DESC:[19] This patent describes the subject matter for patenting with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. The principles described herein may be embodied in many different forms.

[20] Illustrative embodiments of the invention now will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. Indeed, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like numbers refer to like elements throughout.

[21] FIG. 1 illustrates a system 100 for power management of wearable devices that provides a holistic guidance to the wearer such that the wearer gets an estimation of the expected battery usage in the near future, thereby enabling the user to take a well-informed decision regarding whether to conserve the battery power by shutting down few non-essential activities or charge the wearable device if there is an option to do so. Fig. 3 illustrates a method 300 implemented in the system 100 for prediction of power consumption pattern of wearable devices. The present invention will be explained in relation to Fig. 1 and 3 in the ensuing description. The present invention envisages an artificial intelligence (AI) module built into the system 100 that considers the historical battery usage pattern based on the wearer’s activities on the wearable device and provides a guidance to the wearer about the expected battery consumption in the near future. The AI module also suggests corrective options to the wearer to enable him/her to conserve power of the wearable device to prolong the usage capability with limited battery power. Alternatively, if the wearer anticipates that he/she would be away from power source for long duration, based on the guidance on expected power consumption, the wearer may decide to charge the wearable device in a timely manner. The system includes at least one wearable device 105 that is capable of communicably coupling with at least one mobile device 110 for exchange of information therewith. The wearable device 105 includes one or more sensors 105a for measuring physical activity and or physiological parameters of the wearer. In one embodiment of the present invention, the one or more sensors 105a may sense weather related parameters, such as ambient humidity and temperature. The present invention envisages that ambient humidity and temperature affects the battery performance and drain thereof and hence, it could be an important parameter for consideration. In another embodiment of the present invention, the ambient humidity and temperature related data may be collected through any online repository, mobile device 110 or website that reports real-time data pertaining to humidity and temperature for the specific location where the wearer is located. The wearable device 105 additionally includes a transceiver 105b for enabling the wearable device 105 to be communicably coupled to the mobile device 110, besides including a display 105c to display notifications pertaining to at least the physical activity and/or physiological parameters (such as heart rate, pulse, oxygen saturation level and the like) of the wearer, social media or productivity related activities and battery usage and conservation information. The various components of the wearable device 105 are powered by a rechargeable battery 105d. The wearable device 105 also includes one or more software applications running on a processor 105e. The software applications monitor the physical and/or physiological activities of the wearer, collect pertinent data related to such activities and generate notifications related to the collected data, which are displayed on the display 105c. The wearable device 105 may also receive notifications from the mobile device 110 pertaining to service or carrier related messages, which are displayed on the display 105c. The processor also keeps track of the battery consumption on account of various device configuration settings such as brightness of the display 105c, the time for which the display screen 105c remains active, notification alerts and vibration, background processes and battery age. Besides, the processor 105e also keeps track of the battery usage arising due to activity of the user on social media interactions, such as facebook, Instagram, whatsapp, personal emails and the like, or through productivity tools, such as accessing emails or messaging platforms like MS Teams. It would be apparent that all activities related to monitoring, communicating, interaction and displaying would result in consumption of battery, thereby resulting in depletion thereof over prolonged usage.

[22] The present invention envisages that the system 100 also includes a server 115 that is communicably coupled to at least the wearable device 105 either directly or through the mobile device 110, as shown in Fig. 1. The server 115 includes a communication module 116 to enable the communicable coupling with the wearable device 105. The server 115 is adapted to exchange information with the wearable device 105 related to at least the battery usage related data thereof. Particularly, the processor 105e of the wearable device 105 continually captures the real-time battery usage data on account of the monitoring and measurement of one or more of the various activities specified above, i.e. measurement of physical activity of the user, measurement and tracking of physiological parameters of the user, monitoring the social media related activities of the user, measurement of humidity and ambient temperature of the location of the wearer, device configuration settings, social media interactions and productivity related activity of the user, as shown in step 305 in Fig. 3, and shares the same with the server 115, which in turn stores the same in a data repository. The present invention envisages to predict the future battery usage pattern for the wearer so that he/she may be aware of the expected drain pattern of the battery of the wearable device to enable them to plan a charging operation of the wearable device. To enable this, the present invention uses the historical data related to battery consumption of the wearable device and generate a prediction specific to the wearable device. It has been identified that each wearer of a wearable device may have a specific usage pattern and thus, prediction for the battery life should be as accurate as possible to the expected usage pattern of the specific wearer.

