Temporal targeting of advertisements

• US 7,672,937 B2
• Filed: 04/11/2007
• Issued: 03/02/2010
• Est. Priority Date: 04/11/2007
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Madhavan, Anand, Kapur, Shyam
• Primary Examiner(s): Le; Uyen T.
• Application Number:
  US11/786,238
• Publication Number:
  US 20080255935A1
• Time in Patent Office: 1,056 Days
• Field of Search: None
• US Class Current: 707/752
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0267 Wireless devices

Abstract

A system and method utilize temporal targeting of content, such as advertisements. The targeting may be based on time of day, day of year, season or upcoming holidays. In addition, prior search history may be utilized to determine current popularity and/or predict future popularity for a particular concept that may be used for targeting.

Claims

1. A computerized method for selecting a targeted advertisement, the method comprising:

determining a temporal indicator;

receiving, over a network, a set of available advertisements that are dependent on the temporal indicator;

analyzing, with a processor, the set of available advertisements to determine advertisements relevant with respect to a time period indicated by the temporal indicator, wherein the relevance is measured by reviewing a search log database to determine a frequency with which a topic from the advertisement is found, from the search log database, in historical search queries that correspond with the time period indicated by the temporal indicator, further wherein the correspondence with the time period comprises at least one of a similar season, a similar date, or a similar time of day;

selecting the targeted advertisement from the set of available advertisements, wherein the targeted advertisement is selected by the processor based on the analysis to include the relevant advertisements; and

providing the selected targeted advertisement for display.

2. The method according to claim 1 wherein the temporal indicator comprises a date and a time of day.

3. The method according to claim 1 wherein the temporal indicator comprises a season.

4. The method according to claim 1 wherein the similar date identifies at least one of a season, holiday, day of week, or combinations thereof.

5. The method according to claim 1 wherein at least one advertisement from the set of available advertisements is associated with search results from a search query.

6. The method according to claim 1 wherein the correspondence comprises comparing a current date indicated by the temporal indicator with a past date, wherein the past date is from a previous year to the current date, further wherein the past date comprises the similar date when it corresponds with the current date.

7. The method according to claim 6 wherein the analysis comprises identifying a popular historical search query from the past date.

8. The method according to claim 1 further comprising:

identifying, for each of the set of available advertisements, at least one topic related to the advertisement; and

determining a current relevance, an expected relevance, or a combination thereon of the at least one topic for each of the set of available advertisements;

wherein the targeted advertisement is selected based on the determined current relevance, the expected relevance, or a combination thereof.

9. The method according to claim 8 wherein the current relevance reflects a current popularity and the expected relevance reflects an expected popularity.

10. In a computer readable storage medium having stored therein data representing instructions executable by a programmed processor for determining a spike in popularity of a search query, the storage medium comprising instructions operative for:

analyzing at least one search log, wherein the at least one search log includes a plurality of search queries, wherein the analysis includes reviewing the plurality of search queries over time;

reviewing a frequency for at least some of the plurality of search queries;

determining when the at least some of the plurality of search queries experience a spike in relevance over time based on the reviewed frequency;

identifying a topic for each search query of the plurality of search query that has previously experienced the spike in relevance;

identifying a time from which the identified topic experienced the spike in relevance;

analyzing the time from which the identified topic experienced the spike to determine when a spike will reoccur; and

selecting an advertisement for the topic when the identified time for the spike will reoccur based on the analysis.

11. The storage medium according to claim 10 wherein the identified time includes at least one of a season of the experienced spike, a time of day of the experienced spike, a day of a week of the experienced spike, or a date of the experienced spike.

12. The storage medium according to claim 11 wherein the reoccurrence is predicted from the identified time of the experienced spike.

13. The storage medium according to claim 11 wherein the identified time comprises the date of the experienced spike, further wherein the spike in popularity may be predicted based on the recurrence of popularity on the recurring date.

14. The storage medium according to claim 10 wherein the determination of the spike in popularity includes reviewing historical search logs.

15. The storage medium according to claim 10 wherein the spike in popularity may be predicted based on a recurrence of popularity on a recurring time.

16. A computer system displaying search results with an advertisement, the system comprising:

a search engine configured to provide the search results for a search keyword;

a search log database coupled with the search engine and configured to receive the search keyword that is searched in the search engine, wherein the search log database stores a plurality of search keywords that are searched over a period of time and stores a time that each search keyword of the plurality of search keywords is searched;

a temporal analyzer coupled with the search log database and configured to analyze the search log database to determine which keywords are relevant at which temporal period and correlate a current temporal period with the temporal periods from the search log database to identify topics related to the keywords that are likely to be popular at the current temporal period; and

an advertisement server that receives the analysis from the temporal analyzer for selecting the advertisement to display, wherein the advertisement is selected from a plurality of advertisements based on the identified topics that are popular at the current temporal period.

17. The system according to claim 16 wherein the temporal period comprises a date, a time of day, season, or combination thereof.

18. The system according to claim 17 wherein the time of day is a current time, which comprises a current date.

19. The system according to claim 16 further comprising a data source coupled with the search log database and configured to provide additional search keywords to be stored in the search log database.

20. The system according to claim 16 further comprising a user device coupled with the search engine, wherein a user of the user device enters the search keyword and receives the search results for that keyword.

21. The system according to claim 16 further comprising an advertisement server coupled with the search engine and configured to provide an advertisement displayed with the search results, wherein the advertisement is targeted based on at least one identified topic that is popular at the current time.

22. In a computer readable storage medium having stored therein data representing instructions executable by a programmed processor for selecting relevant content, the storage medium comprising instructions operative for:

receiving search queries;

recording the received search queries as search query data in a search log database, wherein the search query data includes a date and time of day for the recorded search queries;

utilizing the search query data to identify date-based topics and time-based topics in the search queries, wherein the date-based topics have popularity influenced by the date and time-based topics have popularity influenced by the time;

identifying, upon receipt of a current search request, one of the date-based topics that corresponds to a date of receipt of the current search request; and

selecting the relevant content for display based on the identified date-based topic.

23. The computer readable medium according to claim 22 wherein the relevant content comprises an advertisement that is displayed with search results from the received search query.

24. The computer readable medium according to claim 22 further comprising:

utilizing the search query data to identify time-based topics in the search queries, wherein the time-based topics have popularity influenced by the time;

identifying, upon receipt of a current search request, one of the time-based topics that corresponds to the time of receipt of the current search request; and

selecting the relevant content for display based on the identified time-based topic.

25. A computerized method for selecting a targeted advertisement, the method comprising:

receiving a search query at a search engine;

providing, by the search engine, a search results page with an advertisement slot that includes search results from athe search query;

accessing a search log stored in a search log database that comprises past search queries and a timing for the past search queries;

comparing, with a processor, a current time of the received search query with the search log to identify popular past search queries whose timing corresponds with the current time of the received search query, wherein the timing comprises a season, a date, or a time of day, further wherein popularity is determined based on a number of searches for a past date or past time of day;

analyzing the identified past popular search queries to determine advertisements that are related to the identified past popular search queries; and

displaying the targeted advertisement selected from the determined advertisements.