Abstract: Implementations set forth herein relate to generating and rendering continuing content (e.g., natural language content) that can be used, by a human user, in completing a partial spoken utterance of the user. The continuing content can be rendered via a wearable device (e.g., earbuds or eyeglasses). In various implementations, generating and/or rendering of the continuing content can be performed automatically (at least when certain condition(s) are satisfied) responsive to the partial spoken utterance and independent of any user input(s) that explicitly invokes the generating and/or the rendering. Furthermore, in many implementations, at least rendering of the continuing content is selectively performed. For example, automatic rendering of the continuing content can be selectively performed when certain condition(s) are satisfied, such as detection of a disfluency following the partial spoken utterance.

Abstract: Implementations of the present disclosure include actions of receiving image data of an image capturing a scene, receiving data describing one or more entities determined from the scene, the one or more entities being determined from the scene, determining one or more actions based on the one or more entities, each action being provided at least partly based on search results from searching the one or more entities, and providing instructions to display an action interface comprising one or more action elements, each action element being to induce execution of a respective action, the action interface being displayed in a viewfinder.

Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

Abstract: Methods, systems, and apparatus for receiving a query image, receiving one or more entities that are associated with the query image, identifying, for one or more of the entities, one or more candidate search queries that are pre-associated with the one or more entities, generating a respective relevance score for each of the candidate search queries, selecting, as a representative search query for the query image, a particular candidate search query based at least on the generated respective relevance scores and providing the representative search query for output in response to receiving the query image.

Abstract: At least one aspect of the present disclosure is directed to systems and methods of generating on-device content items to improve security and network utilization. A client device can access content resources and category information from a data structure in the memory the memory of the client device. The client device can generate on-device content items based on the content resources and the category information. The client device can receive an indication to display a content item in an application executing on the client device. The client device can scan the client device for context information to create a relevant device context. The client device can select an on-device content item based on the relevant device context. The client device can provide the selected on-device item to the application for display, detect an interaction with the displayed content item, and update a content selection model or a content generation model.

Abstract: A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.

Abstract: A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.

Abstract: Systems and methods are provided for a content-based security for computing devices. An example method includes identifying content rendered by a mobile application, the content being rendered during a session, generating feature vectors from the content and determining that the feature vectors do not match a classification model. The method also includes providing, in response to the determination that the feature vectors do not match the classification model, a challenge configured to authenticate a user of the mobile device. Another example method includes determining a computing device is located at a trusted location, capturing information from a session, the information coming from content rendered by a mobile application during the session, generating feature vectors for the session, and repeating this until a training criteria is met. The method also includes training a classification model using the feature vectors and authenticating a user of the device using the trained classification model.

Abstract: Methods, systems, and apparatus for receiving a query image, receiving one or more entities that are associated with the query image, identifying, for one or more of the entities, one or more candidate search queries that are pre-associated with the one or more entities, generating a respective relevance score for each of the candidate search queries, selecting, as a representative search query for the query image, a particular candidate search query based at least on the generated respective relevance scores and providing the representative search query for output in response to receiving the query image.

Abstract: Systems and methods for partitioning a large model that has been configured to use a model-synthesis approach in which multiple basis models are combined to generate a final output. The present technology provides systems and methods for identifying a device-specific or subject-specific subset of those basis models to be used on a given device, such that it need not store the weight matrices for the entire set of basis models, and may perform inference using only the weight matrices of the identified subset of basis models. In some examples, the subset of basis models used by a given device may be updated based on actual usage and feedback. Likewise, in some examples, the model may be trained in a federated setting in which multiple devices each utilize different subsets of the basis models, and share training signals with a full copy of the model.

