an output device 1160 configured to provide an output to the user and may include, for example, one or more of an audio device (e.g., one or more speakers), a haptic device to provide haptic feedback to a user, a light source (e.g., one or more light sources such as LEDs which provide visual feedback to a user), and the like.

[0078] The wearable computing device 1100 may include communication interface 1170. For example, the communication interface 1170 may include one or more network interface cards (e.g., wireless network adapters) configured to enable the communication of information over a network (e.g., network 1200) in a wired or wireless manner. For example, the communication interface 1170 may include a serial interface (e.g., using a serial communication protocol including Universal Serial Bus), a Bluetooth interface, a Wi-Fi interface, a cellular interface, ethernet interface, a fiber channel interface, etc.

[0079] The wearable computing device 1100 may include one or more sensors 1180. For example, the one or more sensors 1180 may include one or more motion sensors 1182 (e.g., an inertial measurement unit (IMU) which includes one or more accelerometers and / or one or more gyroscopes) which can be used to capture motion information with respect to thewearable computing device 1100. For example, the one or more sensors 1180 may include one or more biometric sensors 1184 (e.g., photoplethysmography (PPG) sensors, electrocardiogram (ECG) sensors, etc.). For example, the one or more sensors 1180 may include one or more location sensors 1186 (e.g., GPS sensors, GNSS sensors, IMU sensors, etc.), a magnetometer, and the like. The one or more sensors 1180 can also include one or more cameras. For example, the one or more cameras may include an imaging sensor (e g., a complementary metal-oxide-semiconductor (CMOS) or charge-coupled device (CCD)) to capture, detect, or recognize a user's behavior, figure, expression, etc.

[0080] The wearable computing device 1100 may include an operating mode selector 1190. For example, the operating mode selector 1190 may be configured to select a particular mode of operation for the wearable computing device 1100. For example, operating modes of the wearable computing device 1100 may include a bedtime mode 1192, an exercise mode 1194, a power savings mode 1196, etc. For example, the bedtime mode 1192 may be associated with a user sleeping. For example, the bedtime mode 1192 may be a mode in which the w earable computing device 1100 activates sleep tracking to monitor a sleep pattern of the user, prevents notifications from disturbing the user while the user is sleeping, lowers a power setting of the wearable computing device 1100, changes lighting setting of the wearable computing device 1100, etc. For example, the exercise mode 1194 may be a mode in which the wearable computing device 1100 activates fitness tracking to monitor exercise activity of the user (e.g., monitor a step count, monitor a heart rate, monitor distance information, etc.). For example, the power savings mode 1196 may be a mode in which the wearable computing device 1100 conserves battery life by disabling non-essential features (e.g., reducing screen brightness, disabling applications, etc.). The wearable computing device 1100 may include other operating modes (e.g., a travel mode, a work mode, a do not disturb mode, etc.).

[0081] Example system 1000 may include a user data store 1350. In some implementations, u user data store 1350 can represent a single database. In some implementations, the user data store 1350 represents a plurality of different databases accessible to the wearable computing device 1100, server computing system 1300, and external computing device 1400. In some examples, the user data store 1350 can include biometric information of a user or a plurality of users. In some examples, the user data store 1350 can include information regarding one or more user profiles, including a variety of user data such as user preference data, user demographic data, user calendar data, user social network data, user historicalhealth data, and the like. For example, the user data store 1350 can include any biometric information or information associated with the biometric information (e.g., motion information associated with the collection of the biometric information, time information associated with the collection of the biometric information, location information associated with the collection of the biometric information, wearable computing device 1100 associated with the collection of the biometric information, etc.). The user biometric information and associated information may be associated with a user account.

[0082] The user data store 1350 is provided to illustrate potential data that could be analyzed or stored, in some embodiments, by the wearable computing device 1100 and / or server computing system 1300 to maintain a record of biometric information associated wdth a user, for example. However, such user data may not be collected, used, or analyzed unless the user has consented after being informed of what data is collected and how such data is used. Further, in some embodiments, the user can be provided with a tool (e.g., in a biometric measurement application, a sleep tracking application, an exercise application, a user account, etc.) to revoke or modify the scope of permissions. In addition, certain information or data can be treated in one or more ways before it is stored or used, so that personally identifiable information is removed or stored in an encrypted fashion. Thus, particular user information stored in the user data store 1350 may or may not be accessible to the wearable computing device 1100 and / or server computing system 1300 based on permissions given by the user, or such data may not be stored in the user data store 1350 at all.

