Suggesting and/or providing targeting criteria for advertisements

• US 10,580,033 B2
• Filed: 05/16/2017
• Issued: 03/03/2020
• Est. Priority Date: 12/31/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Koningstein, Ross, Spitkovsky, Valentin, Harik, Georges, Shazeer, Noam M.
• Primary Examiner(s): Bekerman, Michael
• Application Number:
  US15/596,210
• Publication Number:
  US 20170249662A1
• Time in Patent Office: 1,022 Days
• Field of Search: 705 141- 1473
• CPC Class Codes: G06F 16/316 Indexing structures
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

Keyword suggestions that are category-aware (and field-proven) may be used to help advertisers better target the serving of their ads, and may reduce unused ad spot inventory. The advertiser can enter ad information, such as a creative, a landing Webpage, other keywords, etc. for example. A keyword facility may use this entered ad information as seed information to infer one or more categories. It may then request that the advertiser confirm or deny some basic feedback information (e.g., categories, Webpage information, etc.). For example, an advertiser may be provided with candidate categories and may be asked to confirm (e.g., using checkboxes) which of the categories are relevant to their ad. Keywords may be determined using at least the categories. The determined keywords may be provided to the advertiser as suggested keywords, or may automatically populate ad serving constraint information as targeting keywords. The ad server system can run a trial on the determined keywords to qualify or disqualify them as targeting keyword.

Claims

1. A method, comprising:

receiving, by one or more computing devices, a submitted keyword that controls distribution of an audio file to content rendering devices;

accessing, by the one or more computing devices, a keyword to category index to identify a category of the keyword;

identifying, by the one or more computing devices, different keywords that are indexed to the category of the keyword as suggested keywords for controlling distribution of the audio file;

ordering, by the one or more computing devices, the suggested keywords based on performance information, including;

receiving, by the one or more computing devices and from a given content rendering device, audio input of one or more search terms;

distributing, by the one or more computing devices, the audio file to the given content rendering device based on the one or more search terms matching one of the suggested keywords;

updating performance information for the one of the suggested keywords based on the distribution of the audio file; and

ranking the one of the suggested keywords among others of the suggested keywords based on the updated performance information, wherein ranking the one of the suggested keywords among others of the suggested keywords comprises ranking the one of the suggested keywords based on how many unused presentation spots would be filled using the one of the suggested keywords relative to how many of the unused presentation spots would be filled using each of the others of the suggested keywords; and

suggesting one or more highest ranked suggested keywords as a keyword that controls distribution of the audio file.

2. The method of claim 1, comprising:

parsing, from one or more search queries, one or more first keywords;

storing, using a hardware storage device associated with a computer system including a plurality of networked computers, an index data structure including a plurality of entries that each include (1) a keyword of the one or more first keywords, and (2) one or more categories that include the keyword by virtue of the one or more categories being in a same entry of the index data structure, a lookup key of the index data structure being a keyword-based lookup key; and

performing an index inversion operation on the index data structure to generate an inverted index data structure.

3. The method of claim 2, wherein the inverted index data structure stores a plurality of entries that each include 1) a category and (2) one or more second keywords associated with the category by virtue of the one or more second keywords being in a same entry of the inverted index data structure, the lookup key being updated to include a category-based lookup key.

4. The method of claim 3, wherein identifying the different keywords comprises:

accessing the inverted index data structure; and

identifying the plurality of entries that include the category of the keyword; and

identifying the one or more second keywords as the different keywords based on the inclusion of the one or more keywords in the same entry of the inverted index data structure.

5. The method of claim 4 comprising:

performing qualification testing of the one or more second keywords that were identified as the different keywords; and

determining that at least one of the different keywords is qualified for use as a keyword that controls distribution of the audio file; and

determining that one or more of the different keywords is unqualified for use as a keyword that controls distribution of the audio file, wherein suggesting one or more highest ranked suggested keywords comprises suggesting only the at least one of the different keywords that is qualified for use as a keyword that controls distribution of the audio file.

6. The method of claim 1, wherein the audio file distributed using the suggested one or more highest ranked keywords is distinctively presented relative to search results that are distributed in response to a query matching the suggested one or more highest ranked keywords.

7. An apparatus comprising:

one or more processors; and

at least one storage device storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including;

receiving a submitted keyword that controls distribution of an audio file to content rendering devices;

accessing a keyword to category index to identify a category of the keyword;

identifying different keywords that are indexed to the category of the keyword as suggested keywords for controlling distribution of the audio file;

ordering the suggested keywords based on performance information, including;

receiving, from a given content rendering device, audio input of one or more search terms;

distributing the audio file to the given content rendering device based on the one or more search terms matching one of the suggested keywords;

updating performance information for the one of the suggested keywords based on the distribution of the audio file; and

ranking the one of the suggested keywords among others of the suggested keywords based on the updated performance information, wherein ranking the one of the suggested keywords among others of the suggested keywords comprises ranking the one of the suggested keywords based on how many unused presentation spots would be filled using the one of the suggested keywords relative to how many of the unused presentation spots would be filled using each of the others of the suggested keywords;

and suggesting one or more highest ranked suggested keywords as a keyword that controls distribution of the audio file.

