Claims:1. A system (10) to track and monitor one or more human activities, wherein the system (10) comprises:
one or more processors (20);
an activity input module (30) operable by the one or more processors (20), and configured to receive a plurality of inputs from a plurality of sources;
an activity processing module (40) operable by the one or more processors (20), and configured to:
create a plurality of processing models for the corresponding one or more human activities, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof;
process the plurality of inputs using the at least one of the plurality of processing models; and
analyse a plurality of processed inputs for monitoring the one or more human activities of a user,
wherein the plurality of processing models is configured to learn from at least one of historic data, real-time data, or a combination thereof to optimize the analysis of the plurality of processed inputs;
an activity training module (50) operable by the one or more processors (20), and configured to:
generate at least one feedback for the corresponding one or more human activities to enable training for the user;
customize the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof; and
create a database to store the at least one notification, at least one customized notification, or a combination thereof, to enable the user to access the database at any interval of time;
a source monitoring module (60) operable by the one or more processors (20), and configured to:
create one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources; and
generate a correction factor for each of the one or more monitoring models to track and monitor at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time.
2. The system (10) as claimed in claim 1, wherein the one or more human activities comprises one of exercises, postures, gaming, physiotherapy or yoga.
3. The system (10) as claimed in claim 1, wherein the plurality of sources comprises at least one of a heatmap, a camera, one or more wearable devices, historic data, a computing device, or a combination thereof.
4. The system (10) as claimed in claim 1, wherein the plurality of processing models comprises a plurality of micro processing models using one of an artificial intelligence technique, a machine learning technique, or a combination thereof.
5. The system (10) as claimed in claim 1, wherein the at least one behavior corresponds to deterioration or aging of the plurality of sources.
6. The system (10) as claimed in claim 1, wherein the training of the user corresponds to training for one of strength, flexibility, balance, or a combination thereof for the user.
7. A method for tracking and monitoring one or more human activities, wherein the method comprises:
receiving, by an activity input model, a plurality of activity inputs from a plurality of sources;
creating, by an activity processing module, a plurality of processing models for the corresponding one or more human activities, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof;
processing, by the activity processing module, the plurality of inputs using the at least one of the plurality of processing models;
analysing, by the activity processing module, a plurality of processed inputs for monitoring the one or more human activities of a user;
generating, by an activity training module, at least one feedback for the corresponding one or more human activities to enable training for the user;
customizing, by the activity training module, the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof;
creating, by the activity training module, a database for storing the at least one notification, at least one customized notification, or a combination thereof, for enabling the user to access the database at any interval of time;
creating, by a source monitoring module, one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources; and
generating, by the source monitoring module, a correction factor for each of the one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time.
8. The method as claimed in claim 7, wherein tracking and monitoring of the one or more human activities comprises tracking and monitoring one of exercises, postures, gaming, physiotherapy or yoga.
9. The method as claimed in claim 7, wherein receiving the plurality of activity inputs from the plurality of sources comprises receiving the plurality of activity inputs from at least one of a heatmap, a camera, one or more wearable devices, historic data, a computing device, or a combination thereof.
10. The method as claimed in claim 7, wherein creating the plurality of processing models comprises creating a plurality of micro processing models using one of an artificial intelligence technique, a machine learning technique, or a combination thereof.

Dated this 26th day of February 2021

Signature

Harish Naidu
Patent Agent (IN/PA-2896)
Agent for the Applicant

, Description:FIELD OF INVENTION
[0001] Embodiments of a present disclosure relate to tracking of human activities such as physical activities, and more particularly, to a system and method to track and monitor to generate feedback and provide training.
