Digital Commons Network^™

Compound Task Request And Translation, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may be configured to receive a compound task request. A compound task request is a single request to perform multiple (i.e., more than one) tasks. The compound task request may be in the form of a single spoken phrase. The interactive assistance may receive the spoken phrase, determine that the spoken phrase contains a request to perform multiple actions, and perform all of the actions requested by the spoken phrase. For example, the compound task request may be a request to translate a …

Using An Interactive Assistant As A Password Vault, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may be configured to securely store passwords, access codes, private keys, digital certificates, and other secret information. When the interactive assistant receives a request from the user to perform an action that requires the use of the secret information stored by the interactive assistant, the interactive assistant can provide such secret information to web sites, services, devices, systems, and the like to authenticate the interactive assistant to gain access to resources as part of performing the requested action. For example, when the interactive …

User Control Of Content Playback By An Interactive Assistant, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may be configured to dynamically adjust the playback of content (e.g., audible content output by the interactive assistant) in response to receiving a user command. Over the course of time, a user may engage in various different interactions with the assistant by submitting queries, performing searches, requesting select information, providing instructions, and the like. At any point in time, during playback of content provided by the interactive assistant, the user may issue a command to adjust the playback of such content. For example, …

Sleep Mode For An Interactive Assistant, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may, after previously receiving explicit user authorization to process user input, be configured to stop processing further user input (e.g., audible user input) for a period of time or until the occurrence of one or more detected events. Over the course of time, a user may engage in various different interactions with the assistant by submitting queries, performing searches, requesting select information, providing instructions, and the like. At any point in time, the user may request that the interactive assistant enter a sleep …

Allocation Of Advertisement Extensions & Formats, Patrick Hummel, Roberto J. Bayardo Jr, Shaohua Sun, Gagan Aggarwal, Kishor Barman, Kshipra Uday Bhawalkar, Jean-Francois Crespo, Ying Wang

Defensive Publications Series

This document describes a process of optimizing the selection of a budget-constrained advertiser's formats when allocating the budget of a budget-constrained advertiser. Such optimization is performed by selectively choosing which formats to allocate to this advertiser based on the advertiser's budget. In particular, this document describes allocating formats to budget-constrained advertisers in advertising auctions to create value for the advertisers and an advertiser manager.

Composite Digital Content Optimization, Wanghuan Chu, Shuchao Bi

Defensive Publications Series

A digital content rotation system that distributes digital content items a sufficient number of times to generate a statistical model for prediction of performance of the digital content items, while also preventing overall system degradation of content provided by content providers. The predicted performance of various digital content items is used as weights in a distribution rotation, thereby providing an optimal balance of exploitation and exploration of content performance.

Automatic Context-Based Customization Of Voicemail Response, Alexandru Damian, Victor Carbune

Defensive Publications Series

This disclosure describes a voicemail generator to provide automatic context-based custom voicemail responses, when users provide consent to access contextual data for generation of voicemail responses. The voicemail generator employs a prediction model that is configured to predict multiple factors, e.g., action type, user availability, and caller-specific customizations, that are used to automatically generate a customized voicemail response.

Creation Of Music Playlists Using An Interactive Assistant, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may be configured to create artist-specific or other criteria-based music playlists based on queries from a user. For example, an interactive assistant may accept queries from a user, perform a search of songs and related content based on certain criteria specified in the queries, and generate or modify music playlists based on the search results. The interactive assistant may also execute one or more applications, such as a music application, to play the songs included in the generated playlists.

Creation Of Theme-Based And/Or Genre-Based Music Playlists Using An Interactive Assistant, Google Inc.

Defensive Publications Series

An interactive assistant, referred to herein as “an interactive assistant,” “a virtual assistant,” or simply “an assistant,” may be configured to create comprehensive playlists based on singer/artist, composer, genre, theme, or other criteria, based on queries from a user. For example, an interactive assistant may accept queries from a user, perform searches for songs and related content based on certain theme-based and/or genre-based criteria specified in the queries (e.g., criteria for one or more love songs, happy songs, scary songs, sad songs, hard-rock songs, and the like), and generate or modify music playlists based on the search results. The interactive …

Using Object Detection To Extract Structured Content From Documents, Natalya Fridman Noy, Jeffrey Dudek

Defensive Publications Series

Structured content such as figures, tables, graphs, captions, and other graphical material often capture the essence of a document. Experienced readers often review the graphical material in a document first to quickly grasp the contents of the document. It is thus evident that identifying and extracting the structured content of a document, e.g., graphical components, is important in building a deeper semantic understanding of the document.

