-
公开(公告)号：US11042413B1
公开(公告)日：2021-06-22
申请号：US16508100
申请日：2019-07-10
Applicant: Facebook, Inc.
Inventor： Ahmad Byagowi , Michael Maroye Lambeta , Martin Mroz
Abstract: Utilization metrics associated with a plurality of eligible compute tasks executable on a plurality of field-programmable gate arrays are determined. The utilization metrics are evaluated to dynamically identify a reallocation of an identified field-programmable gate array resource of the field-programmable gate arrays to handle a selected eligible compute task of the eligible compute tasks. The identified field-programmable gate array resource is automatically reprogrammed to handle the selected eligible compute task.
-
公开(公告)号：US20210183397A1
公开(公告)日：2021-06-17
申请号：US17182951
申请日：2021-02-23
Applicant: Facebook, Inc.
Inventor： Xiaohu Liu , Baiyang Liu , Rajen Subba
Abstract: In one embodiment, a method includes by a client system associated with a user, receiving, at the client system, a user input from the user, parsing, by the client system, the first user input to identify a request to execute a function to be performed by an assistant system of several assistant systems associated with the client system, determining whether the user is authorized to access the assistant system by comparing a voiceprint of the user to several voiceprints stored on the client system, sending, from the client system to the assistant system in response to determining the user is authorized to access the assistant system, a request to set an assistant xbot of the assistant system into a listening mode, and receiving, at the client system from the assistant system, an indication that the assistant xbot is in listening mode.
-
公开(公告)号：US11039278B1
公开(公告)日：2021-06-15
申请号：US16119751
申请日：2018-08-31
Applicant: Facebook, Inc.
Inventor： Jason Michael Carreiro , Lionel Laurent Reyero , Jacob Perkowski
Abstract: A method includes determining an operating condition associated with a mobile device based on contextual information associated with one or more of usage information of the mobile device, user activity of a user of the mobile device, or location information. If the operating condition satisfies a threshold power-consumption condition, the method further includes adjusting a frequency of collecting location information of the mobile device and collecting information on a plurality of locations associated with the mobile device for a particular time period based on the adjusted frequency of collecting the location information. The method further includes adjusting a frequency of uploading collected location information to a server associated with a social-networking system and sending the information on the plurality of locations for a particular time period to the social-networking system based on the adjusted frequency of uploading collected location information for building a location timeline for the mobile device.
-
公开(公告)号：US11032398B1
公开(公告)日：2021-06-08
申请号：US16692504
申请日：2019-11-22
Applicant: Facebook, Inc.
Inventor： Tom Herbert , Blake Ross Matheny
Abstract: A system for providing a message-based protocol for multiplexing messages sent via a stream-based connection protocol is provided. A multiplexing system provides high-level sockets of the message-based protocol that interact with low-level sockets of a stream-based connection protocol. The multiplexing system executes in a privilege mode. To send a message, an application uses a high-level socket to provide a request to send the message using the multiplexing system. The multiplexing system selects an available low-level socket from a group of sockets and sends the message via that socket. The message is sent as an atomic operation. If, during the sending of the message, the application requests to send another message, the multiplexing system selects another available low-level socket of the group and sends the other message via the selected low-level socket.
-
公开(公告)号：US11032316B1
公开(公告)日：2021-06-08
申请号：US16215657
申请日：2018-12-11
Applicant: Facebook, Inc.
Inventor： Ravneet Singh Sidhu
Abstract: An online system detects imposter pages based on machine learning techniques. The online system maintains a plurality of authenticated pages and a plurality of unauthenticated pages, each of which is associated with a name and an image. From the plurality of unauthenticated pages, the online system filters out one or more unauthenticated pages that are associated with names of authenticated pages to obtain a group of candidate pages. Further, the online system pairs each candidate page up with an authenticated page. The candidate page has a name and/or image similar to the authenticated page. The online system inputs the candidate page and the authenticated page into a trained model. The trained model outputs an imposter score indicating a likelihood that the candidate page is an imposter page. The online system takes actions on the candidate page based on the imposter score.
