Digital Commons Network^™

System And Method For Automatic Near Exact Keyword Canonicalization, Justin Lewis, Gavin James

Defensive Publications Series

This disclosure relates to systems and methods for automatic near-exact keyword canonicalization. In particular, a keyword management system is provided that, based on keywords input by an advertiser, algorithmically derives a set of canonicalized IDs that represent the input keywords and near-exact formulations. The keyword management system also dynamically updates the collection of canonicalized IDs, as necessary, in response to new keywords input by the advertiser. The system is also configured to provide user feedback so as to educate the advertiser about the canonicalization of the entered keywords.

Distributed Audience Lists, David Pattison

Defensive Publications Series

This document describes a technique for storing and retrieving audience lists in a distributed manner by using a blockchain. Script executed by a user device can generate a pair of public and private keys for a user. The user can sign a message containing the public key and other information using the private key and upload the message to a blockchain corresponding to an audience list. A data processing system can search the blockchain for the public key and utilizing the information in the audience list maintained using the blockchain to better serve the user.

Removing Undesirable Audio Features From A Media Stream, Luke Macpherson

Defensive Publications Series

A feature correction system is used to remove undesirable audio and video features from a media stream. The system determines an undesirable audio feature in the media stream by detecting a region that is relatively silent or has a predetermined speech disfluency, e.g., umms, y’knows, or ahhs. Further, the system establishes a start time and an end time for the undesirable audio feature. The system then detects video frames in the media stream that include the undesirable audio feature. The system finally performs feature correction for the undesirable audio feature and/or the video frames according to one or more predetermined …

Automatic Image Timestamp Correction, Jeremy Pack

Defensive Publications Series

Images captured with digital cameras include timestamp information that indicates date and time of capture, e.g., based on a date/time setting in the camera. However, such information excludes the time zone in which the image was captured. Consequently, a true time of capture, e.g., UTC (Universal Coordinated Time) of images captured with such cameras is unknown. For example, for a camera that is set to Pacific Standard Time (PST) while capturing images in New York, the images would include a timestamp that is offset from a New York local time by three hours. This disclosure describes techniques to analyze images …

Threshold-Free Selection Of Taxonomic Multilabels, Hsin-Yi Lin, Brian Milch, Michel Adar, Scot Fang, Rene Van De Veerdonk

Defensive Publications Series

In online search or content selection systems, significant computational resources are expended to classify or categorize electronic documents into topics, concepts, or entities. A classifier can process, parse or otherwise analyze the document to assign one or more labels to the document based on the taxonomy. The classifier can generate a score for each of the labels, and provide the labels and the scores to other components or modules for further downstream processing. To keep downstream processes efficient without causing excessive processing of labels, the classifier may filter out the labels to return a subset of labels based on comparing …

System And Method For Content Ingestion And Optimized Content Delivery, Manikandan Gopalakrishnan

Defensive Publications Series

A system is described for packaging multiple content types into a single package. For example, the package can contain combinations of video content, image content, audio content, and metadata that defines how the types of content are related and used. The package can then be processed and stored, e.g., in a proprietary format with a metadata file that describes how the content is related (e.g., how audio content is to be combined with text content).

Optical Circulator For Free Space Optical Communication, Chiachi Wang

Defensive Publications Series

A free space optical communication system transmits and receives optical signals in a colorless manner using an optical circulator. The system installs the optical circulator with a single mode (SM) fiber at port 1, a double clad (DC) fiber at port 2, and a multimode (MM) fiber at port 3. The system injects a first optical signal into a core of the SM fiber. The system then routes the first optical signal at port 1, using the optical circulator, into a SM core of the DC fiber via Port 2. Further, the system injects a second optical signal into a …

System For Detecting End Of Speech Utterance For Safe Interruption, Dimitri Kanevsky