Techniques presented herein automatically extract the structured content of documents. Machine-learning techniques, e.g., object detection, computer vision, etc., are used to recognize and extract the structured content. The techniques work well regardless of the …

Verifying Client Media Playback Using Unique Embedded Metadata, Benjamin Seligman, Christopher Dinn, Damien Levin

Defensive Publications Series

The described subject matter is directed to injecting metadata into a media stream at (or just after) a cache edge of a content delivery network (“CDN”). A unique instance value (e.g., included within a tag or uniform resource locator (“URL”)), is embedded by an edge device into metadata for the media stream. Examples of media stream metadata include, but are not limited to, D3 timed metadata inserted in an MPEG-2 transport stream or an emsg box in the ISO-BMFF video container for MPEG-DASH. When a streaming media player receives the metadata, it generates a network request or callback request including …

Decoding Text With Errors Due To Auto-Correction, Thomas Deselaers, Victor Carbune

Defensive Publications Series

Auto-correction techniques implemented in software keyboards attempt to mitigate user errors in text entry by analyzing user input and automatically generating corrections. This approach can result in inaccurate corrections (auto-corruptions), e.g., when users enter words that are out of vocabulary, uncommon words, abbreviations, etc. When such phrases are sent, e.g., as messages, recipient users may not understand the sender’s intent or make sense of the received text.

This disclosure describes techniques to decode received text that has errors produced by auto-correction. The techniques include reconstructing possible touch point sequences that led to the phrase, determining alternative phrases that correspond to …

Disposable Apps, Leon Nicholls

Defensive Publications Series

This disclosure describes techniques that enable end users that do not possess technical knowhow, e.g., knowledge of software development, to create apps. The apps can be standalone, e.g., run directly on an operating system, or be integrated into other apps or software. For example, the apps can be integrated into a conversational assistant, a browser, etc. The user-generated apps are designated for a specific event and/or a specific time period. When the user-generated app is no longer needed, the app and its data are automatically destroyed.

Dynamic Determination Of Rcs Video Share Capability, Jean-Philippe Cormier

Defensive Publications Series

Mobile video calling requires determination of whether the available network is capable of supporting video calls. In Rich Communication Suite (RCS), such determination is static and is made at the time of call initiation. Such an approach limits usefulness of video share call functionality, e.g., when network conditions change during a call.

This disclosure describes techniques to determine at regular intervals whether an available network at a user location or cell site supports video calling. A network performance database is queried periodically to determine whether the network at a user’s location supports video calling. If video calling is supported, the …

Allocating Rf Spectrum Partitions In A Cbrs Network, Yi Hsuan

Defensive Publications Series

Methods for allocating portions of an available radio frequency spectrum to wireless access points and systems for carrying out such methods are disclosed herein. An example method can include receiving location and transmission information for a plurality of wireless access points associated with respective networks. A coexistence graph for the plurality of wireless access points is generated based on the received information. The coexistence graph is divided into coexistence areas. For each coexistence area, a coloring algorithm is executed to determine a number of colors needed to color the nodes in the coexistence area such that no two connected nodes …

Pause Viewing Button For A Multiple-Person Household To Facilitate Resuming Later, Rochelle Edwards

Defensive Publications Series

A method for resuming playback of a media item after user co-participation in playback of the media item is described. A processing device provides playback of a media item to a first user and a second user. The processing device determines that the first user is not participating in the playback at a first point in time corresponding to a first temporal location in the media item and that the second user is not participating in the playback at a second point in time corresponding to a second temporal location in the media item. The processing device receives a request …

Context-Sensitive Audio Notifications, Sandro Feuz, Victor Carbune, Thomas Deselaers, Google Inc.

