Query Generation Using Natural Language Input

Patent metadata

Field	Value
Publication number	US-2022261442-A1
Application number	US-202217661651-A
Country	US
Kind code	A1
Filing date	May 2, 2022
Priority date	Jul 24, 2019
Publication date	Aug 18, 2022
Grant date	—

Abstract

Methods and systems for generation of a database schema compliant search query based on a natural language input are described herein. Natural language input may be received from a computing device. The natural language input may be associated with multiple search requests to a database. The natural language input may be parsed into a plurality of segments. The plurality of segments may be, for example, one or more words of a text string. At least one identifier for the plurality of segments may be associated with one or more confidence values. The natural language input may be converted into a single search query based on the confidence values and/or on a set of rules. The single search query may be initiated with respect to the database. The single search query may fetch content more efficiently than the multiple search requests.

First claim

What is claimed is:

1 . A method comprising:
receiving, by a computing device, a text string corresponding to natural language input; determining, by the computing device, one or more confidence values corresponding to one or more of a plurality of segments of the text string; converting, by the computing device, in response to determining that at least a subset of the one or more confidence values is equal to or greater than a threshold, and based on a set of rules defined by a first GraphQL database schema, the natural language input into a single search query executable by Application Programming Interface (API) in a query language of GraphQL; and initiating, by the computing device and based on a second GraphQL database schema different from the first GraphQL database schema, the single search query to fetch content from a database so as to prevent transmission of multiple search requests responsive to the natural language input.

2 . The method of claim 1 , further comprising:
discarding one or more of the plurality of segments based on determining that a first confidence value of the one or more confidence values satisfies a second threshold.

3 . The method of claim 1 , wherein converting the natural language input into the single search query is further based on determining, based on the set of rules, that one or more of the plurality of segments corresponds to a search operation.

4 . The method of claim 1 , further comprising:
validating the single search query based on the second GraphQL database schema.

5 . The method of claim 1 , further comprising:
updating, based on detecting a change to the database, the set of rules.

6 . The method of claim 1 , wherein the one or more confidence values correspond to two or more of the plurality of segments, and wherein determining that at least the subset of the one or more confidence values is equal to or greater than the threshold is based on comparing a combined value of the one or more confidence values to the threshold.

7 . An apparatus comprising:
one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
receive a text string corresponding to natural language input;
determine one or more confidence values corresponding to one or more of a plurality of segments of the text string;
convert, in response to determining that at least a subset of the one or more confidence values is equal to or greater than a threshold, and based on a set of rules defined by a first GraphQL database schema, the natural language input into a single search query executable by Application Programming Interface (API) in a query language of GraphQL; and
initiate, based on a second GraphQL database schema different from the first GraphQL database schema, the single search query to fetch content from a database so as to prevent transmission of multiple search requests responsive to the natural language input.

8 . The apparatus of claim 7 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
discard one or more of the plurality of segments based on determining that a first confidence value of the one or more confidence values satisfies a second threshold.

9 . The apparatus of claim 7 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to convert the natural language input further based on determining, based on the set of rules, that one or more of the plurality of segments corresponds to a search operation.

10 . The apparatus of claim 7 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
validate the single search query based on the second GraphQL database schema.

11 . The apparatus of claim 7 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
update, based on detecting a change to the database, the set of rules.

12 . A system comprising:
a first computing device, and a second computing device; wherein the first computing device is configured to:
determine one or more confidence values corresponding to one or more of a plurality of segments of a text string that corresponds to natural language input;
convert, based on a set of rules defined by a first GraphQL database schema, the natural language input into a single search query executable by Application Programming Interface (API) in a query language of GraphQL; and
send, to the second computing device, the single search query; and
wherein the second computing device is configured to:
validate, based on a second GraphQL database schema different from the first GraphQL database schema, the single search query based on the second GraphQL database schema.

13 . The system of claim 12 , wherein the second computing device is further configured to:
use the single search query to fetch content from a database so as to prevent transmission of multiple search requests responsive to the natural language input.

14 . The system of claim 12 , wherein the second GraphQL database schema defines a different quantity of rules as compared to the first GraphQL database schema.

15 . The system of claim 12 , wherein the first computing device is further configured to:
discard one or more of the plurality of segments based on determining that a first confidence value of the one or more confidence values satisfies a second threshold.

16 . The system of claim 12 , wherein the first computing device is configured to convert the natural language input further based on determining, based on the set of rules, that one or more of the plurality of segments corresponds to a search operation.

17 . The system of claim 12 , wherein the first computing device is further configured to:
validate the single search query based on the second GraphQL database schema.

18 . The system of claim 12 , wherein the first computing device is further configured to:
remove, from the text string and based on a stop word list, one or more words.

19 . The system of claim 12 , wherein the first computing device is further configured to:
update, based on detecting a change to the database, the set of rules.

20 . The system of claim 12 , wherein the first computing device is configured to convert the natural language input into the single search query based on determining that at least a subset of the one or more confidence values is equal to or greater than a threshold.

Assignees

• Citrix Systems Inc

Inventors

• Khillar Shiv Prasad
• Shaik Saifulla
• Tank Nagendra

Classifications

• G06F16/24522 Primary

  Translation of natural language queries to structured queries · CPC title

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title