Tokenized representations of sensor data of a wearable computing device

Abstract

A method for controlling a wearable computing device includes receiving, via a controller, sensor data from one or more sensors of the wearable computing device. The method also includes generating, via a machine-learned tokenization model programmed in the controller on the wearable computing device, tokenized sensor data based on the sensor data. The tokenized sensor data includes the sensor data compressed into a compressed bitstream. Further, the method includes transmitting, via the controller on the wearable computing device, the tokenized sensor data to a remote computing device.

Description

Technical Field

[0001] This disclosure generally relates to wearable computing devices, and more specifically, to lexicalizing sensor data from wearable computing devices in order to facilitate the offloading of sensor data from the wearable computing device. Background Technology

[0002] Advances in sensor and wearable technologies have made it increasingly possible for individuals to collect data about themselves. Furthermore, artificial intelligence systems are increasingly including large, foundational machine learning models capable of providing health assessments and / or recommendations to users based on collected sensor data. However, wearable technologies may lack the computational resources available for storing and / or implementing each of the diverse AI systems used to perform specific health assessments and / or recommendations. Summary of the Invention

[0003] Aspects and advantages of embodiments of this disclosure will be set forth in part in the description which follows, or may be learned from the description or by practice of the embodiments.

[0004] In one aspect, this disclosure relates to a method for controlling a wearable computing device. The method includes receiving sensor data from one or more sensors of the wearable computing device via a controller. The method also includes generating lexicalized sensor data based on the sensor data via a machine learning lexicalization model programmed in the controller on the wearable computing device. The lexicalized sensor data includes sensor data compressed into a compressed bitstream. Furthermore, the method includes transmitting the lexicalized sensor data to a remote computing device via the controller on the wearable computing device.

[0005] In another aspect, this disclosure relates to a wearable computing device. The wearable computing device includes a controller that includes at least one processor. The at least one processor is configured to perform a plurality of operations. The plurality of operations include receiving sensor data from one or more sensors of the wearable computing device. The plurality of operations also include generating lexicalized sensor data based on the sensor data via a machine learning lexicalization model programmed in the controller. The lexicalized sensor data includes sensor data compressed into a compressed bitstream. Furthermore, the plurality of operations include transmitting the lexicalized sensor data to a remote computing device.

[0006] Other exemplary aspects of this disclosure relate to other systems, methods, apparatuses, tangible non-transitory computer-readable media, and devices for performing the functions described herein. These and other features, aspects, and advantages of the various implementations will be better understood with reference to the following description and the appended claims. The accompanying drawings, which are incorporated in and form a part of this specification, illustrate implementations of this disclosure and, together with the description, help to explain the relevant principles. Attached Figure Description

[0007] Referring to the accompanying drawings, this specification sets forth a complete and feasible disclosure of the invention, including its preferred mode, for those skilled in the art, in which:

[0008] Figure 1 A perspective view of an embodiment of a wearable computing device according to the present disclosure is shown;

[0009] Figure 2 It shows Figure 1 A schematic diagram of the computing elements of a wearable computing device;

[0010] Figure 3 A schematic diagram of an embodiment of a computing environment according to the present disclosure is shown;

[0011] Figure 4 A block diagram of an embodiment of a server system for a wearable computing device according to the present disclosure is shown;

[0012] Figures 5A to 5B A block diagram illustrating an embodiment of a lexicalization module for a wearable computing device according to the present disclosure is shown; and

[0013] Figure 6 A flowchart is shown of an embodiment of a method for unloading lexicalized sensor data from a wearable computing device according to the present disclosure.

[0014] The repeated reference numerals across multiple figures are intended to identify the same features in various implementations. Detailed Implementation

[0015] Reference will now be made in detail to embodiments, one or more examples of which are illustrated in the accompanying drawings. Each example is provided to illustrate embodiments and not to limit the scope of this disclosure. In fact, it will be apparent to those skilled in the art that various modifications and changes can be made to the embodiments without departing from the scope or spirit of this disclosure. For example, features shown or described as part of one embodiment may be used in conjunction with another embodiment to produce yet another embodiment. Therefore, aspects of this disclosure are intended to cover such modifications and changes.

[0016] Overview

[0017] The repeated use of reference numerals and / or numbers in this specification and / or accompanying drawings is intended to indicate the same or similar features, elements, or operations of this disclosure. For the sake of brevity, repeated descriptions of reference numerals and / or numbers in this specification have been omitted.

[0018] As cited herein, the terms “includes” and “including” are intended to be inclusive in a manner similar to the term “comprising.” As cited herein, the terms “or” and “and / or” are generally intended to be inclusive, meaning that “A or B” or “A and / or B” are each intended to mean “A or B or both.” As cited herein, the terms “first,” “second,” “third,” etc., are used interchangeably to distinguish one component or entity from another and are not intended to indicate the location, functionality, or importance of individual components or entities. As cited herein, the terms “couple,” “couples,” “coupled,” and / or “coupling” refer to chemical coupling (e.g., chemical bonding), communication coupling, electrical and / or electromagnetic coupling (e.g., capacitive coupling, inductive coupling, direct and / or connection coupling, etc.), mechanical coupling, operative coupling, optical coupling, and / or physical coupling.

[0019] As referenced herein, the term "system" can refer to hardware (e.g., dedicated hardware), computer logic executing on a general-purpose processor (e.g., a central processing unit (CPU)), and / or some combination thereof. In some embodiments, the "system" described herein may be implemented in hardware, dedicated circuitry, firmware, and / or software that controls a general-purpose processor. In some embodiments, the "system" described herein may be implemented as a program code file stored on a storage device, loaded into memory, and executed by a processor, and / or provided as a computer program product from, for example, computer-executable instructions stored in a tangible computer-readable storage medium (e.g., random access memory (RAM), hard disk, optical media, magnetic media).