8. The apparatus of claim 7, wherein the instructions cause the one or more processors to perform operations comprising:

parsing, from one or more search queries, one or more first keywords;

storing, using a hardware storage device associated with a computer system including a plurality of networked computers, an index data structure including a plurality of entries that each include (1) a keyword of the one or more first keywords, and (2) one or more categories that include the keyword by virtue of the one or more categories being in a same entry of the index data structure, a lookup key of the index data structure being a keyword-based lookup key; and

performing an index inversion operation on the index data structure to generate an inverted index data structure.

9. The apparatus of claim 8, wherein the inverted index data structure stores a plurality of entries that each include 1) a category and (2) one or more second keywords associated with the category by virtue of the one or more second keywords being in a same entry of the inverted index data structure, the lookup key being updated to include a category-based lookup key.

10. The apparatus of claim 9, wherein identifying the different keywords comprises:

accessing the inverted index data structure; and

identifying the plurality of entries that include the category of the keyword; and

identifying the one or more second keywords as the different keywords based on the inclusion of the one or more keywords in the same entry of the inverted index data structure.

11. The apparatus of claim 10, wherein the instructions cause the one or more processors to perform operations comprising:

performing qualification testing of the one or more second keywords that were identified as the different keywords; and

determining that at least one of the different keywords is qualified for use as a keyword that controls distribution of the audio file; and

determining that one or more of the different keywords is unqualified for use as a keyword that controls distribution of the audio file, wherein suggesting one or more highest ranked suggested keywords comprises suggesting only the at least one of the different keywords that is qualified for use as a keyword that controls distribution of the audio file.

12. The apparatus of claim 7, wherein the audio file distributed using the suggested one or more highest ranked keywords is distinctively presented relative to search results that are distributed in response to a query matching the suggested one or more highest ranked keywords.

14. The non-transitory computer readable medium of claim 7, wherein the instructions cause the one or more processors to perform operations comprising:

parsing, from one or more search queries, one or more first keywords;

storing, using a hardware storage device associated with a computer system including a plurality of networked computers, an index data structure including a plurality of entries that each include (1) a keyword of the one or more first keywords, and (2) one or more categories that include the keyword by virtue of the one or more categories being in a same entry of the index data structure, a lookup key of the index data structure being a keyword-based lookup key; and

performing an index inversion operation on the index data structure to generate an inverted index data structure.

15. The non-transitory computer readable medium of claim 8, wherein the inverted index data structure stores a plurality of entries that each include 1) a category and (2) one or more second keywords associated with the category by virtue of the one or more second keywords being in a same entry of the inverted index data structure, the lookup key being updated to include a category-based lookup key.

16. The non-transitory computer readable medium of claim 9, wherein identifying the different keywords comprises:

accessing the inverted index data structure; and

identifying the plurality of entries that include the category of the keyword; and

identifying the one or more second keywords as the different keywords based on the inclusion of the one or more keywords in the same entry of the inverted index data structure.

17. The non-transitory computer readable medium of claim 10, wherein the instructions cause the one or more processors to perform operations comprising:

performing qualification testing of the one or more second keywords that were identified as the different keywords; and

determining that at least one of the different keywords is qualified for use as a keyword that controls distribution of the audio file; and

determining that one or more of the different keywords is unqualified for use as a keyword that controls distribution of the audio file, wherein suggesting one or more highest ranked suggested keywords comprises suggesting only the at least one of the different keywords that is qualified for use as a keyword that controls distribution of the audio file.

18. The non-transitory computer readable medium of claim 7, wherein the audio file distributed using the suggested one or more highest ranked keywords is distinctively presented relative to search results that are distributed in response to a query matching the suggested one or more highest ranked keywords.

13. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

at least one storage device storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including;

receiving a submitted keyword that controls distribution of an audio file to content rendering devices;

accessing a keyword to category index to identify a category of the keyword;

identifying different keywords that are indexed to the category of the keyword as suggested keywords for controlling distribution of the audio file;

ordering the suggested keywords based on performance information, including;

receiving, from a given content rendering device, audio input of one or more search terms;

distributing the audio file to the given content rendering device based on the one or more search terms matching one of the suggested keywords;

updating performance information for the one of the suggested keywords based on the distribution of the audio file; and

ranking the one of the suggested keywords among others of the suggested keywords based on the updated performance information, wherein ranking the one of the suggested keywords among others of the suggested keywords comprises ranking the one of the suggested keywords based on how many unused presentation spots would be filled using the one of the su nested keywords relative to how many of the unused presentation spots would be filled using each of the others of the suggested keywords; and

suggesting one or more highest ranked suggested keywords as a keyword that controls distribution of the audio file.