Defensive Publications Series

A system and method for detecting end of speech utterance for safe interruption using audio and video processing software or application is disclosed. The system includes hardware that determines the speaker’s intonation in real time or with minimal delay and displays this visually on a screen along with a transcript of the speech delivered by the speaker. The speaker’s intonation and end of speech could be identified in the system display in real-time as rising and falling of pitch at the end of speech. The system and method could be implemented as a module of any video call or conference …

System And Method For Providing Assistive Video/Audio Conference Channel, Liat Kaver Oreamuno

Defensive Publications Series

A system and method are disclosed for providing an assistive video/audio conference channel to a user with hearing assistive devices. The system could be configured to provide a separate channel in a videoconferencing application setting accessible to hearing assistive devices. The channel could be capable of sending audio from any remote speaker. The system and method could be implemented as a virtual additional assistive channel to the existing videoconferencing software applications.

Estimating Building Risk Using Imagery And Machine Learning, Michael Greene

Defensive Publications Series

The present disclosure describes systems and methods that use available imagery of a building or other structure in combination with one or more machine learning techniques or machine-learned models to assist in estimating risk associated with the building. The systems and methods described herein can also be adapted to predict failure risk of various types of infrastructure (e.g., utility infrastructure such as power lines and power line poles) and/or industrial assets. Risk assessment can be useful for various objectives including assessment for insurance purposes, valuation purposes, etc. In one example, one or more machine learning models can be used to …

Assessing Brand Visibility Using Machine Learning, Sujoy Banerjee, Michael Greene

Defensive Publications Series

The present disclosure describes systems and methods that leverage one or more machine learning techniques or machine-learned models to perform a large scale statistical assessment of the visibility of an advertising campaign. More particularly, a processing pipeline is provided that takes input imagery and outputs an indication of a visibility of a brand. The pipeline can include a brand recognition neural network and a brand visibility scoring engine. Keywords associated with the present disclosure include: machine learning; neural network; deep learning; model; training; image; imagery; advertisement; advertising; ads; campaign, brand; logo; visibility; effectiveness; score; location; traffic; emblem; trademark; label.

"Interaction Between Audience And Game Players During Live Streaming Of Games", Jack Greenberg

Defensive Publications Series

Watching others play video games is a popular online activity. Video of a game in progress for a particular game player or team is broadcast live to an online audience, along with a feed of text shared among spectators and game players. Currently, spectators can interact with other spectators and the game players by posting text or emoji. This disclosure describes techniques that enable spectators to provide game resources to particular game players as gifts. The resources can include any object within the game and can have an impact on the outcome of a game. Greater interactivity and engagement can …

Establishing Proximity-Based Trust Of Nearby Devices Through Audio Communication, David Aristizabal, Adam Liss

Defensive Publications Series

A method for establishing proximity-based trust of nearby devices through audio communication is disclosed. The method includes a protocol for devices that communicate over audio within a predetermined distance from each other to verify proximity. A packet token is included at the end of each packet. After each packet ends broadcasting, the sending device listens for a response from the receiving device for a window of time corresponding to the time it takes for sound to make a round-trip through the predetermined distance. This mechanism could be used in mobile application development where applications are required to ensure co-presence within …

System And Method For Providing Assistive Video/Audio Conference Channel, Liat Kaver Oreamuno, Dimitri Kanevsky

Defensive Publications Series

A system and method are disclosed for providing an assistive video/audio conference channel to a user with hearing assistive devices. The system could be configured to provide a separate channel in a videoconferencing application setting accessible to hearing assistive devices. The channel could be capable of sending audio from any remote speaker. The system and method could be implemented as a virtual additional assistive channel to the existing videoconferencing software applications.