[0083] Referring to FIG. IB, an example block diagram of a network reselection optimizer application of a wearable computing device is shown, according to one or more examples of the disclosure. FIG. IB illustrates that the network reselection optimizer application 1130 can include a motion determiner 1132, a location determiner 1134, a sleep determiner 1136, one or more machine-learned models 1138, and an optimized network reselection setting determiner 1139. How ever, the network reselection optimizer application 1130 may include fewer or more features than that shown in FIG. IB.

[0084] Operations of the network reselection optimizer application 1130 will now be described in more detail with reference to FIGS. 2A through 2B and the flow diagram of a non-limiting computer-implemented method shown in FIG. 3.

[0085] FIGS. 2A-2B are example tables depicting example optimized network reselection settings, according to one or more examples of the disclosure. FIG. 3 is a flow diagram of anexample, non-limiting computer-implemented method according to one or more examples of the disclosure.

[0086] The flow diagram of FIG. 3 illustrates a method 3100 for implementing an optimized network reselection setting determined based on biometric information indicating whether a user is asleep and status information indicating a state of the wearable computing device 1100, to perform a network reselection operation. Although shown in a particular sequence or order, unless otherwise specified, the order of the processes can be modified. Thus, the illustrated embodiments should be understood only as examples, and the illustrated processes can be performed in a different order, and some processes can be performed in parallel. Additionally, one or more processes can be omitted in various embodiments. Thus, not all processes are required in every embodiment. Other process flows are possible.

[0087] At operation 3110, the method 3100 can include a wearable computing device (e.g., wearable computing device 1100), receiving biometric information. For example, the network reselection optimizer application 1130 may receive biometric information associated with a user of the wearable computing device 1100 from the one or more biometric sensors 1184. For example, the biometric information may include heart rate information, oxygen saturation levels, body temperature, heart rate variability information, physical activity information (e.g., steps taken, distance traveled, etc.).

[0088] The biometric infonnation may indicate whether a user is sleeping. For example, the sleep determiner 1136 may be configured to determine whether a user is sleeping according to known methods (e.g., using one or more sleep algorithms). For example, the sleep determiner 1136 may consider body movement information (e.g., accelerometer information, gyroscope information, etc.), heart rate information, light information (e.g., ambient light information), sound information, an operating mode of the wearable computing device 1100 (e.g., bedtime mode 1192), etc., to determine whether the user asleep. For example, the sleep determiner 1136 may receive information relating to whether a user is asleep via the one or more motion sensors 1182, the one more biometric sensors 1184, the one or more location sensors 1186, the operating mode selector 1190, etc.

[0089] At operation 3120, the method 3100 can include the wearable computing device (e.g., wearable computing device 1100), receiving status information indicating a state of the wearable computing device. For example, the network reselection optimizer application 1130 may receive status information indicating a state of the wearable computing device1100.

[0090] For example, the status information may indicate movement information about the wearable computing device 1100 (e.g., about whether the wearable computing device 1100 is below a threshold movement level (e.g., is stationary), is in motion, being transported in a vehicle, etc.) The movement information about the wearable computing device 1 100 may be determined by the motion determiner 1132, for example.

[0091] For example, the status information may indicate location information about the wearable computing device 1100 (e.g., whether the wearable computing device 1100 is in a particular room, a particular building, etc.). The location of the wearable computing device 1100 may be determined by the location determiner 1134, for example.

[0092] For example, the status information may indicate an operating mode of the wearable computing device 1100 (e.g., in the bedtime mode 1192, exercise mode 1194, power savings mode 1196, etc.). The operating mode of the wearable computing device 1100 may be determined based on a selection of an operating mode via the operating mode selector 1190, for example.

[0093] For example, the motion determiner 1132 may be configured to determine whether the wearable computing device 1100 is below a threshold movement level (e.g., is stationary) or moving (above the threshold movement level). The motion determiner 1132 may determine movement information about the wearable computing device 1100 based on information from the one or more motion sensors 1182, the one or more location sensors 1186, etc. For example, the motion determiner 1132 may be configured to determine whether the wearable computing device 1100 is moving at a rate greater than a threshold level. For example, the motion determiner 1132 may be configured to determine whether the wearable computing device 1100 is moving for a duration of time greater than a first movement threshold level. In some implementations, when the wearable computing device 1100 is moving at the rate greater than the first movement threshold level, the motion determiner 1132 may be configured to determine the wearable computing device 1100 is moving in a vehicle. In some implementations, when the wearable computing device 1100 is moving for the duration of time greater than a second movement threshold level, the motion determiner 1132 may be configured to determine movement of the wearable computing device 1100 is not temporary or is not inadvertent or is intentional. In some implementations, when the wearable computing device 1100 is moving for the duration of time less than the secondmovement threshold level, the motion determiner 1132 may be configured to determine movement of the wearable computing device 1100 is temporary, is inadvertent, or is unintentional.

