US 12,271,386 B2
Determination apparatus, determination method, and non-transitory computer readable storage medium
Kota Tsubouchi, Tokyo (JP); Shuji Yamaguchi, Tokyo (JP); and Hiroaki Taguchi, Tokyo (JP)
Assigned to YAHOO JAPAN CORPORATION, Tokyo (JP)
Filed by Yahoo Japan Corporation, Tokyo (JP)
Filed on Mar. 10, 2021, as Appl. No. 17/198,008.
Claims priority of application No. 2020-050258 (JP), filed on Mar. 19, 2020.
Prior Publication US 2021/0357415 A1, Nov. 18, 2021
Int. Cl. G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06F 16/28 (2019.01)
CPC G06F 16/24573 (2019.01) [G06F 16/24575 (2019.01); G06F 16/24578 (2019.01); G06F 16/248 (2019.01); G06F 16/285 (2019.01)] 13 Claims
OG exemplary drawing
 
1. A determination device comprising:
a processor, configured to:
acquire a search log;
acquire a reference query from an operator;
specify, using the search log, a plurality of input customers who have input the reference query;
specify, using the search log, search queries input by the plurality of input customers;
divide the search queries into time periods based on dates and times when the search queries were input, wherein the time periods comprise one or more positive periods and one or more negative periods, wherein each of the one or more positive time periods is a time period after a date and time when the reference query was input, and each of the one or more negative time periods is a time period before the date and time when the reference query was input;
categorize, for each time period, the search queries into categories;
determine, for each time period, a number of categories required to account for more than a predetermined percentage of the categorized search queries;
determine, for each time period, whether the determined number of categories exceeds a threshold value;
in response to determining, for at least one of the time periods comprising the one or more positive periods and the one or more negative periods, that the determined number of categories exceeds the threshold value, modify a length of the at least one of the time periods; and
perform listing optimization associated with the search queries based on modified length of each time period.