Automated intent to action mapping in augmented reality environments

1. A method for mapping an intent to an action of a user in augmented reality procedures, the method comprising:

receiving a user activity from the user;

monitoring the received user activity;

matching a concept with the monitored user activity, wherein the matched concept is extracted from an intent database, wherein natural language processing is utilized to derive the extracted concept from a plurality of knowledge documents and a plurality of relevant sources;

identifying a task based on the extracted concept and the monitored user activity;

presenting a decision tree, from an intent database, based on the extracted concept and identified task, wherein the decision tree comprises of a plurality of intended steps to be performed by the user to complete a desired action;

in response to determining that the user successfully performed an intended step within the plurality of intended steps, presenting a next intended step from the plurality of intended steps from the presented decision tree; and

in response to determining that the user is unable to follow at least one given instruction from the intended step, providing at least one form of additional guidance to the user for performing the intended step.

2. The method of claim 1 , wherein monitoring the received user activity, further comprises:

utilizing a video recognition and three-dimensional tracking software.

3. The method of claim 1 , wherein the at least one form of additional guidance comprises a visual aid, a verbal aid, or a plurality of textual data.

4. The method of claim 1 , further comprising:

determining that the user is unable to perform the intended step from the plurality of intended steps;

determining that the user is incorrectly engaged in the intended step; and

reconstructing the decision tree, wherein the reconstructed decision tree is associated with an actual intent and a desired action of the user.

5. The method of claim 1 , further comprising:

ingesting at least one document from the plurality of knowledge documents and the plurality of relevant sources;

extracting at least one task from the ingested document;

converting the extracted task into a decision tree; and

storing the decision tree in the intent database.

6. The method of claim 2 , further comprising:

monitoring a plurality of user's tools by utilizing three-dimensional tracking software; and

determining the intended step of the user based on the monitored plurality of user's tools and recognition software, wherein a piece of training data based on offline training was created for the recognition software.

7. The method of claim 6 , further comprising:

creating offline training for a plurality of general tasks;

generating training data associated with the plurality of general tasks from the created offline training;

comparing the created offline training to the monitored user activity; and

associating the intent of the user with the desired action based on the compared offline training and monitored user activity.

8. A computer system for mapping an intent to an action of a user in augmented reality procedures, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

receiving a user activity from the user;

monitoring the received user activity;

matching a concept with the monitored user activity, wherein the matched concept is extracted from an intent database, wherein natural language processing is utilized to derive the extracted concept from a plurality of knowledge documents and a plurality of relevant sources;

identifying a task based on the extracted concept and the monitored user activity;

presenting a decision tree, from an intent database, based on the extracted concept and identified task, wherein the decision tree comprises of a plurality of intended steps to be performed by the user to complete a desired action;

in response to determining that the user successfully performed an intended step within the plurality of intended steps, presenting a next intended step from the plurality of intended steps from the presented decision tree; and

in response to determining that the user is unable to follow at least one given instruction from the intended step, providing at least one form of additional guidance to the user for performing the intended step.

9. The computer system of claim 8 , wherein monitoring the received user activity, further comprises:

utilizing a video recognition and three-dimensional tracking software.

10. The computer system of claim 8 , wherein the at least one form of additional guidance comprises a visual aid, a verbal aid, or a plurality of textual data.

11. The computer system of claim 8 , further comprising:

determining that the user is unable to perform the intended step from the plurality of intended steps;

determining that the user is incorrectly engaged in the intended step; and

reconstructing the decision tree, wherein the reconstructed decision tree is associated with an actual intent and a desired action of the user.

12. The computer system of claim 8 , further comprising:

ingesting at least one document from the plurality of knowledge documents and the plurality of relevant sources;

extracting at least one task from the ingested document;

converting the extracted task into a decision tree; and

storing the decision tree in the intent database.

13. The computer system of claim 9 , further comprising:

monitoring a plurality of user's tools by utilizing three-dimensional tracking software; and

determining the intended step of the user based on the monitored plurality of user's tools and recognition software, wherein a piece of training data based on offline training was created for the recognition software.

14. The computer system of claim 13 , further comprising:

creating offline training for a plurality of general tasks;

generating training data associated with the plurality of general tasks from the created offline training;

comparing the created offline training to the monitored user activity; and

associating the intent of the user with the desired action based on the compared offline training and monitored user activity.

15. A computer program product for mapping an intent to an action of a user in augmented reality procedures, comprising:

one or more computer-readable storage tangible media and program instructions stored on at least one of the one or more computer-readable tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving a user activity from the user;

monitoring the received user activity;

matching a concept with the monitored user activity, wherein the matched concept is extracted from an intent database, wherein natural language processing is utilized to derive the extracted concept from a plurality of knowledge documents and a plurality of relevant sources;

identifying a task based on the extracted concept and the monitored user activity;

presenting a decision tree, from an intent database, based on the extracted concept and identified task, wherein the decision tree comprises of a plurality of intended steps to be performed by the user to complete a desired action;

in response to determining that the user successfully performed an intended step within the plurality of intended steps, presenting a next intended step from the plurality of intended steps from the presented decision tree; and

in response to determining that the user is unable to follow at least one given instruction from the intended step, providing at least one form of additional guidance to the user for performing the intended step.

16. The computer program product of claim 15 , wherein monitoring the received user activity, further comprises:

utilizing a video recognition and three-dimensional tracking software.

17. The computer program product of claim 15 , wherein the at least one form of additional guidance comprises a visual aid, a verbal aid, or a plurality of textual data.

18. The computer program product of claim 15 , further comprising:

determining that the user is unable to perform the intended step from the plurality of intended steps;

determining that the user is incorrectly engaged in the intended step; and

reconstructing the decision tree, wherein the reconstructed decision tree is associated with an actual intent and a desired action of the user.

19. The computer program product of claim 15 , further comprising:

ingesting at least one document from the plurality of knowledge documents and the plurality of relevant sources;

extracting at least one task from the ingested document;

converting the extracted task into a decision tree; and

storing the decision tree in the intent database.

20. The computer program product of claim 16 , further comprising:

monitoring a plurality of user's tools by utilizing three-dimensional tracking software; and

determining the intended step of the user based on the monitored plurality of user's tools and recognition software, wherein a piece of training data based on offline training was created for the recognition software.

21. The computer program product of claim 20 , further comprising:

creating offline training for a plurality of general tasks;

generating training data associated with the plurality of general tasks from the created offline training;

comparing the created offline training to the monitored user activity; and

associating the intent of the user with the desired action based on the compared offline training and monitored user activity.