公开(公告)号：US12260628B2

公开(公告)日：2025-03-25

申请号：US17724140

申请日：2022-04-19

Applicant: Lemon Inc.

Inventor： Xiangyu Zeng ,  Hongyu Xiong ,  Yiqi Feng ,  Han Wang ,  Yuan Gao ,  Qingyi Lu ,  Rui Li

IPC: G06V10/80 ,  G06V10/22 ,  G06V10/40 ,  G06V20/40 ,  G06V20/62 ,  G06V30/14 ,  G10L15/26

Abstract: Implementations of the present disclosure relate to methods, devices, and computer program products of extracting a feature for multimedia data that comprises a plurality of medium types. In a method, a first feature is determined for a first medium type in the plurality of medium types by masking a portion in a first medium object with the first medium type. A second feature is determined for a second medium type other than the first medium type in the plurality of medium types. The feature is generated for the multimedia data based on the first and second features. With these implementations, multiple medium types are considered in the feature extraction, and thus the feature may fully reflect various aspects of the multimedia data in an accurate way.

公开(公告)号：US11675873B1

公开(公告)日：2023-06-13

申请号：US17809513

申请日：2022-06-28

Applicant: Lemon Inc.

Inventor： Han Wang ,  Hongyu Xiong ,  Zheng Chen ,  Tianyu Zhang ,  Yiqi Feng ,  Yuan Gao ,  Xiangyu Zeng ,  Rui Li ,  Qingyi Lu ,  Yihan Yang ,  Yu Zhang ,  Bin Liu

IPC: G06F16/958 ,  G06F16/954

CPC classification number: G06F16/958 ,  G06F16/954

Abstract: There are provided methods, devices, and computer program products for similarity determination. In a method, first and second access data are obtained for a first and a second group of users who access a first and a second website, respectively. A first and a second jump path are generated for the first and second groups of users based on the first and second access data, respectively. The first and second jump paths describe access history for the first and second groups of users among webpages in the first and second websites, respectively. A similarity is determined between the first and second websites based on the first and second jump paths. Here, access data are used for similarity determination and unvisited webpages are not considered in the similarity determination. Therefore, the computation workload may be lowered, and the noise caused by the unvisited webpages may be reduced.

公开(公告)号：US12204850B2

公开(公告)日：2025-01-21

申请号：US17728248

申请日：2022-04-25

Applicant: LEMON INC.

Inventor： Hongyu Xiong ,  Han Wang ,  Rui Li ,  Yiqi Feng ,  Yuan Gao ,  Xiangyu Zeng ,  Qingyi Lu ,  Bin Liu

IPC: G06F40/211 ,  G06F16/33 ,  G06F40/14 ,  G06F40/30

Abstract: Embodiments of the present disclosure relate to semantic parsing for short text. According to embodiments of the present disclosure, a method is proposed. The method comprises: obtaining a set of sentences associated with a short text, each of the set of sentences containing all of words in the short text; determining a set of syntactic features associated with the set of sentences, each of the set of syntactic features indicating at least one of a constituency relation and a dependency relation of the corresponding sentence; and determining a semantic structure of the short text based on the set of syntactic features.

公开(公告)号：US20230359824A1

公开(公告)日：2023-11-09

申请号：US17737918

申请日：2022-05-05

Applicant: Lemon Inc.

Inventor： Qingyi Lu ,  Yuan Gao ,  Hongyu Xiong ,  Han Wang ,  Bin Liu ,  Xiangyu Zeng ,  Rui Li ,  Yiqi Feng

IPC: G06F40/295 ,  G06F40/30 ,  G06F16/901

CPC classification number: G06F40/295 ,  G06F16/9024 ,  G06F40/30 ,  G06N20/00

Abstract: Embodiments of the present disclosure relate to feature crossing for machine learning. According to example embodiments of the present disclosure, a method comprises determining a semantic correlation relationship between a plurality of feature categories, the semantic correlation relationship indicating respective degrees of semantic correlation between respective pairs of feature categories among the plurality of feature categories; obtaining at least two features classified in at least two of the plurality of feature categories for machine learning; and performing feature crossing on the at least two features based on the semantic correlation relationship.