Back to results
US 2014/0280221 A1Published application
Tailoring user experience for unrecognized and new users
AssigneeGoogle Inc.
InventorsPi-Chuan Chuang, Daniel Ramage
Life of this patent
Estimating the term…
Abstract
A system stores a table mapping users to attributes, and stores a second table mapping the users to products associated with a source domain. The system determines a set of top scoring products for each of the attributes, and creates, using the top scoring products, a model that is predictive of an activity in a target domain, the target domain being separate from the source domain. The system detects a behavior from a particular user accessing the target domain, and generates a personalized prediction for the particular user based on the model, in response to the detecting the behavior.
Claims20
A method comprising:
- storing a table mapping users to attributes;
- storing a second table mapping the users to products associated with a source domain;
- determining, using a processor of a computer system, a set of top scoring products for each of the attributes;
- creating, using the top scoring products, a model that is predictive of an activity in a target domain, the target domain being separate from the source domain;
- detecting a behavior from a particular user accessing the target domain;
- and
- generating a personalized prediction for the particular user based on the model, in response to the detecting the behavior.
4 more elements
A method comprising:
- determining users having a set of matching attributes;
- storing a set of products associated with a source domain and accessed by each of the users;
- determining a subset of the products corresponding to each attribute of the set of matching attributes;
- creating, using the subset of the products, a model that is predictive of an activity in a target domain, the target domain being separate from the source domain;
- determining that a particular user lacks recorded behavior in the source domain;
- in response to determining that the particular user lacks recorded behavior in the source domain, determining that the particular user has sufficient recorded behavior in a proxy domain, the proxy domain being separate from the source domain and having similar properties as the source domain;
- and
- in response to determining that the particular user has sufficient recorded behavior in the proxy domain, generating a personalized prediction for the particular user based on the sufficient recorded behavior in the proxy domain, using the model, the personalized prediction for the particular user being generated in response to the particular user performing the activity while accessing the target domain.
5 more elements
A system comprising:
- a memory storing instructions;
- and
- a processor operably coupled to the memory and configured to execute the instructions to cause the system to perform operations including:
- determining users having a set of matching attributes;
- storing a set of products associated with a source domain and accessed by each of the users;
- determining a subset of the products corresponding to each attribute of the set of matching attributes;
- creating, using the subset of the products, a model that is predictive of an activity in a target domain, the target domain being separate from the source domain;
- determining that a particular user lacks recorded behavior in the source domain;
- in response to determining that the particular user lacks recorded behavior in the source domain, determining that the particular user has sufficient recorded behavior in a proxy domain, the proxy domain being separate from the source domain and having similar properties as the source domain;
- and
- in response to determining that the particular user has sufficient recorded behavior in the proxy domain, generating a personalized prediction for the particular user based on the sufficient recorded behavior in the proxy domain, using the model, the personalized prediction for the particular user being generated in response to the particular user performing the activity while accessing the target domain.
8 more elements
Dependencies are inferred from the claim text.