Defensive Publications Series

A method is disclosed for triggering context-sensitive audio notifications. Systems and devices according to the method also predict a least disruptive moment to trigger a notification within a given period of time. The method comprises two parts. In the first part, a machine learning (“ML”) subsystem determines a current context of a user (based on, e.g., surrounding audio environment, current location, user calendar, etc.) and assesses the potential disruptiveness of an audible notification in the current context. The ML subsystem predicts a time-series of scores denoting the disruptiveness of the audible notification if emitted at particular times in the future. …

A/B Experiment Framework For Native Ads In Ad Servers, Bo Lin, Chetna Mcdonald, Roman Apostol, Sonny Thai, Woo Lee, Mikhail Shalai, Zutao Zhu, Olawale Abiri

Defensive Publications Series

Techniques are described for experiment frameworks around server-side rendering of native advertising content for presentation within an application environment. As described, a server receives a request, from a client device, for content that includes a content slot identifier. The server, using the content slot identifier, accesses a database to identify a presentation schema used to arrange content components and generates rendered content files according to a specific configuration for display within the environment of the resource. The server renders the content components based on the identified presentation schema and transmits the rendered content to the client device for display within …

Self Configuration Of Wireless Devices For Cloud Deployments, Frédéric Brunner, Jean-Michel Lauriol

Defensive Publications Series

In a context of Cloud deployments, we need to find a way for “out of the box” devices with no MMI (Man to Machine Interface) capabilities to easily discover the Cloud Service Provider and Application Server instance they are attached to.

These devices “MMI less” are devices without input (e.g. keyboard ) or output (e.g. Display) allowing user to type any characters or read information on the screen, typically wireless DECT (Digital Enhanced Cordless Telecommunications) Base Station or WLAN (Wireless Local Area Networks) Access Points.

Virtual Assistant Service For Patients And Caregivers

Defensive Publications Series

A major healthcare cost is the lack of strict adherence to, or outright non-compliance with, medicines and medical schedule by patients. The techniques disclosed herein assist patients by automatically performing routine healthcare-related tasks, e.g., reminding patients to take medications at appropriate times; ordering prescription refills at pharmacies; scheduling and managing medical appointments; tracking and charting their vital statistics, e.g., blood glucose, blood pressure, heart rate, etc.; asking for and logging patient symptoms, etc. The virtual personal assistant uses a machine learning model to adapt itself to the particulars of the patient. The virtual personal assistant may interface with the patient …

Assistant Enabled Entertainment System, Google Inc.

Defensive Publications Series

A virtual, intelligent, or computational assistant (e.g., also referred to simply as an “assistant”) is described that relies on supplemental data (e.g., contextual information, user information, etc.) to determine media, including movies, television shows, music, etc., that a user may want to consume and provide recommendations or automatically perform actions based on to assist the user in consuming the media. With explicit permission from a user, the assistant may access a user’s location history, calendar, e-mail, messages, past assistant interactions, contacts, photos, search history, sensor data, social network accounts, and other contextual or user information develop recommendations. The supplemental data …

Proactive Assistance For A Predicted Destination, Google Inc.

Defensive Publications Series

A virtual, intelligent, or computational assistant (e.g., also referred to simply as an “assistant”) is described that relies on supplemental data (e.g., contextual information, user information, etc.) to predict a user’s destination and offer to assist the user with actions the user will likely want to take at the predicted destination. With explicit permission from a user, the assistant may access a user’s location history, calendar, e-mail, messages, past assistant interactions, contacts, photos, search history, sensor data, and other contextual or user information to predict a destination of a user as well as actions the user will likely want to …

Assistant Generated Answers Using Supplemental Data, Google Inc.

Defensive Publications Series

A virtual, intelligent, or computational assistant (e.g., also referred to simply as an “assistant”) is described that relies on supplemental data (e.g., contextual information, user information, etc.) to decipher, and determine answers to, user queries. With explicit permission from a user, the assistant may access a user’s location history, calendar, e-mail, messages, past assistant interactions, contacts, photos, search history, sensor data, and other contextual or user information to answer a user query. The supplemental data can be stored locally on a device that is executing the assistant or in a cloud computing environment that is accessible to the assistant from …

