US 12,229,175 B2
Legal document search and ranking using machine learning during legal interactions
Michael Okerlund, Minneapolis, MN (US); and Milena Higgins, Minneapolis, MN (US)
Assigned to Cloud Court, Inc., Minneapolis, MN (US)
Appl. No. 18/278,777
Filed by Cloud Court, Inc., Minneapolis, MN (US)
PCT Filed Feb. 28, 2022, PCT No. PCT/US2022/018198
§ 371(c)(1), (2) Date Aug. 24, 2023,
PCT Pub. No. WO2022/183125, PCT Pub. Date Sep. 1, 2022.
Claims priority of provisional application 63/154,498, filed on Feb. 26, 2021.
Prior Publication US 2024/0134895 A1, Apr. 25, 2024
Prior Publication US 2024/0232240 A9, Jul. 11, 2024
Int. Cl. G06F 7/00 (2006.01); G06F 3/16 (2006.01); G06F 16/38 (2019.01); G06N 20/00 (2019.01); G06Q 50/18 (2012.01); G10L 15/02 (2006.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 15/30 (2013.01)
CPC G06F 16/334 (2019.01) [G06F 3/167 (2013.01); G06F 16/38 (2019.01); G06N 20/00 (2019.01); G06Q 50/18 (2013.01); G10L 15/02 (2013.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 15/30 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method for performing document search and ranking, the method being implemented by a computer, the method comprising:
obtaining a transcript of a legal interaction that includes a trial or a deposition, and displaying the transcript via a user interface;
generating a query parameter based on at least the transcript, and transmitting the query parameter to a database search engine;
receiving a list of documents retrieved by the database search engine corresponding to the query parameter;
for each respective document in the list of documents, processing an input comprising (i) document information of the respective document and (ii) contextual information of the legal interaction using a feature extraction machine learning model to generate a respective feature representation; and
processing the feature representations of the list of documents to generate a ranking result.