BACKGROUND
[0002] Human activities are defined as are the various actions for recreation, living, or necessity done by people. The activities may include leisure, entertainment, industry, recreation, entertainment, healthcare, war, exercise, or the like. One such exercise may include one of yoga, gym, gymnastic, Pilates and the like. To reach the proficiency of these activities, tracking and monitoring of the same is at most important. In a conventional approach, the activities are viewed by a trainer or a professional physically, and the trainer or a professional is expected to train a user performing the activities. In such approach, due to the interference of the human, the approach may be prone to errors, and may lack efficiency. Also, the monitoring and training in such approaches cannot happen in absence of the professional or the trainer.
[0003] Hence, there is a need for an improved system and method to track and monitor to generate feedback and provide training.
BRIEF DESCRIPTION
[0004] In accordance with one embodiment of the disclosure, a system to track and monitor one or more human activities is provided. The system includes one or more processors. The system also includes an activity input module configured to receive a plurality of inputs from a plurality of sources. The system also includes an activity processing module configured to create a plurality of processing models for the corresponding to one or more human activities, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof. The activity processing module is also configured to process the plurality of inputs using the at least one of the plurality of processing models. The activity processing module is also configured to analyse a plurality of raw or processed inputs for monitoring the one or more human activities of a user. The plurality of processing models is configured to learn from at least one of historic data, real-time data, or a combination thereof to optimize the analysis of the plurality of inputs. The system also includes an activity training module configured to generate at least one feedback for the corresponding one or more human activities to enable training for the user. The activity training module is also configured to customize the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof. The activity training module is also configured to create a database to store the at least one notification, at least one customized notification, or a combination thereof, to enable the user to access the database at any interval of time. The system also includes a source monitoring module configured to create one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources. The source monitoring module is also configured to generate a correction factor for each of the one or more monitoring models to track and monitor at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time.
[0005] In accordance with another embodiment, a method for tracking and monitoring one or more human activities is provides. The method includes receiving a plurality of inputs from a plurality of sources. The method also includes creating a plurality of processing models for the corresponding one or more human activities, using one of an artificial intelligence technique, a machine learning technique, a mathematical algorithm, a mathematical formula or a combination thereof. The method also includes processing the plurality of inputs using the at least one of the plurality of processing models. The method also includes analysing a plurality of raw or processed inputs for monitoring the one or more human activities of a user. The method also includes generating at least one feedback for the corresponding one or more human activities to enable training for the user. The method also includes customizing the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof. The method also includes creating a database for storing the at least one notification, at least one customized notification, or a combination thereof, for enabling the user to access the database at any interval of time. The method also includes creating one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources. The method also includes generating a correction factor for each of the one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time.
[0006] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF THE DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0007] FIG. 1 is a block diagram representation of a system to track and monitor one or more human activities in accordance with an embodiment of the present disclosure;
[0001] FIG. 2 is a block diagram representation of an exemplary embodiment of the system to track and monitor exercise posture of a user of FIG. 1 in accordance with an embodiment of the present disclosure;
[0002] FIG. 3 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure; and
[0008] FIG. 4a and FIG. 4b are flow charts representing steps involved in a method for tracking and monitoring one or more human activities in accordance with an embodiment of the present disclosure.
[0009] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0010] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0011] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0012] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0013] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0014] Embodiments of the present disclosure relate to a system and method for tracking and monitoring one or more human activities. As used herein, the term “activities” is defined as is any bodily activity that enhances or maintains physical fitness and overall health and wellness of the user. In one embodiment, the one or more human activities may include one of exercises, such as gym, gymnastic, or the like; postures, gaming, physiotherapy, yoga, or the like. In such embodiment, the one or more human activities may be performed at a specific location, in any location, one a pre-defined equipment such as a mat, or the like. The system may assist the user in tracking, monitoring and guiding the user while performing the exercise. In one specific embodiment, the one or more human activities of the user may be performed on a digital mat such as a digital yoga mat, or the like.
[0015] FIG. 1 is a block diagram representation of a system (10) to track and monitor one or more human activities in accordance with an embodiment of the present disclosure. The system (10) includes one or more processors (20). The system (10) also includes an activity input module (30). The activity input module (30) is configured to receive a plurality of inputs from a plurality of sources. In one embodiment, the plurality of inputs may include data associated to the one or more human activities performed by the user either in real time, or at a specific time interval.
