Searching based on application usage

    公开(公告)号:US10445326B2

    公开(公告)日:2019-10-15

    申请号:US14985605

    申请日:2015-12-31

    Inventor: Eric Glover

    Abstract: A method includes retrieving event analytics data for a software application installed on a plurality of user devices. The event analytics data indicates a number of times each of the application states of the software application were accessed by the user devices. The method further includes mapping function names to the application states accessed by the user devices, each of the function names indicating a functionality associated with the software application. The method further includes determining a usage fraction value for each of the function names, the usage fraction value for each function name indicating the number of times the function name was mapped relative to the number of times each of the function names was mapped. Additionally, the method includes receiving a search query, generating search results based on at least one of the usage fraction values, and transmitting search results.

    Generating advertisements using functional clusters

    公开(公告)号:US10387505B2

    公开(公告)日:2019-08-20

    申请号:US14981732

    申请日:2015-12-28

    Abstract: A deep linking system includes an advertising engine. The advertising engine includes one or more processors configured to receive an advertisement request and identify one or more advertisement records based on the advertisement request and triggering data included in the one or more advertisement records. The one or more processors are further configured, for each advertisement record, to identify one or more cluster records based on the underlying sponsored state of the identified advertisement record and determine an advertisement score for the identified advertisement record based on the identified cluster records. The one or more processors select one or more of the identified advertisement records based on the advertisement scores, generate advertisement objects based on the selected advertisement records, and transmit the advertisement objects to the remote device.

    Latent semantic indexing in application classification

    公开(公告)号:US10229190B2

    公开(公告)日:2019-03-12

    申请号:US14272366

    申请日:2014-05-07

    Abstract: An application classifier classifies applications using latent semantic indexing (LSI) vectors of the applications. The application classifier uses a machine-learned model generated based on pairs of LSI vectors of positive and negative training sets of applications, where the positive training set includes applications within a desired category and the negative training set includes applications outside of the desired category. For a given application, the application classifier determines whether the application belongs to the desired category based on similarity of an LSI vector of the application and LSI vectors of positive and negative exemplar applications, as determined by the machine-learned model. If the LSI vector of the application is similar to an LSI vector of at least one positive exemplar application and not similar to an LSI vector of any of the negative exemplar applications, the application is determined to belong to the desired category.

Patent Agency Ranking