Semantic advertising selection from lateral concepts and topics

• US 8,260,664 B2
• Filed: 02/05/2010
• Issued: 09/04/2012
• Est. Priority Date: 02/05/2010
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Vadlamani, Viswanath, Srivastava, Abhinai, Najm, Tarek, Vaddadi, Phani, Surendran, Arungunram Chandrasekaran, Prasad, Rajeev, Srikanth, Munirathnam
• Primary Examiner(s): VANDERHORST, MARIA VICTORIA
• Application Number:
  US12/701,330
• Publication Number:
  US 20110196737A1
• Time in Patent Office: 942 Days
• Field of Search: 707/738, 707/739
• US Class Current: 705/14.49
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

Advertisements are selected for presentation on search result pages and web pages based on phrases generated from lateral concepts and topics identified for the search result pages and web pages. A search query or an indication of a web page is received for which advertisements are to be provided. Lateral concepts and topics are identified based on the search query or content of the web page. The lateral concepts and topics are used as phrases for selecting advertisements from an advertisement inventory. Selected advertisements are provided for presentation on a search results page in response to a search query or on a web page initially identified.

Claims

1. One or more computer-readable media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform a method comprising:

receiving a search query or an indication of a web page;

identifying one or more lateral concepts based on content identified as being relevant to the search query or content of the web page, wherein each lateral concept is identified as a candidate phrase for advertisement selection purposes;

identifying one or more topics based on the search query or the content of the web page, wherein each topic is identified as a candidate phrase for advertisement selection purposes in accordance with the following;

determining if an ontology mapping exists for the search query, wherein the ontology mapping includes a query similar to the search query and a first set of topics that were previously identified as relevant;

if an ontology mapping exists for the search query, retrieving the first set of topics based on the ontology mapping and adding the first set of topics to a list of topics;

if an ontology mapping does not exist for the search query, performing a search using the search query to obtain a plurality of search results, each search result corresponding with a document snippet;

receiving at least a portion of the document snippets as a document set for further analysis;

comparing each document snippet in the document set to an ontology of topics;

for each document snippet in which positive topic identification is determined based on the comparison between the document snippet and the ontology of topics, assigning the document snippet to one or more corresponding topics from the ontology of topics having positive topic identification with the document snippet, removing the document snippet from the document set, and adding at least one or more of the corresponding topics identified from the ontology of topics to the list of topics;

comparing each document snippet remaining in the document set to an ontology of partial topics, wherein the document set does not include each document snippet having positive topic identification with the ontology of topics;

for each remaining document snippet in which positive partial topic identification is determined based on the comparison between the document snippet and the ontology of partial topics, assigning the document snippet to one or more corresponding partial topics, removing the document snippet from the document set, naming at least one or more corresponding partial topics having one or more assigned document snippets;

and adding at least one or more named partial topics to the list of topics;

computing independent key-phrases from document snippets remaining in the document set, wherein the document set does not include each document snippet having positive topic identification with the ontology of topics and each document snippet having positive partial topic identification with the ontology of partial topics, assigning documents to independent key-phrases, identifying at least one key-phrase topic, and adding the at least one key-phrase topic to the list of topics;

selecting one or more phrases from the identified candidate phrases;

querying an advertisement inventory using the one or more selected phrases to select one or more advertisements; and

providing the one or more advertisements for presentation to a user.

2. The one or more computer-readable media of claim 1, wherein identifying one or more lateral concepts comprises:

obtaining a first set of content from storage that corresponds to the search query or content of the web page;

identifying a plurality of categories associated with the obtained first set of content;

and selecting a subset of the plurality of identified categories as lateral concepts.

3. The one or more computer-readable media of claim 1, wherein identifying one or more lateral concepts comprises:

calculating similarity between content in storage and the search query or the content of the web page;

creating a collection of content having a predetermined number of content similar to the search query or the content of the web page;

identifying a plurality of categories that correspond to content in the collection of content; and

selecting several identified categories as lateral concepts.

