Intuit, Inc.

Flipboard, Inc.

Vaibhav Sharma

Grace Wu

Shashank Shashikant Rao

Susrutha Gongalla

Carly Wood

Ngoc Nhung Ho

Jing Zhao

Nhung Ho

Prasannavenkatesh Chandrasekar

Mark Rietveld

Geert H Weening

Brooke Henderer

Aspects of the present disclosure provide techniques for classifying a trip. Embodiments include receiving, from a plurality of users, a plurality of historical trip records. Each of the plurality of historical trip records may comprise one or more historical trip attributes and historical classification information. Embodiments include training a predictive model, using the plurality of historical trip records, to classify trips based on trip records. Training the predictive model may comprise determining a plurality of hot spots based on the historical trip records, each of the plurality of hot spots comprising a region encompassing one or more locations, and associating, in the predictive model, the plurality of hot spots with historical classification information. Embodiments include receiving, from a user, a new trip record comprising a plurality of trip attributes related to a trip and using the predictive model to predict a classification for the trip based on the trip record.

Method and system for smart detection of business hot spots

Certain aspects of the present disclosure provide techniques for intelligent grouping of travel data for review through a user interface. In one embodiment, a method for providing grouped travel data to a user interface of an application, comprises: receiving a plurality of trip records from an application running on a remote device; providing a first subset of the plurality of trip records to a prediction model; providing a second subset of the plurality of trip records to a model training module; receiving labels for each trip record of the first subset of the plurality of trip records from the prediction model; grouping the first subset of the plurality of trip records based on the received labels; and transmitting the grouped first subset of the plurality of trip records to the application running on the remote device.

Intelligent grouping of travel data for review through a user interface

A digital magazine server logs user interactions with content provided by the server, including the topic of the content and time of the interaction by the user. For each user of the server, the server segments the time interval (e.g., a day) of the user's interactions with content into time periods, e.g., fixed time periods or automatically determined time periods, and ranks topics of interest for each time period. The server also obtains a list of topics that each user interacted with each day. The digital magazine server uses a time segmentation module based on content interaction data and associated timing information from the users of the server. Upon receiving a request for content from a user, the digital magazine server ranks the content for display to the user based on the match between the content and the ranked topics for the user during the current time associated with the request.

Pattern matching for content in digital magazine

A digital magazine application executing on a client device presents digital content to a user. Historical connectivity data describing connectivity between the client device and a network is obtained and is used to determine a predicted disconnection time indicating an anticipated loss of connectivity between the client device and the network. The historical connectivity is also used to determine a preload time prior to the predicted disconnection time. Content selected by the digital magazine server is communicated to the client device at the determined preload time for storage by the client device. Content may be selected for transmission based on attributes of content previously requested when the connection between the client device and network has less than a threshold bandwidth. At the preload time, for example, the client device requests a section of a digital magazine associated with content previously requested at times of low-bandwidth network connectivity.

Providing digital content for offline consumption

A content stream including content items retrieved from various applications executing on a client device is presented by the client device. A set of content items associated with a topic matching a stream topic associated with the content stream is identified from the retrieved content items. Quality scores are determined for each content item in the set providing a measure of a user's interest in each content item. A display set of content items is selected based on the quality scores, with one or more content items from the display set displayed based on a stream template. The stream template includes multiple slots each associated with one or more content items, and specifies a relative position of different slots to each other.

Growing community of inventors

Mountain View, CA, United States of America

Vaibhav Sharma