Claims:WE CLAIM:
1. A method of providing real-time guidance to users during troubleshooting of devices, the method comprising:
receiving, by a guidance providing system (101), user input indicating troubleshooting actions on a device (105), by a user (106), wherein the user input comprises textual input and non-textual input;
identifying, by the guidance providing system (101), an object in the device (105) associated with the troubleshooting actions and state of the user (106) while performing the troubleshooting actions, from the non-textual input;
mapping, by the guidance providing system (101), the object, identified from the non-textual input with the textual input to obtain a mapped user input;
verifying, by the guidance providing system (101), consistency of the mapped user input based on a conversation information (207) and domain specific content associated with the device;
extracting, by the guidance providing system (101), at least one of, sequence of instructions corresponding to the mapped user input, based on the state of the user (106) and one or more similar troubleshooting actions, obtained from a knowledge database (107); and
providing, by the guidance providing system (101), troubleshooting instructions based on at least one of, the sequence of instructions and the one or more similar troubleshooting actions, to the user (106) for real-time guidance, during troubleshooting of the device (105).
2. The method as claimed in claim 1, wherein the textual input comprises at least one of speech data and text data associated with the troubleshooting actions.
3. The method as claimed in claim 1, wherein the non-textual input comprises at least one of images, videos, actions, and gestures of the user (106) while executing the troubleshooting actions and one or more region of interest provided by the user (106) by annotating the images.

4. The method as claimed in claim 1, wherein the conversation information (207) comprises at least one of, pre-stored conversation history and response to real-time queries provided to the user (106).
5. The method as claimed in claim 1, wherein the one or more similar troubleshooting actions are obtained by comparing the troubleshooting actions with one or more troubleshooting actions performed previously by the user (106) for a similar problem.
6. The method as claimed in claim 1, wherein verifying the consistency of the mapped user input comprises:
determining, by the guidance providing system (101), one or more collocation terms in the mapped user input by splitting the mapped user input into one or more sentences;
detecting, by the guidance providing system (101), context of the mapped user input by mapping the mapped user input against the knowledge database (107);
identifying, by the guidance providing system (101), a relation among one or more frames of the one or more sentences based on predefined frames and VerbNet analysis;
creating, by the guidance providing system (101), one or more lexical chains by detecting prominent named entities based on prestored domain specific features; and
mapping, by the guidance providing system (101), one or more co-references identified in the one or more sentences with the prominent named entities based on predefined reference score.
7. The method as claimed in claim 1, wherein the knowledge database (107) comprises troubleshooting information for a plurality of domains and one or more troubleshooting actions performed by the user (106).
8. A guidance providing system (101) for providing real-time guidance to users during troubleshooting of devices, comprising:
a processor (113); and
a memory (111) communicatively coupled to the processor (113), wherein the memory (111) stores processor instructions, which, on execution, causes the processor (113) to:
receive user input indicating troubleshooting actions on a device (105), by a user (106), wherein the user input comprises textual input and non-textual input;
identify an object in the device (105) associated with the troubleshooting actions and state of the user (106) while performing the troubleshooting actions, from the non-textual input,
map the object, identified from the non-textual input, with the textual input to obtain a mapped user input;
verify consistency of the mapped user input based on a conversation information (207) and domain specific content associated with the device (105);
extract at least one of, sequence of instructions corresponding to the mapped user input, based on the state of the user (106) and one or more similar troubleshooting actions, obtained from a knowledge database (107); and
provide troubleshooting instructions based on at least one of, the sequence of instructions and the one or more similar troubleshooting actions, to the user (106) for real-time guidance during troubleshooting of the device (105).
9. The guidance providing system (101) as claimed in claim 8, wherein the textual input comprises at least one of speech and text data associated with the troubleshooting actions.
10. The guidance providing system (101) as claimed in claim 8, wherein the non-textual input comprises at least one of images, videos, actions, and gestures of the user (106) while executing the troubleshooting actions and one or more region of interest provided by the user (106) by annotating the images.

11. The guidance providing system (101) as claimed in claim 8, wherein the conversation information (207) comprises at least one of, pre-stored conversation history and response to real-time queries provided to the user (106).
12. The guidance providing system (101) as claimed in claim 8, wherein the processor (113) obtains the one or more similar troubleshooting actions by comparing the troubleshooting actions with one or more troubleshooting actions performed previously by the user (106) for a similar problem.

13. The guidance providing system (101) as claimed in claim 8, wherein the processor (113) verifies the consistency of the mapped user input by:
determining one or more collocation terms in the mapped user input by splitting the mapped user input into one or more sentences;
detecting context of the mapped user input by mapping the mapped user input against the knowledge database (107);
identifying a relation among one or more frames of the one or more sentences based on predefined frames and VerbNet analysis;
creating one or more lexical chains by detecting prominent named entities based on prestored domain specific features; and
mapping one or more co-references identified in the one or more sentences with the prominent named entities based on predefined reference score.

14. The guidance providing system (101) as claimed in claim 8, wherein the knowledge database (107) comprises troubleshooting information for a plurality of domains and one or more troubleshooting actions performed by the user (106).

Dated this 29th day of May, 2018

R Ramya Rao
Of K&S Partners
Agent for the Applicant
IN/PA-1607
, Description:TECHNICAL FIELD
The present subject matter is related in general to troubleshooting guidance, more particularly, but not exclusively to method and system for providing real-time guidance to users during troubleshooting of devices.