DEVICES, SYSTEMS, AND METHODS TO CREATE CUSTOMIZED MESSAGES BASED ON CONTEXTUAL INFORMATION

1 . A method for creating a customized message to a user, comprising:

receiving a request to generate the customized message to the user;

receiving user data;

retrieving historical health data that correlates with the user data;

generating a contextual prompt for a model, wherein the contextual prompt is based on the user data and the historical health data that correlates with the user data; and

providing the contextual prompt to the model, wherein the contextual prompt causes the model to create the customized message.

2 . The method of claim 1 , wherein the customized message comprises a customized activity suggestion.

3 . The method of claim 2 , wherein the customized activity suggestion comprises an exercise, an exercise length, an intensity level of the exercise, an exercise date, an exercise start time, recommended recovery time, dietary information, or any combination thereof.

4 . The method of claim 1 , wherein the customized message comprises a customized motivational message.

5 . The method of claim 1 , wherein receiving the request to generate the customized message comprises:

receiving the request from a mobile device.

6 . The method of claim 1 , wherein receiving the user data comprises:

receiving the user data from an exercise device.

7 . The method of claim 1 , wherein the user data comprises a training history, a goal, patterns in training, an activity level, injuries, strengths, weaknesses, or motivation information.

8 . The method of claim 7 , wherein the patterns in training comprise a time spent on an activity, a time between activities, preferred weekdays for performing an activity, preferred hours for performing an activity, or any combination thereof.

9 . The method of claim 7 , wherein the training history comprises one or more activities performed by the user.

10 . The method of claim 7 , wherein the strengths, the weaknesses, or both are identified by the user.

11 . The method of claim 7 , wherein the strengths, the weaknesses, or both are automatically identified by an exercise device or a mobile device.

12 . The method of claim 1 , wherein the historical health data comprises exercise programs, behavioral science information, behavioral health science, injury recovery information, or any combination thereof.

13 . The method of claim 1 , wherein generating the contextual prompt comprises:

generating the contextual prompt with a retrieval augmented generation (RAG) system.

14 . The method of claim 1 , wherein the model is a large language model (LLM).

15 . The method of claim 1 , further comprising:

delivering the customized message to the user.

16 . A computing device for facilitating creating a customized message to a user, comprising:

one or more processors and one or more memories, the one or more memories comprising instructions which, when executed by the one or more processors, cause the computing device to:

receive a request to generate the customized message to the user;

receive user data;

retrieve, a historical health data that correlate with the user data;

generate a contextual prompt for a model wherein the contextual prompt is based on the user data and the historical health data that correlates with the user data; and

provide the contextual prompt to the model, wherein the contextual prompt causes the model to create the customized message.

17 . The computing device of claim 16 , wherein the customized message comprises a customized activity suggestion.

18 . The computing device of claim 16 , wherein the historical health data comprises exercise programs, behavioral science information, behavioral health science, injury recovery information, or any combination thereof.

19 . A method for training a model, comprising:

receiving a plurality of historical health data, wherein the plurality of historical health data is divided into plurality of subsets;

providing the plurality of subsets as input for the model, wherein the model includes plurality of parameters;

performing a validation for the model, wherein performing the validation for the model comprises a cross-validation, a consistency check, a physical model evaluation, or any combination thereof;

adjusting one or more of the plurality of parameters to fine-tune the model; and

validating the model when all subsets of the plurality of historical health data match with an output received from the model.

20 . The method of claim 19 , wherein receiving the plurality of historical health data comprises:

preprocessing the plurality of historical health data.