-
Patent Agency Ranking
公开(公告)号：US11030235B2
公开(公告)日：2021-06-08
申请号：US16066719
申请日：2016-12-27
Applicant: Facebook, Inc.
Inventor： Jan Erik Solem , Yubin Kuang , Johan Gyllenspetz , Peter Neubauer , Pau Gargallo Piracés
IPC: G06F16/54 , G06F16/29 , G06F16/9537 , G06F16/58 , G01C21/36 , G06F16/583 , G06F16/51 , G06F16/2457
Abstract: The present invention relates to a method for navigating through a set of images depicting a scenery, said method comprising: receiving information relating to a subset of images within said set of images, said information comprising metadata of each image, said subset of images comprising images being acquired from a geographical position, which is within a bounding area surrounding the geographical position of a current image within the set of images; receiving weight information, said weight information controlling weights to be given to a plurality of different measures of similarities based on different types of metadata; and calculating a plurality of combined measures of similarity for pairs of images in the subset of images, said calculating being performed using said metadata and said weight information.
-
公开(公告)号：US20210165691A1
公开(公告)日：2021-06-03
申请号：US16701019
申请日：2019-12-02
Applicant: Facebook, Inc.
Inventor： Abdulkadir Utku Diril , Olivia Wu , Krishnakumar Narayanan Nair , Anup Ramesh Kadkol , Aravind Kalaiah , Pankaj Kansal
Abstract: A system comprises a processor coupled to a plurality of memory units. Each of the plurality of memory units includes a request processing unit and a plurality of memory banks. The processor includes a plurality of processing elements and a communication network communicatively connecting the plurality of processing elements to the plurality of memory units. At least a first processing element of the plurality of processing elements includes a control logic unit and a matrix compute engine. The control logic unit is configured to access data from the plurality of memory units using a dynamically programmable distribution scheme.
-
公开(公告)号：US11023941B2
公开(公告)日：2021-06-01
申请号：US16280789
申请日：2019-02-20
Applicant: Facebook, Inc.
Inventor： Mary Pao-an Ku , Anand Subbarayan , Bowen Pan
Abstract: The present disclosure is directed toward systems and methods for managing electronic messages via a social networking system. For example, systems and methods described herein involve organizing electronic messages and/or communication threads related to a product offered by sale via the social networking system. Furthermore, systems and methods described herein can generate and send electronic messages that are related to the status of a product that a product seller has advertised for sale via the social networking system.
-
公开(公告)号：US11023823B2
公开(公告)日：2021-06-01
申请号：US15449448
申请日：2017-03-03
Applicant: Facebook, Inc.
Inventor： Emanuel Alexandre Strauss
Abstract: An online system maintains machine learning models that determine risk scores for content items indicating likelihoods of content items violating content policies associated with the machine learning models. When the online system obtains an additional content policy, the online system applies a maintained machine learning model to a set including content items previously identified as violating or not violating the additional content policy. The online system maps the risk scores determined for content items of the set to likelihoods of violating the additional content policy based on the identifications of content times in the set violating or not violating the additional content policy. Subsequently, the online system applies the maintained machine learning model to content items and determines likelihoods of the content items violating the additional content policy based on the mapping of risk scores to likelihood of violating the additional content policy.
-
公开(公告)号：US11023772B2
公开(公告)日：2021-06-01
申请号：US16590256
申请日：2019-10-01
Applicant: Facebook, Inc.
Abstract: In one embodiment, a feature map of an image having h×w pixels and a patch having one or more pixels of the image are received. The patch has been processed by a first set of layers of a convolutional neural network and contains an object centered within the patch. The patch is then processed using the feature map and one or more pixel classifiers of a classification layer of a deep-learning model, where the classification layer includes h×w pixel classifiers, with each pixel classifier corresponding to a respective pixel of the patch. Each of the pixel classifiers used to process the patch outputs a respective value indicating whether the corresponding pixel belongs to the object centered in the patch.
-
-
-
-
-
-
-
-
-
Search Results
8633
records
(took 0.046 seconds)