"System For Detecting End Of Speech Utterance For Safe Interruption", Dimitri Kanevsky, Richard Lyon

Defensive Publications Series

A system and method for detecting end of speech utterance for safe interruption using audio and video processing software or application is disclosed. The system includes hardware that determines the speaker’s intonation in real time or with minimal delay and displays this visually on a screen along with a transcript of the speech delivered by the speaker. The speaker’s intonation and end of speech could be identified in the system display in realtime as rising and falling of pitch at the end of speech. The system and method could be implemented as a module of any video call or conference …

System And Method For Speech Recognition, Dimitri Kanevsky, Tara Sainath

Defensive Publications Series

The present disclosure is directed to a system and method for speech recognition. A user will provide a speech input to a computing device, which will be recognized and processed. The user can also provide authorization to the computing device to sense and process the speech input via one or more sensor(s) that are utilized to detect the position, movement, etc. of the user’s lips, and in some aspects tongue. If explicitly authorized by the user, the computing device can receive the speech input via the one or more sensors that are utilized to detect the position, movement, etc. of …

3d Object Search System, Wallace P. Scott

Defensive Publications Series

The subject matter of the present disclosure relates to searching a large repository of 3D models (e.g., objects) to find models similar to a query model. More specification, the subject matter of the present disclosure relates to semi-structuring of the 3D model data and implementing of approximate similarity algorithms in the search. Such a search may detect potential intellectual property infringements, both physical and virtual.

Systems and methods described here provide comparative analysis results between 3D objects that may exhibit superficial and/or abstract similarities. The objective is to efficiently sort through large datasets (e.g., a library …

Line Rate Ethernet Traffic Testing, Sean Howarth, Ke Dong, Xinfa Wu, Huy Nguyen, Brian Tran

Defensive Publications Series

The invention discloses a Ethernet traffic testing system for determining a packet error­rate of a link between an optical network unit (ONU) and an optical line terminal (OLT). The system determines that the ONU detects a test message from the OLT. The system then causes the ONU to send data received from the OLT back to the OLT. Further, the system causes the OLT to reflect back data received from the ONU in order to form a closed loop. The system then causes the OLT to inject data bits in the closed loop till the number of bits circulating in …

Voice Commands Coordination Between The Same App On Multiple Devices, Jakub Miara

Defensive Publications Series

A system and method are disclosed for voice command coordination between instances of the same application running on multiple devices. The devices could be any that process voice commands, such as smartphones, tablets, smartwatches, laptops or IoT devices. The system coordinates the devices by broadcasting short communicates using humaninaudible sonic frequencies. In the first step of the method, the user gives a voice command, which is received in a number of devices that interpret the command. Each device determines a relevancy score of the command and then broadcasts the score as short communicates using inaudible sonic frequencies that are received …

Multibrand Geographical Experiments And Analysis, Arthur Owen

Defensive Publications Series

Entities expend significant resources to advertise or market their services or products to potential customers. Advertisements can be provided to potential customers via online advertisement infrastructure, including, for example, by a content selection server for display on a web page or other application executed or provided by a computing device. However, it may be challenging to measure the causal impact advertising can have on sales for a brand or product.

Integrated Storage Of Handheld Controller In Headset, Maaike Evers, Phan Thao Benno Dang, Byeong Seon Oh, Michael Simonian

Defensive Publications Series

A head mounted display (HMD) or other display headset includes an integrated storage area concomitant with the lens region of the headset. The integrated storage area is used to store a handheld controller associated with the headset, with the added benefit of the handheld controller serving as a cover for the lenses of the headset.

Collaborative Distributed Speech Recognition, Sara Basson, Dimitri Kanevsky

Defensive Publications Series

The disclosure includes a captioning system configured to caption a video. A video may be identified for captioning. The video may be submitted to automated speech recognition engines. A transcription of audio from the video may be received from the automated speech recognition engines. It may be determined whether to accept or create a final transcription. If not, the video may be submitted to one or more manual speech recognition engines. If the final transcription is accepted or created, at least one of the automated speech recognition engines or one of the manual speech recognition engines may be rewarded based …

Automatic Cinemagraphs From Video, Ronald Wotzlaw, Li Wei

Defensive Publications Series

This document describes techniques to generate a cinemagraph from a video automatically and without user input. The techniques enable accurate determination of moving regions of pixels in the video which are suitable for animation, by determining mask regions using a dense optical flow technique. Described techniques enable selection of frame sequences from the video that provide smooth and engaging animations for the cinemagraph, by looking for pixel motion under particular criteria. Techniques enable multiple independent cinemagraph animations to be smoothly provided in a single cinemagraph image.