[23] To enable a precise prediction of the battery consumption for a particular wearable device, the present invention envisages that the server 115 includes a predictive module 120 that is capable of providing the wearer with a holistic guidance related to conserving battery based on the analysis of his/her battery consumption pattern. The predictive module 120 is provided with real time data pertaining to battery consumption gathered by the processor 105e on account of the function of monitoring of physical activity, collection of physiological data pertaining to the user, device configuration settings, social media interactions and productivity related interactions of the wearer on the wearable device 105. Also, the prediction module 120 may be provided real-time data pertaining to temperature and humidity at the location of the wearer at the particular time instance, as shown in 310 in Fig. 3. Additionally, the predictive module 120 is trained on historical data, stored in the server 115, pertaining to the battery usage pattern of the wearer in respect of all of the afore-mentioned activities. In particular, the historical data may include additional qualifiers like the time of the day when the wearer performs specific activities (physical/professional/social media related), the duration for which each of the activities have been performed, the frequency of performing the activities in a day/week/month/year, and the like. For instance, if the wearer is a working professional who devotes time to exercise during early morning hours for 4 days in a week; receives maximum office work related notifications between 9 am to 4 pm on Monday, Tuesday, Thursday, and Friday; takes personal calls with a family member every night; takes a walk before going to sleep, such historical data for a predetermined duration (say half yearly or annually) is provided to the predictive module 120 for training purposes. As shown in Fig.2, the predictive module 120 includes a training data module 125 that receives the historical data related to battery usage, stored in the server 115, for training an artificial intelligence module 130. The artificial intelligence module 130, coupled to the training data module 125, utilizes any known machine learning regression models, such as linear regression, logistic regression, polynomial regression, support vector regression, decision tree regression, random forest regression, ridge regression, lasso regression and the like to generate a prediction on the expected battery consumption for the wearable device. The prediction module 120 further includes a testing module 135 that tests the accuracy of the artificial intelligence module 130 by providing testing data culled from the historical data, and the accuracy, precision, recall and F1 score of the artificial intelligence module 130 is determined. Basically, it is checked as regards how accurately the artificial intelligence module 130 is capable of predicting the battery consumption over a period of time. The test results are fed back to the artificial intelligence module 130 in case any corrections are required for enhancing the accuracy of prediction. The artificial intelligence module 130, once ready, is provided with the real time data of battery usage of the wearable device 105 , and optionally the determined weather parameters, to generate a prediction of the expected battery consumption of the wearable device based on the usual activity pattern of the wearer, as per 315 in Fig. 3.

[24] The predictive model takes into consideration the importance level of different activities undertaken by the wearer on the wearable device that result in battery consumption. In an embodiment of the present invention, the different activities may be assigned specific weights. . Table 1 below depicts one exemplary embodiment where weights have been assigned to the different activities that are taken into consideration by the wearable device 105. It may be noted that the described example elucidates one of the examples of the wearable device 105 that measures only specific parameters. The example is being provided for the sake of explanation and should not be considered as limiting the scope of the present invention to the described parameters only. Other embodiments may consider a combination of similar such parameters and assign different weights as per the type of usage of the wearable device.
Table 1: Weights assigned to the parameters considered by predictive model
Parameter Activity Weight
Notifications Device configuration setting 0.11
Report watch data Device configuration setting 7.83
Standby Device configuration setting 1.07
Alarm reminder Device configuration setting 8.40
Weekly physical actvity Physical activity interaction 1.24.
Time check Device configuration setting 9.15
Heart rate check Physiological parameter measurement 0.46
Incoming call Productivity tool activity 16.94
Outgoing call Productivity tool activity 8.78
Music Social media related activity 0
Calendar Reminders Device configuration setting 8.62
SpO2 measurement Physiological parameter measurement 10.94
Breath Physiological parameter measurement 12.02
Screen off pointer Device configuration setting 14.29
Atm. Pressure Weather parameter 0.11
The predictive module 120 applies these weights across the measured parameters to determine the predictive model of the present invention.

Thus, the wearer would be provided with information regarding how long his battery is expected to last on that particular day. In addition, the wearer is provided suggestions regarding the battery conservation steps he/she could undertake, such as by avoiding few activities or shutting down monitoring of few activities that consume high battery power. Thus, considering the example above, if the wearable device is at 50% battery on Friday morning, the predictive module would consider the historical data pertaining to usual expected activities of the wearer on Fridays and provide a notification to the wearer that the wearable device 105 is expected to shut down in next 2 hours. The wearer would then be provided suggestions regarding shutting down notifications for office emails and messages to enhance the battery life to last for 3 hours instead. Moreover, the predictive module 120 also identifies the activities that are less likely to be performed (such as no physical activity after 12noon) by the wearer during the remaining part of the day and consequently suggests him/her to shut down the tracking of physical activity by sensors.

