US 11,722,371 B2
Utilizing unstructured data in self-organized networks
Bruno dos Santos Silva, McKinney, TX (US); and Diogo Tadeu Silva de Araujo, Cedar Park, TX (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on May 17, 2021, as Appl. No. 17/302,939.
Application 17/302,939 is a continuation of application No. 16/527,204, filed on Jul. 31, 2019, granted, now 11,044,155.
Prior Publication US 2021/0273850 A1, Sep. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. H04W 24/02 (2009.01); H04L 41/0823 (2022.01); G06F 16/2458 (2019.01); G06N 3/08 (2023.01); H04L 41/16 (2022.01); G06N 3/044 (2023.01); H04W 84/18 (2009.01)
CPC H04L 41/0823 (2013.01) [G06F 16/2465 (2019.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01); H04L 41/16 (2013.01); G06F 2216/03 (2013.01); H04W 84/18 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for optimizing user experience by utilizing at least one self-organizing network (SON), the method comprising:
utilizing a SON controller to generate one or more predictions associated with one or more optimizations for a plurality of unstructured data, wherein the plurality of unstructured data is normalized and associated with one or more combined data sets, wherein normalizing the plurality of unstructured data includes:
associating a collected plurality of mobile data into a first data set and a collected plurality of social media data into a second data set;
fusing the first data set associated with the plurality of mobile data with the second data set associated with the plurality of social media data by appending at least one column of one data set into another data set by utilizing a data source to create the one or more combined data sets; and
structuring the collected plurality of unstructured data associated with the fused first data set and the corresponding fused second data set; and
implementing the one or more optimizations to an antennae signal based on the one or more predictions.