US 11,886,478 B2
Performance metric prediction and content item text suggestion based upon content item text
Shaunak Mishra, Jersey City, NJ (US); Changwei Hu, New Providence, NJ (US); Kevin Yen, Jersey City, NJ (US); Manisha Verma, Secaucus, NJ (US); Yifan Hu, Mountain Lakes, NJ (US); Maxim Ivanovich Sviridenko, New York, NY (US); Avinash Chukka, Milpitas, CA (US); Max Edward Beech, Surrey (GB); Chao-Hung Wang, Taipei (TW); Hua-Ying Tsai, Hsinchu (TW); Kamil Michal Zasadzinski, Taipei (TW); Wei Yu Lin, Taipei (TW); and Yu Tian, Secaucus, NJ (US)
Assigned to Yahoo Assets LLC, New York, NY (US)
Filed by Verizon Media Inc., New York, NY (US)
Filed on May 7, 2021, as Appl. No. 17/314,137.
Prior Publication US 2022/0358153 A1, Nov. 10, 2022
Int. Cl. G06F 7/00 (2006.01); G06F 16/35 (2019.01); G06F 16/335 (2019.01); G06N 20/00 (2019.01); G06F 18/22 (2023.01); G06F 18/21 (2023.01)
CPC G06F 16/35 (2019.01) [G06F 16/335 (2019.01); G06F 18/217 (2023.01); G06F 18/22 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
displaying a content item text interface via a client device;
receiving, via the content item text interface, a first set of content item text;
determining, based upon the first set of content item text, a first performance metric score;
determining, based upon the first set of content item text and a plurality of sets of content item text associated with a plurality of content items, a plurality of similarity scores associated with the plurality of sets of content item text, wherein:
the plurality of sets of content item text comprises a second set of content item text of a first content item of the plurality of content items; and
a first similarity score of the plurality of similarity scores is associated with a similarity between the first set of content item text and the second set of content item text;
selecting, based upon the plurality of similarity scores and a plurality of performance metric scores associated with the plurality of sets of content item text, one or more sets of content item text from among the plurality of sets of content item text, wherein:
the plurality of performance metric scores comprises one or more performance metric scores associated with the one or more sets of content item text; and
the one or more performance metric scores are higher than the first performance metric score;
determining, based upon the first performance metric score and the one or more performance metric scores associated with the one or more sets of content item text, a text strength classification of the first set of content item text, wherein the text strength classification corresponds to a first classification based upon a determination of whether the one or more performance metric scores meet a threshold performance metric score based upon the first performance metric score; and
displaying, via the client device, at least one of one or more representations of the one or more sets of content item text or an indication of the text strength classification.