US 11,940,879 B2
Data protection method, electronic device and computer program product
Qiang Chen, Shanghai (CN); Jing Yu, Shanghai (CN); Jiayang Xu, Shanghai (CN); and Danqing Sha, Shanghai (CN)
Assigned to EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed by EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed on Sep. 30, 2020, as Appl. No. 17/060,040.
Claims priority of application No. 202010787827.7 (CN), filed on Aug. 7, 2020.
Prior Publication US 2022/0043714 A1, Feb. 10, 2022
Int. Cl. G06F 11/14 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/1451 (2013.01) [G06N 20/00 (2019.01); G06F 2201/84 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A data protection method, comprising:
determining an object feature for each protection object in a set of protection objects to obtain determined object features, the set of protection objects comprising a protection object configured with a predetermined data protection strategy, wherein the protection object comprises a predetermined attribute, an external attribute, and an internal attribute, wherein the set of protection objects comprises at least one of the following: a virtual machine, a database, a physical device, or a file system, and wherein the predetermined attribute specifies one of an operating system of the protection object, a size of storage devices of the protection object, and a number of processing units of the protection object;
monitoring the protection object from outside of the operating system of the protection object to obtain the external attribute;
logging into the operating system of the protection object to obtain the internal attribute;
training a classification model based on a corresponding object feature of the protection object, wherein the classification model comprises a support vector machine, wherein the object feature of the protection object comprises a plurality of feature items;
determining, using the classification model, a set of candidate objects belonging to a same class as the protection object according to the determined object feature of the protection object;
ranking the set of candidate objects according to the plurality of feature items to obtain a set of ranked candidate objects;
determining at least one candidate object based on the set of ranked candidate objects; and
configuring the predetermined data protection strategy to include the at least one candidate object.