[0016] In one exemplary embodiment, the plurality of sources may include at least one of a heatmap, a camera, one or more wearable devices, historic data, a computing device, or a combination thereof, or the like. In such embodiments, the plurality of inputs may be retrieved from the corresponding one or more sources in real time or from a storage unit upon being stored.
[0017] More specifically, the user may be associated to the corresponding plurality of sources, which enable the one or more sources to track the one or more human activities performed by the user. For example, the wearable device may track the number of steps walked by the user in an entire day. In one specific embodiment, the monitored data may be stored in the storage unit associated to the corresponding plurality of sources.
[0018] Furthermore, the system (10) includes an activity processing module (40) configured to create a plurality of processing models for the corresponding one or more human activities, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof. In one embodiment, the plurality of processing models may correspond to a plurality of micro processing models, a plurality of mathematical models, or a combination thereof, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof. As used herein, the term “artificial intelligence” refers to sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals, such as visual perception, speech recognition, decision-making, and translation between languages. Also, the term “machine learning” refers to an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly program. In one exemplary embodiment, the technique may include a mathematical, a computational or a combination thereof. The activity specific models, the micro models, or a combination may consume lesser resources and may be faster in performance. Hereafter the term model also encompasses such activity or task specific micro models using artificial intelligence, machine learning technique, or the like.
[0019] More specifically, the activity processing module (40) may create the corresponding plurality of models for a specific session or a specific purpose associated to the corresponding one or more human activities. For example, an ML model may be created by the activity processing module (40) to process and analyse the number of steps walked by the user each day, further to which the model may analyse if the performed activity is rightly done by the user.
[0020] The activity processing module (40) is also configured to process the plurality of inputs using the at least one of the plurality of processing models. In one exemplary embodiment, each of the plurality of processing models may process the plurality of inputs based on a set of pre-defined instruction. For example, the activity processing module (40) on receiving the data from the wearable device may process the data to extract at least one of the number of steps walked by the user per day, heart rate of the user, blood pressure of the user, or the like. These data may be processed upon being instructed by the corresponding plurality of processing model. More specifically, the activity processing module (40) may create a first processing model for processing data associated to health conditions of the user, a second processing model to determine the physical activities performed by the user. Similarly, the activity processing module (40) may create multiple models to process multiple different data associated to the one or more human activities of the user. For another example, the activity processing module (40) may create a behavioral model to process behavior of the user while the user may be playing a game in a corresponding computing device. Such processing may be achieved using one of the AI technique, the ML technique or the like.
[0021] Furthermore, the activity processing module (40) is also configured to analyse a plurality of processed inputs for monitoring the one or more human activities of a user. Referring to the above-mentioned embodiment, the activity processing module (40) with the help of the corresponding processing models, may analyse if the one or more activities being performed by the user is right and meeting all the requirements. In such embodiments, the analysis may be performed based on the pre-defined set of instructions. For example, the activity processing module (40) may analyse if the number of steps walked by the user is sufficient to maintain a good health for the user based on the pre-defined health condition of the user. Here the pre-defined health conditions of the user is associated to the pre-defined instructions, which may be retrieved and may be stored in the storage unit of the corresponding plurality of sources.
[0022] Consequently, the plurality of processing models is configured to learn from at least one of historic data, real-time data, or a combination thereof to optimize the analysis of the plurality of processed inputs. In one embodiment, the historic data may be associated to the pre-defined set of instructions. The real-time data may be associated to the data retrieved by the corresponding plurality of sources in real time as and when the user is performing the one or more human activities. More specifically, the plurality of processing models through the ML technique and the AI technique, learns to enhance the analysis process.
