US 11,782,988 B2
Query understanding methods and systems
Federico Tomasi, London (GB); Rishabh Mehrotra, London (GB); Brian Christian Peter Brost, Brooklyn, NY (US); Aasish Kumar Pappu, Jersey City, NJ (US); Hugo Flávio Ventura Galvão, Stockholm (SE); and Mounia Lalmas-Roelleke, Saffron Walden (GB)
Assigned to Spotify AB, Stockholm (SE)
Filed by Spotify AB, Stockholm (SE)
Filed on Sep. 21, 2020, as Appl. No. 17/27,239.
Prior Publication US 2022/0092118 A1, Mar. 24, 2022
Int. Cl. G06F 16/9035 (2019.01); G06F 16/9038 (2019.01); G06N 5/025 (2023.01); G06N 3/04 (2023.01); G06F 18/22 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01)
CPC G06F 16/9035 (2019.01) [G06F 16/9038 (2019.01); G06F 18/214 (2023.01); G06F 18/2185 (2023.01); G06F 18/22 (2023.01); G06N 3/04 (2013.01); G06N 5/025 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A query understanding system, comprising:
at least one processor; and
non-transitory computer-readable storage having stored thereon instructions which, when executed by the at least one processor, cause the at least one processor to:
generate a plurality of non-focused query features that quantify a non-focused query; and
generate a prediction associated with the non-focused query based on the plurality of non-focused query features, including to apply a set of threshold-based rules on the plurality of non-focused query features, the prediction being a probability that the non-focused query will generate results that include under-served content.