Abstract: An audience measurement service may monitor broadcasts in a region, ingesting closed captioning data, metadata, displayed text or logos, performing facial recognition on people, and/or generating audio/video fingerprints of broadcast content to create a database of content and associated keywords, along with times at which the content was broadcast. The audience measurement service may receive user search queries from a search provider and detect “spiking” queries. The audience measurement service may determine whether the spiking queries are related, contextually and temporally, to an item of content identified in the database, and infer that users generating the queries likely viewed the item of content. In some implementations, the audience measurement service may also infer that the users likely viewed other items of content (e.g. advertisements) displayed during the prior or subsequent few minutes on the same broadcast channel as the query-triggering item.

Abstract: Systems and methods for joining a device to a fabric using an assisting device include an indication to add a joining device to a fabric. If the joining device supports network-assisted fabric pairing, a first connection is established between a commissioning device and the assisting device. The assisting device also connects to a joining device. Through the assisting device, the commissioning device and the joining device establish a communication channel over which fabric credentials may be sent.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for audio classifiers. In one aspect, a method includes obtaining a plurality of video frames from a plurality of videos, wherein each of the plurality of video frames is associated with one or more image labels of a plurality of image labels determined based on image recognition; obtaining a plurality of audio segments corresponding to the plurality of video frames, wherein each audio segment has a specified duration relative to the corresponding video frame; and generating an audio classifier trained using the plurality of audio segment and the associated image labels as input, wherein the audio classifier is trained such that the one or more groups of audio segments are determined to be associated with respective one or more audio labels.

Abstract: A logical segmentation data processing system includes a data retrieval interface configured to receive, from a remote geo-caching data system, geo-caching data representing geographic locations specified by the remote geo-caching data system. The data processing system includes a logical segmentation engine configured to segment a geographic map into geo-areas, each geo-area comprising a subset of the geographic locations represented by the geo-caching data. The data processing system includes an evaluation engine configured to rank, for each of a plurality of the geo-areas, geographic locations in that geo-area. The data processing system includes an aggregation engine configured to select, from each of the plurality of geo-areas, one or more geographic locations with a higher ranking, relative to the rankings of other geographic locations in that geo-area, and to aggregate the selected geographic locations.

Abstract: In embodiments of mesh network addressing, a router registers an address for an end device and assigns a child identifier to the end device. The router encodes an endpoint identifier of the end device, and a router identifier of the router into an Endpoint Identifier, which the router incorporates into a Routing Locator (RLOC) for the end device. The router responds to address queries and receives data packets on behalf of the end device. The router stores the data packets for the end device until the router can forward the data packets to the end device.

Abstract: Apparatus and methods related to stored software libraries are provided. A computing device can receive versioned-shared-library information for a first software library used by a software application, where the versioned-shared-library information can include an identifier. The computing device can determine whether the computing device stores a copy of the first software library identified in the versioned-shared-library information by the identifier. The computing device can send a request for one of a full executable and a stripped executable for the software application, where the full executable includes the first software library, and where the stripped executable excludes the first software library. In response to the request, the computing device can receive the full executable or the stripped executable for the software application.

Abstract: A computer-implemented technique includes initiating, at a first computing device including one or more processors, communication with a second computing device via a short-range wireless communication protocol. The technique includes receiving, at the first computing device, a set of information from the second computing device via the short-range wireless communication protocol, the set of information for configuring communication via a different, second wireless communication protocol.

Abstract: The present disclosure is generally related to a data processing system to detect potential exfiltration of audio data by agent applications can include a data processing system. The data processing system can identify, from an I/O record, an input received from the digital assistant application via a microphone of a client device, an output received from the agent application after the input, and a microphone status for the microphone. The data processing system can determine that the output is terminal based on the input and the output. The data processing system can identify the microphone status as in the enabled state subsequent to the input. The data processing system can determine that the agent application is unauthorized to access audio data acquired via the microphone of the client device based on determining that the output is terminal and identifying the microphone status as enabled.

Abstract: Systems and methods for prefetching content items for display by applications executed on computing devices are provided. The method can include transmitting a first request for content to display within an environment of the application, the first request for content including a first parameter to be used to determine a first content item for display; storing in an associated memory element, the first parameter, transmitting a follow-on request for content including the first parameter of the first request for content; receiving a follow-on content item responsive to the follow-on request for content; storing the follow-on content item in a local cache structure specific to the application; transmitting a second request for content; retrieving, in response to the second request, the follow-on content item from the local cache structure; and displaying, in response to the second request, the follow-on content item within the environment of the application on the computing device.