[25] Therefore, the present invention envisages that the wearer is provided with a holistic guidance not only based on his actual usage of the wearable device but also the historical usage pattern of the wearer, thereby providing a more accurate suggestion to the wearer regarding conserving power. As a result, the wearer is better informed about the expected battery usage in near future and based on such realistic prediction, the wearer may be able to take a well-informed decision regarding conserving battery power and/or charging the battery. The present invention, thus, is advantageous over the existing solutions that are unable to provide an accurate prediction of battery consumption as the same only utilize the information about current battery consumption.

[26] Since other modifications and changes varied to fit specific operating requirements and environments are apparent to those skilled in the art, the invention is not considered limited to the example chosen for purposes of disclosure, and covers all changes and modifications which do not constitute departures from the true spirit and scope of this invention.

[27] Having thus described the invention, what is desired to be protected by Letters Patent shall be presented in claims that will be subsequently appended.

[28] Although the invention has been explained in relation to its preferred embodiment, it is to be understood that many other possible modifications and variations can be made without departing from the spirit and scope of the invention as herein described.

[29] As one of ordinary skill in the art may appreciate, the example system and method described herein can be modified. For example, certain steps can be omitted, certain steps can be carried out concurrently, and other steps can be added. Although particular embodiments of the invention have been described in detail, it is understood that the invention is not limited correspondingly in scope, but includes all changes, modifications and equivalents coming within the spirit and terms of the description herein.

[30] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended description of invention.

[31] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention shall be defined later in claims, and may include other examples that occur to those skilled in the art.
,CLAIMS:1. A system 100 for prediction of power consumption pattern of wearable devices, the system comprising:
a server 115 comprising a communication module for enabling communicable coupling of the server, and a predictive module 120 for predicting power consumption; and
a wearable device 105 capable of tracking one or more of a physical activity, physiological parameters, social media interaction activity and productivity related activity of a wearer, the wearable device 105 being communicably coupled to the server 115 and comprising
a battery to power the wearable device 105,
at least one sensor to measure at least one of the physical activity and the physiological parameters of the wearer,
a processor 105e adapted to collect data pertaining to battery usage due to any of the measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity of the wearer, and
a transceiver to communicably couple the wearable device 105 to the communication module of the server,
wherein the predictive module 120 receives real-time and historical data related to the battery usage due to any of the measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity of the wearer collected by the processor 105e, and
wherein the predictive module determines expected battery consumption of the wearable device to predict the power consumption pattern of the wearable device.
2. The system for prediction of power consumption pattern of wearable devices as claimed in claim 1, wherein the predictive module additionally receives real-time data related to ambient humidity and temperature for predicting the expected battery consumption of the wearable device.
3. The system for prediction of power consumption pattern of wearable devices as claimed in claim 2, wherein the real-time data related to the ambient humidity and temperature is collected by the at least one sensor.
4. The system for prediction of power consumption pattern of wearable devices as claimed in claim 1, wherein the physiological parameters comprise at least one of pulse rate and oxygen saturation level in the blood stream of the user.
5. The system for prediction of power consumption pattern of wearable devices as claimed in claim 1, wherein the historical data related to the battery usage due to any of the measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity pertains to the time of the day when the wearer performed the said activities, the duration for which each of the activities were 7performed and the daily frequency of performance of the said activities.
6. The system for prediction of power consumption pattern of wearable devices as claimed in claim 1, wherein the prediction module 120 comprises
a training data module 125 adapted to receive training data derived from the historical data related to the battery usage due to any of the measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity,
an artificial intelligence module 130 coupled to the training data module 125 to receive the training data and generate the prediction of power consumption pattern of the wearable device 105 by application of regression methods; and
a testing module 135 coupled to the artificial intelligence module 130 to validate the accuracy of the prediction of the artificial intelligence module 130.
7. A method for prediction of power consumption pattern of wearable devices, the method comprising:
collecting real-time data pertaining to battery usage due to any of measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity of a wearer of a wearable device;
providing the collected real-time data to a predictive model trained using historical data related to the battery usage due to any of the measurement of the physical activity and the physiological parameters by the at least one sensor, the social media interaction activity and the productivity related activity of the wearer; and
determining expected battery consumption of the wearable device to predict the power consumption pattern of the wearable device,
wherein the historical data pertains to the time of the day when the wearer performed the said activities, the duration for which each of the activities were performed and the daily frequency of performance of the said activities.
8. The method for prediction of power consumption pattern of wearable devices as claimed in claim 7, wherein collecting real-time data comprises receiving real-time data related to ambient humidity and temperature.