US 12,265,563 B2
System and method for querying of unstructured text using graph analysis
Sharon Hüffner, Berlin (DE); Rohit Jain, Ventura, CA (US); Devin H. Redmond, Encinitas, CA (US); and Richard B. Sutton, San Mateo, CA (US)
Assigned to THETA LAKE, INC., Santa Barbara, CA (US)
Filed by THETA LAKE, INC., Santa Barbara, CA (US)
Filed on Jan. 7, 2022, as Appl. No. 17/570,878.
Claims priority of provisional application 63/134,669, filed on Jan. 7, 2021.
Prior Publication US 2022/0215046 A1, Jul. 7, 2022
Int. Cl. G06F 16/00 (2019.01); G06F 16/2457 (2019.01); G06F 16/334 (2025.01); G06F 16/353 (2025.01); G06F 16/901 (2019.01)
CPC G06F 16/334 (2019.01) [G06F 16/24575 (2019.01); G06F 16/353 (2019.01); G06F 16/9024 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A system for identifying items in unstructured text, the system comprising:
a memory storing unstructured text ingested from one or more content sources;
a processor; and
a non-transitory computer readable medium storing instructions translatable by the processor, the instructions when translated by the processor perform:
providing a plurality of predetermined query strings, each of the predetermined query strings relating to concepts to be identified in target text of the one or more content sources;
defining relationships between different terms included in a first query string of the plurality of query strings;
identifying matches between terms in the first query string and terms in the target text;
generating a graph having nodes corresponding to the identified matches between terms in the first query string and terms in the target text;
based on the defined relationships between terms in the first query string, determining that a group of nodes of the generated graph match the first query string; and
mapping text in the target text corresponding to the determined match to identify a portion of the target text that meets requirements of the first query string.