[0020] As mentioned, advancements in sensor and wearable technologies have made it increasingly possible for individuals to collect data about themselves. However, gaining self-knowledge can be more challenging than simple data collection. For example, individuals may expect knowledge about health assessments and / or recommendations that can be derived from the collected sensor data. Consequently, increasingly, artificial intelligence systems that include large-scale underlying machine learning models capable of providing individuals with the desired knowledge based on the collected sensor data are being implemented. However, wearable technologies may lack the computational resources available to store and / or implement each of the disparate AI models used to perform specific health assessments and / or recommendations.

[0021] Driven by the need to implement various artificial intelligence models to provide individuals with corresponding health assessments and / or recommendations, this disclosure relates to a wearable computing device configured to lexicalize sensor data from the wearable computing device to facilitate the offloading of sensor data from the wearable computing device. Therefore, in embodiments, the wearable computing device is configured to provide lexicalized sensor data to a remote computing device for processing by at least one machine learning model. In embodiments, the wearable computing device may generate lexicalized sensor data, such as sensor data lexes or lexical embeddings, in at least one embedding space of at least one machine learning model. The lexicalized sensor data can be processed by the machine learning model to provide a user with health assessments and / or recommendations. By implementing the machine learning model in a computing device with more computing resources than the wearable computing device, offloading the lexicalized sensor data from the wearable computing device to a remote computing device for processing can improve the accuracy of the output from the machine learning model.

[0022] Furthermore, lexicalization of sensor data can provide relatively high fidelity, which can further improve the accuracy of the output from machine learning models. In addition, lexicalization of sensor data can help ensure the protection of user-related collected data.

[0023] Furthermore, privacy-related controls can be provided to users, allowing them to choose whether and when the systems, programs, or features described herein can enable the collection of health-related data and / or user information (e.g., information about a user's social networks, social actions, or activities, occupation, user preferences, or current location) and whether content or communications that may be sensitive or privacy-related are sent to the user from the server. Additionally, certain data can be processed in one or more ways before storage or use, such that personally identifiable information is removed. For example, a user's identity can be processed so that personally identifiable information cannot be determined, or the user's geographic location information obtained therein can be generalized (e.g., down to the city, zip code, or state level), making it impossible to determine the user's specific location. Therefore, users can control what information about themselves is collected, how that information is used, and what information is provided to them. To this end, any user-related information collected as described herein (e.g., personal medical data, health status, etc.) can remain private and confidential and not be improperly used or published.

[0024] Furthermore, one or more security measures can be implemented to ensure the protection of users' demographic and / or physiological data. For example, password or fingerprint authentication can be used to control access to users' demographic and physiological or other personal data. Moreover, such user data can be stored in a privacy-enhancing manner and not shared without the user's explicit consent. For example, such data can be encrypted to protect it from unauthorized access.

[0025] The exemplary aspects of this disclosure provide several technical effects, benefits, and / or improvements of computing techniques.

[0026] Example devices and systems

[0027] Now refer to the attached diagram, Figure 1 A perspective view of an example wearable computing device 100 according to one or more example embodiments of the present disclosure is shown. In the example embodiments, the wearable computing device 100 may include, for example, a wearable physiological monitoring device that can be worn by a user 10 and / or capture one or more types of physiological data of the user (e.g., HR data, motion data (e.g., accelerometer data), body temperature data, respiratory rate data, blood pressure data, blood oxygen level data, electrical skin activity (EDA) data, stress-related data).

[0028] Furthermore, in embodiments, the wearable computing device 100 may include a display 102, an attachment component 104, a fixing component 106, and a button 108 that may be located on one side of the wearable computing device 100. In embodiments, both sides of the display 102 may be (e.g., mechanically, operatively) coupled to the attachment component 104. In some embodiments, the fixing component 106 may be located on, (e.g., mechanically, operatively) coupled to, and / or integrated with the attachment component 104. In these or other embodiments, the fixing component 106 may be positioned opposite the display 102 at the opposite end of the attachment component 104. In some embodiments, the button 108 may be located on one side of the wearable computing device 100, below the display 102.

[0029] Furthermore, display 102 may include any type of electronic display or screen known in the art. For example, in some embodiments, display 102 may include a liquid crystal display (LCD) or an organic light-emitting diode (OLED) display, such as, for example, a transmissive LCD or a transmissive OLED display. Further, display 102 may be configured to provide brightness, contrast, and / or color saturation characteristics according to display settings that may be maintained by the control circuitry and / or other internal components and / or circuitry of the wearable computing device 100. In some embodiments, display 102 may include a touchscreen, such as, for example, a capacitive touchscreen. For example, in these embodiments, display 102 may include a surface capacitive touchscreen or a projected capacitive touchscreen, which may be configured to respond to contact with a charge-retaining member or tool, such as a human finger. While wearable computing device 100 is shown having display 102 in exemplary embodiments of this disclosure, it should be understood that in some embodiments, wearable computing device 100 may not have any type of display unit.

[0030] In some embodiments, the display 102 may be configured to provide (e.g., render) various information, such as time, date, physiological data of a user wearing the wearable computing device 100, readings based on user input, and / or other information. In embodiments, physiological data may include, but is not limited to, HR data (e.g., heart rate per minute), motion data (e.g., movement data, accelerometer data), blood pressure data, body temperature data, respiratory rate data, blood oxygen level data, EDA data, stress-related data, and / or any other physiological data that a person skilled in the art would understand can be measured by the wearable computing device 100. In some embodiments, readings based on user input may include, but are not limited to, activities performed by the user, the user's sleep schedule, and / or any other metrics that a person skilled in the art would understand can be input into the wearable computing device 100 by the user.

