US 12,475,881 B2
Method of generating conversation information using examplar-based generation model and apparatus for the same
Enkhbayar Erdenee, Seoul (KR); Beom Su Kim, Seoul (KR); Seok Jun Seo, Seoul (KR); Sang Il Ahn, Cheongju-si (KR); Bu Ru Chang, Seoul (KR); and Seung Ju Han, Seoul (KR)
Assigned to Hyperconnect LLC, Dallas, TX (US)
Filed by Hyperconnect LLC, Seoul (KR)
Filed on Jun. 2, 2022, as Appl. No. 17/805,191.
Claims priority of application No. 10-2021-0112545 (KR), filed on Aug. 25, 2021; and application No. 10-2022-0010973 (KR), filed on Jan. 25, 2022.
Prior Publication US 2023/0077528 A1, Mar. 16, 2023
Int. Cl. G06F 40/30 (2020.01); G06F 18/2413 (2023.01); G06N 3/084 (2023.01); G10L 15/06 (2013.01); G10L 15/16 (2006.01)
CPC G10L 15/063 (2013.01) [G10L 15/16 (2013.01)] 6 Claims
OG exemplary drawing
 
1. A method of training a conversation model in an electronic apparatus, the method comprising:
identifying a first context;
identifying a first response set corresponding to the first context based on a first model;
excluding, from the first response set, at least one response that exists outside a first range in an embedding space from a gold response corresponding to the first context, wherein the first range is determined based on a k-means algorithm or a k-Nearest Neighbor (kNN) algorithm;
excluding, from the first response set, at least another response that is included in a second range in the embedding space from the gold response, wherein the second range indicates a Jaccard Filter Boundary in the embedding space;
identifying a response subset including a plurality of responses selected from the first response set based on the gold response;
calculate relevance scores, each relevance score indicating a degree of relevance to the gold response for a response in the plurality of responses; and
training a second model based on the first context, the response subset, and the relevance scores.