Predicting future queries from log data
A system, media, and method for selecting future queries are provided. The selected future queries are used to transmit appropriate online advertising to a user that issues queries to a search engine. The search engine is coupled to a prediction component that predicts what subject the user is going to be interested in and when the user will be interested in the subject. The prediction component returns a future query using statistical language models representing a query history of the user and aggregate query histories for a community of users.
1. One or more computer readable storage media storing instructions for performing a method of presenting advertisements for a predicted future query, the method comprising:
identifying a predicted future query;
selecting advertisements that correspond to the future predicted query;
and
displaying the advertisements for a time period that corresponds to a predicted time period that a user will issue the future predicted query.
2. The storage media of claim 1 , wherein the predicted future query is based on previous activities of the user observed through previously received user queries and common behaviors of other users represented in query log data.
3. The storage media of claim 1 , wherein the advertisements include banner advertisements, text, images, audio, or video.
4. The storage media of claim 1 , wherein the predicted time period is one of: immediately, 24 hours, one month, three month, or one quarter.
5. The storage media of claim 1 , wherein the predicted future query is associated with a recurring event.
6. The storage media of claim 1 , wherein the predicted future query is identified based on a background model.
7. The storage media of claim 1 , wherein the predicted future query is identified based on a lifetime model.
8. A computer-implemented method of presenting advertisements for a predicted future query, the method comprising:
identifying a predicted future query;
selecting advertisements that correspond to the future predicted query;
and
displaying the advertisements for a time period that corresponds to a predicted time period that a user will issue the future predicted query.
9. The method of claim 8 , wherein the predicted future query is based on previous activities of the user observed through previously received user queries and common behaviors of other users represented in query log data.
10. The method of claim 8 , wherein the predicted time period is one of: immediately, 24 hours, one month, three month, or one quarter.
11. The method of claim 8 , wherein the predicted future query is associated with a recurring event.
12. The method of claim 8 , wherein the advertisements are displayed to the user proximate to a time the predicted future query is identified or the advertisements are communicated after a period of time has expired since the predicted future query was identified, the period of time is one of a quarter year, a month, a bi-week, or a week.
13. The method of claim 8 , wherein the predicted future query is identified based on a background model.
14. The method of claim 8 , wherein the predicted future query is identified based on a lifetime model.