US 11,720,632 B2
Genealogy item ranking and recommendation
Peng Jiang, Lehi, UT (US); Tyler Folkman, Lehi, UT (US); Tsung-Nan Liu, Lehi, UT (US); Yen-Yun Yu, Lehi, UT (US); Ruhan Wang, Lehi, UT (US); Jack Reese, Lehi, UT (US); and Azadeh Moghtaderi, Lehi, UT (US)
Assigned to Ancestry.com Operations Inc., Lehi, UT (US)
Filed by Ancestry.com Operations Inc., Lehi, UT (US)
Filed on Jan. 9, 2023, as Appl. No. 18/94,795.
Application 18/094,795 is a continuation of application No. 16/406,891, filed on May 8, 2019, granted, now 11,551,025.
Claims priority of provisional application 62/668,269, filed on May 8, 2018.
Claims priority of provisional application 62/668,795, filed on May 8, 2018.
Prior Publication US 2023/0161819 A1, May 25, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/901 (2019.01); G06N 20/00 (2019.01); G06F 18/2113 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01)
CPC G06F 16/9027 (2019.01) [G06F 18/2113 (2023.01); G06F 18/2148 (2023.01); G06F 18/2178 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a non-transitory computer-readable medium comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
generate, using a first feature generator configured to receive a first type of genealogy items and to generate a feature vector for each of the received first type of genealogy items, a first set of feature vectors for each of a plurality of the first type of genealogy items;
generate, using a second feature generator configured to receive a second type of genealogy items and to generate a feature vector for each of the received second type of genealogy items, a second set of feature vectors for each of a plurality of the second type of genealogy items;
generate, using a feature extender configured to transform a size of an input feature vector to an extended size, a set of extended feature vectors comprising feature vectors from the first and second sets of feature vectors, wherein each of the extended feature vectors has a normalized vector size;
input the set of extended feature vectors to a machine learning model configured to generate a rank-ordered list of the set of extended feature vectors; and
store a portion of the genealogy items corresponding to the extended feature vectors in rank-ordered list.