4. The one or more computer-readable media of claim 1, wherein naming a partial topic comprises:

identifying occurrences of a partial topic identifier word for the partial topic within one or more document snippets assigned to the partial topic;

extracting words and/or phrases occurring around identified occurrences of the partial topic identifier word within the one or more document snippets;

counting frequency of each extracted word and/or phrase;

selecting a most frequently used word or phrase;

and naming the partial topic using the partial topic identifier and the most frequently used word or phrase.

5. The one or more computer-readable media of claim 4, wherein counting frequency of each extracted word and/or phrase comprises tracking position of each extracted word and/or phrase relative to the partial topic identifier word, and wherein naming the partial topic comprises sequencing the partial topic identifier word and the most frequently used word or phrase based on position information for the most frequently used word or phrase.

6. The one or more computer-readable media of claim 1, wherein computing independent key-phrases from document snippets remaining in the document set comprises:

generating candidate key-phrases from the document snippets remaining in the document set;

evaluating candidate key-phrases for independence;

merging mutually dependent candidate key-phrases; and

identifying a most frequent candidate key-phrase for each group of merged mutually dependent key-phrases.

7. The one or more computer-readable media of claim 1, wherein selecting one or more phrases from the candidate phrases comprises:

ranking each candidate phrase based on an estimate of an extent to which each candidate phrase will produce advertising revenue;

and selecting the one or more phrases based on ranking.

8. The one or more computer-readable media of claim 1, wherein querying the advertisement inventory using the one or more selected phrases to select one or more advertisements comprises performing an auction process to select the one or more advertisements based on relevance of each advertisement to the one or more phrases and based on monetization factors associated with each advertisement.

9. The one or more computer-readable media of claim 1, wherein a search query is received, and wherein providing the one or more advertisements for presentation to the user comprises providing the one or more advertisements for presentation on a search results page including search results in response to the search query.

10. The one or more computer-readable media of claim 9, wherein the search results page includes the one or more lateral concepts allowing the user to access content associated with the one or more lateral concepts.

11. The one or more computer-readable media of claim 10, wherein the search results page includes the one or more topics in a table of contents allowing the user to select a topic from the one or more topics to view content associated with the selected topic.

12. The one or more computer-readable media of claim 1, wherein an indication of a web page is received, and wherein providing the one or more advertisements for presentation to the user comprises providing the one or more advertisements for presentation on the web page.

13. One or more computer-readable media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform a method comprising:

receiving a search query;

performing a search using the search query to identify content from storage that corresponds with the search query;

identifying a plurality of categories associated with the obtained content;

selecting a subset of the plurality of identified categories as lateral concepts, wherein the lateral concepts are identified as candidate phrases for advertisement selection;

receiving a plurality of documents snippets from the search;

identifying a first set of one or more candidate topics by comparing one or more document snippets to an ontology of topics;

identifying a second set of one or more candidate topics by comparing one or more document snippets to an ontology of partial topics;

identifying a third set of one or more candidate topics by generating key-phrase topics from one or more document snippets;

selecting topics from the first, second, and third set of candidate topics as candidate phrases for advertisement selection;

selecting one or more phrases from the identified candidate phrases;

querying an advertisement inventory using the one or more selected phrases to select one or more advertisements; and

providing the one or more advertisements for presentation to a user.

14. The one or more computer-readable media of claim 13, wherein identifying the third set of one or more candidate topics by generating key-phrase topics from one or more document snippets includes computing independent key-phrases from document snippets remaining in the document set by:

generating candidate key-phrases from one or more document snippets using a Markov chain based method;

evaluating candidate key-phrases for independence;

merging mutually dependent candidate key-phrases; and

identifying a most frequent candidate key-phrase for each group of merged mutually dependent key-phrases.

15. The one or more computer-readable media of claim 13, wherein providing the one or more advertisements for presentation to the user comprises providing the one or more advertisements for presentation on a search results page including search results in response to the search query.

16. The one or more computer-readable media of claim 15, wherein the search results page includes the lateral concepts allowing the user to access content associated with the lateral concepts.

17. The one or more computer-readable media of claim 15, wherein the search results page includes the topics in a table of contents allowing the user to select a topic from the table of contents to view search results associated with the selected topic.