Back to results
US 11,687,597 B2Granted
Low entropy browsing history for content quasi-personalization
AssigneeGoogle Inc.
InventorsGang Wang, Marcel M. M. Yung
Life of this patent
Estimating the term…
Abstract
The present disclosure provides systems and methods for content quasi-personalization or anonymized content retrieval via aggregated browsing history of a large plurality of devices, such as millions or billions of devices. A sparse matrix may be constructed from the aggregated browsing history, and dimensionally reduced, reducing entropy and providing anonymity for individual devices. Relevant content may be selected via quasi-personalized clusters representing similar browsing histories, without exposing individual device details to content providers.
Claims20
A method, comprising:
- identifying, by a first application executing on a client device, a browsing history associated with the client device, the browsing history recording information resources accessed by the client device via the first application;
- applying, by the first application, a classification model to the browsing history to identify a first class from a plurality of classes;
- receiving, by the first application from a content publisher device, an information resource comprising primary content and a content slot available to receive content from a content selection service;
- generating, by the first application, a request for content comprising a secure cookie including a class identifier for the first class;
- and transmitting, by the first application, the request for content to the content selection service, the content selection service using the class identifier for the first class to select a content item to insert into the content slot of the information resource.
2 more elements
A system, comprising:
- a computing device comprising a network interface in communication with a content publisher device and a content selection service, one or more processors executing a browser application, and a memory storing a browsing history recording information resources accessed by the browser application;
- and wherein the browser application is configured to:
- applying a classification model to the browsing history to identify a first class from a plurality of classes, receive, from the content publisher device, an information resource comprising primary content and a content slot available to receive content from a content selection service, generate a request for content comprising a secure cookie including a class identifier for the first class, and transmit the request for content to the content selection service, the content selection service using the class identifier for the first class to select a content item to insert into the content slot of the information resource.
A system, comprising:
- one or more computing devices, each computing device comprising a network interface and one or more processors;
- wherein the one or more computing devices are configured to:
- receive, from each of a plurality of client computing devices, a profile based on a browsing history of the corresponding client computing device, each profile comprising an n- dimensional vector, aggregate the plurality of n-dimensional vectors of the plurality of profiles into a matrix, generate, from the matrix, a set of parameters for a classification model, and transmit, to each of the plurality of client computing devices, the set of parameters, each client computing device utilizing the set of parameters to classify the browsing history of the corresponding client computing device.
Dependencies are inferred from the claim text.