| CPC G06F 16/90332 (2019.01) [G06F 40/20 (2020.01); G06N 3/02 (2013.01); G06N 5/02 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] | 6 Claims |

|
1. A computer-implemented method for generating a domain specific reasoning-based meaning representation of a query, the computer-implemented method comprising:
receiving, by a processor, a query from a user, wherein the query is handwritten text contained in unstructured data;
scanning a plurality of pixels in the unstructured data, based on a neural network associated with an image recognition module;
predicting, by the processor, a plurality of letters, based on the scanning;
identifying, by the processor, a plurality of words from the predicted plurality of letters, based on pattern matching or pattern recognition;
tokenizing, by the processor, each identified word in the query, based on a natural language processing system;
transforming, by the processor, the query into a structured proposal, based on each of the tokenized words; and
generating, by the processor, a reasoning-based meaning representation of the structured proposal, wherein generating the reasoning-based meaning representation of the structured proposal comprises identifying one or more concepts associated with the structured proposal and assigning one or more properties to each of the one or more identified concepts, wherein the one or more properties are based, at least in part, on universal facts, and recognizing whether the one or more properties is one of the following: a measurable property, an aggregation of a measurable property, a ranking of a property, a counting of a property, and a temporal relation property;
determining, by the processor, if the structured proposal is consistent, based on a domain reasoning knowledge base and the reasoning-based meaning representation; and
responsive to determining the structured proposal is not consistent, correcting, by the processor, the structured proposal.
|