公开(公告)号：US11501107B2

公开(公告)日：2022-11-15

申请号：US16868942

申请日：2020-05-07

Applicant: Adobe Inc.

Inventor： Ayush Chauhan ,  Shiv Kumar Saini ,  Parth Gupta ,  Archiki Prasad ,  Amireddy Prashanth Reddy ,  Ritwick Chaudhry

IPC: G06K9/62 ,  G06N3/063 ,  G11C16/14 ,  G06Q10/10 ,  G06F7/544

Abstract: This disclosure involves using key-value memory networks to predict time-series data. For instance, a computing system retrieves, for a target entity, static feature data and target time-series feature data. The computing system can normalize the target time-series feature data based on a normalization scale. The computing system also generates input data by, for example, concatenating the static feature data, the normalized time-series feature data, and time-specific feature data. The computing system generates predicted time-series data for the target metric of the target entity by applying a key-value memory network to the input data. The key-value memory network can include a key matrix learned from training static feature data and training time-series feature data, a value matrix representing time-series trends, and an output layer with a continuous activation function for generating predicted time-series data.

公开(公告)号：US11694165B2

公开(公告)日：2023-07-04

申请号：US17960585

申请日：2022-10-05

Applicant: Adobe Inc.

Inventor： Ayush Chauhan ,  Shiv Kumar Saini ,  Parth Gupta ,  Archiki Prasad ,  Amireddy Prashanth Reddy ,  Ritwick Chaudhry

IPC: G06F18/214 ,  G06N3/063 ,  G06F18/24 ,  G11C16/14 ,  G06Q10/109 ,  G06F7/544

CPC classification number: G06F18/214 ,  G06F18/24 ,  G06N3/063 ,  G06F7/5443 ,  G06Q10/109 ,  G11C16/14

Abstract: A system implements a key value memory network including a key matrix with key vectors learned from training static feature data and time-series feature data, a value matrix with value vectors representing time-series trends, and an input layer to receive, for a target entity, input data comprising a concatenation of static feature data of the target entity, time-specific feature data, and time-series feature data for the target entity. The key value memory network also includes an entity-embedding layer to generate an input vector from the input data, a key-addressing layer to generate a weight vector indicating similarities between the key vectors and the input vector, a value-reading layer to compute a context vector from the weight and value vectors, and an output layer to generate predicted time-series data for a target metric of the target entity by applying a continuous activation function to the context vector and the input vector.

公开(公告)号：US20230031050A1

公开(公告)日：2023-02-02

申请号：US17960585

申请日：2022-10-05

Applicant: Adobe Inc.

Inventor： Ayush Chauhan ,  Shiv Kumar Saini ,  Parth Gupta ,  Archiki Prasad ,  Amireddy Prashanth Reddy ,  Ritwick Chaudhry

IPC: G06K9/62 ,  G06N3/063

Abstract: A system implements a key value memory network including a key matrix with key vectors learned from training static feature data and time-series feature data, a value matrix with value vectors representing time-series trends, and an input layer to receive, for a target entity, input data comprising a concatenation of static feature data of the target entity, time-specific feature data, and time-series feature data for the target entity. The key value memory network also includes an entity-embedding layer to generate an input vector from the input data, a key-addressing layer to generate a weight vector indicating similarities between the key vectors and the input vector, a value-reading layer to compute a context vector from the weight and value vectors, and an output layer to generate predicted time-series data for a target metric of the target entity by applying a continuous activation function to the context vector and the input vector.

公开(公告)号：US20210350175A1

公开(公告)日：2021-11-11

申请号：US16868942

申请日：2020-05-07

Applicant: Adobe Inc.

Inventor： Ayush Chauhan ,  Shiv Kumar Saini ,  Parth Gupta ,  Archiki Prasad ,  Amireddy Prashanth Reddy ,  Ritwick Chaudhry

IPC: G06K9/62 ,  G06F7/544 ,  G11C16/14 ,  G06Q10/10 ,  G06N3/063

Abstract: This disclosure involves using key-value memory networks to predict time-series data. For instance, a computing system retrieves, for a target entity, static feature data and target time-series feature data. The computing system can normalize the target time-series feature data based on a normalization scale. The computing system also generates input data by, for example, concatenating the static feature data, the normalized time-series feature data, and time-specific feature data. The computing system generates predicted time-series data for the target metric of the target entity by applying a key-value memory network to the input data. The key-value memory network can include a key matrix learned from training static feature data and training time-series feature data, a value matrix representing time-series trends, and an output layer with a continuous activation function for generating predicted time-series data.