US 11,915,334 B2
Information processing device and information processing method for predicting presence or absence of user at visit destination from sensed data
Reiko Kirihara, Tokyo (JP); Norihiro Takahashi, Tokyo (JP); Saki Yokoyama, Tokyo (JP); and Satoshi Hosokawa, Tokyo (JP)
Assigned to SONY CORPORATION, Tokyo (JP); and SONY MOBILE COMMUNICATIONS INC., Tokyo (JP)
Appl. No. 16/641,380
Filed by SONY CORPORATION, Tokyo (JP); and SONY MOBILE COMMUNICATIONS INC., Tokyo (JP)
PCT Filed Jul. 3, 2018, PCT No. PCT/JP2018/025134
§ 371(c)(1), (2) Date Feb. 24, 2020,
PCT Pub. No. WO2019/049492, PCT Pub. Date Mar. 14, 2019.
Claims priority of application No. 2017-171780 (JP), filed on Sep. 7, 2017.
Prior Publication US 2020/0193546 A1, Jun. 18, 2020
Int. Cl. G10L 15/22 (2006.01); G06Q 50/28 (2012.01); G01C 21/34 (2006.01); G08B 21/02 (2006.01); G08B 21/22 (2006.01); G10L 15/00 (2013.01)
CPC G06Q 50/28 (2013.01) [G01C 21/34 (2013.01); G08B 21/02 (2013.01); G08B 21/22 (2013.01); G10L 15/00 (2013.01); G10L 15/005 (2013.01); G10L 15/22 (2013.01); G10L 15/222 (2013.01); G10L 2015/223 (2013.01)] 14 Claims
OG exemplary drawing
 
14. An information processing method executed by a processor, comprising:
acquiring sensed data associated with a first user;
acquiring action history data of the first user that includes a plurality of past actions of the first user;
determining a plurality of sensed data-action relevance scores based on the sensed data and the action history data, wherein each sensed data-action relevance score of the plurality of sensed data-action relevance scores indicates a relevance between the sensed data and a corresponding action of the plurality of past actions;
estimating an action of the first user from the plurality of past actions, based on the plurality of sensed data-action relevance scores;
acquiring lifestyle data associated with the first user;
determining a score indicating a relevance between the lifestyle data and the estimated action;
predicting a future action of the first user based on the determined score indicating the relevance between the lifestyle data and the estimated action;
predicting one of a presence of the first user or an absence of the first user at a visit destination, based on the predicted future action;
setting, based on an age of a second user that is less than a determined age, the second user as a non-target user for prediction of one of a presence of the second user or an absence of the second user at the visit destination; and
outputting, to an external device, a result of the prediction of the one of the presence or the absence of the first user at the visit destination.