Systems and methods for a context aware conversational agent for journaling based on machine learning

1. A method for context aware journaling comprising:

generating, by a software conversational agent, a journaling model based on a first real-time activity data, and engagement data associated with one or more tasks of a user, wherein the journaling, model uses machine-learning to:

identify a preconfigured context pattern on associated with the first real-time activity data, and

map performance associated with the one or more tasks based at least on the engagement data;

determining a preferred interaction mode from a plurality of interaction modes based on comparing a second real-time activity data to the identified context pattern;

generating prompts based on the journaling model and the determined preferred interaction mode, the prompts comprising a series of prompts generated based on topics selected by the journaling model, each prompt is generated based on a user sentiment indicator from the journaling model and content of each prompt is adapted based on the determined preferred interaction mode;

adaptively providing one or more of the prompts to gather an additional engagement data on the selected topic based on the identified context pattern in view of the second real-time activity data, wherein adaptively providing the prompt comprises an autonomous interaction to initiate feedback from the user on the topic selected by the journaling model using the determined preferred interaction mode; and

updating a set of journal entries of the journaling model for the selected topic based on receiving the additional engagement data,

wherein to map performance associated with one or more tasks comprises:

analyzing the engagement data of the user associated with the one or more tasks to identify content topics and the user sentiment indicators for each of the one or more tasks;

associating each of the one or more tasks with at least one content topic;

tracking the user sentiment indicators through each of the one or MOM tasks for each respective topic; and

mapping performance for each respective topic based at least on changes of the tracked user sentiment indicators from the additional engagement data.

2. The method of claim 1 , wherein adaptively providing the prompt comprise an autonomous interaction using at least one of a chat-bot an audio agent, and a virtual avatar.

3. The method of claim 1 , wherein the additional engagement data comprising self-reflection on a goal associated with one or more tasks.

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

selecting a topic from the journaling model; and

determining a question using a natural language processor based on a preferred interaction mode.

5. The method of claim 1 , further comprising at least one additional prompt based on the additional engagement data.

6. The method of claim 1 , wherein engagement data comprises feedback associated with the one or more tasks and wherein adaptively providing the prompt comprises:

gathering the second real-time activity data from a location of the user; and

initiating the autonomous interaction with the user in the determined preferred interaction mode.

7. The method of claim 1 , wherein adaptively providing the prompt is triggered based on assessing the second real-time activity data in view of the identified context pattern.

8. The method of claim 1 , wherein adaptively providing the prompt comprises selecting an output device based on the second real-time activity data in view of the identified context pattern.

9. The method of claim 1 , wherein activity data comprises one or more of location data, physiological data, computer usage, phone usage, and sensor data.

10. The method of claim 1 , wherein the one or more tasks are associated with at least one of work, fitness, and personal goals of the user.

11. The method of claim 1 , wherein the journaling model is generated using machine-learning further associated with one or more of training data, user preferences, and clinical guidelines.

12. The method of claim 1 , wherein the series of prompts are ordered based on the determined preferred interaction mode.

13. The method of claim 1 , wherein the content of the prompts comprises dynamic elements extracted from prior engagement data.

14. A system comprising:

a memory; and

a processor coupled to the memory configured to:

generate, by a software conversational agent, a journaling model based on a first real-time activity data and engagement data associated with one or more tasks of a user, wherein the journaling model uses machine-learning to:

identify a preconfigured context pattern associated with the first real-time activity data, and

map performance associated with the one or more tasks based at least on the engagement data;

determine a preferred interaction mode from a plurality of interaction modes based on comparing a second real-time activity data with the identified context pattern;

generating prompts based on the journaling model and the determined preferred interaction mode, the prompts comprising a series of prompts generated based on topics selected by the journaling model, each prompt is generated based on a user sentiment indicator from the journaling model and content of each prompt is adapted based on the determined preferred interaction mode;

adaptively providing one or more of the prompts to gather an additional engagement data on the selected topic based on the identified context pattern in view of the second real-time activity data, wherein adaptively providing the prompt comprises an autonomous interaction to initiate feedback from the user on the topic by the journaling model using the determined preferred interaction mode; and

updating a set of journal entries of the journaling model for the selected topic based on receiving the additional engagement data,

wherein to map performance associated with one or more tasks comprises:

analyzing the engagement data of the user associated with the one or more tasks to identify content topics and the user sentiment indicators for each of the one or more tasks:

associating each of the one or more tasks with at least one content topic;

tracking the user sentiment indicators through each of the one or more tasks for each respective topic; and

mapping performance for each respective topic based at least on changes of the tracked user sentiment indicators from the additional engagement data.

15. The system of claim 14 , wherein the plurality of preferred interaction modes includes at least one of a chat-bot, an audio agent, and a virtual avatar.

16. The system of claim 14 , wherein to adaptively provide the prompt, the processor is further to compare the second real-time activity data from a location of the user to the identified context pattern to determine an output modality for the prompt, wherein the output modality is text, audio, or visual.

17. A non-transitory computer readable medium, comprising instructions that when execute by a processor, the instructions to:

generate, by a software conversational agent, a journaling model based on a first real-time activity data and engagement data associated with one or more tasks of a user, wherein the journaling model uses machine-learning to:

identify a preconfigured context pattern associated with the first real-time activity data, and

map performance associated with the one or more tasks based at least on the engagement data;

determine a preferred interaction mode from a plurality of interaction modes based on comparing second real-time activity data with the identified context pattern;

generating prompts based on the journaling model and the determined preferred interaction mode, the prompts comprising a series of prompts generated based on topics selected by the journaling model, each prompt is generated based on a user sentiment indicator from the journaling model and content of each prompt is adapted based on the determined preferred interaction mode:

adaptively providing one or more of the prompts to gather an additional engagement data on the selected topic based on the identified context pattern in view of the second real-time activity data, wherein adaptively providing the prompt comprises an autonomous interaction to initiate feedback from the user on the topic selected by the journaling model using the determined preferred interaction mode; and

updating a set of journal entries of the journaling model for the selected topic based on receiving the additional engagement data,

wherein to map performance associated with one or more tasks comprises:

analyzing the engagement data of the user associated with the one or more tasks to identify content topics and the user sentiment indicators for each of the one or more tasks;

associating each of the one or more tasks with at least one content topic;

tracking the user sentiment indicators through each of the one or more tasks for each respective topic; and

mapping performance for each respective topic based at least on changes of the tracked user sentiment indicators from the additional engagement data.

18. The non-transitory computer readable medium of claim 17 , wherein the prompt is triggered based on a pre-set schedule.

19. The non-transitory computer readable medium of claim 17 , wherein the prompt comprises a series of questions, wherein the series of questions are generated based on topics from the journaling model, wherein each question is generated based on a user sentiment indicator from the journaling model, wherein each question is adapted based on a type of output device.