Abstract: Systems and methods are provided for a personalized entity repository. For example, a computing device comprises a personalized entity repository having fixed sets of entities from an entity repository stored at a server, a processor, and memory storing instructions that cause the computing device to identify fixed sets of entities that are relevant to a user based on context associated with the computing device, rank the fixed sets by relevancy, and update the personalized entity repository using selected sets determined based on the rank and on set usage parameters applicable to the user. In another example, a method includes generating fixed sets of entities from an entity repository, including location-based sets and topic-based sets, and providing a subset of the fixed sets to a client, the client requesting the subset based on the client's location and on items identified in content generated for display on the client.

Abstract: Systems and methods are provided for sharing a screen from a mobile device. For example, a method includes receiving, at a second mobile device, an image of a screen captured from a first mobile device and determining whether to trigger an automated action. The method may also include displaying, responsive to not triggering the automated action, annotation data generated for the image with the image on a display of the second mobile device, the annotation data including at least one visual cue corresponding to content in the image relevant to a user of the second mobile device. The method may further include, responsive to triggering the automated action, determining that a mobile application associated with the image is installed on the second mobile device and replaying user input actions received with the image on the second mobile device starting from a reference screen associated with the mobile application.

Abstract: A computing system: receives a first user input from a user selecting a portion of the query image; detects text in a first area of the query image associated with the portion of the query image selected by the user; obtains first search results and a suggested search query, based on a first optical character recognition (OCR) operation performed with respect to the text in the first area of the query image and a second OCR operation performed with respect to further text in a second area of the query image, different from the first area of the query image; and provides a first user interface for display to the user, the first user interface comprising the first search results and the suggested search query. The first processing power associated with the first OCR operation is greater than a second processing power associated with the second OCR operation.

Abstract: Systems and methods are provided for a personalized entity repository. For example, a computing device comprises a personalized entity repository having fixed sets of entities from an entity repository stored at a server, a processor, and memory storing instructions that cause the computing device to identify fixed sets of entities that are relevant to a user based on context associated with the computing device, rank the fixed sets by relevancy, and update the personalized entity repository using selected sets determined based on the rank and on set usage parameters applicable to the user. In another example, a method includes generating fixed sets of entities from an entity repository, including location-based sets and topic-based sets, and providing a subset of the fixed sets to a client, the client requesting the subset based on the client's location and on items identified in content generated for display on the client.

Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

Abstract: Systems and methods are shown for providing private local sponsored content selection and improving intelligence models through distribution among mobile devices. This allows greater data gathering capabilities through the use of the sensors of the mobile devices as well as data stored on data storage components of the mobile devices to create predicted models while offering better opportunities to preserve privacy. Locally stored profiles comprising machine intelligence models may also be used to determine the relevance of the data gathered and in improving an aggregated model for identifying the relevance of data and the selection of sponsored content items. Distributed optimization is used in conjunction with privacy techniques to create the improved machine intelligence models. Publishers may also benefit from the improved privacy by protecting the statistics of type or volume of sponsored content items shown with publisher content.

Abstract: Methods, systems, and apparatus for receiving a query image and a user tap location, processing the received query image based on the user tap location, identifying one or more entities associated with the processed query image and in response to receiving (i) the query image, and (ii) the user tap location, providing information about the identified one or more of the entities.

Abstract: Implementations of the present disclosure include actions of receiving image data of an image capturing a scene, receiving data describing one or more entities determined from the scene, the one or more entities being determined from the scene, determining one or more actions based on the one or more entities, each action being provided at least partly based on search results from searching the one or more entities, and providing instructions to display an action interface comprising one or more action elements, each action element being to induce execution of a respective action, the action interface being displayed in a viewfinder.

Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

Abstract: Implementations of the present disclosure include actions of receiving image data of an image capturing a scene, receiving data describing one or more entities determined from the scene, the one or more entities being determined from the scene, determining one or more actions based on the one or more entities, each action being provided at least partly based on search results from searching the one or more entities, and providing instructions to display an action interface comprising one or more action elements, each action element being to induce execution of a respective action, the action interface being displayed in a viewfinder.