[0031] The attachment component 104 can be used to attach (e.g., attach, fasten) the wearable computing device 100 to its user (e.g., to the body or clothing of user 10). In some embodiments, the attachment component 104 may take the form of, for example, a strap, elastic band, cord, and / or any other attachment form that a person skilled in the art will understand can be used to attach the wearable computing device 100 to a user. For example, the wearable computing device 100 may be configured as a bracelet, watch, ring, electrode, finger clip, toe clip, chest strap, ankle strap, and / or a device for placement in a pocket. In additional or alternative embodiments, the wearable computing device 100 may be embedded in something that comes into contact with user 10, such as, for example, clothing, a cushion, blanket, pillow, and / or another accessory that may be positioned under user 10.

[0032] The securing component 106 facilitates attachment of the attachment component 104 to a user of the wearable computing device 100. In some embodiments, the securing component 106 may include, but is not limited to, pin and hole locking mechanisms (e.g., buckles), magnetic systems, locks, clips, and / or any other type of fastener that a person skilled in the art will understand can be used to facilitate attachment of the wearable computing device 100 to a user. In embodiments, the wearable computing device 100 does not include the securing component 106. For example, in an embodiment, the wearable computing device 100 may be secured to the user with a strap that can be attached to the user's wrist and / or another suitable appendage.

[0033] Button 108 allows a user to interact with the wearable computing device 100 and / or allows a user to provide a form of input to the wearable computing device 100. For example, as described above, in an example embodiment, the wearable computing device 100 may include a screen, such as a touchscreen, which can receive input via (e.g., by means of) a user's touch. In additional or alternative embodiments, the wearable computing device 100 may include a microphone that can receive input via (e.g., by means of) a user's voice commands.

[0034] Now for reference Figure 2 This illustrates a block diagram of a wearable computing device 100 according to one or more exemplary embodiments of the present disclosure. That is, for example, Figure 2 A block diagram of one or more internal and / or external components of a wearable computing device 100 according to one or more exemplary embodiments of the present disclosure is shown.

[0035] Although certain embodiments are disclosed herein in the context of wearable physiological monitoring devices, it should be understood that this disclosure is not limited thereto. For example, it should be understood that any suitable type of computing device or computing device (such as, for example, client computing devices, laptops, tablets, servers (e.g., described below and...)) can be used. Figure 4 The combination of the server system 312 described herein, wearable computing device 100, mobile computing device 304 such as a smartphone, and / or another computing device, whether or not wearable, is used to perform and / or implement the physiological monitoring principles and features disclosed herein.

[0036] like Figure 2 As shown, the wearable computing device 100 can be worn by user 10 and / or can be configured to collect data about activities performed by user 10 and / or the physiological state of user 10. In some embodiments, the data may include motion data about the user's movement and / or physiological data obtained by measuring various physiological characteristics of user 10 (e.g., heart rate, respiratory data, body temperature, blood oxygen level, perspiration level, movement data).

[0037] Furthermore, as shown, the wearable computing device 100 may include a control circuitry system 110. Although in Figure 2 While certain modules and / or components are shown as part of the control circuitry system 110 in the figures, it should be understood that the control circuitry system 110 associated with the wearable computing device 100 and / or other components or devices according to exemplary embodiments of this disclosure may include additional components and / or circuitry systems, such as, for example Figure 2 One or more additional components of the components shown in the diagram. Furthermore, in some embodiments, one or more of the components shown in the control circuitry system 110 may be omitted and / or differ from those in the diagram. Figure 2 The components shown and described in association with it.

[0038] The term "control circuit system" is used herein in its broad and / or general sense and may include any combination of software and / or hardware elements, devices, and / or features that can be implemented in relation to the operation of the wearable computing device 100. Furthermore, in certain contexts herein, the term "control circuit system" may be used substantially interchangeably with one or more of the terms "controller," "integrated circuit," "IC," "application-specific integrated circuit," "ASIC," "controller chip," etc.

[0039] The control circuitry system 110 may include one or more processors 181, one or more memory devices 183, and / or electrical connections. In embodiments, the control circuitry system 110 may be implemented on a system-on-a-chip (SoC); however, those skilled in the art will recognize that other hardware and / or firmware implementations are possible.

[0040] In one or more embodiments, processor 181 may be configured to execute computer-readable instructions that, when executed, cause wearable computing device 100 to perform one or more operations. In at least one embodiment, processor 181 may be configured to execute operational code (e.g., instructions, processing threads, software) of wearable computing device 100, such as firmware. Figure 2 In the example embodiments depicted herein, processor 181 may each be a central processing unit (CPU), a microprocessor, a microcontroller, an integrated circuit (e.g., an application-specific integrated circuit (ASIC)), and / or another type of processing device. In this example embodiment or another example embodiment, processor 181 may be (e.g., electrically, communicatively, physically, operatively) coupled to one or more components of control circuitry system 110 and / or wearable computing device 100, such that processor 181 may facilitate one or more operations according to the embodiments described herein.

[0041] In an embodiment, such as Figure 2 As shown, computer-readable instructions and / or operation codes executable by processor 181 may be stored in one or more data storage devices of wearable computing device 100, such as memory device 183 of wearable computing device 100. In some embodiments, memory device 183 may be (e.g., electrically, communicatively, physically, operatively) coupled to control circuitry system 110 and / or one or more components of wearable computing device 100, such that memory device 183 may facilitate one or more operations according to the embodiments described herein.

[0042] Memory device 183 may store computer-readable and / or computer-executable entities (e.g., data, information, applications, models, algorithms) that can be created, modified, accessed, read, retrieved, and / or executed by each processor in processor 181. In some embodiments, memory device 183 may be configured, included, (e.g., operatively) coupled to a computing system and / or a medium, such as, for example, one or more computer-readable media, volatile memory, non-volatile memory, random access memory (RAM), read-only memory (ROM), hard disk drive, flash drive, and / or other memory devices, and / or otherwise associated with said computing system and / or medium. In these or other embodiments, such one or more computer-readable media may include, be configured, (e.g., operatively) coupled to one or more non-transitory computer-readable media, and / or otherwise associated with one or more non-transitory computer-readable media.

