US 12,222,935 B2
Decision support system for data retrieval
Eric Laufer, Montreal (CA); and Francois Maillet, Montreal (CA)
Assigned to ServiceNow Canada Inc., Montreal (CA)
Appl. No. 17/753,216
Filed by ServiceNow Canada Inc., Montreal (CA)
PCT Filed Aug. 26, 2020, PCT No. PCT/CA2020/051160
§ 371(c)(1), (2) Date Feb. 24, 2022,
PCT Pub. No. WO2021/035347, PCT Pub. Date Mar. 4, 2021.
Claims priority of provisional application 62/894,267, filed on Aug. 30, 2019.
Prior Publication US 2022/0292087 A1, Sep. 15, 2022
Int. Cl. G06F 16/00 (2019.01); G06F 16/242 (2019.01); G06F 16/245 (2019.01); G06F 16/248 (2019.01); G06F 16/25 (2019.01); G06F 16/28 (2019.01)
CPC G06F 16/245 (2019.01) [G06F 16/243 (2019.01); G06F 16/248 (2019.01); G06F 16/258 (2019.01); G06F 16/285 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A system for retrieving data, the system comprising:
a non-transitory storage medium storing computer-readable instructions thereon; and
at least one processor operatively connected to the non-transitory storage medium, the at least one processor, upon executing the computer-readable instructions, being configured for:
receiving a natural language query from a user;
decomposing said natural language query into query elements using at least one natural language processing (NLP) model;
determining, using at least one classifier, query types and respective query parameters for said query based on said query elements and relationships between query elements for said query;
selecting at least one suitable function for said query from a set of functions based on said query types, said respective query parameters and the relationships between the query elements to formulate at least one database query;
retrieving data from at least one knowledge graph database operatively connected to the system, using said at least one database query;
processing said data retrieved from the at least one knowledge graph database based on the relationships between the query elements to thereby determine a response to said query; and
formatting said response into a formatted response to said natural language query from said user.