Method and system for automatic resolution of user queries

• US 10,776,700 B2
• Filed: 09/09/2016
• Issued: 09/15/2020
• Est. Priority Date: 09/10/2015
• Status: Active Grant

• Current Assignee: Senseforth, Inc.
• Original Assignee: Senseforth, Inc.
• Inventors: Kadiri, Krishna, Marri, Shridhar, Radhakrishnan, Ritesh, CV, Suryaprakash, Khazi, Tousif
• Primary Examiner(s): Fan, Shiow-Jy
• Application Number:
  US15/261,685
• Publication Number:
  US 20170075988A1
• Time in Patent Office: 1,467 Days
• Field of Search: 701769, 707769
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

The present disclosure relates to a method and system for automatic resolution of user queries by a query resolution system. The query resolution system receives user queries from a plurality of input sources, where the user queries are in a natural language. Further, the query resolution system determines user intent by analysing the user queries. Upon determination of user intent, the query resolution system resolves the user queries dynamically by performing one of providing a response for the user queries by retrieving information from one of a database and external data sources based on the user intent and routing the user queries to a query domain resource for resolving the user queries, where the query domain resources is determined based on the user intent.

Claims

1. A method for automatic resolution of user queries, the method comprising:

receiving, by a query resolution system, user queries from a plurality of input sources, wherein the user queries are in a natural language;

determining, by the query resolution system, in real-time, a user intent associated with the user queries, wherein the user intent comprises at least one of information on entities present in the user queries, information on metadata extracted from the user queries, domain specific information associated with the user queries or user emotion information, wherein the user intent is determined by performing sequentially;

tokenization on the user queries to identify one or more tokens;

assembling the one or more tokens to identify one or more sentences;

identifying parts of speech in each of the one or more sentences;

identifying declensions to classify relationship indicators in the one or more sentences;

determining clauses, actions, negation, subject, type of sentences used, status, concepts, synonym details, and indirect references in the one or more sentences; and

performing orthographic co-reference on noun phrases to obtain frequency of noun phrases in the one or more sentences; and

resolving, by the query resolution system, the user queries dynamically by performing one of;

providing, by the query resolution system, a resolution for the user queries by retrieving information from one of a database and external data sources based on the user intent; and

routing, by the query resolution system, the user queries to a query domain resource for resolving the user queries, wherein the query domain resource is an expertise in a domain related to the user queries and is determined based on the user intent.

2. The method as claimed in claim 1, wherein the user queries are analysed by cognitive computing techniques.

3. The method as claimed in claim 1, further comprising determining a need for ticketing the user queries based on the user intent.

4. The method as claimed in claim 3, further comprising assigning a ticket to the user queries based on the need for ticketing.

5. The method as claimed in claim 1, further comprising generating insights information based on a plurality of user queries and corresponding responses received over a period of time.

6. The method as claimed in claim 1, further comprising assigning a priority to the user queries based on the user intent, historical data for similar types of queries and information from media sources.

7. A query resolution system for automatic resolution of user queries, comprising:

a processor; and

a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to;

receive user queries from a plurality of input sources, wherein the user queries are in a natural language;

determine in real-time user intent associated with by analysing the user queries, wherein the user intent comprises at least one of, information on entities present in the user queries, information on metadata extracted from the user queries, domain specific information associated with the user queries or user emotion information,

wherein the user intent is determined by performing sequentially;

tokenization on the user queries to identify one or more tokens;

assembling the one or more tokens to identify one or more sentences;

identifying parts of speech in each of the one or more sentences;

identifying content boundary based on the one or more sentences;

identifying declensions to classify relationship indicators in the one or more sentences;

determining clauses, actions, negation, subject, type of sentences used, status, concepts, synonym details, and indirect references in the one or more sentences; and

performing orthographic co-reference on noun phrases to obtain frequency of noun phrases in the one or more sentences; and

resolve the user queries dynamically by performing one of;

providing a resolution for the user queries by retrieving information from one of a database and external data sources based on the user intent; and

routing the user queries to a query domain resource for resolving the user queries, wherein the query domain resource is an expertise in a domain related to the user queries and is determined based on the user intent.

8. The query resolution system as claimed in claim 7, wherein the processor analyses the user queries by cognitive computing techniques.

9. The query resolution system as claimed in claim 7, wherein the processor further determines a need for ticketing the user queries based on the user intent.

10. The query resolution system as claimed in claim 9, wherein the processor further assigns a ticket to the user queries based on the need for ticketing.

11. The query resolution system as claimed in claim 7, wherein the processor further generates insights information based on a plurality of user queries and corresponding responses received over a period of time.

12. The query resolution system as claimed in claim 7, wherein the processor further assigns a priority to the user queries based on the user intent, historical data for similar types of queries and information from media sources.