US 12,332,922 B2
Systems and methods for developing and organizing a knowledge base comprised of data collected from myriad sources
Oscar David Corredor Ortega, Bogota (CO); Henry Forsyth Keenan, San Juan, PR (US); Andrés Felipe Valencia Duque, Pereira (CO); Juan David Martínez Castillo, Cartago (CO); Alejandro Dominguez Rosales, Bogota (CO); Andrés Pérez Buriticá, Bogota (CO); and Jose Martinez, San Juan, PR (US)
Assigned to Red Atlas, Inc., San Juan, PR (US)
Filed by RED ATLAS INC., San Juan, PR (US)
Filed on Jul. 3, 2024, as Appl. No. 18/763,747.
Claims priority of provisional application 63/511,773, filed on Jul. 3, 2023.
Prior Publication US 2025/0013650 A1, Jan. 9, 2025
Int. Cl. G06F 16/29 (2019.01); G06F 16/215 (2019.01); G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06F 16/28 (2019.01); G06N 5/022 (2023.01); G06N 5/04 (2023.01)
CPC G06F 16/29 (2019.01) [G06F 16/215 (2019.01); G06F 16/243 (2019.01); G06F 16/24575 (2019.01); G06F 16/248 (2019.01); G06F 16/287 (2019.01); G06N 5/022 (2013.01); G06N 5/04 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A system for building a knowledge base, the system comprising a processor and a non-transitory computer readable medium storing instructions such that when the instructions are executed by the processor, the system is configured to:
receive, at an ingestion engine, multi-modal data from one or more sources, wherein the multi-modal data includes text;
analyze, by a feature extraction engine using language model parameters, the multi-modal data associated with the text;
identify, based on the analysis of the text by the feature extraction engine using a large language model associated with the language model parameters, a first feature, a second feature, and a third feature;
determine, based on a database, that the database includes a first key associated with the first feature;
store, in the database, an association between the first feature and the first key;
determine, based on the database, that the database includes a second key associated with the second feature;
store, in the database, an association between the second feature and the second key;
determine, based on the database, that no key exists that is associated with the third feature;
store, in the database, an association between the third feature and a dump key;
receive, from a plurality of users, search queries, wherein the search queries include keywords associated with features;
determine, by a dynamic field engine, that a number of search queries from the search queries include a keyword associated with the third feature;
create, by the dynamic field engine, a new key in the database, wherein the new key is associated with the third feature;
store, in the database, an association between the third feature and the new key;
receive a search query for searching the database;
identify, based on the search query via natural language processing, search features;
identify, based on the search query via the large language model, search features;
query the database, based on the search features, to generate search results;
generate, based on the search results, a standardized graphical user interface, wherein the standardized graphical user interface includes one or more search results and a legend including at least one of the search features; and
cause presentation, via an electronic display device, of the standardized graphical user interface.