Selecting representative metrics datasets for efficient detection of anomalous data
Granted: June 26, 2018
Patent Number:
10009363
Certain embodiments involve selecting metrics that are representative of large metrics datasets and that are usable for efficiently performing anomaly detection. For example, a data graph is generated that represents metrics datasets having values for respective metrics. Each node in the graph represents a respective metric, and each edge between nodes represents a respective correlation between a given pair of the metrics datasets. The nodes are grouped into clusters. For each cluster,…
Concepts for asset identification
Granted: June 26, 2018
Patent Number:
10008056
Systems, methods, apparatus, and computer program products are provided for identifying assets (e.g., mobile assets and/or personnel assets). In one embodiment, a mobile asset can be uniquely identified from RFID tags. In another embodiment, mobile assets and personnel assets can be identified from captured image data. After identification, it can be determined whether the asset (e.g., mobile asset and/or personnel asset) is authorized for one or more activities and a corresponding…
Tool for creating and editing arcs
Granted: June 26, 2018
Patent Number:
10008014
A tool is provided via a user interface for a digital media application that supports digital illustrations. The tool combines operations to create different types of segments for a drawing shape and covert between types of segments. The tool is configured to analyze the drawing to recognize segments that are straight, arc, or curved portions of the drawing path. For segments recognized as curved, the segments are represented as Bezier curve segments. For segments recognized as straight,…
Systems and methods for predicting and pricing of gross rating point scores by modeling viewer data
Granted: June 26, 2018
Patent Number:
10007926
Systems and methods are disclosed for characterizing websites and viewers, for predicting GRPs (Gross Rating Points) for online advertising media campaigns, and for pricing media campaigns according to GRPs delivered as opposed to impressions delivered. To predict GRPs for a campaign, systems and methods are disclosed for first characterizing polarized websites and then characterizing polarized viewers. To accomplish this, a truth set of viewers with known characteristics is first…
Font replacement based on visual similarity
Granted: June 26, 2018
Patent Number:
10007868
Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing…
Automatic positioning of a video frame in a collage cell
Granted: June 26, 2018
Patent Number:
10007847
A computer-implemented method of positioning a video frame within a collage cell includes, for a given one of a plurality of video frames, generating a polygon encompassing a portion of the respective video frame containing at least one visual element. The polygon has a center position corresponding to a first point within the respective video frame. The center position of the polygon of a given frame is then changed to a new center position based at least in part on an average center…
Irregular pattern identification using landmark based convolution
Granted: June 19, 2018
Patent Number:
10002622
Pattern identification using convolution is described. In one or more implementations, a representation of a pattern is obtained that is described using data points that include frequency coordinates, time coordinates, and energy values. An identification is made as to whether sound data described using irregularly positioned data points includes the pattern, the identifying including use of a convolution of the frequency or time coordinates to determine correspondence with the…
Utilizing deep learning for rating aesthetics of digital images
Granted: June 19, 2018
Patent Number:
10002415
Systems and methods are disclosed for estimating aesthetic quality of digital images using deep learning. In particular, the disclosed systems and methods describe training a neural network to generate an aesthetic quality score digital images. In particular, the neural network includes a training structure that compares relative rankings of pairs of training images to accurately predict a relative ranking of a digital image. Additionally, in training the neural network, an image rating…
System and method for parts-based digital rights management
Granted: June 19, 2018
Patent Number:
10002237
Various embodiments of a system and method for parts-based digital rights management are described. Various embodiments may include a digital rights management component configured to receive content comprising a plurality of portions of content. The digital rights management component may also receive a license for the encrypted content; the license may include a plurality of permissions each specific to a respective portion of the content. Additionally, each permission may specify one…
Neural network patch aggregation and statistics
Granted: June 12, 2018
Patent Number:
9996768
Neural network patch aggregation and statistical techniques are described. In one or more implementations, patches are generated from an image, e.g., randomly, and used to train a neural network. An aggregation of outputs of patches processed by the neural network may be used to label an image using an image descriptor, such as to label aesthetics of the image, classify the image, and so on. In another example, the patches may be used by the neural network to calculate statistics…
