公开(公告)号：US12086198B2

公开(公告)日：2024-09-10

申请号：US18461049

申请日：2023-09-05

申请人： Google LLC

发明人： Suddha Kalyan Basu ,  Wei Fan ,  Daniel Glasner ,  Sushrut Suresh Karanjkar ,  Thomas Richard Strohmann ,  Shubhang Verma ,  Manas Ashok Pathak ,  Wenyuan Yin ,  Sundeep Tirumalareddy

IPC分类号： G06F16/50 ,  G06F16/538 ,  G06F16/583 ,  G06F16/587 ,  G06F16/9538 ,  G06N3/02 ,  G06F16/90

CPC分类号： G06F16/9538 ,  G06F16/538 ,  G06F16/583 ,  G06F16/587 ,  G06N3/02

摘要： Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

公开(公告)号：US11782998B2

公开(公告)日：2023-10-10

申请号：US17277820

申请日：2020-02-28

申请人： Google LLC

发明人： Suddha Kalyan Basu ,  Wei Fan ,  Daniel Glasner ,  Sushrut Suresh Karanjkar ,  Thomas Richard Strohmann ,  Shubhang Verma ,  Manas Ashok Pathak ,  Wenyuan Yin ,  Sundeep Tirumalareddy

IPC分类号： G06F16/50 ,  G06N3/02 ,  G06F16/9538 ,  G06F16/583 ,  G06F16/538 ,  G06F16/587 ,  G06F16/90 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06F16/9538 ,  G06F16/538 ,  G06F16/583 ,  G06F16/587 ,  G06N3/02

摘要： Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

公开(公告)号：US20230409653A1

公开(公告)日：2023-12-21

申请号：US18461049

申请日：2023-09-05

申请人： Google LLC

发明人： Suddha Kalyan Basu ,  Wei Fan ,  Daniel Glasner ,  Sushrut Suresh Karanjkar ,  Thomas Richard Strohmann ,  Shubhang Verma ,  Manas Ashok Pathak ,  Wenyuan Yin ,  Sundeep Tirumalareddy

IPC分类号： G06F16/9538 ,  G06F16/583 ,  G06F16/538 ,  G06F16/587 ,  G06N3/02

CPC分类号： G06F16/9538 ,  G06F16/583 ,  G06F16/538 ,  G06F16/587 ,  G06N3/02

摘要： Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.