US 11,914,651 B2
Classification and selective filtering of a data set
Prabhuranjan Parhi, Visakhapatnam (IN); Mohan Gopal Meher, Sonepur (IN); Utpal Kanti Patra, Visakhapatnam (IN); and Jyothi Jaggumahantri, Visakhapatnam (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Nov. 6, 2019, as Appl. No. 16/675,327.
Prior Publication US 2021/0133249 A1, May 6, 2021
Int. Cl. G06F 16/90 (2019.01); G06F 16/9035 (2019.01); G06F 16/906 (2019.01)
CPC G06F 16/9035 (2019.01) [G06F 16/906 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method for classifying and filtering data, the method comprising:
training a classification neural network model using data associated with different content categories;
categorizing, by one or more computer processors using the classification neural network model, a portion of a data segment according to content of the portion to identify a category;
translating, by the one or more computer processors, the category into an entry in a user content preference dictionary;
correlating, by the one or more computer processors, the portion with the user content preference dictionary;
assigning, by the one or more computer processors, a content weight to the portion according to correlated entries in the user content preference dictionary;
setting a threshold value for the category;
determining, by the one or more computer processors, that the content weight falls below the threshold value, or falls at or above the threshold value;
masking from presentation, by the one or more computer processors, the portion having a content weight below a threshold value;
presenting the portion having a content weight at or above the threshold value upon a display;
adjusting the threshold value according to user activities yielding an adjusted threshold value for the category; and
presenting a portion having a content weight at or above the adjusted threshold value upon the display.