Abstract: Systems and methods are provided for improving communications between infrastructures using RPCs. An authoritative endpoint in a first infrastructure receives a registration request from a non-authoritative server in a second infrastructure through a transport layer on which a remote procedure call (RPC) layer depends. This request establishes a connection with the authoritative endpoint. The authoritative entity authenticates and registers the non-authoritative entity, and receives RPCs from client devices through the non-authoritative entity. The authoritative entity provides responses to the RPCs through the non-authoritative entity over the established connection. The authoritative entity also performed load-shedding operations, such as notifying the non-authoritative entity of a time to live of the connection. The RPC requests and responses sent over the connection may be chunked into frames, each frame identifying a stream to which it belongs.

Abstract: Systems and method for implementing third party services in digital service platform are provided. More specifically, an application program interface can be provided by a first service provider to a second service provider. The application program interface can be configured to receive one or more access parameters and can be associated with implementing one or more services of the second service provider in one or more services of a second service provider. The one or more access parameters can then be received by the first service provider from the second service provider. Once the one or more access parameters have been received, the first service provider can receive a request from a user for access to the one or more services of the second service provider. The first service provider can then determine whether to grant access to the user based on the access parameters.

Abstract: A low cost, robust, wireless sensor that provides an extended period of operability without maintenance is described. The wireless sensors are configured to communicate with a base unit or repeater. When the sensor unit detects an anomalous ambient condition (e.g., smoke, fire, water, etc.) the sensor communicates with the base unit and provides data regarding the anomalous condition. The sensor unit receives instructions to change operating parameters and/or control external devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

Abstract: This document generally describes systems and methods for dynamically adapting speech recognition for individual voice queries of a user using class-based language models. The method may include receiving a voice query from a user that includes audio data corresponding to an utterance of the user, and context data associated with the user. One or more class models are then generated that collectively identify a first set of terms determined based on the context data, and a respective class to which the respective term is assigned for each respective term in the first set of terms. A language model that includes a residual unigram may then be accessed and processed for each respective class to insert a respective class symbol at each instance of the residual unigram that occurs within the language model. A transcription of the utterance of the user is then generated using the modified language model.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving at a computing device that is in a locked state, one or more user inputs to unlock the device and to execute at least one command that is different from a command for unlocking the device. The method further includes executing in response to the user inputs to unlock the device an unlocking operation by the device to convert the device from a locked state to an unlocked state. The method further includes executing the at least one command in response to receiving the user inputs to execute the at least one command. The at least one command executes so that results of executing the at least one command are first displayed on the device to a user automatically after the device changes from the locked state to the unlocked state.

Abstract: Systems and methods for automatically generating remarketing lists based on client sessions are provided. The system can include a visitor management module to identify client sessions established at a website. The visitor management module can determine node pairs including destination nodes and referrer nodes. The system can include a graph construction module to construct a graph including the node pairs and edges between the node pairs representing click-through rates. The system can include a graph clustering module to assign information resources to a first group based on one of i) a number of edges between the nodes and a conversion node or ii) click-through rates of node pairs including. The system includes a remarketing list generation module to assign the first group of information resources to a remarketing list. The remarketing list generation module can assign client identifiers that accessed the first group of information resources to the remarketing list.

Abstract: Various methods and systems for smart home devices are presented. Such smart home devices may include one or more environmental sensors that are configured to detect the presence of one or more environmental conditions. Such smart home devices may include a light comprising a plurality of lighting elements. Such a light may be configured to illuminate using a plurality of colors and, possibly, a plurality of animation patterns. Such smart home devices may include a processing system configured to cause the light to illuminate using the plurality of colors and the plurality of animation patterns in response to a plurality of states of the smart home device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for keyword spotting. One of the methods includes training, by a keyword detection system, a convolutional neural network for keyword detection by providing a two-dimensional set of input values to the convolutional neural network, the input values including a first dimension in time and a second dimension in frequency, and performing convolutional multiplication on the two-dimensional set of input values for a filter using a frequency stride greater than one to generate a feature map.