公开(公告)号：US11556841B2

公开(公告)日：2023-01-17

申请号：US16447810

申请日：2019-06-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Qing Duan ,  Xiaowen Zhang ,  Xiaoqing Wang ,  Junrui Xu

IPC: G06N20/00 ,  G06F16/29 ,  G06F16/901 ,  G06K9/62

Abstract: Technologies for generating a graph containing clusters of feature attribute values for training a machine learning model for content item selection and delivery are provided. The disclosed techniques include, for each entity, of a plurality of entities, a system identifies transitions from one geographic location to another geographic location. A graph is generated based on the transitions associated with each entity. The graph comprises nodes representing geographic locations and edges connecting the nodes. Each of the edges connects two nodes, represents a transition from one geographic location to another geographic location, and each edge represents an edge weight value that is based on frequencies of transitions between geographic locations represented by the two connected nodes. The system generates a plurality of clusters from the nodes based upon the edge weight value of each edge. The system includes the plurality of clusters as features in a machine learning model.

公开(公告)号：US20210133266A1

公开(公告)日：2021-05-06

申请号：US16669198

申请日：2019-10-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Xiaowen Zhang ,  Qing Duan ,  Xiaoqing Wang ,  Junrui Xu

IPC: G06F16/9536 ,  G06N20/00 ,  G06F16/9535

Abstract: In an example the output of a machine learned model is a score is then compared to a threshold, and if the score transgresses the threshold, the corresponding item is available to be recommended to the user via the graphical user interface. In an example embodiment, rather than a fixed (static) threshold, a dynamic threshold is utilized. This dynamic threshold is based on a harmonic mean of probabilities utilized in the GLMix model. Specifically, the GLMix model may calculate and utilize the probability that a user will engage with a particular item via a graphical user interface, and also a probability that a user will dismiss a particular item via a graphical user interface.

公开(公告)号：US11194877B2

公开(公告)日：2021-12-07

申请号：US16669198

申请日：2019-10-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Xiaowen Zhang ,  Qing Duan ,  Xiaoqing Wang ,  Junrui Xu

IPC: G06F16/9536 ,  G06F16/9535 ,  G06N20/00

Abstract: In an example the output of a machine learned model is a score is then compared to a threshold, and if the score transgresses the threshold, the corresponding item is available to be recommended to the user via the graphical user interface. In an example embodiment, rather than a fixed (static) threshold, a dynamic threshold is utilized. This dynamic threshold is based on a harmonic mean of probabilities utilized in the GLMix model. Specifically, the GLMix model may calculate and utilize the probability that a user will engage with a particular item via a graphical user interface, and also a probability that a user will dismiss a particular item via a graphical user interface.

公开(公告)号：US20200311162A1

公开(公告)日：2020-10-01

申请号：US16367716

申请日：2019-03-28

Applicant: Microsoft Technology Licensing, LLC

Inventor： Junrui Xu ,  Meng Meng ,  Girish Kathalagiri Somashekariah ,  Huichao Xue ,  Varun Mithal ,  Ada Cheuk Ying Yu

IPC: G06F16/9536 ,  G06F16/903 ,  G06N20/00

Abstract: The disclosed embodiments provide a system for selecting recommendations based on title transition embeddings. During operation, the system obtains a word embedding model of a set of job histories. Next, the system calculates similarities between pairs of the embeddings produced by the word embedding model from attributes associated with titles in the set of job histories. The system then identifies, based on the similarities, job titles with high similarity to a current title of the candidate. Finally, the system outputs the job titles for use in selecting job recommendations for the candidate.

公开(公告)号：US20210312237A1

公开(公告)日：2021-10-07

申请号：US16838773

申请日：2020-04-02

Applicant: Microsoft Technology Licensing, LLC

Inventor： Qing Duan ,  Junrui Xu ,  Huichao Xue ,  Jianqiang Shen

IPC: G06K9/62 ,  G06N3/08 ,  G06F3/0482

Abstract: In an example embodiment, a first machine learned model is trained to produce output, and a second machine learned model is then trained using training data that has been labeled, at least partially, using the output of the first machine learned model. The first machine learned model is trained to output a measure of how strong a positive signal in the training data really is. Specifically, this measure indicates the level of intention of a user who has engaged in a first user interface action with respect to a piece of content to engage in a subsequent second user interface action with the same piece of content.

公开(公告)号：US20200311568A1

公开(公告)日：2020-10-01

申请号：US16365050

申请日：2019-03-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Huichao Xue ,  Girish Kathalagiri Somashekariah ,  Ye Yuan ,  Varun Mithal ,  Junrui Xu ,  Ada Cheuk Ying Yu

IPC: G06N5/04 ,  G06F16/9535 ,  G06F16/9536 ,  G06N20/00 ,  G06F16/901

Abstract: In some embodiments, a computer system selects a first subset of candidate content items based on their filter scores that are generated based on a partial generalized linear mixed model comprising a baseline model and a user-based model, with the baseline model being a generalized linear model, and the user-based model being a random effects model based on user actions by the target user directed towards reference content items related to the candidate content items. In some embodiments, the computer system then selects a second subset from the first subset based on recommendation scores that are generated based on a full generalized linear mixed model comprising the baseline model, the user-based model, and an item-based model, with the item-based model being a random effects model based on user actions directed towards the candidate online content item by reference users related to the target user.

公开(公告)号：US11797619B2

公开(公告)日：2023-10-24

申请号：US16838773

申请日：2020-04-02

Applicant: Microsoft Technology Licensing, LLC

Inventor： Qing Duan ,  Junrui Xu ,  Huichao Xue ,  Jianqiang Shen

IPC: G06F3/0482 ,  G06F16/9535 ,  G06N3/08 ,  G06F18/214 ,  G06F18/22

CPC classification number: G06F16/9535 ,  G06F3/0482 ,  G06F18/2155 ,  G06F18/22 ,  G06N3/08

Abstract: In an example embodiment, a first machine learned model is trained to produce output, and a second machine learned model is then trained using training data that has been labeled, at least partially, using the output of the first machine learned model. The first machine learned model is trained to output a measure of how strong a positive signal in the training data really is. Specifically, this measure indicates the level of intention of a user who has engaged in a first user interface action with respect to a piece of content to engage in a subsequent second user interface action with the same piece of content.

公开(公告)号：US20210192460A1

公开(公告)日：2021-06-24

申请号：US16726547

申请日：2019-12-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Junrui Xu ,  Qing Duan ,  Xiaowen Zhang ,  Xiaoqing Wang ,  Benjamin Le ,  Aman Grover

IPC: G06Q10/10 ,  G06F16/9535 ,  G06F16/9538 ,  G06N20/00 ,  G06N5/04

Abstract: Technologies for leveraging machine learning techniques to present content items to an entity based upon prior interaction history of the entity are provided. The disclosed techniques include identifying a first plurality of content items with which the entity has interacted during prior entity sessions. Interactions include selecting, viewing, or dismissing content items during prior entity sessions. For each content item in the first plurality, a learned embedding is identified, where each of the embeddings represent a vector of content item features mapped in a vector space. An aggregated embedding is generated based on the identified embeddings. A comparison is performed between the aggregated embedding and embeddings corresponding to a second plurality of content items. Based on the comparison, a subset of content items from the second plurality of content items is identified. The subset of content items is then presented on a computing device of the entity.