[0023] In one exemplary embodiment, the activity processing module (40) may be further configured to generate an analysis result for the performed analysis on the plurality of inputs received by the plurality of sources. The analysis result may be in sync with the pre-stored instruction.
[0024] The system (10) further includes an activity training module (50) which is configured to generate at least one feedback for the corresponding one or more human activities to enable training for the user. In one embodiment, the at least one feedback may include one of a session in any of a multimedia form, a notification, or the like. In one exemplary embodiment, based on the analysis result, if the result notifies any scope of improvisation of the one or more human activities of the user, the same may be conveyed for the user in the from of training, which may be held in any of desired form. In such embodiment, the desired form may be chosen by the user, the professional or the trainer, the system (10), or the combination thereof. In one exemplary embodiment, training of the user may correspond to training for one of strength, flexibility, balance, or a combination thereof for the user. In another exemplary embodiment, training of the user may correspond to assessment training of the user, which may further include as mood, calmness, personalized instruction, and the like associated to the user.
[0025] The activity training module (50) is also configured to customize the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof. In one embodiment, a form of the at least one feedback, content of the at least one feedback, or the like may be chosen by said entities based on requirement, analysis result, or the like.
[0026] The activity training module (50) is further configured to create a database to store the at least one notification, at least one customized notification, or a combination thereof, to enable the user to access the database at any interval of time. More specifically, the activity training module (50) may store all the data within the database. In one embodiment, the database may be stored in the storage unit associated to the corresponding plurality of sources. In such embodiment, the storage unit may be a local storage unit, a remote storage unit such as cloud storage, or a combination thereof.
[0027] Furthermore, the system (10) includes a source monitoring module (60) configured to create one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources. In one embodiment, the plurality of sources may be operatively coupled with a plurality of sensors, actuators, or the like which may be configured to extract electrical signals which may be generated by the corresponding plurality of sources. These extracted electrical signals may be further processed and analysed by the corresponding one or more monitoring models. In one specific embodiment, the one or more monitoring models may be created using one of the ML technique, the AI technique, or a combination thereof.
[0028] For example, in the wearable device which the user may wear to monitor the movement of the user may include one or more inertial sensors. For these inertial sensors, a corresponding sensor monitoring model may be created by the source monitoring module (60) using a corresponding technique. On creating the sensor model, the source monitoring module (60) simultaneously retrieves data from the one or more inertial sensors and may analyse a sensitivity performance of the same using a behavior pattern of historic data of the one or more inertial sensors. On analysing the same, the source monitoring module (60) with the help of the sensor model analyses that the one or more inertial sensors may have lost the power to sense the most sensitive signal, and may require replacement of the same within the wearable device. The said requirement may be generated as a notification for the user on the corresponding computing device which may be synced with the wearable device.
[0029] The source monitoring module (60) is also configured to generate a correction factor for each of the one or more monitoring models to track and monitor at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time. In one embodiment, the correction factor may refer to a range of threshold values which may be considered while analysing each of the plurality of sensors. In one exemplary embodiment, the behavior of the corresponding plurality of sensors may correspond to deterioration or aging of the plurality of sources.
[0030] In one embodiment, the customization may be based on multiple or subsequent data frame(s) or sets or snapshots from the input sources with respect to the difference between the overall confidence factor of one of prediction, detection, identification, decision from a current or one only data frame or set or snapshot from the input sources and an acceptable threshold value. ‘Confidence factor’ is defined a term used in artificial intelligence for dealing with uncertainty. Accordingly, a set threshold value of say about 95% confidence factor allows only a lesser, which is about 5% of uncertainty, than the set threshold value of say about 85% which is more lenient in accepting the prediction or detection or identification output from the particular model for the particular application.
[0031] In one exemplary embodiment, the system (10) may further include an offline processing module. The offline processing module may be configured to analyse and monitor the one or more recorded data of the human activities of the user. More specifically, the offline execution of the processing models or Mathematical models using the recorded or archived data may be carried out on the cloud storage or, dedicated or special local systems, whereas the real-time execution of the micro models as well as the mathematical models may be carried out on the individual and specific processing cores of the local computing device.
