System and method for parsing user query

Patent metadata

Field	Value
Publication number	US-11544304-B2
Application number	US-201916366396-A
Country	US
Kind code	B2
Filing date	Mar 27, 2019
Priority date	Mar 27, 2018
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

A system and a method for parsing a user query. The system includes a database arrangement operable to store an ontology; and a processing module communicably coupled to the database arrangement. The processing module operable to receive the user query; refine the user query to obtain a search query using an algorithm; generate a plurality of strings for the obtained search query; sort the plurality of strings in a decreasing order of length of the plurality of strings; assign a part-of-speech tag to each of the query segments of the plurality of strings based on the ontology; identify at least one of the query segments as at least one output class or at least one input class based on the assigned part-of-speech tags; and establish semantic associations between the query segments based on the ontology to obtain the parsed user query.

First claim

What is claimed is:

1. A system configured to parse a user query to retrieve a data record from a search database, wherein the system includes a computer system, wherein the computer system comprises:
a memory configured to store an ontology; and
a processor communicably coupled to the memory, the processor being configured to:
receive the user query;
refine the user query to obtain a search query using an algorithm, wherein the search query comprises query segments, wherein the algorithm checks a co-occurrence of words in the user query and wherein the co-occurrence of words is considered a singular query segment;
generate a plurality of strings for the obtained search query, wherein the plurality of strings comprises at least one query segment, and wherein a plurality of strings having two or more query segments are generated using consecutive query segments;
sort the plurality of strings in a decreasing order of length of the plurality of strings, wherein a length of a string corresponds to a number of query segments in the string;
assign a part-of-speech tag to each of the query segments of the plurality of strings based on the ontology, wherein the part-of-speech tag comprises at least one of: a proper noun, a common noun, a pronoun, an adjective, a determiner, a verb, an adverb, a preposition, a conjunction, numerals and an interjection;
identify at least one of the query segments as at least one output class based on the assigned part-of-speech tag, wherein the at least one of the query segments identified as the at least one output class is associated with a broader scope, wherein the broader scope associated with the at least one of the query segments is determined based on the common noun comprised in the assigned part-of-speech tag;
generate a chunked string by removing the at least one of the query segments identified as the at least one output class from a string of the plurality of strings, with a maximum length;
determine the at least one of the query segments as at least one input class based on the generated chunked string, wherein the at least one of the query segments identified as the at least one input class is associated with a narrow scope within the obtained search query, wherein the narrow scope associated with the at least one of the query segments is determined based on the proper noun comprised in the assigned part-of-speech tags;
establish semantic associations between query segments identified as at least one output class and at least one input class, based on the ontology to obtain the parsed user query; and
retrieve at least one context-based data-record based on at least one of:
the identified at least one output class and the identified at least one input class associated with the query segments; and
the established semantic associations between the query segments identified as the at least one output class and the at least one input class.

2. The system of claim 1 , wherein the algorithm used in refining the user query comprises at least one of: natural language processing, text analytics and machine learning techniques.

3. A method for parsing a user query to retrieve a data record from a search database, wherein the method is implemented via a computer system which comprises a memory, wherein the method comprises:
receiving the user query;
refining the user query to obtain a search query using an algorithm, wherein the search query comprises query segments, wherein the algorithm checks a co-occurrence of words in the user query and wherein the co-occurrence of words is considered a singular query segment;
generating a plurality of strings for the obtained search query, wherein the plurality of strings comprises at least one query segment, and wherein a plurality of strings having two or more query segments are generated using consecutive query segments;
sorting the plurality of strings in a decreasing order of length of the plurality of strings, wherein a length of a string corresponds to a number of query segments in the string;
assigning a part-of-speech tag to each of the query segments of the plurality of strings based on an ontology stored in the memory, wherein the part-of-speech tag comprises at least one of: a proper noun, a general noun, a pronoun, an adjective, a determiner, a verb, an adverb, a preposition, a conjunction, numerals and an interjection;
identifying at least one of the query segments as at least one output class based on the assigned part-of-speech tags, wherein the at least one of the query segments identified as the at least one output class is associated with a broader scope, wherein the broader scope associated with the at least one of the query segments is determined based on a common noun comprised in the assigned part-of-speech tags;
generating a chunked string by removing the at least one of the query segments identified as the at least one output class from a string, of the plurality of strings, with a maximum length;
determining the at least one of the query segments as at least one input class based on the generated chunked string, wherein the at least one of the query segments identified as the at least one input class is associated with a narrow scope within the search query, wherein the narrow scope associated with the at least one of the query segments is determined based on the proper noun comprised in the assigned part-of-speech tags;

establishing semantic associations between query segments identified as the at least one output class and the at least one input class based on the ontology to obtain the parsed user query; and
retrieving at least one context-based data-record from the search database based on at least one of:
the identified at least one output class and the at least one input class associated with the at least one of the query segments; and
the established semantic associations between the at least one of the query segments identified as the at least one output class and the at least one input class.

4. The method of claim 3 , wherein the at least one output class comprises a first and second output class, and wherein the method further comprises performing a hierarchy analysis on the first and second output class.

5. The method of claim 4 , wherein the at least one context-based data-record is extracted based upon the first and second output class with lower hierarchy.

6. The method of claim 4 , wherein the at least one context-based data-record is extracted based upon the first and second output class when the first and second output class are at same hierarchy.

7. The method of claim 3 , wherein the method further comprises extracting metadata from the plurality of strings.

8. The method of claim 3 , wherein the method comprises developing the ontology using at least one curated database by:
applying conceptual indexing to a plurality of entity units stored in the at least one curated database;
identifying semantic associations, between the plurality of entity units established in the at least one curated database; and
identifying at least one class tagged with the plurality of entity units in the at least one curated database.

9. The method of claim 3 , wherein the algorithm used in refining the user query comprises at least one of: natural language processing, text analytics and machine learning techniques.

10. A non-transitory computer readable storage medium, containing program instructions for execution on a computer system comprising a memory, which when executed by the computer system cause the computer system to perform method steps for parsing a user query to retrieve a data record from a search database, the method comprising the steps of:
receiving the user query;
refining the u

Assignees

• Innoplexus Ag

Inventors

• Tripathi Gaurav
• Patil Prashant
• Kewalramani Rohit
• Dharma Dileep
• Agarwal Vatsal

Classifications

• G06F16/367

  Ontology · CPC title

• G06F16/33 Primary

  Querying · CPC title

• G06F16/3329 Primary

  Natural language query formulation · CPC title

• G06F16/3332 Primary

  Query translation · CPC title

• G06F40/117

  Tagging; Marking up (details of markup languages G06F40/143); Designating a block; Setting of attributes (style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154) · CPC title