公开(公告)号：US20230065676A1

公开(公告)日：2023-03-02

申请号：US17462814

申请日：2021-08-31

Applicant: Cisco Technology, Inc.

Inventor： Joel Abraham Obstfeld ,  Pete Rai ,  Marcelo Yannuzzi

IPC: G06K19/06 ,  H04L29/08

Abstract: In one embodiment, a code authentication service maintains a mapping of uniform resource locators and key information embedded into codes. The code authentication service receives, from a requesting device, a domain name system resolution request for a particular uniform resource locator. The code authentication service determines, based on the mapping, whether the domain name system resolution request is associated with valid key information for the particular uniform resource locator. The code authentication service provides, to the requesting device, a domain name system resolution response that indicates an address associated with the particular uniform resource locator, when the code authentication service determines that the domain name system resolution request includes valid key information for the particular uniform resource locator.

公开(公告)号：US20200218751A1

公开(公告)日：2020-07-09

申请号：US16819783

申请日：2020-03-16

Applicant: Cisco Technology, Inc.

Inventor： Hugo Latapie ,  Enzo Fenoglio ,  Andre Surcouf ,  Joseph T. Friel ,  Pete Rai

IPC: G06F16/36 ,  H04L12/24 ,  G06F16/33 ,  G06F16/9535

Abstract: A method comprises collecting, by a computing device located at an edge of a network, data items corresponding to information transmitted by endpoints using the network, generating, by the computing device, a probabilistic hierarchy using the data items, generating, by the computing device using the probabilistic hierarchy and natural language data, a similarity metric, generating, by the computing device using the probabilistic hierarchy, the natural language data, and the similarity metric, an ontology, detecting, by the computing device using the ontology, an anomaly, and in response to detecting the anomaly, sending a notification.

公开(公告)号：US10542298B2

公开(公告)日：2020-01-21

申请号：US15447215

申请日：2017-03-02

Applicant: Cisco Technology, Inc.

Inventor： Stephen Tallamy ,  Pete Rai ,  Colin John Davies ,  Simon Dyke ,  Olivier Frebourg

IPC: H04N21/234 ,  H04N21/2187 ,  H04N21/258 ,  H04N21/2668 ,  H04N21/25 ,  H04N21/475 ,  H04N21/2665

Abstract: A method for generating ad hoc video stream channels is implemented on at least one computing device and includes: receiving a multiplicity of incoming user video feeds, where schedules for the incoming user video feeds are unknown; classifying the multiplicity of incoming user video feeds according to at least a genre; selecting at least one incoming video feed from among the multiplicity of incoming user video feeds for inclusion in at least one video stream channel, where the selecting is according to selection criteria, and the selection criteria are based at least on the classifying; generating at least one outgoing video stream for the at least one video stream channel according to the selecting; and delivering the at least one outgoing video stream to presentation devices.

公开(公告)号：US20150193497A1

公开(公告)日：2015-07-09

申请号：US14474153

申请日：2014-08-31

Applicant: Cisco Technology, Inc.

Inventor： Stephen Charles Tallamy ,  Laurent Edmond Pierre Bertrand ,  Pete Rai

IPC: G06F17/30

CPC classification number: G06F17/30386 ,  G06N5/02 ,  G06N5/022

Abstract: In one embodiment, a method includes obtaining a first data set from a first data source and a second data set from a second data source, the first data set including a first plurality of entities and the second data set including a second plurality of entities. The method also includes identifying a verified relationship between a first entity from the first plurality of entities and a second entity from the second plurality of entities and determining that a third entity from the first plurality of entities has a first same-as relationship with a fourth entity from the second plurality of entities based on one or more of the verified relationship or relationships between the first plurality of entities and the second plurality of entities. The method further includes generating first output data including the first same-as relationship.

Abstract translation: 在一个实施例中，一种方法包括从第一数据源和第二数据源获得第一数据集，第一数据集包括第一多个实体，第二数据集包括第二多个实体。 该方法还包括识别来自第一多个实体的第一实体与来自第二多个实体的第二实体之间的经验证的关系，并且确定来自第一多个实体的第三实体具有与第四个实体的第一个相同的关系 基于所述第一多个实体和所述第二多个实体之间的经验证的关系或关系中的一个或多个，来自所述第二多个实体的实体。 该方法还包括产生包括第一相同关系的第一输出数据。

公开(公告)号：US20240232307A1

公开(公告)日：2024-07-11

申请号：US18151242

申请日：2023-01-06

Applicant: Cisco Technology, Inc.

Inventor： Pete Rai ,  Joel Abraham Obstfeld ,  Simon Peter James Dyke ,  James Geoffrey Walker

IPC: G06F21/32

CPC classification number: G06F21/32 ,  G06F2221/2133

Abstract: Methods that generate a proof-of-life indicator used by a metaverse platform to indicate whether an avatar is being controlled by or is representative of a human user or a software-based entity. In these methods, a plurality of data streams are obtained from a plurality of sensors that are configured to monitor activity of a user that is active within the metaverse environment. The plurality of data streams relate to behavioral and biometric characteristics of the user that is interacting within the metaverse environment. The methods involve determining whether the user is a human user or a software-based entity based on aggregating attribute information extracted from the plurality of data streams, generating a proof-of-life indicator that indicates whether the user is the human user or the software-based entity and a confidence level associated with the proof-of-life indicator, and providing the proof-of-life indicator in the metaverse environment.