Quality Modeling For Communications, Satyam Shaw, Amit Agarwal, Nandan Dixit, Gaurav Bhaya, Dan Liu, Anshul Kothari

Defensive Publications Series

The disclosure describes techniques for collecting quality information about communications that are initiated by activation of navigation elements on a user interface of a user device. The quality information may include user survey data and communication characteristics data. The communication, referred to hereinafter “click-to-communicate”, may include for example, placing a telephone call to a predesignated telephone number (such as “call click”, “click-to-talk” or “click-to-call”), chatting through a chat window (such as “click-to-chat”), texting (such as “click-to-text”), downloading of software programs (such as “click-to-download”), transferring to a webpage (such as “click-to-deep link”), etc. A system collects characteristics of the communication that …

Presence Indication In Real-Time Chat Applications, Johan Wikström

Defensive Publications Series

This document describes techniques to display presence indicators in real-time chat applications. The techniques enable accurate presence indicators with low overheads. A server compares successive timestamps to determine whether a time threshold is met. If the time threshold is met, the server pushes an updated last-seen timestamp to clients. Otherwise, the server only selectively pushes the updated last-seen timestamp to clients. The client polls the server if the last-seen timestamp meets a threshold difference from the current time. The combination of pushing by a server and polling by a client to selectively update last-seen timestamps enables accurate and consistent representation …

Systems And Methods For Delivering A Content Item To A User, Scott Davies, Justin Lewis

Defensive Publications Series

We propose techniques for delivering a relevant content item to a user. These techniques may render the relevant content item more likely to be delivered as one of the first impressions following the occurrence of a specified event. In some implementations, the event may be the expiration of the user’s free trial period for a subscription service. In some other implementations, the event may be a search query entered by the user. The techniques discussed in this paper may track the number of other content items delivered to a user since the occurrence of the event, and may use this …

Media File Selection And Targeting, Justin Lewis, Gavin James

Defensive Publications Series

A media file selection and targeting system selects and targets media files to one or more groups of people. The media file targeting system displays at least one media files choice to users in a group conversation. The system then presents an option to the users to vote upon the media file choices. Further, the system determines a media file, from the media files displayed, with the most votes and plays the media file with the greatest number of votes from all the users in the group conversation.

System And Method For Implementing Real-Time Conferencing, Alexander Faaborg, Emmet Connolly

Defensive Publications Series

The present disclosure is directed to a system and method for initiating a real- time audio/video-conference. A hosting computing device will communicate with the user computing devices at, or a short time before, a scheduled time of the conference. Each user computing device and/or the hosting computing device will determine if there are any users ready to participate in the conference. If there are no users ready for the conference (e.g., there are no users in the rooms associated with the user computing devices), the conference will be initiated by the user computing device(s) and/or the hosting computing device such …

Inferring Merchant Review Scores From Payment Data, Matthew Sharifi, Dominik Roblek

Defensive Publications Series

Users complete payment transactions with various merchants using a wallet application or similar payment application maintained by an account management computing system. The account management computing system creates a predictive model or trains a machine learnt regression function or classifier model to predict the merchant review score based on the payment information received from the user device. A merchant is identified to derive a merchant review score and the account management computing system identifies the business type of the identified merchant. Payment data that corresponds to completed payment transaction between various users and the identified merchant are identified. Each part …

Systems And Methods For Sharing Ads With Friends, Ping Fu, Jinqing Li, Michael O'Herlihy

Defensive Publications Series

This paper describes methods and systems for sharing ads with friends or contacts across multiple platforms. The solution described in this paper provides a straightforward way for users to share ads without relying on other social networking platforms or communication platform mediums (such as email, text messaging apps, among others). The solution also makes ad sharing more personalized as it enables users to choose one or more specific contacts with which to share ads. The system can be configured to insert or otherwise embed an actuable object (for instance, a share object) on the ad. Responsive to a user taking …