Detecting homologies in encrypted and unencrypted documents using fuzzy hashing
Granted: June 12, 2018
Patent Number:
9996603
Techniques are provided for automatically detecting homologies between documents based on structural characteristics. Various statistics relating to the COS structure of a PDF document are compiled. The statistics are input into a rolling hash function to generate a digital fingerprint of the document. Fingerprints from two similar documents will have small edit distances between them, and can therefore be classified similarly or provided as results to a fingerprint-based search. For…
Systems and techniques for determining user engagement with video advertisements to determine optimized cost per impressions
Granted: June 5, 2018
Patent Number:
9992538
Systems and methods disclosed herein provide for determining changes in the device engagement data as a video advertisement is played on a video application executing in a mobile computing device. A user engagement engine collects device engagement data over multiple intervals of playback of the video advertisement. The device engagement data includes data indicating the spatial orientation of the mobile computing device and data indicating the volume level. The user engagement engine…
Real-time tracking collection for video experiences
Granted: June 5, 2018
Patent Number:
9992537
Methods and systems for tracking events associated with use of video content are disclosed. A method collects events associated with use of video content at a computing device. In response to determining that a tracking interval has elapsed, the method optimizes the collected events by grouping similar events together, serializes the optimized events by structuring the optimized events in a defined format, and creates a tracking call to send the serialized events to a remote computing…
Video denoising using optical flow
Granted: June 5, 2018
Patent Number:
9992387
In techniques for video denoising using optical flow, image frames of video content include noise that corrupts the video content. A reference frame is selected, and matching patches to an image patch in the reference frame are determined from within the reference frame. A noise estimate is computed for previous and subsequent image frames relative to the reference frame. The noise estimate for an image frame is computed based on optical flow, and is usable to determine a contribution of…
Method to synthesize personalized phonetic transcription
Granted: June 5, 2018
Patent Number:
9990916
Technology related to improving synthesis of foreign regional nouns using personalized and culturally correct phonetic transcription is described. The technology includes systems and methods for generating personalized speech by receiving an input, the input including textual data, identifying a regional noun in the textual data, and determining a user accent classification based on a context of the input. The method may further include determining a personalized phonetic transcription…
Camera-based brush creation
Granted: June 5, 2018
Patent Number:
9990740
In embodiments of camera-based brush creation, an image is displayed in a brush application interface of a virtual brush application on a computing device. A photo capture selection can be received through the brush application interface to initiate capturing a digital photo of the image with a camera device of the computing device. A brush can then be created for the virtual brush application based on the image and brush-edit inputs, and the brush saved as a brush template in a brush…
Planar region guided 3D geometry estimation from a single image
Granted: June 5, 2018
Patent Number:
9990728
Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then…
Generating image features based on robust feature-learning
Granted: June 5, 2018
Patent Number:
9990558
Techniques for increasing robustness of a convolutional neural network based on training that uses multiple datasets and multiple tasks are described. For example, a computer system trains the convolutional neural network across multiple datasets and multiple tasks. The convolutional neural network is configured for learning features from images and accordingly generating feature vectors. By using multiple datasets and multiple tasks, the robustness of the convolutional neural network is…
Contextual analysis engine
Granted: June 5, 2018
Patent Number:
9990422
A contextual analysis engine systematically extracts, analyzes and organizes digital content stored in an electronic file such as a webpage. Content can be extracted using a text extraction module which is capable of separating the content which is to be analyzed from less meaningful content such as format specifications and programming scripts. The resulting unstructured corpus of plain text can then be passed to a text analytics module capable of generating a structured categorization…
Attestation for electronic signatures
Granted: May 29, 2018
Patent Number:
9984242
Techniques for generating a document according to attestation requirements are provided. A method determines attestation requirements for electronically signing an electronic document. The method modifies the document based in part on the requirements, and then provides the modified document to users requested to electronically sign the document, wherein the users are only permitted to electronically sign the document in circumstances satisfying the requirements. An electronic signature…