公开(公告)号：US11816636B2

公开(公告)日：2023-11-14

申请号：US17412753

申请日：2021-08-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Liwei Wu ,  Wenjia Ma ,  Jaewon Yang ,  Yanen Li

IPC: G06Q10/1053 ,  G06N20/20 ,  G06Q10/0631 ,  G06N5/01

CPC classification number: G06Q10/1053 ,  G06N5/01 ,  G06N20/20 ,  G06Q10/063112

Abstract: Techniques for mining training data for use in training a dependency model are disclosed herein. In some embodiments, a computer-implemented method comprises: obtaining training data comprising a plurality of reference skill pairs, each reference skill pair comprising a corresponding first reference skill and a corresponding second reference skill, the plurality of reference skill pairs being included in the training data based on a co-occurrence of the corresponding first and second reference skills for each reference skill pair in the plurality of reference skill pairs, the co-occurrence comprising the corresponding first and second reference skills co-occurring for a same entity; and training a dependency model with a machine learning algorithm using the training data, the dependency model comprising a logistic regression model or a data gradient boosted decision tree (GBDT) model. The dependency model may then be used to identify corresponding dependency relations for a plurality of target skill pairs.

公开(公告)号：US20230086724A1

公开(公告)日：2023-03-23

申请号：US17412753

申请日：2021-08-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Liwei Wu ,  Wenjia Ma ,  Jaewon Yang ,  Yanen Li

IPC: G06Q10/10 ,  G06Q10/06 ,  G06N20/20 ,  G06N5/00

Abstract: Techniques for mining training data for use in training a dependency model are disclosed herein. In some embodiments, a computer-implemented method comprises: obtaining training data comprising a plurality of reference skill pairs, each reference skill pair comprising a corresponding first reference skill and a corresponding second reference skill, the plurality of reference skill pairs being included in the training data based on a co-occurrence of the corresponding first and second reference skills for each reference skill pair in the plurality of reference skill pairs, the co-occurrence comprising the corresponding first and second reference skills co-occurring for a same entity; and training a dependency model with a machine learning algorithm using the training data, the dependency model comprising a logistic regression model or a data gradient boosted decision tree (GBDT) model. The dependency model may then be used to identify corresponding dependency relations for a plurality of target skill pairs.