[0094] For example, the location determiner 1134 may be configured to determine a location of the wearable computing device 1 100. For example, the location determiner 1 134 may be configured to determine the location of the wearable computing device 1100 based on information from the one or more motion sensors 1182, the one or more location sensors 1186, etc. For example, the location determiner 1134 may be configured to determine whether the wearable computing device 1100 is located in a particular room of a building, a particular location (e.g., a house, an office, etc.), etc. For example, the location of the wearable computing device 1100 may be used to determine an optimized network reselection setting as described herein.

[0095] At operation 3130, the method 3100 can include the wearable computing device (e.g., wearable computing device 1100), determining whether a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected is less than a network signal strength threshold value. For example, the optimized network reselection setting determiner 1139 may be configured to determine whether a signal strength associated with a connection between the wearable computing device 1100 and a network (e.g., network 1200) to which the wearable computing device 1100 is connected is less than a network signal strength threshold value.

[0096] For example, the optimized network reselection setting determiner 1139 can be configured to determine a signal strength associated with the wearable computing device 1100. In some implementations, the optimized network reselection setting determiner 1139 may be configured to measure or calculate a Received Signal Strength Indicator (RS SI) value as the signal strength. In some implementations, the optimized network reselection setting determiner 1139 may be configured to measure or calculate a reference signal received power (RSRP) value as the signal strength. In some implementations, the optimized network reselection setting determiner 1139 may be configured to determine the RSSI or RSRP value based on a difference between a signal transmission power and losses (e.g., path loss) which occur during propagation of the signal. In some implementations, optimized network reselection setting determiner 1139 may be configured to measure or calculate a signal -to- noise ratio (SNR) as the signal strength. For example, the SNR value corresponds to a measure of the ratio between the received signal power and the background noise power.

[0097] At operation 3140, the method 3100 can include the wearable computing device (e.g., wearable computing device 1100), maintaining the same (current) network connection when the signal strength is greater than (not less than) the network signal strength threshold value. For example, the optimized network reselection setting determiner 1139 can be configured to maintain the current (same) network connection when the signal strength associated with the connection between the wearable computing device 1100 and the network 1200 to which the wearable computing device 1100 is connected is not less than the network signal strength threshold value. The network signal strength threshold value may correspond to a value at which the wearable computing device 1100 experiences a connection with poor quality, poor data performance, etc. For example, a RSRP network signal strength threshold value may be -90 dBm, -SOdBm, etc. For example, a RSRQ network signal strength threshold value may be -15 dB, -10 dB, etc.

[0098] At operation 3150, the method 3100 can include the w earable computing device (e.g., wearable computing device 1100), implementing an optimized network reselection setting determined based on various information including biometric information indicating whether the user is asleep and status information indicating the state of the wearable computing device, to perform a network reselection operation, when the signal strength is less than the network signal strength threshold value. For example, the signal strength may be less than the network signal strength threshold value when the wearable computing device 1100 is obstructed by an object (e.g., the wearable computing device 1100 is hidden under a blanket, blocked by a body part, etc.).

[0099] The optimized network reselection setting determiner 1139 can be configured to implement an optimized network reselection setting determined based on biometric information indicating whether the user is asleep and status information indicating the state of the wearable computing device 1100, to perform a network reselection operation. The one or more machine-learned models 1138 can be trained to output an optimized network reselection setting which is determined based on various inputs including biometric information indicating whether the user is asleep and status information indicating the state of the wearable computing device 1100.

