Search

US-20260128155-A1 - WELLNESS PRACTICE RECOMMENDATION

US20260128155A1US 20260128155 A1US20260128155 A1US 20260128155A1US-20260128155-A1

Abstract

A system and method for generating personalized wellness recommendations in real time, based on a user's emotional state, contextual situation, and interaction history. The system leverages a large language model (LLM) integrated with an emotion ontology based on the Wheel of Emotion to analyze both user-submitted input and historical behavior. In some embodiments, the system extracts emotional and situational cues from natural language input and recommends wellness practices that match specified preferences including emotional impact, guidance level, and duration. A fallback prioritization logic is applied to ensure relevant results even when exact matches are unavailable. The system may also generate a compassionate message aligned with the user's inferred emotional state and return structured output. In automated embodiments, the system selects a weighted mix of familiar and exploratory content. The architecture includes preference drift tracking, confidence-based filtering, and memory-optimized re-ranking to improve emotional targeting and user engagement.

Inventors

  • Anastasia Filipenko

Assignees

  • Anastasia Filipenko

Dates

Publication Date
20260507
Application Date
20251101

Claims (20)

  1. 1 . A method for providing meditation recommendations, the method comprising: receiving, via a sign-up module, user profile data and storing the user profile data in a user database; receiving, via an input module, request data comprising user text or voice describing a current emotional state and an available time duration; accessing a meditation database storing records tagged with at least one emotion category from a Wheel-of-Emotion framework, a desired outcome, a guidance level, and a duration; executing a processing pipeline in which an LLM engine applies an input analysis module, using an NLP engine and the Wheel-of-Emotion framework, to the request data to generate one emotional-state classification; filtering, by a meditation matching module, the meditation records to those whose stored emotion tag equals the emotional-state classification; applying, by the meditation matching module, a fixed order of precedence: current emotional state, then desired outcome, then guidance level, then available time; performing temporal adjustment, by the meditation matching module, by first selecting meditations within a threshold of the available time, then—if available—selecting shorter alternatives, and then—if available—selecting meditations closest to but exceeding the available time; presenting, via a graphical user interface (GUI), a compassionate message and multiple recommendation cards each with at least a title, guidance level, duration, and Play and Try again controls; replacing, by the GUI, a previously presented set of the recommendation cards with an updated set of the recommendation cards in the same view when the LLM engine outputs updated recommendation data; in an automated mode, generating, by a personalized recommendation module, recommendations using stored user interactions in a historical database, including a mix of familiar and exploratory meditations according to predetermined percentages; recording, by a feedback module, skips, selections, completions, and ratings in the historical database and providing the recorded feedback to the LLM engine; and responsive to any of the following events: (a) a change to the available time, (b) a clarification of the emotional state, (c) a Try again request, or (d) a skip input received via the GUI, automatically, during the same user session, recomputing, by the LLM engine, recommendations by re-applying the fixed order of precedence and the temporal-adjustment steps, and updating the recommendations presented on the GUI.
  2. 2 . The method of claim 1 , wherein the stored records are further tagged with a meditation name, a meditation description, an emotional impact, and associated wellness goals.
  3. 3 . The method of claim 1 , further comprising in the automated mode generating, by the personalized recommendation module without real-time user input, recommendations based on: the user's previous emotional states within a predetermined time period, the user's interests, the user's preference for guidance, the user's wellness goals, and other user-specific parameters derived from the historical database or user data.
  4. 4 . The method of claim 1 , further comprising: receiving, by the GUI, a user swipe-based interaction to allow the user to indicate interest or disinterest in personalized meditation recommendations; and recording, by an activity tracking module, user responses to the personalized recommendations in the historical database for future analysis.
  5. 5 . The method of claim 1 , further comprising processing the request data, by the LLM engine, using natural language processing to extract the contextual input phrases such as the attributes for recommendation generation.
  6. 6 . The method of claim 1 , wherein analyzing the request data comprises: using a large language model to semantically interpret user input, generate a descriptive emotional label, and programmatically map the label to a predefined emotion category of the Wheel-of-Emotion framework.
  7. 7 . The method of claim 1 , wherein the recommendation module is configured to apply a weighted selection strategy to select a first proportion of meditation practices matching the user's prior interests, guidance level, goals, or emotional state, and a second proportion of meditation practices that differ from prior selections, such that the combined set of recommendations includes both familiar and exploratory content.