[0043] Still referencing Figure 2 The control circuit system 110 may include a lexicalization module 111, a physiological indicator module 141, and / or other modules and / or data that may be used to facilitate one or more operations described herein. The lexicalization module 111 may include one or more hardware and / or software components and / or features that can be configured to lexicalize sensor data, as further described below.

[0044] The wearable computing device 100 may further include one or more sensors 143 communicatively coupled to the lexicalization module 111 and / or the physiological indicators module 141. In embodiments, the sensor 143 may include an inertial measurement unit (IMU) comprising one or more accelerometers and / or one or more gyroscopes. The accelerometer may be used to capture motion information about the wearable computing device 100. The gyroscope may also be used, additionally or alternatively, to capture motion information about the wearable computing device 100. For example, the IMU may be configured as a six-axis or six-dimensional inertial measurement unit (e.g., a three-axis accelerometer and a three-axis gyroscope). When the wearable computing device 100 is worn or carried by a user, the motion information obtained via the IMU may be associated with the user. The IMU may further include one or more magnetometers, one or more barometers, and / or any other suitable sensors.

[0045] In additional or alternative embodiments, sensor 143 may include a physiological sensor that, according to various embodiments disclosed herein, can be configured to collect physiological data from a user. For example, the physiological sensor may include a heart rate sensor, a photoplethysmography (PPG) sensor, and / or other physiological sensors. In some embodiments, the physiological sensor may be disposed on, coupled to, embedded in, and / or integrated into the wearable computing device 100, and / or otherwise associated with the wearable computing device 100 such that, when the wearable computing device 100 is worn by a user, the physiological sensor may be in contact with or substantially in contact with human skin. For example, in embodiments, the physiological sensor may be disposed inside or on the skin side of the wearable computing device 100 (e.g., the side of the wearable computing device 100 that contacts, touches, and / or faces the user's skin), coupled to the inside or skin side of the wearable computing device 100, and / or otherwise associated with that inside or skin side. In additional and / or alternative embodiments, the wearable computing device 100 may be configured to receive physiological data of a user from one or more physiological sensors external to the wearable computing device 100 (e.g., not embedded and / or integrated in the wearable computing device).

[0046] In an embodiment, as mentioned, the physiological indicator module 141 may be communicatively coupled to the sensor 143, such that the physiological indicator module 141 can receive data collected by the sensor 143 from the user 10. The physiological indicator module 141 may calculate physiological indicators based on the user 10's data (e.g., calculated according to known physiological indicators), including but not limited to the user 10's cardiac, respiratory, neurological, musculoskeletal, and other physiological indicators. For example, the physiological indicator module 141 may include a machine learning model trained to receive sensor data as input and generate physiological indicators and / or evaluations as output. In additional or alternative embodiments, the wearable computing device 100 may be configured to communicate with another computing device or server that can analyze and / or interpret the collected sensor data (e.g., calculated according to known physiological indicators), as further described below.

[0047] exist Figure 2 In the example embodiments depicted, the wearable computing device 100 may include one or more data storage components 151 communicatively coupled to the control circuitry system 110. Figure 2(Represented as "Data Storage 151" in the original text). Data storage component 151 may include any suitable or desired type of data storage, such as, for example, solid-state memory, which may be volatile or non-volatile. In some embodiments, such solid-state memory of the wearable computing device 100 may include any of a variety of technologies, such as, for example, flash memory integrated circuits, phase-change (PC) memory, phase-change (PC) random access memory (RAM), programmable metallized cell RAM (PMC-RAM or PMCm), bidirectional unified memory (OUM), resistive RAM (RRAM), NAND memory, NOR memory, EEPROM, ferroelectric memory (FeRAM), MRAM, or other discrete NVM (non-volatile solid-state memory) chips. In some embodiments, data storage component 151 may be used to store system data, such as operating system data and / or system configuration or parameters. In some embodiments, wearable computing device 100 may include data storage used as buffer and / or cache memory for operation by control circuitry system 110.

[0048] Data storage component 151 may include various sub-modules that can be implemented to facilitate the physiological monitoring and cardiac assessment principles and features disclosed herein. For example, in at least one embodiment, data storage component 151 may include one or more sub-modules, which may include, but are not limited to: an information collection module (e.g., a physiological indicators module 141) that manages the collection of physiological data, demographic data, and / or anthropometric data; a heart rate determination module that determines the value and / or pattern of one or more types of heart rate of user 10; a lexicalization module 111; a sleep detection module that detects sleep attempts or initiations made by user 10; a presentation module that manages the presentation of information that can be associated with cardiac assessment to user 10; a feedback management module that collects and interprets any input data and / or feedback received from user 10; and / or another sub-module.

[0049] The wearable computing device 100 may further include a power storage module 153 (in Figure 2 The power storage module (referred to as "power storage 153") may include a rechargeable battery, one or more capacitors, or other charge retention devices. In some embodiments, the control circuitry 110 may utilize the power stored by the power storage module 153 for operation of the wearable computing device 100, such as for powering the display 102. In some embodiments, the power storage module 153 may be accessible via the host interface of the wearable computing device 100 (e.g., via one or more host interface circuitry systems and / or component 176). Figure 2It is referred to as “Host Interface 176” and / or receives power through other means.