[0100] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include a time associated with triggering the network reselection operation. For example, the optimized netw ork reselection setting determiner 1139 can be configured to, when thebiometric information indicates the user is asleep and the status information indicates the wearable computing device 1100 is below a threshold movement level (e.g., is stationary) , change the time associated with triggering the network reselection operation. For example, the optimized network reselection setting determiner 1139 can be configured to increase a period of time for triggering the network reselection operation subsequent to the signal strength being less than the network signal strength threshold value (e.g., increasing the time from 1 second to 30 seconds, 1 minute, 1 hour, etc.). For example, the optimized network reselection setting determiner 1139 can be configured to, when the biometric information indicates the user is awake or the status information indicates movement of the wearable computing device 1100 exceeds the threshold movement level, maintain the time associated with triggering the network reselection operation.

[0101] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include an optimal wireless network platform among a plurality of wireless network platforms. For example, the plurality of wireless network platforms can include a Wi-Fi wireless netw ork platform, a Long-Term Evolution wireless network platform, and the like. For example, the optimized netw ork reselection setting determiner 1139 can be configured to switch to the optimal wireless network platform to perform the network reselection operation, in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a netw ork signal strength threshold value.

[0102] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include an optimal frequency band among a plurality of frequency bands. For example, the optimized netw ork reselection setting determiner 1139 can be configured to switch to the optimal frequency band to perform the network reselection operation, in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a network signal strength threshold value.

[0103] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include an optimal network carrier among a plurality of network carriers. For example, the optimized network reselection setting determiner 1139 can be configured to switch to the optimalnetwork carrier to perform the network reselection operation, in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a network signal strength threshold value.

[0104] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include an optimal public land mobile network (PLMN) component among a plurality of PLMN components. PLMN refers to the cellular network infrastructure that provides mobile communication services to users. For example, a PLMN can encompass various components and technologies that enable computing devices to connect to the network, make calls, send text messages, use data services, etc. Example PLMN components may include mobile stations, base transceiver stations, base station controllers, etc. The PLMN can provide different generations of cellular technology (e.g., 2G, 3G, 4G (LTE), 5G, etc.). For example, the optimized network reselection setting determiner 1139 can be configured to utilize the optimal PLMN component to perform the network reselection operation, in response to a signal strength associated with a connection between the wearable computing device 1100 and a network to which the wearable computing device 1100 is connected being less than a network signal strength threshold value.

[0105] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine the optimized network reselection setting which can include a network signal strength threshold value. For example, the optimized network reselection setting determiner 1139 can be configured to set the network signal strength threshold value (e.g., as determined by the one or more machine-learned models 1138). For example, when the biometric information and status information indicates the user is asleep and the status information indicates the wearable computing device 1100 is less than a threshold movement level (e.g., is stationary or moving slowly or for a short period of time), the optimized network reselection setting determiner 1139 can be configured to increase a default signal strength threshold value to an optimized signal strength threshold value which is set as the network signal strength threshold value. For example, when the biometric information and status information indicates the user is awake or the status information indicates movement of the wearable computing device 1100 exceeds the threshold movement level, the optimized network reselection setting determiner 1139 can be configured to maintain the default signal strength threshold value as the network signal strength threshold value.

[0106] In some implementations, the optimized network reselection setting determiner 1139 can be configured to determine (and implement) a plurality of optimized network reselection settings which can include a combination of two or more optimized network reselection settings including a time associated with triggering the network reselection operation, an optimal wireless network platform, an optimal frequency band, an optimal network carrier, an optimal PLMN component, a network signal strength threshold value, and the like.

[0107] FIGS. 2A-2B are example tables depicting example optimized network reselection settings, according to one or more examples of the disclosure.

[0108] For example, in FIG. 2A the table 2100 includes example optimized network reselection settings including a first optimized network reselection setting 2120 (e.g., top three frequency bands) and a second optimized network reselection setting 2130 (e g., top three network carriers) for locations 2110 in a building (e g., a first room 2140 and a second room 2150). For example, the first optimized network reselection setting 2120 and the second optimized network reselection setting 2130 can correspond to outputs from the one or more machine-learned models 1138.

[0109] According to examples of the disclosure, the network reselection optimizer application 1130 may be configured to receive various inputs (e g., operation mode data including bedtime mode sensor data, motion data including body movement data, location data including a location of the wearable computing device 1100, biometric data associated with the user, etc.). The network reselection optimizer application 1130 can be configured to implement one or more machine-learned models 1138 to learn which particular frequency bands, network carriers, and the like are optimal given particular conditions. For example, the one or more machine-learned models 1138 can learn a particular frequency band or a network carrier which is optimal for the wearable computing device 1100 to switch to when a signal strength associated with the wearable computing device 1100 falls below a network signal strength threshold value given that a user is located in a particular room at a particular time and is asleep.

