US 12,406,153 B2
Dynamic contrarian view analysis in natural language content
Olav Laudij, San Diego, CA (US); Pierre Haren, Cottonwood Heights, UT (US); Eric David Jensen, Sandy, UT (US); and Craig Matthew Trim, Ventura, CA (US)
Assigned to Causality Link LLC, Cottonwood Heights, UT (US)
Filed by Causality Link LLC, Cottonwood Heights, UT (US)
Filed on Mar. 13, 2023, as Appl. No. 18/120,688.
Prior Publication US 2024/0311578 A1, Sep. 19, 2024
Int. Cl. G06F 40/40 (2020.01); G06F 40/103 (2020.01)
CPC G06F 40/40 (2020.01) [G06F 40/103 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
constructing a modified natural language processing (NLP) engine, the constructing comprising:
enabling the NLP engine to extract, from an input comprising a first content including a first assertion, a plurality of knowledge blocks;
configuring a computational module to operate with the NLP engine to compute a metric corresponding to a first knowledge block in the plurality of knowledge blocks, the metric evaluating a corpus of content against the first knowledge block, wherein the computational module causes a behavior of the NLP engine to adjust the metric using a half-life hyperparameter on a consensus detected in the corpus;
further configuring the NLP engine to dynamically determine a contrarian view expressed in a corpus of content by comparing the metric with the first knowledge block and identifying the first assertion as a contrarian assertion, wherein the contrarian assertion is an assertion that has a contrary correlation with the consensus detected in the corpus; and
causing a presentation device to visually associate an indication of the contrarian assertion with a portion of the first content.