[0050] The wearable computing device 100 may further include one or more connectivity components 170, which may include, for example, a wireless transceiver 172. The wireless transceiver 172 may be communicatively coupled to one or more antenna devices 195, which may be configured to wirelessly transmit data and / or power signals to and / or receive data and / or power signals from the wearable computing device 100 using, but not limited to, peer-to-peer, WLAN, and / or cellular communications. For example, the wireless transceiver 172 may be used to transfer data and / or power between the wearable computing device 100 and an external computing device, which may be configured to interface with the wearable computing device 100. In some embodiments, the host interface 176 may include, for example, wired and / or wireless interface components that may communicatively couple the wearable computing device 100 to an external computing device to receive data and / or power from and / or transmit data to it. The host interface 176 according to the example embodiment can utilize any suitable or desired communication protocol and / or physical connector and / or otherwise associate with said communication protocol and / or physical connector, such as, for example, Universal Serial Bus (USB), Micro USB, Wi-Fi, Bluetooth, FireWire, PCIe, etc. For wireless connectivity, the host interface 176 according to the example embodiment can be combined with a wireless transceiver 172.

[0051] In addition, such as Figure 2 As shown, the connectivity component 170 may further include one or more HMIs 174, which can be used by the wearable computing device 100 to receive input data from the user 10 and / or provide output data to the user 10. For example, in some embodiments, the HMI 174 of the wearable computing device 100 may include a touchscreen display that can be configured to provide (e.g., render) output data to the user 10 and / or receive user input through contact between the user and the touchscreen display. In some embodiments, the HMI 174 may further comprise and / or include one or more buttons or other input / output components or features.

[0052] Now for reference Figure 3 A diagram illustrating an example computing environment 300 according to one or more example embodiments of the present disclosure is shown. As shown, according to one or more embodiments, Figure 3 The computing environment 300 depicted illustrates an example networking relationship between a wearable computing device 100 and a remote computing device (such as a mobile computing device 304 and / or a server system 312).

[0053] Referring to the above and Figure 2 The exemplary embodiments depicted herein indicate that the wearable computing device 100 according to exemplary embodiments of this disclosure can perform analysis and / or interpretation of a portion of the sensor data of the user 10, and / or perform operations based on that portion of the sensor data. Thus, in some embodiments, the wearable computing device 100 may be able to and / or be configured to collect that portion of the sensor data of the user 10 and / or perform operations using such readings.

[0054] However, the wearable computing device 100 may include one or more infrastructure constraints that limit the wearable computing device 100's ability to analyze and / or interpret all sensor data for the user 10 and / or perform operations based on all sensor data. As used herein, "infrastructure constraint" generally refers to a variable representing the available resources for the wearable computing device 100 to perform the desired operations. Thus, in embodiments, infrastructure constraints may include power storage capacity, available data storage for storing sensor data, available computing resources for executing machine learning models to analyze and / or interpret sensor data, and / or any other suitable resources that may limit the performance of the wearable computing device 100.

[0055] Therefore, the wearable computing device 100 can communicate with remote computing devices 304 and 312, which have more available computing resources than the wearable computing device 100 to analyze and / or interpret all the sensor data. Due to infrastructure constraints of the wearable computing device 100, it may not be able to transmit raw sensor data to the remote computing devices 304 and 312. Therefore, the wearable computing device 100 can be configured to generate lexicalized sensor data via the lexicalization module 111, which, as will be further described below, can be transmitted to the remote computing devices 304 and 312 given the infrastructure constraints of the wearable computing device 100.

[0056] Therefore, the wearable computing device 100 can relay lexicalized sensor data to remote computing devices 304, 312 via one or more networks 306 to other devices. In some embodiments, this includes relaying the lexicalized sensor data to a device that can serve as an internet-accessible data source, thereby allowing the collected data to be viewed, for example, at remote computing devices 304, 312 using a web browser or a web-based application. For example, the wearable computing device 100 can use sensor 143 to capture, compute, and / or store sensor data of user 10, for example, while being worn by user 10. The wearable computing device 100 can then send the lexicalized sensor data, representing the sensor data, to mobile computing device 304 and / or server system 312 (e.g., periodically or continuously) via network 306, where user 10 and / or another entity (e.g., a healthcare professional) can store, process, and visualize the data. Therefore, in embodiments, mobile computing device 304 may be configured to generate smart notification 310 and provide smart notification 310 to user 10, for example, via display 308 or a second computing device. In some embodiments, smart notification 310 may include a physiological assessment, which may be output by a machine learning model programmed in remote computing devices 304, 312.

[0057] In one or more embodiments, communication between the wearable computing device 100 and the mobile computing device 304 may be facilitated by a network 306. In some embodiments, the network 306 may include one or more of the following: an ad hoc network, a peer-to-peer link, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a wireless WAN (WWAN), a metropolitan area network (MAN), a portion of the Internet, a portion of the Public Switched Telephone Network (PSTN), a cellular telephone network, and / or any other type of network. In some embodiments, communication between the wearable computing device 100 and the mobile computing device 304 may also be performed via a direct wired connection. In these or other embodiments, this direct wired connection may be associated with any suitable or desired communication protocol and / or physical connector, such as, for example, Universal Serial Bus (USB), Micro USB, Wi-Fi, Bluetooth, FireWire, PCIe, etc.

[0058] In example embodiments, various computing devices can communicate with wearable computing device 100 to facilitate the user's cardiac assessment and / or changes (e.g., improvements). Although in Figure 3In the example embodiment shown, the mobile computing device 304 is depicted as a smartphone, but it should be understood that this disclosure is not limited thereto. For example, the mobile computing device 304 according to the example embodiment may include, for example, having... Figure 3 The depicted display 308 includes smartphones, personal digital assistants (PDAs), mobile phones, tablets, personal computers, laptops, smart TVs, video game consoles, and / or other computing devices that may be external to the wearable computing device 100.

