US 12,088,674 B2
Method, electronic device, and computer program product for data processing
Zhen Jia, Shanghai (CN); Anzhou Hou, Shanghai (CN); Danqing Sha, Shanghai (CN); and Bin He, Shanghai (CN)
Assigned to EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed by EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed on Apr. 9, 2021, as Appl. No. 17/226,396.
Claims priority of application No. 202110276371.2 (CN), filed on Mar. 15, 2021.
Prior Publication US 2022/0294867 A1, Sep. 15, 2022
Int. Cl. G06F 15/16 (2006.01); G06F 16/783 (2019.01); H04L 67/131 (2022.01)
CPC H04L 67/131 (2022.05) [G06F 16/7834 (2019.01); G06F 16/7837 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, based on a category of a target data content segment requested by a terminal device, a target tag for the target data content segment;
acquiring a reference tag set, the reference tag set being generated at least in part by processing a plurality of distinct historical data groups comprising respective distinct sets of historical data content segments, the processing comprising identifying historical data content segments of the respective distinct sets of historical data content segments having duplicate content tags in the distinct historical data groups and deduplicating the historical data content segments of the respective distinct sets of historical data content segments by including in the reference tag set a plurality of reference tags for respective selected instances of the historical data content segments identified as having duplicate content tags in the distinct historical data groups, a reference tag in the reference tag set being generated based on a category of a historical data content segment previously provided to the terminal device; and
determining redundancy of the target data content segment based on comparison between the target tag and the reference tag set;
wherein the generating, acquiring and determining are performed in at least one computing device associated with an edge server;
wherein the at least one computing device associated with the edge server implements a trained machine learning model, the trained machine learning model being configured to process at least one of a foreground layer, a foreground object and a background layer of at least one image of the target data content segment requested by the terminal device, to generate at least a portion of the target tag as a semantic tag characterizing the at least one of the foreground layer, the foreground object and the background layer; and
wherein a result of the determining is utilized to control whether or not at least a portion of the target data content segment is provided from the edge server to the terminal device.