[0110] For example, the one or more machine-learned models 1138 may be trained to limit (bound) the search window of frequency bands / network carriers according to a location of the user. For example, in the same building (e.g., a house) different floors or rooms may have different frequency bands / network carriers. For example, a room on the top floor (e.g., first room 2140) may have different frequency bands / network carriers which are optimal (e.g.,which have a higher quality signal, a greatest signal strength, etc.) compared to a room on a bottom floor (e.g., second room 2150). The one or more machine-learned models 1138 may be trained to determine in advance the set of the frequency bands / network carriers in the building which are optimal for searching in a reselection process. This set may be much less than the entire set of frequency bands / network carriers the wearable computing device 1100 might otherwise search. Thus, computing resources including battery resources and processing resources may be conserved by not searching over all frequency bands and network carriers.

[0111] For example, if a user sleeps in the same bedroom at generally the same time of day, in some implementations the network reselection optimizer application 1130 may be configured to prioritize attempting to connect to a particular frequency band (or top frequency bands) which has (have) been identified by the one or more machine-learned models 1138 as most likely for the wearable computing device 1100 to successfully connect to, when the signal strength associated with the wearable computing device 1100 drops below a network signal strength threshold value. For example, in some implementations the network reselection optimizer application 1130 may be configured to instead delay the reselection process for a few seconds or a few minutes because the one or more machine- learned models 1138 has determined the user’s movement patterns and predicts that the original signal (and signal strength) will be restored shortly. For example, in some implementations (e.g., as shown in the example of FIG. 2B) the network reselection optimizer application 1130 may be configured to instead change the network signal strength threshold value (e.g., by increasing the threshold some amount such as 6 dB or 10 dBm) so that the reselection process does not begin until the signal quality is lower than in other circumstances where the reselection process would begin earlier in time.

[0112] For example, in FIG. 2B the table 2200 includes example optimized network reselection settings which correspond to adjusting a network signal strength threshold value 2230 based on status information 2210 (e.g., whether a movement of the wearable computing device 1100 is greater than a threshold level) and biometric information 2220 (e.g., whether a user is asleep). For example, in FIG. 2B the table 2100 indicates a signal strength threshold value may be adjusted (e.g., increased) when the movement information is less than a threshold level and the user is asleep. For example, if the user is asleep and the wearable computing device 1100 moves for a short time or slowly moves, the one or more machine- learned models 1138 may be trained to adjust (e.g., increase) the network signal strengththreshold value (which may be a default signal strength threshold value) to an optimized signal strength threshold value. For example, in FIG. 2B the table 2100 indicates a signal strength threshold value may be maintained when the movement information is more than a threshold level and the user is asleep or awake. For example, if the wearable computing device 1100 moves for a long time or moves quickly (e.g., as if being transported in a vehicle), the one or more machine-learned models 1138 may be trained to maintain the default signal strength threshold value as the network signal strength threshold value.

[0113] As described herein, the network reselection optimizer application 1130 can be configured to implement one or more machine-learned models 1138 which are trained to leam to increase a default signal strength threshold value to an optimized signal strength threshold value which is set as the network signal strength threshold value based on biometric information associated with the user and status information associated with the wearable computing device 1100. For example, the one or more machine-learned models 1138 can be trained to preemptively increase the default signal strength threshold value to the optimized signal strength threshold value, given certain conditions (e.g., that a user is located in a particular room at a particular time and is asleep and is not moving excessively, the wearable computing device 1100 is in the bedtime mode 1192, etc.). For example, the one or more machine-learned models can be trained to reactively increase the default signal strength threshold value to the optimized signal strength threshold value as the signal strength worsens and approaches or crosses a currently set network signal strength threshold value (e.g., the default signal strength threshold value), given certain conditions (e.g., that a user is located in a particular room at a particular time and is asleep and is not moving excessively).

[0114] For example, the one or more machine-learned models 1138 may be trained (e.g., based on using reinforcement learning) to leam the user’s movement pattern while the user is asleep. The one or more machine-learned models 1138 may be trained using a reward system that rewards a model which conserves power, maintains connectivity, establishes connectivity quickly, etc. On the other hand, the reward system may penalize a model which results in power being drained, has a lack of connectivity (unintentionally), takes too long to establish connectivity, etc. With a fingerprint of the user’s behavior, knowledge of a sleep or bedtime mode, knowledge of the user’s sleep pattern, movement patterns, use of specific operating modes like the bedtime mode 1192, exercise mode 1194, power savings mode 1196, current environment information, status information of the wearable computing device 1100, and thelike, the one or more machine-learned models 1138 may be configured to adjust or not adjust the network signal strength threshold value as indicated in FIG. 2B.