[0059] Remote computing devices 304 and 312 can be configured to use lexicalized sensor data from user 10 to determine physiological indicators of user 10 and / or perform physiological assessments of user 10 based on the sensor data. For example, remote computing devices 304 and 312 may include one or more machine learning models, which may include at least one physiological assessment model. In such embodiments, the physiological assessment model is configured to use machine learning to generate one or more physiological indicators and / or assessments for the user. For example, in one embodiment, in response to receiving lexicalized sensor data from user 10, the machine learning model can be trained to output physiological indicators and / or assessments. More specifically, remote computing devices 304 and 312 include more computing resources than wearable computing device 100, which allows remote computing devices 304 and 312 to determine physiological indicators and / or assessments in a more computationally efficient manner.

[0060] A machine learning model can be or includes one or more machine learning models or model components. Example machine learning models can include neural networks (e.g., deep neural networks) or generative models (e.g., large language models (LLMs), non-linear or linear models, decision tree-based models, support vector machines, hidden Markov models, Bayesian networks, and / or k-means clustering models, etc.). Example machine learning models may also use other architectures to replace or supplement those specifically mentioned in this article.

[0061] Neural networks such as those described herein can include feedforward neural networks, recurrent neural networks (e.g., long short-term memory recurrent neural networks), convolutional neural networks, and / or other forms of neural networks. Some example machine learning models may utilize attention mechanisms, such as self-attention. For example, some example machine learning models may include multi-head self-attention models (e.g., transformer models). In another embodiment, the machine learning models described herein may include rule-based methods, wherein actions are selected based on a predetermined set of if-then rules or mathematical expressions with predefined parameters.

[0062] For details, please refer to the following: Figure 3 and Figure 4Wearable computing device 100 can send lexicalized sensor data of user 10 to server system 312 (e.g., via network 306). In this embodiment, server system 312 can analyze the received lexicalized sensor data to perform physiological assessments and / or can use the received lexicalized sensor data to update user profile of user 10, which can be stored in memory 316 of server system 312. Figure 4 In database 314 (e.g., logs).

[0063] In some embodiments, server system 312 may be implemented on one or more independent data processing devices or a distributed computer network. In some embodiments, server system 312 may employ various virtual devices and / or services from third-party service providers (e.g., third-party cloud service providers) to provide the underlying computing resources and / or infrastructure resources of server system 312. In some embodiments, server system 312 may include, but is not limited to, handheld computers, tablet computers, laptop computers, desktop computers, or any two or more combinations of these data processing devices or other data processing devices.

[0064] For details, please refer to the following: Figure 4 The server system 312 may include one or more processors 318, such as, for example, one or more CPUs. In these or other embodiments, the server system 312 may include one or more network interfaces 320, which may include, for example, input / output (I / O) interfaces to the mobile computing device 304 and / or the wearable computing device 100. In some embodiments, the server system 312 may include one or more communication buses for interconnecting these components.

[0065] According to an example embodiment, memory 316 may include high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices; and optionally may include non-volatile memory, such as one or more disk storage devices, one or more optical disk storage devices, one or more flash memory devices, or one or more other non-volatile solid-state memory devices. Optionally, memory 316 may include one or more storage devices that may be located remotely from processor 318 (e.g., processing unit). Further, memory 316, or alternatively, the non-volatile memory within memory 316, may include a non-transitory computer-readable storage medium. In some embodiments, memory 316 or the non-transitory computer-readable storage medium of memory 316 may store one or more programs, modules, and data structures. In these embodiments, such programs, modules, and data structures may include, but are not limited to, one or more operating systems in an operating system, which may include processes for handling various basic system services and for performing hardware-related tasks.

[0066] Now for reference Figure 5A and Figure 5B The diagram illustrates a block diagram of an embodiment of the lexicalization module 111 according to this disclosure. Wearable computing device 100 may be configured to collect sensor data 410 of user 10 using embedded sensors and / or external devices, as mentioned above. In some embodiments, sensor data 410 may optionally be preprocessed by a processing system (not shown). Various types of preprocessors and preprocessing may be provided for different implementations. As an example, sensor data 410 may be preprocessed to generate text representations that may be lexicalized into text lexical units for processing by a machine learning model programmed in remote computing devices 304, 312. For example, sensor data 410 may be provided to a machine learning classification model configured to generate one or more predictions or classifications of the raw sensor data 410. The predictions or classifications may be represented as text that may be provided to a text lexicalizer to generate one or more text lexical units as input to the machine learning model. For example, sensor data 410 may be provided as input to a machine learning classification or prediction model configured to determine contextual features. The model may output a textual representation of the contextual features. Contextual features can include information about the context surrounding and / or nearby to the user and / or information directly about the user's context, such as the user's location, activity level, etc.

[0067] Sensor data 410 can then be provided to lexer 402. Lexer 402 may include one or more hardware and / or software components and / or features that can be configured to perform the operations described herein. Lexer 402 can generate lexified sensor data (e.g., via vector quantization algorithms) based on sensor data 410. Lexified sensor data includes sensor data 410 compressed into a compressed bitstream. For example, given the infrastructure constraints of wearable computing device 100, lexer module 111 can generate lexicals 412 that embed and compress the sensor data 410 into a representation that can be transmitted via network 306. Further, lexicals 412 may be processable by machine learning models programmed in remote computing devices 304, 312. In additional or alternative embodiments, given the infrastructure constraints of wearable computing device 100, lexer 402 can generate fragments, chunks, or other subsets of data that can be transmitted via network 306 based on sensor data.

[0068] In an example embodiment, lexer 402 may include one or more machine learning lexer models 403 configured to generate one or more sensor data lexical units 412 as output in response to sensor data 410 as input. In some examples, the machine learning lexer model 403 may embed the sensor data lexical units 412 into the embedding space of a machine learning model programmed in remote computing devices 304, 312. The embedding model may compress and represent the lexical units 412 as lexical embeddings. The machine learning lexer model 403 may be configured to generate sensor data lexical units 412 adapted for processing in the common embedding space of the machine learning models programmed in remote computing devices 304, 312. In an embodiment, the machine learning lexer model 403 may generate lexical embeddings by embedding the sensor data lexical units 412 into the embedding space of a machine learning model programmed in remote computing devices 304, 312. For example, lexer 402 may include one or more machine learning embedding models 405, such as transformers or encoders configured to embed sensor data lexics 412 into the embedding space of a machine learning model programmed in remote computing devices 304, 312. In an example embodiment, the embedding space of the machine learning model programmed in remote computing devices 304, 312 may be a latent embedding space, a text embedding space, an image embedding space, and / or an audio embedding space.

