IBM’s invention analyzes fitness activity and provides real-time fitness training

958 Views
Credit: Flickr

A patent application of IBM was published on the United States Patent and Trademark Office website on May 30th 2019 that relates to real-time fitness activity tracking and fitness training. The patent publication is titled “Adaptive fitness training.”

IBM developed an algorithm to receive fitness activity data of the user and recommend changes to the fitness activity while the user is engaged in the activity. These recommendations are provided based on the fitness goals of the user. The invention also forecasts likely results of the recommended changes.

This real-time activity tracking is done using wearable devices like smartwatches or fitness bands.

IBM notes in the patent filing that changing exercise routine and intensity for both strength training and cardiovascular exercise has an added benefit of accelerated fat burning during the same time period as compared to standard low intensity exercises.

Activity tracking devices monitor many exercise characteristics, such as steps, distance, heart rate, and estimated calories burned.

Real-time fitness training

According to an aspect of the IBM’s invention, there is a computer-implemented method, computer program product, and/or system to analyze fitness procedures that perform(s) the following steps (not necessarily in the following order):

(i) Receive input to capture fitness and wellness goal of a user;

(ii) Receive input to capture data from at least one wearable of the user, such as a smartwatch with sensors that is used to capture real-time data and other user information, such as weight;

(iii) Receive input to capture external information, such as studies and social media, to gather information about fitness and wellness;

(iv) Storing listing of fitness and wellness resources available to the user

(v) Storing captured data;

(vi) Analyzing external information with respect to the goal and real-time data of the user and to other data and resources to recommend activity types, wait times between activities, and intensity for activity.

FIG. 2 from the IBM’s patent application shown below is a flowchart showing a first embodiment method performed, at least in part, by the first embodiment system.

FIG. 3 from the IBM’s patent application is a block diagram view of a machine logic (for example, software) portion of the first embodiment system.

Detailed description of the above figures is given below:

Program #300 operates to receive real-time activity data for analysis to determine if the user should change the exercise type, wait duration between exercises, or intensity level to optimize the effectiveness (or increase an effectiveness level) of the current activity for fitness goals and objectives of the user.

Program #300 notifies the user of the changes while the user is engaged in the activity. Program #300 recommends changes to future activities in the fitness plan and changes to the fitness plan, and program #300 forecasts the results of the changes.

FIG. 2 shows flowchart #250 depicting a method according to the present invention. FIG. 3 shows program #300 for performing at least some of the method steps of flowchart #250. This method and associated software will now be discussed, over the course of the following paragraphs, with extensive reference to FIG. 2 (for the method step blocks) and FIG. 3 (for the software blocks).

Processing begins at step S 255, where goal module (“mod”) #305 receives fitness goals of a user. For example, goal mod #305 may receive a goal to lose weight or a goal to increase strength. In this embodiment, goal mod #305 receives a current fitness condition of the user and a goal fitness condition with measurable indicators, which measure the progress of the user.

For example, goal mod #305 may receive a starting weight and a goal weight of the user. In this example, goal mod #305 receives intermediate weights of the user, which indicate progress towards the goal weight. In another example, goal mod #305 receives a current repetition and weight ability of the user and receive a target repetition and weight.

Processing proceeds to step S 260, where plan mod #310 recommends a fitness plan to the user. In this embodiment, plan mod #310 searches online resources for fitness plans based on a defined type, objective, and social sentiment.

Alternatively, a fitness advisor suggests fitness plans to the user. In this embodiment, plan mod #310 utilizes historic activity data correlated with an effectiveness level to rank fitness plans based on likely result. In this embodiment, plan mod #310 recommends a fitness plan based on the ranking. Alternatively, a fitness advisor specifies a fitness plan for the user.

Processing proceeds to step S 265, where activity mod #315 receives fitness activity data. In this embodiment, activity mod #315 receives exercise type, intensity, and duration data, while the user is engaged in the activity.

For example, activity mod #315 receives number of steps taken, distance, floors ascended/descended, and date and time data. In another example, activity mod #315 receives sensor data from a wearable device, including heart rate and/or motion data.

Processing proceeds to step S 270, where analysis mod #320 analyzes the fitness activity data. In this embodiment, analysis mod #320 determines characteristics of the activity data, such as activity type, activity duration, wait time duration, fitness equipment data, and/or fitness intensity.

In this embodiment, analysis mod #320 analyzes the activity data by comparing the fitness goals and current progress with initial fitness data and a pre-defined progress timeline.

In this embodiment, analysis mod #320 determines target values, also referred to as optimized values, based on historic activity data, and analysis mod #320 compares the target values to the current activity data to determine the effectiveness level of the current activity.

Processing proceeds to step S 275, where recommendation mod #325 recommends changes to the fitness activity. In this embodiment, recommendation mod #325 recommends changes to the current fitness activity, while the user is engaged in the activity, to increase the effectiveness level of the activity based on the optimized values.

For example, recommendation mod #325 may recommend an increase/decrease in intensity, a shortening/lengthening of rest times between exercises, or a change of activity type based on the determined effectiveness level of the current activity in step S 270.

Processing proceeds to step S 280, where forecast mod #330 recommends changes to the fitness plan and forecasts likely results. In this embodiment, forecast mod #330 compares measurable indicators of the current activity to initial fitness data to determine the effectiveness level of the current activity.

In this embodiment, forecast mod #330 forecasts the likely most effective changes to the fitness plan based on determined effectiveness level of activities during a pre-defined period. For example, forecast mod #330 may recommend changes to future activities in the fitness plan, or forecast mod #330 may recommend alternative activities to be completed as part of a modified fitness plan.

This US patent publication 20190160333 was initially filed on November 28th, 2017.

Let us know your thoughts in the comments section.   

Subscribe to our newsletter to stay updated on latest inventions.

2+
Spread the word
  • 1
    Share

Leave a Reply

Your email address will not be published. Required fields are marked *