US 12,481,832 B2
Providing item discovery guidance based on automatically-discerned subjective considerations
Sebastian Wickenburg, Bothell, WA (US); David Fagnan, Shoreline, WA (US); Steven Hoelscher, Seattle, WA (US); and Michael Rowell, Bellevue, WA (US)
Assigned to Artica Inc., Bellevue, WA (US)
Filed by Artica Inc., Bellevue, WA (US)
Filed on Apr. 5, 2023, as Appl. No. 18/296,210.
Prior Publication US 2024/0338526 A1, Oct. 10, 2024
Int. Cl. G06F 40/30 (2020.01); G06F 3/04847 (2022.01)
CPC G06F 40/30 (2020.01) [G06F 3/04847 (2013.01)] 17 Claims
OG exemplary drawing
 
3. A method in a computing system, the method comprising:
accessing a plurality of textual reviews each of an item among a plurality of items in a distinguished item category;
applying a large language model to the accessed reviews to identify a plurality of subjective considerations for the plurality of items in the distinguished item category;
applying a large language model to the accessed reviews to select portions each mentioning one of the identified plurality of subjective considerations;
performing automatic sentiment analysis on each selected portion;
for each respective subjective consideration of the plurality of subjective considerations, for each respective item of the plurality of items in the distinguished item category, generating a value for the respective subjective consideration based on a sentiment analysis result for portions mentioning the respective subjective consideration in reviews of the respective item; and
storing the generated values.