US 12,436,974 B2
Resource conservation based on query complexity
Katherine Irene Cook, Seattle, WA (US); Hui Liu, Kenmore, WA (US); Ashutosh Devendrakumar Adhikari, Toronto (CA); Payal Bajaj, Redmond, WA (US); and Bradley Moore Abrams, Palo Alto, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Feb. 28, 2024, as Appl. No. 18/590,656.
Prior Publication US 2025/0272313 A1, Aug. 28, 2025
Int. Cl. G06F 16/28 (2019.01); G06F 16/2457 (2019.01)
CPC G06F 16/285 (2019.01) [G06F 16/24573 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for artificial intelligence (AI) model selection based on query complexity, comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
receiving a first input query;
classifying, by a response classifier, the first input query with a first response complexity score;
comparing the first response complexity score to a threshold score;
selecting, based at least in part on the comparison of the first response complexity score to the threshold score, a first AI model of a set of two or more AI models for generating a response to the first input query, wherein each AI model of the set of two or more AI models has different performance characteristics;
generating a first prompt including the first input query;
providing the first prompt as input to the first AI model;
receiving a first response as output from the first AI model; and
surfacing the first response.