公开(公告)号：US12141827B1

公开(公告)日：2024-11-12

申请号：US17548055

申请日：2021-12-10

Applicant: Amazon Technologies, Inc.

Inventor： Sunil Mallya Kasaragod ,  Abhinav Goyal ,  Yahor Pushkin ,  Srikanth Doss Kadarundalagi Raghura ,  Rishita Rajal Anubhai ,  Kasturi Bhattacharjee ,  Smaranda Muresan ,  Siddharth Chaitanyakumar Varia ,  Federico Torreti

IPC: G06F40/284 ,  G06F40/205 ,  G06Q10/0631 ,  G06Q30/0204

Abstract: A global segmenting and analysis service of a provider network may receive documents (e.g., posts, product reviews) from different applications. The service may analyze the documents to identify target entities and sentiment. The service may generate different levels of sentiment data and store data into a segmented database. For example, the service may store within-document level sentiment, document-level sentiment, and multi-document level sentiment for a target entity. The service may also update the entity taxonomy automatically or with only a small number of sample documents. The client may query the service for the segmented sentiment data.

公开(公告)号：US20240160651A1

公开(公告)日：2024-05-16

申请号：US18065803

申请日：2022-12-14

Applicant: Amazon Technologies, Inc.

Inventor： Kasturi Bhattacharjee ,  Rashmi Gangadharaiah ,  Senthil C. Chidambaram ,  Ankit Kapoor ,  Sharon Shapira ,  Tony Chun Tung Ng ,  Deepak Seetharam Nadig

IPC: G06F16/2457 ,  G06F16/242 ,  G06F16/28

CPC classification number: G06F16/24578 ,  G06F16/242 ,  G06F16/285

Abstract: Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified.

公开(公告)号：US20250029129A1

公开(公告)日：2025-01-23

申请号：US18908673

申请日：2024-10-07

Applicant: Amazon Technologies, Inc.

Inventor： Sunil Mallya Kasaragod ,  Abhinav Goyal ,  Yahor Pushkin ,  Srikanth Doss Kadarundalagi Raghura ,  Rishita Rajal Anubhai ,  Kasturi Bhattacharjee ,  Smaranda Muresan ,  Siddharth Chaitanyakumar Varia ,  Federico Torreti

IPC: G06Q30/0204 ,  G06F40/205 ,  G06F40/284 ,  G06Q10/0631

Abstract: A global segmenting and analysis service of a provider network may receive documents (e.g., posts, product reviews) from different applications. The service may analyze the documents to identify target entities and sentiment. The service may generate different levels of sentiment data and store data into a segmented database. For example, the service may store within-document level sentiment, document-level sentiment, and multi-document level sentiment for a target entity. The service may also update the entity taxonomy automatically or with only a small number of sample documents. The client may query the service for the segmented sentiment data.

公开(公告)号：US11689432B1

公开(公告)日：2023-06-27

申请号：US17657437

申请日：2022-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Kasturi Bhattacharjee ,  Rashmi Gangadharaiah ,  Sharon Shapira ,  Ankit Kapoor ,  Tony Chun Tung Ng ,  Senthil Chock Chidambaram ,  Deepak Seetharam Nadig

IPC: H04L41/5061 ,  H04L41/50 ,  H04L41/5074

CPC classification number: H04L41/5064 ,  H04L41/5032 ,  H04L41/5074

Abstract: The present disclosure generally relates to a feedback processing service that can receive customer input, as customer feedback corresponds to a service context. The feedback processing service aggregates semantically similar feedback as a cluster. Then, the feedback processing service can prioritize each of the clusters by ranking each of the clusters.