  8. 8 . A meditation recommendation system comprising: a sign-up module to receive user profile data; a user database configured to store the user profile data; an input module to receive request data comprising user text or voice describing a current emotional state and an available time; a meditation database storing records tagged with at least one emotion category from a Wheel-of-Emotion taxonomy, a desired outcome, a guidance level, and a duration; an LLM engine comprising: an input analysis module configured to apply an NLP engine and the Wheel-of-Emotion taxonomy to the request data to produce an emotional-state classification; and a meditation matching module configured to: (i) filter meditations to those whose stored emotion tag equals the emotional-state classification; (ii) apply a fixed order of precedence: current emotional state, then desired outcome, then guidance level, then available time, and (iii) perform temporal adjustment by first selecting meditations within a threshold of the available time, then—if available-shorter alternatives, and then—if available-meditations closest to but exceeding the available time; a graphical user interface (“GUI”) configured to present a compassionate message and multiple recommendation cards each with at least a title, guidance level, duration, and Play and Try again controls; wherein the GUI replaces a previously presented set of the recommendation cards with an updated set of the recommendation cards in the same view when the LLM engine outputs updated recommendation data; a historical database; a personalized recommendation module configured to generate automated recommendations using user interactions stored in the historical database; and a feedback module configured to record skips, selections, completions, and ratings in the historical database and to provide the feedback to the LLM engine; wherein, responsive to any of the following events (a) a change to the available time, (b) a clarification of the emotional state, (c) a Try again request, or (d) a skip input received via the GUI, the LLM engine automatically, during the same user session, recomputes recommendations by re-applying the prioritization order and the temporal-adjustment steps and updates the recommendations presented on the GUI.
  9. 9 . The system of claim 8 , wherein the records stored in the meditation database are further tagged with an emotional impact, a practice duration, and associated wellness goals.
  10. 10 . The system of claim 8 , wherein the personalized recommendation module is further configured to generate recommendations based on a mix of familiar and exploratory meditations according to predetermined percentages.
  11. 11 . The system of claim 8 , wherein the LLM is further configured to analyze the historical database, and the user data; and to automatically generate personalized meditation recommendations without real-time user input based on: the user's previous emotional states within a predetermined time period, the user's interests, the user's preference for guidance, the user's wellness goals, and other user-specific parameters derived from the historical database or user data.
  12. 12 . The system of claim 11 , wherein the GUI is further configured to facilitate swipe-based interaction by the user to indicate interest or disinterest in personalized meditation recommendations; and the system further comprising an activity tracking module configured to record user responses to the personalized meditation recommendations in the historical database for future analysis.
  13. 13 . The system of claim 8 , wherein the input analysis module is further configured to process the request data using natural language processing to extract the contextual input phrases such as the attributes for recommendation generation.
  14. 14 . The system of claim 8 , wherein the input analysis module is configured to use the LLM to: interpret user input, generate a descriptive emotion label, and map the emotion label to a corresponding emotion category of the Wheel-of-Emotion framework.
  15. 15 . The system of claim 8 , wherein the personalized recommendation module is configured to generate a weighted set of recommendations comprising a majority portion selected from previously preferred meditation characteristics and a minority portion selected from meditation practices differing from the user's historical preferences, based on a predetermined weight distribution.
  16. 16 . The system of claim 8 , wherein the personalized recommendation module is further configured to: receive a natural language input from a user; analyze the input using the LLM to determine the user's emotional state, a contextual situation, and one or more preferences relating to emotional impact, guidance level, or time available; filter the meditation database to identify candidate practices matching the extracted parameters; implement a fallback hierarchy that selects meditations based on a priority order of emotional relevance, duration fit, and then guidance level; generate a compassion-oriented message aligned with the user's inferred emotional state; and return a structured output comprising the generated message and no more than three recommended meditation practices.
  17. 17 . A method of providing meditation recommendations, the method comprising: receiving a natural language user input; analyzing the input using a large language model (LLM) to extract an emotional state, a contextual situation, and at least one preference selected from: desired emotional impact, guidance level, or duration; identifying a set of meditation practices from a database that match at least one or more of the extracted parameters; applying a fallback prioritization logic if no exact match is found, wherein emotional state and duration are prioritized over guidance level; generating a personalized text message responsive to the extracted emotional state; and returning an output comprising the generated message and a list of one or more selected meditation practices.