Cable Vault Lids With Solar Panels, Eric Street

Defensive Publications Series

This disclosure describes techniques fiber optic cable vault lids with built-in solar panels. Vault lids are built with suitable materials based on deployment location. Power generated by the solar panels is used to power equipment such as Wi-Fi access points, power monitors, etc. within the fiber optic cable vault. Surplus power is supplied to the grid. By having power generation built-in, the fiber optic cable vault lid enable vaults to be deployed in locations where external power is unavailable. This improves the ability to communicate with fiber mid points, maintain health of the fiber network, and ease isolation of faults. …

Applying Machine Learning Techniques To Determine Product Risks

Defensive Publications Series

Generally, the present disclosure is directed to techniques to automatically determine risks associated with a product. In some implementations, the techniques of the present disclosure can include or otherwise leverage one or more machine-learned models to determine if the release and continued sales of product has legal, privacy and/or business vulnerabilities based on identifying sensitive keywords in product-related documentation and product areas.

This disclosure applies machine learning techniques to automate product audits and improve product review quality. Machine learning techniques are applied to proactively identify risks associated with a product, e.g., for a software product or service, the techniques are …

Smart Voicemail With Action Triggers Based On Semantic Understanding, Robin Dua, Sujith Ravi

Defensive Publications Series

Techniques for responding to voicemails based on language processing of voicemails to identify actions that can be performed in response to the voicemails. The actions can be presented as selectable suggestion elements that, when selected, cause certain actions to be performed in reply to the voicemail. For example, a voicemail that includes a question for the recipient can be processed in order to generate selectable suggestion elements for answering the question via text message. Some techniques identify requests (e.g., request for a document, contact information, payment, etc.) from the recipient and, in response, queries can be performed in order to …

Location Specific Assistance Based On Geofencing, Shreedhar Madhavapeddi, Saptarshi Bhattacharya

Defensive Publications Series

Digital assistant and bots serve users by providing suitable information and services. However, users may sometimes require specific information or services, e.g., that are offered exclusively by a third party, that current digital personal assistants cannot provide. For example, specific providers can offer services at or near geographic locations.

Techniques described herein permit a digital assistant to provide users such specialized services by integration with third party providers. Third party providers for a particular location are selected, e.g., via an auction to provide assistance within a geofence, or other mechanisms. Such auctions can also be conducted in real-time in response …

Organizational Productivity Metrics From Document Collaboration, Mansoor Alicherry

Defensive Publications Series

Research has identified many characteristics of productive teams, e.g., initiative, helpfulness, time efficiency, work quality, etc. A metric for productivity that provides a measure of team productivity can help teams identify specific areas of improvement. Techniques disclosed herein identify different aspects of productivity that can be observed in online communication and document creation/management systems. For example, such aspects can include creation of documents, collaborative editing of documents, and communication between users. Further, these aspects are measured to compute a productivity metric. A multigraph is constructed with nodes representing users and edges representing the weight (quality) of creation, collaboration, and communication …

Automatic Correction Of Timestamp And Location Information In Digital Images, Thomas Deselaers, Daniel Keysers

Defensive Publications Series

Image storage and sharing services permit users to store and share images. Such applications typically organize images chronologically. However, chronological organization fails if the timestamp or location information stored in the image metadata (e.g., EXIF) is incorrect. Incorrect information is a common problem, e.g., when images are shared via messaging or social media, the shared image may have the time of sharing, not the time of capture. In another example, geolocation data may be deleted when an image is shared. Further, image timestamps can be inaccurate when multiple users contribute images to a single shared album from cameras that are …

Reporting Road Hazards Using In-Vehicle Camera, Catherine Cardinal, Chin Ngai Sze

Defensive Publications Series

Mobile phones, tablets, wearables, and cars themselves are increasingly aiding drivers. For example, mobile applications can alert drivers of hazardous road conditions, congestion, or accidents along the driver’s route. Additionally, mobile applications permit the reporting of such situations to other users. Occasionally, drivers may want to report nearby vehicles that exhibit unsafe or hazardous driving, or observed road hazards. This disclosure describes techniques to utilize devices (e.g., cameras) within a vehicle to automatically detect information about other vehicles that exhibit hazardous driving and road incidents nearby, such as vehicles driven by intoxicated persons. Further, these techniques also enable a driver …