[0115] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a sleep or bedtime mode, knowledge of the user’s sleep patern, movement paterns, use of specific operating modes, current environment, status information of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized network reselection setting detenniner 1139 with an output that causes the network reselection optimizer application 1130 to atempt to connect to one or more particular frequency bands and / or network carriers if a signal strength drops below a network signal strength threshold value (e.g., QRXLEV-MIN).

[0116] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a sleep or bedtime mode, knowledge of the user’s sleep patern, movement paterns, use of specific operating modes, current environment, status infonnation of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized network reselection seting determiner 1139 with an output that causes the network reselection optimizer application 1130 to delay a time for attempting to reconnect to another network and allow the wearable computing device 1100 to be disconnected from the network (or experience poor signal quality) for a time greater than a default period of time.

[0117] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a sleep or bedtime mode, knowledge of the user’s sleep patern, movement paterns, use of specific operating modes, current environment, status information of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized network reselection seting determiner 1139 with an output that causes the network reselection optimizer application 1130 to blacklist certain frequency bands, in a given context, for a period of time greater than a default period of time so that the wearable computing device 1100 does not atempt to reconnect to certain frequency bands in that context (e.g., changing the blacklist period of time from 300 seconds to 24 hours, 1 week, etc.).

[0118] As mentioned above, aspects of the disclosure have been described in which an optimized network reselection seting is determined based on biometric information indicating whether a user is asleep and status information indicating a state of the wearablecomputing device. However, the disclosure is not limited to these embodiments. As another example, the optimized network reselection setting can be determined based on biometric information indicating a particular activity that is associated with the user (e.g., as indicated by the biometric information) and status information indicating a state of the wearable computing device. For example, the biometric information may indicate a user is associated with various activities including walking, swimming, kayaking, running, exercising in a gy m, driving, etc. The wearable computing device may be configured to, in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value, implement an optimized network reselection setting determined based on the biometric information indicating a particular activity that the user is engaged in (or associated with) and the status information indicating a state of the wearable computing device. For example, as described herein, a machine-learned model may be configured to learn that a particular environment or area (e.g., a region of water, a gym, a garage, park, etc.) has a particular set of network conditions (e g., frequency bands, network carriers, etc.) which are optimal under certain conditions (e.g., given biometric signals that a user is engaged in a particular activity which may reflect various patterns including movement patterns of the user), according to status information of the wearable computing device, according to a time of day, etc.

[0119] For example, the one or more machine-learned models 1138 may be trained (e.g., based on using reinforcement learning) to leam the user’s movement pattern while the user is engaging in a particular activity in various environments and to leam optimal network conditions (e.g., optimal frequency bands, optimal network carriers, etc.) based on the reinforcement learning given a biometric signal indicating an activity undertaken by the user and given state information about the wearable computing device 1100. The one or more machine-learned models 1138 may be trained using a reward system that rewards a model which conserves power, maintains connectivity, establishes connectivity quickly, etc. On the other hand, the rew ard system may penalize a model which results in power being drained, has a lack of connectivity (unintentionally), takes too long to establish connectivity , etc. With a fingerprint of the user’s behavior, knowledge of a particular activity or exercise mode, knowledge of the user’s activity pattern, movement patterns, use of specific operating modes like the exercise mode 1194, power savings mode 1196, and the like, the one or moremachine-learned models 1138 may be configured to adjust or not adjust the network signal strength threshold value.

[0120] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a particular activity or exercise mode, knowledge of the user’s activity pattern, movement patterns, use of specific operating modes like the exercise mode 1 194, power savings mode 1196, current environment, status information of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized network reselection setting determiner 1139 with an output that causes the network reselection optimizer application 1130 to attempt to connect to one or more particular frequency bands and / or network carriers if a signal strength drops below a network signal strength threshold value (e.g., QRXLEV-MIN).

[0121] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a particular activity or exercise mode, knowledge of the user’s activity pattern, movement patterns, use of specific operating modes like the exercise mode 1194, power savings mode 1196, current environment, status information of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized network reselection setting determiner 1139 with an output that causes the network reselection optimizer application 1130 to delay a time for attempting to reconnect to another network and allow the wearable computing device 1100 to be disconnected from the network (or experience poor signal quality) for a time greater than a default period of time.

