US 11,921,674 B2
Data compression by using cognitive created dictionaries
Sharathchandra Umapathirao Pankanti, Yorktown Heights, NY (US); Erik Rueger, Kelsterbach (DE); and Rolf Schaefer, Kelsterbach (DE)
Assigned to BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD., Beijing (CN)
Filed by BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Aug. 18, 2020, as Appl. No. 16/996,049.
Application 16/996,049 is a continuation of application No. 15/475,939, filed on Mar. 31, 2017, granted, now 10,838,922.
Prior Publication US 2020/0379953 A1, Dec. 3, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/17 (2019.01); G06F 16/174 (2019.01); G06N 3/045 (2023.01); G06N 5/045 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/1744 (2019.01) [G06N 3/045 (2023.01); G06N 5/045 (2013.01); G06N 20/00 (2019.01)] 5 Claims
OG exemplary drawing
 
1. A computer-implemented compression method, the method comprising:
creating compressed data via a first system from input data;
sending a decoding hint detailing a compression strategy for the compressed data and the compressed data from the first system to a second system,
wherein the first system teaches the second system how to recreate the input using the decoding hint while the second system teaches the first system a result of recreating the input data using the teaching that the first system provides to the second system;
wherein the compressed data is created with a minimum size with an effort level of decoding, the effort level of decoding is dependent on a number of computing steps of the second system, and
wherein feedback is sent to the first system if the recreated input and the input do not match;
the method further comprising:
in response to receiving the feedback by the first system,
modifying the compression strategy for the input data;
updating the decoding hint to detail the modified compression strategy;
repeating the creating and the sending to confirm that the modified compression strategy creates compressed data including a minimum size by comparing a new size to the measured size; and
in response to determining that a quality of the recreated input is greater than a predetermined threshold value, sending the compressed data and stopping sending the decoding hint to the second system, the quality of the recreated input is a difference between the input and the recreated input.