Title:
TYPE ESTIMATION MODEL GENERATION SYSTEM AND TYPE ESTIMATION SYSTEM
Document Type and Number:
WIPO Patent Application WO/2021/005982
Kind Code:
A1
Abstract:
The present invention aims to appropriately classify users on the basis of songs used. A model generation system 10 included in a recommendation server 1 is a type estimation model generation system that generates type estimation models used in type estimation regarding which of a plurality of types a user belongs. The model generation system for type estimation comprises: a training data acquisition unit 11 that obtains time series information for training, which is training data used in machine learning and indicates time series information pertaining to a plurality of songs that have been used, and type information for training, which indicates the type that the user who used the plurality of songs belongs to; and a model generation unit 12 that, once information on the basis of the time series information for training has been entered into a type estimation model, in song units and in the time series order, performs machine learning using the information on the basis of the type information for learning, as outputs for the type estimation model, and generates a type estimation model.
Inventors:
TANAKA SHIGEKI (JP)
FUKAZAWA YUSUKE (JP)
FUKAZAWA YUSUKE (JP)
Application Number:
PCT/JP2020/023774
Publication Date:
January 14, 2021
Filing Date:
June 17, 2020
Export Citation:
Assignee:
NTT DOCOMO INC (JP)
International Classes:
G10K15/04; G06F16/906; G16C20/70
Domestic Patent References:
| WO2017155966A1 | 2017-09-14 |
Foreign References:
| US20150297109A1 | 2015-10-22 | |||
| JP2008176398A | 2008-07-31 |
Attorney, Agent or Firm:
HASEGAWA Yoshiki et al. (JP)
Download PDF:
Previous Patent: SURFACE TREATMENT AGENT
Next Patent: WORKING FLUID COMPOSITION FOR REFRIGERATOR, REFRIGERATOR OIL AND REFRIGERATOR
Next Patent: WORKING FLUID COMPOSITION FOR REFRIGERATOR, REFRIGERATOR OIL AND REFRIGERATOR