Google Inc.

John Mathias Barr

Geon Hyuk Park

Somit Gupta

Anish Acharya

Sundeep Singh Khandpur

Gavin Edward Bee

A system and machine-implemented method for real-time facial recognition at an image capture device is provided. The method includes capturing an image at an image capture device, the image containing at least a first person, analyzing the image to identify one or more data points corresponding to the first person, determining if mapping information corresponding to the one or more data points is locally available at the image capture device, sending a request to a remote device for mapping information when it is determined that mapping information corresponding to the one or more data points is not locally available at the image capture device, receiving mapping information corresponding to the one or more data points in response to the request and locally storing the mapping information at the image capture device.

Local real-time facial recognition

A method includes identifying a plurality of content types in a database of a social network, wherein members produce and request content of different content types from the database. Job types to be performed on each content type are identified, when requests for content are received from members of the social network. A sharding process for each content type is selected based on the job types to be performed on the content types. The database is sharded into first group of shards for content types having job types that are parallel processing efficient and into second group of shards for content types having job types that are linear processing efficient. The first and second group of shards define a multi-shard database. Requests for contents are serviced from the first group or the second group of shards from the multi-shard database depending on the job types associated with the requests.

Shard data based on associated social relationship

Aspects of the present disclosure are directed to methods and systems for applying electronic signatures to an electronically stored document wherein the electronic signatures are associated with a specific revision of that electronically stored document (revision specific electronic signatures).

Method and apparatus for applying revision specific electronic signatures to an electronically stored document

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a method are provided where the method includes receiving information from an image processing source that includes one or more images of a view area associated with a device, wherein the view area is an area located in front of a display screen associated with the device, wherein the view area enables one or more entities to view the display screen; determining one or more entities located within the view area based at least in part on the one or more images of the view area associated with the device; validating the one or more entities located within the view area; and when an entity within the view area is not validated, producing a security response.

Securing information using entity detection

Aspects and implementations of the present disclosure are directed to systems and methods of selecting content for presentation to a viewing user. In general, in some implementations, a data processing system identifies a topic for a document requested by a user, determines a confidence score for a correlation between the topic and the document, determines a sentiment score for a sentiment towards the topic, and determines, for a candidate content item, a predicted acceptance score based on the confidence score, the sentiment score, and acceptance history data for the candidate content item. The data processing system selects a candidate content item for presentation to the user based, at least in part, on the predicted acceptance score.

Sentiment and topic based content determination methods and systems

A computing device may extract keywords from a phone call or other audio communication and later display those keywords in a call log or in a caller ID. In one example, a method performed by at least one processor of a first computing device includes receiving speech inputs during an audio communication between the first computing device and a second device. The method further includes performing speech-to-text processing on the speech inputs to generate text based on the speech inputs. The method further includes performing keyword extraction processing on the text to generate one or more keywords based on the text, that score highly as relevant indicators of the audio communication, based on one or more keyword extraction criteria. The method further includes storing the one or more keywords in association with identifying information associated with the second device. The method further includes outputting the one or more keywords, in association with the identifying information associated with the second device, at a display of the first computing device.

Growing community of inventors

CA

John Mathias Barr