US 11,727,058 B2
Unsupervised automatic taxonomy graph construction using search queries
Oren Sar Shalom, Nes Ziona (IL); Alexander Zhicharevich, Hod Hasharon (IL); Rami Cohen, Ashkelon (IL); and Yonatan Ben-Simhon, Tel Aviv (IL)
Assigned to Intuit Inc., Mountain View, CA (US)
Filed by Intuit Inc., Mountain View, CA (US)
Filed on Sep. 17, 2019, as Appl. No. 16/573,619.
Prior Publication US 2021/0081454 A1, Mar. 18, 2021
Int. Cl. G06F 16/901 (2019.01); G06F 16/953 (2019.01)
CPC G06F 16/9024 (2019.01) [G06F 16/953 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a plurality of search queries submitted to at least one computerized search engine, the plurality of search queries comprising a plurality of terms;
calculating, for each query in the plurality of search queries, a corresponding pairwise relation in the plurality of search queries,
wherein the corresponding pairwise relation comprises a corresponding probability of a potential edge relationship between at least two terms of the plurality of terms, to form a plurality of potential edges;
constructing a general graph from the plurality of terms in the plurality of search queries by selecting a plurality of edges from the plurality of potential edges,
wherein the general graph comprises a plurality of nodes representing the plurality of terms used in the plurality of search queries, and
wherein the general graph further comprises a plurality of edges representing semantic relationships among the plurality of nodes; and
constructing a hierarchical graph from the general graph by altering at least one of the plurality of edges among the plurality of nodes in the general graph to form the hierarchical graph.