Walking state learning method, walking state estimation method, road surface condition understanding method, device, and program

摘要

PROBLEM TO BE SOLVED: To accurately recognize a road surface condition according to a walking state of a user. SOLUTION: A series data extraction unit 26 extracts series data representing a series of output values from walking data in which output values of a sensor provided in a portable device 12 carried by a user are recorded together with a time stamp. The unit data extraction unit 28 extracts unit data, which is data in which the series data is divided into unit times, for each unit time from the series data. The label generation unit 30 assigns a label indicating the type of the user's walking state to each unit data based on the input annotation data in which the type of the walking state of the user is recorded in time series together with the time stamp. The learning unit 34 learns a learning model for estimating the label corresponding to the unit data based on each of the unit data and the label given for each unit data by the label generation unit 30. [Selection diagram] Fig. 1