公开(公告)号：US10349093B2

公开(公告)日：2019-07-09

申请号：US14202568

申请日：2014-03-10

Applicant: Cisco Technology Inc.

Inventor： Pete Rai ,  David Richardson

IPC: G06F16/24 ,  H04N21/234 ,  G06F16/245 ,  H04H60/56 ,  H04H60/37 ,  H04N21/266 ,  H04N21/84 ,  G06F16/9032

Abstract: In one embodiment, a method implemented on a computing device for deriving timeline metadata for video content includes: capturing timeline elements through analysis of at least one of audio, visual or language aspects of the video content, interpreting the timeline elements according to associated inferences as indicative of timeline states, evaluating combinations of the timeline states according to a set of rules to derive timeline metadata, where the timeline metadata is associated with at least a portion of the video content.

公开(公告)号：US20180255336A1

公开(公告)日：2018-09-06

申请号：US15447215

申请日：2017-03-02

Applicant: Cisco Technology, Inc.

Inventor： Stephen TALLAMY ,  Pete Rai ,  Colin John Davies ,  Simon Dyke ,  Olivier Frebourg

IPC: H04N21/262 ,  H04N21/2187 ,  H04N21/2365 ,  H04N21/258 ,  H04N21/234

Abstract: A method for generating ad hoc video stream channels is implemented on at least one computing device and includes: receiving a multiplicity of incoming user video feeds, where schedules for the incoming user video feeds are unknown; classifying the multiplicity of incoming user video feeds according to at least a genre; selecting at least one incoming video feed from among the multiplicity of incoming user video feeds for inclusion in at least one video stream channel, where the selecting is according to selection criteria, and the selection criteria are based at least on the classifying; generating at least one outgoing video stream for the at least one video stream channel according to the selecting; and delivering the at least one outgoing video stream to presentation devices.

公开(公告)号：US20150379330A1

公开(公告)日：2015-12-31

申请号：US14453967

申请日：2014-08-07

Applicant: Cisco Technology Inc.

Inventor： Prabhakar Srinivasan ,  Pete Rai

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00261 ,  G06K9/00926 ,  G06K9/4652

Abstract: In one embodiment, a method for detecting faces in video image frames includes comparing a current image frame to a previously processed image frame to determine similarity, discarding the current image frame if the current image frame and the previously processed image frame are, detecting at least one detected facial image in the current image frame, comparing the at least one detected facial image to at least one most recently stored facial image stored in a most recently used (MRU) cache to determine similarity, discarding the at least one detected facial image if the at least one detected facial image and the at least one most recently stored facial image are similar; and storing the at least one detected facial image in the MRU cache if the at least one detected facial image and the at least one most recently stored facial image are not similar.

Abstract translation: 在一个实施例中，用于检测视频图像帧中的面部的方法包括将当前图像帧与先前处理的图像帧进行比较以确定相似性，如果当前图像帧和先前处理的图像帧至少检测到当前图像帧，则至少检测 一个在当前图像帧中检测到面部图像，将至少一个检测到的面部图像与存储在最近使用（MRU）高速缓存中的最近存储的面部图像进行比较，以确定相似性，如果丢弃至少一个检测到的面部图像，则 所述至少一个检测到的面部图像和所述至少一个最近存储的面部图像是相似的; 以及如果所述至少一个检测到的面部图像和所述至少一个最近存储的面部图像不相似，则将所述至少一个检测到的面部图像存储在MRU缓存中。

公开(公告)号：US20240273906A1

公开(公告)日：2024-08-15

申请号：US18108140

申请日：2023-02-10

Applicant: Cisco Technology, Inc.

Inventor： Pete Rai ,  Chris Shenefiel

IPC: G06V20/52 ,  G06V10/70

CPC classification number: G06V20/52 ,  G06V10/70

Abstract: According to one or more embodiments of the disclosure, a device may obtain characteristic data of a surveillance system. The device may inspect the characteristic data of the surveillance system to identify an artificial intelligence-based service that analyzes surveillance data captured by the surveillance system. The device may generate, based on identification of the artificial intelligence-based service, an alert indicative of how the surveillance data captured by the surveillance system is being used. The device may provide the alert for presentation to one or more individuals associated with the surveillance data.

公开(公告)号：US10321178B2

公开(公告)日：2019-06-11

申请号：US14202519

申请日：2014-03-10

Applicant: Cisco Technology Inc.

Inventor： Pete Rai ,  Trevor Smith ,  Stephen-John Craig

IPC: H04N21/262 ,  H04N21/258 ,  H04H20/10 ,  H04N21/2668 ,  H04H60/06

Abstract: In one embodiment of the present invention, a method implemented on a computing device includes: retrieving a set of channel parameters, the set of channel parameters defining a television channel schedule made of a plurality of viewing time periods; retrieving a set of regional parameters relevant to a geographical area, the set of regional parameters defining at least one regional viewing time period of a first duration; identifying a viewing time period from the plurality of viewing time periods relevant to the at least one regional viewing time period by comparing the regional parameters to the channel parameters; retrieving an abstract schedule associated with the identified viewing time period, where the abstract schedule is a pro forma schedule of programs having a second duration and comprising a set of program content items; and generating a concrete television schedule for the at least one regional viewing time period, where the concrete television schedule is a an instantiated finalized schedule produced by mapping the second duration to the first duration and rearranging the set of program content items of the retrieved abstract schedule.