[0069] Machine learning lexicalization model 403 or embedding model 405 can generate lexical embeddings based on sensor data 410. Lexical units 412 or lexical embeddings may contain compressed sensor data 410 that can be transmitted in a computationally efficient manner. Machine learning lexicalization model 403 and / or embedding model 405 can extract contextual features from sensor data 410, which can be compressed to represent as lexical units and / or embeddings. Embedding model 405 may include one or more embedding layers configured to receive features or sensor data 410 and generate lexicalized sensor data, such as sensor data lexical units 412. Embedding layers may include radar embedding layers (e.g., transformers) and text embedding layers (e.g., word embedding layers). The model may include a transformer encoder for generating representations of radar, lidar, optical, ultrasonic, and / or other sensor modalities.

[0070] The lexicalization module 111 may include one or more lexicalizers 402, 502a, 502b for lexicalizing sensor data 410, 510a, 510b of different sensing modalities. In an example embodiment, the lexicalization module 111 may include a single lexicalizer 402 configured to generate sensor data tags 412 from different types of sensors, such as... Figure 5A As shown. For example, a single lexer 402 can be configured to generate one or more lexical units 412 based on sensor data 410 from multiple types of sensors (e.g., ultrasonic sensors, radar sensors, etc.). In another example embodiment, the lexer module 111 may include different lexers 502a, 502b for different types of sensors, such as... Figure 5B As shown. For example, a first lexer 502a can be configured to generate one or more first lexical terms 512a based on first sensor data 510a of a first type of sensor (e.g., an ultrasonic sensor), and a second lexer 512b can be configured to generate one or more second lexical terms 512b based on second sensor data 510b of a different second type of sensor (e.g., a radar sensor). Thus, the lexer 402, 502a, 502b of the lexer module 111 can include a machine learning lexer model configured to generate sensor data terms 412, 512a, 512b in response to sensor data 410, 510a, 510b of one or more sensor modalities.

[0071] Example Method

[0072] Figure 6A flowchart illustrating an embodiment of a computer-implemented method 600 according to the present disclosure is shown. The computer-implemented method 600 can be implemented using, for example, the above references. Figure 1 This is implemented using the wearable computing device 100, mobile computing device 304, and / or server system 312 described in the example embodiments depicted in Figure 5.

[0073] For the purposes of explanation and discussion, Figure 6 The example embodiments shown depict operations performed in a specific order. Those skilled in the art will understand using the disclosure provided herein that various operations or steps of the computer-implemented method 600 or any of the other methods disclosed herein can be adapted, modified, rearranged, performed concurrently, including operations not shown, and / or modified in various ways without departing from the scope of this disclosure.

[0074] As shown at (602), the computer-implemented method 600 may include receiving data from one or more sensors by the wearable computing device 100. The sensor data may include, but is not limited to, the user's motion data and / or physiological data, as discussed above.

[0075] As shown at (604), the computer-implemented method 600 may include generating lexicalized sensor data based on sensor data via a machine learning lexicalization model programmed in the wearable computing device 100. The lexicalized sensor data may include compressed sensor data capable of being transmitted via one or more networks while simultaneously satisfying the infrastructure constraints of the computing device, as discussed above.

[0076] As shown at (606), the computer-implemented method 600 may include transmitting lexicalized sensor data from a wearable computing device 100 to a remote computing device. The remote computing device may include a mobile computing device 304 and / or a server system 312, as discussed above. Thus, the remote computing device can analyze and / or interpret the sensor data in a computationally efficient manner (e.g., due to having relatively more available computing resources).

[0077] Additional Public Content

[0078] This paper discusses technologies related to servers, databases, software applications, and other computer-based systems, as well as the actions taken and information sent to and from such systems. The inherent flexibility of computer-based systems allows for a wide variety of possible configurations, combinations, and partitions of tasks and functionalities among and between components. For example, the processes discussed herein can be implemented using a single device or component, or multiple devices or components working in combination. Databases and applications can be implemented on a single system or distributed across multiple systems. Distributed components can operate sequentially or in parallel.

[0079] While the subject matter has been described in detail with respect to various specific example embodiments, each example is provided by way of illustration and not limitation. Modifications, alterations, and equivalents to such embodiments will be readily apparent to those skilled in the art upon understanding the foregoing. Therefore, this disclosure does not exclude such modifications, alterations, or additions to the subject matter that will be readily understood by those of ordinary skill in the art. For example, features shown or described as part of an embodiment may be used with another embodiment to produce yet another embodiment. Therefore, this disclosure is intended to cover such modifications, alterations, and equivalents.

[0080] Various aspects of this disclosure have been described with reference to their illustrative embodiments. Any and all features of the appended claims can be combined or rearranged in any possible manner, including combinations of claims not expressly listed together, because the illustrative claims dependencies listed herein should not be construed as limiting the scope of possible combinations of features disclosed herein. Therefore, the scope of this disclosure is illustrative rather than limiting, and this disclosure does not exclude such modifications, alterations, or additions to the subject matter that will be readily understood by one of ordinary skill in the art. Furthermore, terms are described herein using lists of illustrative elements connected by conjunctions such as “and,” “or,” “but,” etc. It should be understood that such conjunctions are provided for illustrative purposes only. For example, a sequence of terms and other items connected by a specific conjunction such as “or” may refer to “and / or,” “at least one of,” “any combination,” etc., of the illustrative elements listed therein. Terms such as “based on” should be understood as “at least partially based on.”