  18. 18 . The method of claim 17 , wherein the LLM is constrained to use the Wheel of Emotion framework to extract the emotional state.
  19. 19 . The method of claim 17 , wherein the LLM is configured to use, at least in part, an NLP engine to extract the emotional state.
  20. 20 . The method of claim 17 , wherein identifying a set of meditation practices further comprises using, at least in part, a historical database having information associated with previous meditation recommendations to the user.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63/715,519, filed on Nov. 2, 2024, and titled “System for Wellness Practice Recommendation Using Large Language Models and Method Thereof,” the entire disclosure of which is incorporated herein by reference. FIELD OF THE INVENTION The present invention relates to the field of artificial intelligence (AI)-based wellness applications, and more particularly to a system for wellness practice recommendation using large language models and a method thereof. BACKGROUND OF THE INVENTION Conventional wellness applications, such as Headspace and Calm, offer personalized meditation and mindfulness recommendations based on user inputs during on-boarding, meditation history, and predefined practice pathways. These applications use algorithms that categorize users' preferences based on factors including practice type, duration, and popularity. However, they lack in providing dynamic, real-time personalization that adapts to the user's evolving emotional state or specific feedback. Additional drawbacks associated with similar applications are as follows: While existing wellness applications do offer personalized recommendations, the level of personalization might not be as nuanced as suggested. Their algorithms primarily use basic data points e.g., meditation history, session duration, rather than more sophisticated inputs like real-time emotional state or detailed psychological profiling. For example, when a user selects a practice, future recommendations are often derived from preset categories, which may not evolve with the user's emotional or mental state over time. This one-size-fits-all approach can lead to disengagement, as users may feel that the content lacks personal relevance. As a result, the user engagement diminishes, especially when the app fails to provide interactive feedback that adjusts in real time based on the user's emotional responses. Further, these apps often rely on predefined practice pathways and user segmentation rather than dynamically responding to changing user states. For example, a user might receive recommendations based on their general preferences, but the app might not adapt immediately if the user's stress or mood changes throughout the day. The personalization offered by these conventional systems is surface-level, typically confined to the initial user inputs without considering the user's present emotional states. These systems do not incorporate user feedback about the emotional impact of past practices, the influence of specific meditation guides or authors, or preferences as they evolve over time. This lack of emotional responsiveness can result in generic recommendations, thus reducing the effectiveness of the wellness experience for the user. Although some applications use machine learning, many of the recommendations are still driven by simpler logic-based algorithms or user journey frameworks. This means that they may not leverage complex AI models that could provide deeper personalization. Additionally, users are often overwhelmed by the abundance of available options within these wellness apps. This leads to decision fatigue, as the burden of manually selecting from long lists of meditation practices can be both time-consuming and frustrating. This is especially problematic for users seeking immediate emotional relief or mindfulness guidance, as the process of finding suitable content detracts from the overall experience. Therefore, there is a need for a solution that integrates a real-time emotional analysis system using large language models while allowing for dynamic adaptation and real-time, personalized recommendations of wellness and meditation practices. Further, by continuously assessing the user's emotional feedback, a system should facilitate offering recommendations based on user's current emotional state, reducing decision fatigue, and enhancing user engagement. BRIEF SUMMARY OF THE INVENTION It is an object of the present invention to provide a wellness recommendation system that dynamically adapts to a user's emotional state using real-time semantic interpretation performed by a large language model (LLM). It is another object of the present invention to provide personalized meditation recommendations based on multiple attributes, including emotional state, duration availability, wellness goals and guidance preferences, while continuously refining the system through user feedback. It is yet another object of the present invention to reduce decision fatigue by automating wellness recommendations based on historical data and emotional patterns and user preferences, without requiring the user to choose from a vast array of content. It is an object of the present invention to improve the accuracy and relevance of wellness recommendations over time by recording and analyzing user activity, including feedback and meditation preferences, to train t