公开(公告)号：US20200250234A1

公开(公告)日：2020-08-06

申请号：US16267001

申请日：2019-02-04

Applicant: Adobe Inc.

Inventor： Tommaso Teofili ,  Antonio Sanso

IPC: G06F16/901 ,  G06F16/903 ,  G06K9/62 ,  G06F16/185

Abstract: A computer system generates a similarity-optimized hierarchy for hierarchical data to improve data access performance and content discovery. An example method includes receiving hierarchical data in an original hierarchy having a plurality of nodes and a depth of d, generating a respective embedding for each node of the plurality of nodes, and determining, for each node of the plurality of nodes, respective k-nearest neighbors based on the respective embedding. Starting with nodes at depth din the original hierarchy, the method includes generating sibling groups, each sibling group having at least one node at depth d, identifying, for each node at depth d, a similarity-optimized parent from depth d−1, and associating each node at depth d with its respective similarity-optimized parent in a similarity-optimized hierarchy. The method also includes completing the similarity-optimized hierarchy by repeating the generating, identifying and associating with nodes at depth d−1 until reaching the hierarchy root.

公开(公告)号：US11361096B2

公开(公告)日：2022-06-14

申请号：US16513961

申请日：2019-07-17

Applicant: Adobe Inc.

Inventor： Antonio Sanso ,  Tommaso Teofili

IPC: G06F21/62 ,  G06F16/25

Abstract: Certain embodiments involve controlling the timing of digital publication of sensitive data over a data network, especially in a case where a requirement exists to publish the sensitive data within an established timeframe. For instance, a computing system receives from a client device a request to publish sensitive data. The computing system provides to the client device a challenge useable as input to a verifiable delay function (VDF), responsive to the request. The computing system receives a response to the challenge along with the sensitive data and verifies that the response is a solution to the VDF applied to the challenge. Based on verifying the solution, the computing system publishes the sensitive data.

公开(公告)号：US11163831B2

公开(公告)日：2021-11-02

申请号：US16267001

申请日：2019-02-04

Applicant: Adobe Inc.

Inventor： Tommaso Teofili ,  Antonio Sanso

IPC: G06F16/901 ,  G06K9/62 ,  G06F16/903 ,  G06F16/185

Abstract: A computer system generates a similarity-optimized hierarchy for hierarchical data to improve data access performance and content discovery. An example method includes receiving hierarchical data in an original hierarchy having a plurality of nodes and a depth of d, generating a respective embedding for each node of the plurality of nodes, and determining, for each node of the plurality of nodes, respective k-nearest neighbors based on the respective embedding. Starting with nodes at depth din the original hierarchy, the method includes generating sibling groups, each sibling group having at least one node at depth d, identifying, for each node at depth d, a similarity-optimized parent from depth d−1, and associating each node at depth d with its respective similarity-optimized parent in a similarity-optimized hierarchy. The method also includes completing the similarity-optimized hierarchy by repeating the generating, identifying and associating with nodes at depth d−1 until reaching the hierarchy root.

公开(公告)号：US20210019435A1

公开(公告)日：2021-01-21

申请号：US16513961

申请日：2019-07-17

Applicant: Adobe Inc.

Inventor： Antonio Sanso ,  Tommaso Teofili

IPC: G06F21/62 ,  G06F16/25

Abstract: Certain embodiments involve controlling the timing of digital publication of sensitive data over a data network, especially in a case where a requirement exists to publish the sensitive data within an established timeframe. For instance, a computing system receives from a client device a request to publish sensitive data. The computing system provides to the client device a challenge useable as input to a verifiable delay function (VDF), responsive to the request. The computing system receives a response to the challenge along with the sensitive data and verifies that the response is a solution to the VDF applied to the challenge. Based on verifying the solution, the computing system publishes the sensitive data.

公开(公告)号：US11487709B2

公开(公告)日：2022-11-01

申请号：US16779214

申请日：2020-01-31

Applicant: ADOBE INC.

Inventor： Tommaso Teofili ,  Antonio Sanso

IPC: G06F16/178 ,  H04L67/1095 ,  H04L67/1097 ,  G06F16/182 ,  G06F16/93 ,  G06N3/04

Abstract: Embodiments of the present invention are directed toward systems, methods, and computer storage media for using a neural network language model to identify semantic relationships between file storage specifications for replication requests. By treating file storage specifications (or at least a portion thereof) as “words” in the language model, replication vectors can be determined based on the file storage specifications. Instead of determining the relationship of the file storage specifications based on ordering within a document, the relationship can be based on proximity of the replication requests in a replication session. When a replication request is received from a user, the replication vectors can be used to determine a semantic similarity between the received replication request and one or more additional replication requests.

公开(公告)号：US10970289B2

公开(公告)日：2021-04-06

申请号：US15160743

申请日：2016-05-20

Applicant: Adobe Inc.

Inventor： Tommaso Teofili ,  Michael Marth

IPC: G06F16/2457 ,  G06F16/248

Abstract: Certain embodiments involve ranking search results from an information retrieval system using user query data to provide relevant search results to users of the information retrieval system. For example, a system determines a weight factor associated with a first user that provides a query to the information retrieval system based on a type or role of the first user. The system further determines a boost factor associated with the first user based on the weight factor and a number of consecutive search queries provided by the user. The system uses the boost factor to automatically tune a ranking algorithm to adjust a rank of a search result item resulting from a search query provided by a second user.