[0032] In one exemplary embodiment, the mathematical models may be used for the purposes such as image processing of the CV part of an application or computation of the performance of the physical activity or to ensemble the outputs of the performance models or computation of the ‘analysis result’ using one or more co-ordinates such as weights or coefficients, or the like.
[0033] FIG. 2 is a block diagram representation of an exemplary embodiment of the system (70) to track and monitor exercise posture of a user (80) on a yoga mat (90) of FIG. 1 in accordance with an embodiment of the present disclosure. The user ‘A’ (80) is performing yoga on the yoga mat (90). The user ‘A’ (80) is also wearing a wearable wristwatch (100) to capture data associated to multiple position of the yoga postured of the user on the yoga mat (90). It should be noted that the yoga mat (90) may include a plurality of pressure sensors and position sensors to capture data associated to amount of pressure applied by the user A (80) on each of multiple hands and legs while performing the yoga on the yoga mat (90); position with respect to angle of degree of each of the multiple hands and legs of the user A (80), are captured by the corresponding sensors. Also, at subsequently, data from the wearable wristwatch (100) which may be associated to movement of the user A’s (80) hand may be captured. Further, the captured data from the one or more sensors and the wearable wristwatch (100) may be transmitted to an activity input module (30).
[0034] On the other hand, the system (70) via an activity processing module (40) (which may be operable by one or more processors (20)) may create a position processing model using an ML technique. The position processing model may be associated to the yoga postured performed by the user A (80). Using these position processing model, the data from the one or more sensors and the wearable wristwatch (100) may be processed and analysed to determine an accuracy of the postures of the yoga positions. In a situation, when the user A (80) performs ‘Suryanamaskar’ with wrong postures, an activity training module (50) may generate a feedback notifying the user A (80) that the posture if not as it needs to be performed. On receiving the feedback, the activity training module (50) also generated a training session which may include one or more videos of experts performing the ‘Suryanamaskar’. The one or more videos may be played on the user device (110) which may be operatively coupled the yoga mat (90) and the wearable wristwatch (100), through which the user A (80) gets trained by the system (70) and to improve the performance.
[0035] In addition, a source monitoring module (60) which may be operatively coupled to each of the yoga mat (90) and the wearable wristwatch (100) may monitor durability of the one or more sensors and one or more electrical components of the wearable wristwatch (100). The monitored data may be notified for the user A (80) on the user device (110).
[0036] Furthermore, the system (70), the one or more processors (20), the activity input module (30), the activity processing module (40), the activity training module (50) and a source monitoring module (60) of FIG. 2 are substantially similar to a system (10), one or more processors (20), an activity input module (30), an activity processing module (40), an activity training module (50) and a source monitoring module (60) of FIG. 1.
[0001] FIG. 3 is a block diagram of a computer or a server (120) in accordance with an embodiment of the present disclosure. The server (120) includes processor(s) (130), and memory (140) coupled to the processor(s) (130) through a bus (150).
[0002] The processor(s) (130), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0037] The memory (140) includes a plurality of subsystems stored in the form of executable program which instructs the processor (130) to perform the method steps illustrated in FIG. 4a and FIG. 4b. The memory (140) has following modules: an activity input module (30), an activity processing module (40), an activity training module (50) and a source monitoring module (60).
[0038] The activity input module (30) is configured to receive a plurality of inputs from a plurality of sources.
[0039] The activity processing module (40) is configured to create a plurality of processing models for the corresponding one or more human activities; to process the plurality of inputs using the at least one of the plurality of processing models and to analyse a plurality of processed inputs for monitoring the one or more human activities of a user.
[0040] The activity training module (50) is configured to generate at least one feedback for the corresponding one or more human activities to enable training for the user; to customize the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof and to create a database to store the at least one notification, at least one customized notification, or a combination thereof, to enable the user to access the database at any interval of time.
