公开(公告)号：US10936950B1

公开(公告)日：2021-03-02

申请号：US16816719

申请日：2020-03-12

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Le Song

IPC: G06N3/08 ,  G06F16/21 ,  G06N3/04

Abstract: This disclosure relates to processing sequential interaction data through machine learning. In one aspect, a method includes obtaining a dynamic interaction graph constructed based on a dynamic interaction sequence. The dynamic interaction sequence includes interaction feature groups corresponding to interaction events. Each interaction feature group includes a first object, a second object, and an interaction time of an interaction event that involved the first object and the second object. The dynamic interaction graph includes multiple nodes including, for each interaction feature group, a first node that represents the first object of the interaction feature group and a second node that represents the second object of the interaction feature group. A current sequence corresponding to a current node to be analyzed is determined. The current sequence is input into a Transformer-based neural network model. The neural network model determines a feature vector corresponding to the current node.

公开(公告)号：US11636341B2

公开(公告)日：2023-04-25

申请号：US17188112

申请日：2021-03-01

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Le Song

IPC: G06N3/08 ,  G06F16/21 ,  G06N3/04

Abstract: This disclosure relates to processing sequential interaction data through machine learning. In one aspect, a method includes obtaining a dynamic interaction graph constructed based on a dynamic interaction sequence. The dynamic interaction sequence includes interaction feature groups corresponding to interaction events. Each interaction feature group includes a first object, a second object, and an interaction time of an interaction event that involved the first object and the second object. The dynamic interaction graph includes multiple nodes including, for each interaction feature group, a first node that represents the first object of the interaction feature group and a second node that represents the second object of the interaction feature group. A current sequence corresponding to a current node to be analyzed is determined. The current sequence is input into a Transformer-based neural network model. The neural network model determines a feature vector corresponding to the current node.

公开(公告)号：US11250088B2

公开(公告)日：2022-02-15

申请号：US17222968

申请日：2021-04-05

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Xuqin Liu ,  Le Song ,  Yuan Qi

IPC: G06F16/90 ,  G06F16/9536 ,  G06F16/901

Abstract: Computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for processing interaction sequence data are disclosed. One computer-implemented method includes: obtaining a dynamic interaction graph is obtained, where the dynamic interaction graph is constructed based on a dynamic interaction sequence, including a plurality of interactions arranged in a chronological order, where each interaction includes two objects involved in the interaction and a time of the interaction. In the dynamic interaction graph, a sub-graph corresponding to a target node is determined, where nodes in the sub-graph comprise the target node and connection nodes connected to the target node through a predetermined amount of edges originating from the target node. A feature vector corresponding to the target node is determined based on a node feature of each of the nodes of the sub-graph and directions of edges of the sub-graph.

公开(公告)号：US20210224347A1

公开(公告)日：2021-07-22

申请号：US17222968

申请日：2021-04-05

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Xuqin Liu ,  Le Song ,  Yuan Qi

IPC: G06F16/9536 ,  G06F16/901

Abstract: Computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for processing interaction sequence data are disclosed. One computer-implemented method includes: obtaining a dynamic interaction graph is obtained, where the dynamic interaction graph is constructed based on a dynamic interaction sequence, including a plurality of interactions arranged in a chronological order, where each interaction includes two objects involved in the interaction and a time of the interaction. In the dynamic interaction graph, a sub-graph corresponding to a target node is determined, where nodes in the sub-graph comprise the target node and connection nodes connected to the target node through a predetermined amount of edges originating from the target node. A feature vector corresponding to the target node is determined based on a node feature of each of the nodes of the sub-graph and directions of edges of the sub-graph.

公开(公告)号：US10970350B2

公开(公告)日：2021-04-06

申请号：US16813627

申请日：2020-03-09

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Xuqin Liu ,  Le Song ,  Yuan Qi

IPC: G06F16/90 ,  G06F16/9536 ,  G06F16/901

Abstract: Computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for processing interaction sequence data are disclosed. One computer-implemented method includes: obtaining a dynamic interaction graph is obtained, where the dynamic interaction graph is constructed based on a dynamic interaction sequence, including a plurality of interactions arranged in a chronological order, where each interaction includes two objects involved in the interaction and a time of the interaction. In the dynamic interaction graph, a sub-graph corresponding to a target node is determined, where nodes in the sub-graph comprise the target node and connection nodes connected to the target node through a predetermined amount of edges originating from the target node. A feature vector corresponding to the target node is determined based on a node feature of each of the nodes of the sub-graph and directions of edges of the sub-graph.

公开(公告)号：US20210049458A1

公开(公告)日：2021-02-18

申请号：US16816719

申请日：2020-03-12

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Le Song

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/21

Abstract: This disclosure relates to processing sequential interaction data through machine learning. In one aspect, a method includes obtaining a dynamic interaction graph constructed based on a dynamic interaction sequence. The dynamic interaction sequence includes interaction feature groups corresponding to interaction events. Each interaction feature group includes a first object, a second object, and an interaction time of an interaction event that involved the first object and the second object. The dynamic interaction graph includes multiple nodes including, for each interaction feature group, a first node that represents the first object of the interaction feature group and a second node that represents the second object of the interaction feature group. A current sequence corresponding to a current node to be analyzed is determined. The current sequence is input into a Transformer-based neural network model. The neural network model determines a feature vector corresponding to the current node.

公开(公告)号：US20210049225A1

公开(公告)日：2021-02-18

申请号：US16813627

申请日：2020-03-09

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiaofu Chang ,  Jianfeng Wen ,  Xuqin Liu ,  Le Song ,  Yuan Qi

IPC: G06F16/9536 ,  G06N3/04 ,  G06K9/62 ,  G06F16/901

Abstract: Computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for processing interaction sequence data are disclosed. One computer-implemented method includes: obtaining a dynamic interaction graph is obtained, where the dynamic interaction graph is constructed based on a dynamic interaction sequence, including a plurality of interactions arranged in a chronological order, where each interaction includes two objects involved in the interaction and a time of the interaction. In the dynamic interaction graph, a sub-graph corresponding to a target node is determined, where nodes in the sub-graph comprise the target node and connection nodes connected to the target node through a predetermined amount of edges originating from the target node. A feature vector corresponding to the target node is determined based on a node feature of each of the nodes of the sub-graph and directions of edges of the sub-graph.