Data tagging
A method for tagging and organizing data is provided. In one example, physiological data detected from a wearer of a wearable device is received and associated with a tag based, at least in art, on an input by the wearer. The input may be a state of the wearer, such as physical or mental state, or a rule. The collected physiological data may be organized based on the tag and, in some examples, on other types of received data, such as a wearer's personal data. In other example methods, data may be stored in a database based on one or more tags associated with the data.
1 . A method, comprising:
receiving, by a server from a wearable device, first physiological data captured by a wearable device at a first resolution, wherein the wearable device is configured to be mounted to a body surface of a wearer;
receiving, by the server, an input from the wearer;
associating, by the server, all or part of the first physiological data with a tag based, at least in part, on the input from the wearer;
organizing and storing, by the server, the first physiological data based, at least in part, on the tag;
based on the input from the wearer, causing the wearable device to capture physiological data at a second resolution, the second resolution having a higher sampling rate than the first resolution;
receiving physiological data captured at the second resolution from the wearable device;
learning, by a machine learning (“ML”) model on the server, a rule based at least in part on the tag and the physiological data captured at the second resolution;
causing the wearable device to revert to capturing data at the first resolution;
receiving, by the server, second physiological data from the wearable device; and
responsive to using the ML model to determine an association between the second physiological data and the tag based on the learned rule, associating the second physiological data with the tag.
2 . The method of claim 1 , wherein the tag is generated based, at least in part, on the input from the wearer.
3 . The method of claim 1 , wherein input is a state of the wearer.
4 . The method of claim 3 , wherein the state is selected from the group consisting of:
a type of activity engaged in by the wearer, a task performed by the wearer, a health state of the wearer, a physical state of the wearer, a mental state of the wearer, a mood of the wearer.
5 . The method of claim 1 , further comprising:
receiving, by the server from the wearable device, a second input from the wearer identifying an activity performed by the wearer associated with the second physiological data; and
updating the rule based on the second input and the second physiological data.
6 . The method of claim 1 , wherein organizing the first physiological data comprises aggregating a plurality of physiological data detected from the wearer of a wearable device associated with the tag.
7 . The method of claim 1 , wherein the first physiological data comprises one or more of: (a) heart rate, (b) respiration rate, (c) body temperature, and (d) level of perspiration.
8 . The method of claim 1 , further comprising:
receiving, by the server from a plurality of wearable devices, physiological data obtained from a plurality of wearers of the plurality of wearable devices;
associating, by the server, all or part of the physiological data obtained from the plurality of wearers with one or more tags based, at least in part, on respective inputs from the plurality of wearers; and
organizing, by the server, the data based, at least in part, on the one or more tags.
9 . The method of claim 8 , wherein organizing the physiological data comprises aggregating the physiological data obtained from the plurality of wearers based on the one or more tags.
10 . The method of claim 1 , further comprising:
receiving, by the server, motion data associated with a wearer of the wearable device, wherein the motion data is detected synchronously with the first physiological data;
receiving, by the server, time-synchronization data that indicates a timing relationship between the motion data and the physiological data; and
applying, by the server, the tag to the motion data based, at least in part, on the time-synchronization data.
11 . The method of claim 10 , wherein the motion data comprises one or more of: (a) speed of travel, (b) altitude, (c) acceleration, (d) cadence of movement, (e) intensity of movement, (f) direction of travel, (g) orientation, (h) gravitational force, (i) inertia, and (j) rotation.
12 . The method of claim 1 , further comprising:
receiving, by the server, contextual data associated with the wearer of the wearable device, wherein the contextual data is detected synchronously with the first physiological data;
receiving, by the server, time-synchronization data that indicates a timing relationship between the contextual data and the first physiological data; and
applying, by the server, the tag to the contextual data based, at least in part, on the time-synchronization data.
13 . The method of claim 12 , wherein the contextual data comprises one or more of:
(a) location of the wearer of the device, (b) ambient light intensity, (c) ambient temperature, (c) time of day, (d) a mode of travel of the wearer of the device, and (e) a type of activity the wearer of the device is engaged in.
14 . The method of claim 1 , further comprising:
receiving, by the server, personal data associated with a wearer of the device; and
organizing, by the server, the data, based, at least in part, on the tag and the personal data.
15 . The method of claim 14 , wherein the personal data comprises one or more of: (a) a height of the wearer of the device, (b) a weight of the wearer of the device, (c) an age of the wearer of the device; (d) a gender of the wearer of the device; (e) a race of the wearer of the device; (f) a medical history of the wearer of the device; and (g) an occupation of the wearer of the device.
16 . A system comprising:
a non-transitory computer-readable medium; and
one or more processors configured to execute processor-executable instructions stored in the non-transitory computer-readable medium configured to cause the one or more processors to:
receive, from a wearable device, first physiological data captured by a wearable device at a first resolution, wherein the wearable device is configured to be mounted to a body surface of a wearer;
receive an input from the wearer;
associate all or part of the first physiological data with a tag based, at least in part, on the input from the wearer;
organize and store the first physiological data based, at least in part, on the tag;
based on the input from the wearer, cause the wearable device to capture physiological data at a second resolution, the second resolution having a higher sampling rate than the first resolution;
receiving physiological data captured at the second resolution from the wearable device;
learn, by a machine learning (“ML”) model, a rule based at least in part on the tag and the physiological data captured at the second resolution;
cause the wearable device to revert to capturing data at the first resolution;
receive second physiological data from the wearable device; and
responsive to using the ML model to determine an association between the second physiological data and the tag based on the learned rule, associate the second physiological data with the tag.
17 . The system of claim 16 , wherein the tag is generated based, at least in part, on the input from the wearer.
18 . The system of claim 16 , wherein input is a state of the wearer.
19 . The system of claim 18 , wherein the state is selected from the group consisting of:
a type of activity engaged in by the wearer, a task performed by the wearer, a health state of the wearer, a physical state of the wearer, a mental state of the wearer, a mood of the wearer.
20 . The system of claim 16 , wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium configured to cause the one or more processors to:
receive, from the wearable device, a second input from the wearer identifying a second activity performed by the wearer associated with the second physiological data; and
update the rule based on the second input and the second physiological data.
21 . The method of claim 1 , further comprising:
determining one or more groups in a data store associated with the tag;
storing the second physiological data and the tag in a data store according to the one or more determined groups;
receiving a second input from the wearer indicating a correction of the association of the second physiological data with the tag;
updating, by the ML model on the server, the rule based on the correction; and
associating the second physiological data with a second tag based on the correction.
22 . A non-transitory computer-readable medium comprising processor-executable instructions configured to cause one or more processors to:
receive, from a wearable device, first physiological data captured by a wearable device at a first resolution, wherein the wearable device is configured to be mounted to a body surface of a wearer;
receive an input from the wearer;
associate all or part of the first physiological data with a tag based, at least in part, on the input from the wearer;
organize and store the first physiological data based, at least in part, on the tag; and
based on the input from the wearer, cause the wearable device to capture physiological data at a second resolution, the second resolution having a higher sampling rate than the first resolution;
receiving physiological data captured at the second resolution from the wearable device;
learn, by a machine learning (“ML”) model, a rule based at least in part on the tag and the physiological data captured at the second resolution;
cause the wearable device to revert to capturing data at the first resolution;
receive second physiological data from the wearable device; and
responsive to using the ML model to determine an association between the second physiological data and the tag based on the learned rule, associate the second physiological data with the tag.