[0122] In some implementations, based on the fingerprint of the user’s behavior, knowledge of a particular activity or exercise mode, knowledge of the user’s activity pattern, movement patterns, use of specific operating modes like the exercise mode 1194, power savings mode 1196, current environment, status information of the wearable computing device 1100, and the like, the one or more machine-learned models 1138 may be configured to provide the optimized netw ork reselection setting determiner 1139 with an output that causes the network reselection optimizer application 1130 to blacklist certain frequency bands, in a given context, for a period of time greater than a default period of time so that the wearable computing device 1100 does not attempt to reconnect to certain frequency bands in that context (e.g., changing the blacklist period of time from 300 seconds to 24 hours, 1 week, etc.).

[0123] As mentioned above, aspects of the disclosure have been described in view of thenetwork reselection optimizer application 1130 provided in the wearable computing device 1100 with respect to FIGS. IB through 3. However, some or all of those aspects can also be applied to the network reselection optimizer application 1330 provided in the server computing system 1300, and thus some or all of the functions and operations of the network reselection optimizer application 1130 may also be applied and carried out by the network reselection optimizer application 1330 in a similar fashion, but will not be described again for the sake of brevity. As one example, the network reselection optimizer application 1330 may be configured to determine whether a user is asleep or may determine a location of a user, and provide such information to the wearable computing device 1100. As another example, in some implementations the network reselection optimizer application 1330 may be configured to include one or more machine-learned models which are trained to learn optimal frequency bands and / or network carriers given various conditions (e.g., sleep patterns of a user, movement patterns of a user, etc.).

[0124] Aspects of the above-described example embodiments may be recorded in non- transitory computer-readable media including program instructions to implement various operations embodied by a computer. The media may also include, alone or in combination with the program instructions, data files, data structures, and the like. Examples of non- transitory computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD ROM disks, Blue-Ray disks, and DVDs; magneto-optical media such as optical discs; and other hardware devices that are specially configured to store and perform program instructions, such as semiconductor memory, readonly memory (ROM), random access memory (RAM), flash memory, USB memory, and the like. Examples of program instructions include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter. The program instructions may be executed by one or more processors. The described hardware devices may be configured to act as one or more software modules in order to perform the operations of the above-described embodiments, or vice versa. In addition, a non-transitory computer-readable storage medium may be distributed among computer systems connected through a network and computer-readable codes or program instructions may be stored and executed in a decentralized manner. In addition, the non- transitory computer-readable storage media may also be embodied in at least one application specific integrated circuit (ASIC) or Field Programmable Gate Array (FPGA).

[0125] Each block of the flowchart illustrations may represent a unit, module, segment, orportion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks may occur out of order. For example, two blocks shown in succession may in fact be executed substantially concurrently (simultaneously) or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

[0126] While the disclosure has been described with respect to various example embodiments, each example is provided by way of explanation, not limitation of the disclosure. Those skilled in the art, upon attaining an understanding of the foregoing, can readily produce alterations to, variations of, and equivalents to such embodiments. Accordingly, the disclosure does not preclude inclusion of such modifications, variations and / or additions to the disclosed subject matter as would be readily apparent to one of ordinary skill in the art. For example, features illustrated or described as part of one embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the disclosure covers such alterations, variations, and equivalents.

Claims

WHAT IS CLAIMED IS:

1. A wearable computing device, comprising: at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to: receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a netw ork signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

2. The wearable computing device of claim 1, the at least one processor being further configured to: when the biometric information indicates the user is asleep and the status information indicates movement of the wearable computing device is less than a threshold movement level, increase a default signal strength threshold value to an optimized signal strength threshold value which is set as the network signal strength threshold value, and when the biometric information indicates the user is awake or the status information indicates movement of the wearable computing device exceeds the threshold movement level, maintain the default signal strength threshold value as the network signal strength threshold value.

3. The wearable computing device of claim 1, the optimized network reselection setting including a time associated with triggering the network reselection operation and the at least one processor being further configured to: when the biometric information indicates the user is asleep and the status information indicates movement of the wearable computing device is less than a threshold movement level, change the time associated with triggering the network reselection operation, andwhen the biometric information indicates the user is awake or the status information indicates movement of the wearable computing device exceeds the threshold movement level, maintain the time associated with triggering the network reselection operation.