[0081] The term "capable" should be understood as referring to the possibility of a feature in various implementations, rather than a capability that must exist in every implementation. For example, the phrase "X can perform Y" should be understood as indicating that in various implementations, X may be configured to perform Y, rather than indicating that X must always be able to perform Y in every instance. It should be understood that in various implementations, X may not be able to perform Y and is still within the scope of this disclosure.

[0082] The term "may" should be understood as referring to the possibility of a feature in various implementations, rather than specifying a capability that must exist in every implementation. For example, the phrase "X can perform Y" should be understood as indicating that in various implementations, X may be configured to perform Y, rather than indicating that X must always be able to perform Y in every instance. It should be understood that in various implementations, X may not be able to perform Y and is still within the scope of this disclosure.

Claims

1. A method for controlling a wearable computing device, the method comprising: Receive sensor data from one or more sensors of the wearable computing device via a controller; Lexicalized sensor data is generated based on the sensor data via a machine learning lexicalization model programmed in the controller on the wearable computing device. The lexicalized sensor data includes the sensor data compressed into a compressed bitstream. as well as The morphified sensor data is transmitted to a remote computing device via the controller on the wearable computing device.

2. The method as described in claim 1, wherein, The morphified sensor data is configured to be transmitted via a communication protocol while satisfying the infrastructure constraints of the wearable computing device.

3. The method as described in claim 1, wherein, The morphified sensor data is configured as at least one embedding space for a machine learning model programmed in a remote controller of the remote computing device.

4. The method of claim 3, wherein, The lexicalized sensor data includes one or more lexical embeddings, and the method further includes: Generate one or more sensor data terms; and The one or more lexical embeddings are generated by embedding the one or more sensor data lexicals in the embedding space of the machine learning model.

5. The method of claim 1, wherein: The sensor data includes first sensor data from a first sensor of a first sensor type and second sensor data from a second sensor of a second sensor type; The machine learning lexicalization model includes a first lexicalizer configured to lexicalize the first sensor data and a second lexicalizer configured to lexicalize the second sensor data; as well as Generating lemmatized sensor data based on the sensor data via the machine learning lemmatization model programmed in the controller further includes: The first word element is generated based on the first sensor data via the first word element generator; as well as The second lexical unit is generated based on the second sensor data via the second lexical unitizer.

6. The method of claim 1, wherein: The sensor data includes first sensor data from a first sensor of a first sensor type and second sensor data from a second sensor of a second sensor type; The machine learning lexicalization model includes a lexicalizer configured to lexicalize the first sensor data and the second sensor data; as well as Generating lemmatized sensor data based on the sensor data via the machine learning lemmatization model programmed in the controller further includes: The first lexical unit is generated based on the first sensor data, and the second lexical unit is generated based on the second sensor data, via the lexer.

7. The method of claim 1, further comprising: The user's physiological indicators are identified based on the sensor data via a model programmed in the controller.

8. The method of claim 1, wherein, The morphized sensor data includes one or more sensor data morphemes.

9. The method of claim 1, wherein, The remote computing device includes a user computing device or a server computing device.

10. The method of claim 1, wherein, The wearable computing device includes a smartwatch.

11. A wearable computing device, comprising: The controller includes at least one processor configured to perform a plurality of operations, the plurality of operations including: Receive sensor data from one or more sensors of the wearable computing device; Lexicalized sensor data is generated based on the sensor data via a machine learning lexicalization model programmed in the controller. The lexicalized sensor data includes the sensor data compressed into a compressed bitstream. The morphified sensor data is sent to a remote computing device.

12. The wearable computing device of claim 11, wherein, The morphified sensor data is configured to be transmitted via a communication protocol while satisfying the infrastructure constraints of the wearable computing device.

13. The wearable computing device of claim 11, wherein, The morphified sensor data is configured as at least one embedding space for a machine learning model programmed in a remote controller of the remote computing device.

14. The wearable computing device of claim 13, wherein, The lexicalized sensor data includes one or more lexical embeddings, and wherein the plurality of operations further includes: Generate one or more sensor data terms; and The one or more lexical embeddings are generated by embedding the one or more sensor data lexicals in the embedding space of the machine learning model.

15. The wearable computing device of claim 11, wherein: The sensor data includes first sensor data from a first sensor of a first sensor type and second sensor data from a second sensor of a second sensor type; The machine learning lexicalization model includes a first lexicalizer configured to lexicalize the first sensor data and a second lexicalizer configured to lexicalize the second sensor data; as well as Generating lemmatized sensor data based on the sensor data via the machine learning lemmatization model programmed in the controller further includes: The first word element is generated based on the first sensor data via the first word element generator; as well as The second lexical unit is generated based on the second sensor data via the second lexical unitizer.

16. The wearable computing device of claim 11, wherein: The sensor data includes first sensor data from a first sensor of a first sensor type and second sensor data from a second sensor of a second sensor type; The machine learning lexicalization model includes a lexicalizer configured to lexicalize the first sensor data and the second sensor data; as well as Generating lemmatized sensor data based on the sensor data via the machine learning lemmatization model programmed in the controller further includes: The first lexical unit is generated based on the first sensor data, and the second lexical unit is generated based on the second sensor data, via the lexer.

17. The wearable computing device of claim 11, wherein, The plurality of operations further include: identifying the user’s physiological indicators based on the sensor data via a model programmed in the controller.

18. The wearable computing device of claim 11, wherein, The morphized sensor data includes one or more sensor data morphemes.

19. The wearable computing device of claim 11, wherein, The remote computing device includes a user computing device or a server computing device.

20. The wearable computing device of claim 11, wherein, The wearable computing device includes a smartwatch.

Images