[0041] The source monitoring module (60) is configured to create one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources and to generate a correction factor for each of the one or more monitoring models to track and monitor at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time.
[0042] Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s).
[0043] FIG. 4a and FIG. 4b are flow charts representing steps involved in a method (160) for tracking and monitoring one or more human activities in accordance with an embodiment of the present disclosure. The method (160) includes receiving a plurality of inputs from a plurality of sources in step 170. In one embodiment, receiving the plurality of inputs may include receiving the plurality of inputs by an activity input model. In one exemplary embodiment, receiving the plurality of inputs from the plurality of sources may include receiving the plurality of activity inputs from at least one of a heatmap, a camera, one or more wearable devices, historic data, a computing device, or a combination thereof.
[0044] The method (160) also includes creating a plurality of processing models for the corresponding one or more human activities, using one of an artificial intelligence technique, a machine learning technique, or a combination thereof in step 180. In one embodiment, creating the plurality of processing models may include creating the plurality of processing models by an activity processing module. In one exemplary embodiment, creating the plurality of processing models may include creating a plurality of micro processing models using one of an artificial intelligence technique, a machine learning technique, or a combination thereof.
[0045] Furthermore, the method (160) includes processing the plurality of inputs using the at least one of the plurality of processing models in step 190. In one embodiment, processing the plurality of inputs may include processing the plurality of inputs by the activity processing module.
[0046] The method (160) also includes analysing a plurality of processed inputs for monitoring the one or more human activities of a user in step 200. In one embodiment, analysing the plurality of processed inputs may include analysing the plurality of processed inputs by the activity processing module. The method (160) also includes generating at least one feedback for the corresponding one or more human activities to enable training for the user in step 210. In one embodiment, generating the at least one feedback may include generating the at least one feedback by an activity training module.
[0047] The method (160) also includes customizing the at least one feedback upon receiving a customization input from one of the user, a trained entity, or a combination thereof in step 220. In one embodiment, customizing the at least one feedback may include customizing the at least one feedback by the activity training module.
[0048] The method (160) also includes creating a database for storing the at least one notification, at least one customized notification, or a combination thereof, for enabling the user to access the database at any interval of time in step 230. In one embodiment, creating the database may include creating the database by the activity training module.
[0049] Furthermore, the method (160) includes creating one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources in step 240. In one embodiment, creating the one or more monitoring models may include creating the one or more monitoring models by a source monitoring module.
[0050] The method (160) also includes generating a correction factor for each of the one or more monitoring models for tracking and monitoring at least one behavior of the corresponding plurality of sources to enhance the tracking and monitoring of the one or more human activities of the user in real time in step 250. In one embodiment, generating the correction factor may include generating the correction factor by the source monitoring module.
[0051] It should be noted that all the supporting embodiments of FIG. 4a and FIG. 4b are substantially similar to those explained in FIG. 1, henceforth all the embodiments disclosed in FIG. 1 holds good to corresponding feature, steps and elements of FIG. 4a and FIG. 4b.
[0052] Various embodiments of the present disclosure enable the system to monitor, train, guide and provide feedback for the user for the one or more activities performed by the user. Also, the system monitors the varying parameters of the user while performing the activities both in online mode and also offline mode, which makes the system more accurate and more reliable.
[0053] In addition, the system combines or ensemble all the results for the holistic tracking of human activities for training purposes, or the like. Further, use of several ‘micro’ AI or ML as well as mathematical models will enable leveraging of the multiple and diverse cores that are available on the present-day ‘Edge’ compute systems. Whereas elements of attention or interest are different for yoga practice as against physiotherapy!! And, the ‘expert’ who would analyze the data, review the outputs of the models and thus help in tuning of the on the cloud models.
[0054] Furthermore, the system necessitates use of off-line as well as real-time models and the relevant data which may be recorded and is in real-time.
[0055] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0056] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.