4. The wearable computing device of claim 3, the at least one processor being further configured to change the time associated with triggering the network reselection operation by increasing a period of time for triggering the network reselection operation subsequent to the signal strength being less than the network signal strength threshold value.

5. The wearable computing device of claim 3, the network reselection operation includes switching the wearable computing device between a Wi-Fi network and a Long- Term Evolution network.

6. The wearable computing device of claim 1, the at least one processor being further configured to implement a machine-learned model trained to determine the optimized network reselection setting based on the biometnc information indicating whether the user is asleep and the status information.

7. The wearable computing device of claim 6, the optimized network reselection setting including an optimal frequency band among a plurality of frequency bands, and the at least one processor being further configured to switch to the optimal frequency band to perform the network reselection operation.

8. The wearable computing device of claim 6, the optimized network reselection setting including an optimal network carrier among a plurality of network carriers, and the at least one processor being further configured to switch to the optimal network carrier to perform the network reselection operation.

9. The wearable computing device of claim 6, the optimized network reselection setting including the network signal strength threshold value, and the at least one processor being further configured to perform the network reselection operation based on the network signal strength threshold value determined by the machine-learned model.

10. The wearable computing device of claim 6, the optimized network reselection setting including an optimal wireless network platform among a plurality of wireless network platforms, and the at least one processor being further configured to switch to the optimal wireless network platform to perform the network reselection operation.

11. The wearable computing device of claim 10, the plurality of wireless network platforms including a Wi-Fi wireless network platform and a Long-Term Evolution wireless network platform.

12. The wearable computing device of claim 1, the status information including at least one of movement information associated with the wearable computing device, location information associated with the wearable computing device, or an operating mode of the wearable computing device.

13. The wearable computing device of claim 12, the movement information including movement information which indicates whether movement of the wearable computing device is less than a threshold movement level, the location information including location information which indicates a particular room in a building in which the wearable computing device is located, and the operating mode of the wearable computing device including an operating mode associated with the user being asleep.

14. The wearable computing device of claim 1, the at least one processor being further configured to: implement a machine-learned model, trained based on reinforcement learning and observations of network conditions associated with the wearable computing device in a particular environment, to determine the optimized network reselection setting based on the biometric information indicating whether the user is asleep and a current environment of wearable computing device as indicated by the status information.

15. A wearable computing device, comprising: at least one memory configured to store instructions; and at least one processor configured to execute the instructions stored in the at least one memory to:receive biometric information relating to a user wearing the wearable computing device indicating whether the user is asleep, receive status information indicating a state of the wearable computing device, implement a machine-learned model trained to output an optimized network reselection setting based on the biometric information and the status information, and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, perform a network reselection operation according to the optimized network reselection setting output by the machine-learned model.

16. The wearable computing device of claim 15, the optimized network reselection setting including an optimal frequency band among a plurality of frequency bands, and the at least one processor being further configured to switch to the optimal frequency band to perform the network reselection operation.

17. The wearable computing device of claim 15, the optimized network reselection setting including an optimal public land mobile network (PLMN) component among a plurality of PLMN components, and the at least one processor being further configured to utilize the optimal PLMN component to perform the network reselection operation.

18. The wearable computing device of claim 15, the optimized network reselection setting including the network signal strength threshold value, and the at least one processor being further configured to perform the network reselection operation based on the network signal strength threshold value output by the machine-learned model.

19. The wearable computing device of claim 15, the optimized network reselection setting including a time associated with triggering the network reselection operation and the at least one processor being further configured to perform the network reselection operation based on the time output by the machine-learned model.

20. The wearable computing device of claim 15, the optimized network reselection setting including an optimal wireless network platform among a plurality ofwireless network platforms, and the at least one processor being further configured to switch to the optimal wireless network platform to perform the network reselection operation.

21. A non-transitory computer-readable medium storing instructions that are executable by at least one processor of a wearable computing device, the instructions comprising instructions to cause the at least one processor to: receive biometric information relating to a user wearing the wearable computing device indicating whether a user is asleep; receive status information indicating a state of the wearable computing device; and in response to a signal strength associated with a connection between the wearable computing device and a network to which the wearable computing device is connected being less than a network signal strength threshold value used to trigger reselection, implement an optimized network reselection setting determined based on the biometric information indicating whether the user is asleep and the status information, to perform a network reselection operation.

Images