Action estimation device, action estimation method, and recording medium
AssigneePanasonic Intellectual Property Corporation of America
InventorsTaketoshi NAKAO, Toshiyuki MATSUMURA, Tatsumi NAGASHIMA, Tetsuji FUCHIKAMI
Life of this patent
Estimating the term…
Abstract
An action estimation device includes: an obtainer that obtains sound information pertaining to an inaudible sound, the inaudible sound being a sound in an ultrasonic band collected by a sound collector; and an estimator that estimates an output result, obtained by inputting the sound information obtained by the obtainer into a trained model indicating a relationship between the sound information and action information pertaining to an action of a person, as the action information of the person.
Claims11
An action estimation device comprising:
- an obtainer that obtains sound information pertaining to an inaudible sound, the inaudible sound being a sound in an ultrasonic band collected by a sound collector;
- an estimator that estimates an output result, obtained by inputting the sound information obtained by the obtainer into a trained model indicating a relationship between the sound information and action information pertaining to an action of a person, as the action information of the person;
- a date and time information recorder that records date and time information pertaining to a date and time at which the inaudible sound is collected by the sound collector;
- an adjuster that adjusts a sound collection frequency of the sound collector based on a number of times the action information of the person is estimated by the estimator and the date and time information recorded by the date and time information recorder;
- and
- an outputter that outputs, to the sound collector, information pertaining to the sound collection frequency adjusted by the adjuster.
An action estimation method comprising:
- obtaining sound information pertaining to an inaudible sound, the inaudible sound being a sound in an ultrasonic band collected by a sound collector;
- estimating an output result, obtained by inputting the sound information obtained in the obtaining into a trained model indicating a relationship between the sound information and action information pertaining to an action of a person, as the action information of the person;
- recording date and time information pertaining to a date and time at which the inaudible sound is collected by the sound collector;
- adjusting a sound collection frequency of the sound collector based on a number of times the action information of the person is estimated in the estimating and the date and time information recorded in the recording;
- and
- outputting, to the sound collector, information pertaining to the sound collection frequency adjusted in the adjusting.
Dependencies are inferred from the claim text.