System and method for purchasing advertisements associated with words and phrases
Disclosed is a system and method for enhancing value for advertisers by helping them select and initiate the purchase of an advertisement associated with an advertising (ad) words or phrases that have strong semantic relationships to a given context, but which are not necessarily the most popular ad words or phrases with the highest costs. Advertisements associated with ad words or phrases that have strong semantic relationships to a given context, and yet are still cost effective in that their calculated value exceeds the costs of purchasing the ad keywords, are bid for and bought. In an embodiment, the system and method may be adapted to automatically purchase advertisements associated with ad words or phrases when the ad words or phrases fall within a desired price range based on their calculated value. By automatically purchasing such advertisements, the return on investment (ROI) for an advertiser may be improved.
1. A computer-implemented method for purchasing an advertisement opportunity based on a knowledge representation, the method comprising:
obtaining purchaser-context information associated with at least one purchaser;
computing, using at least one processor executing stored program instructions, a value, specific to the at least one purchaser, of an advertisement opportunity associated with at least one advertising word or phrase, the computing comprising:
identifying, in a knowledge representation encoded as a data structure, a first concept representing at least a portion of the purchaser-context information,
identifying, in the knowledge representation, a second concept with which the at least one advertising word or phrase shares at least one label,
determining a semantic relevance between the first concept and the second concept based at least in part on the first and second concepts' relative positions in a topology of the knowledge representation, and
computing the value of the advertisement opportunity as a function of the determined semantic relevance between the first and second concepts;
comparing the computed value to a purchase price of the advertisement opportunity; and
purchasing the advertisement opportunity in response to determining that the computed value exceeds the purchase price.
2. The computer-implemented method of claim 1 , further comprising identifying the advertising word or phrase based on a retrieval operation or synthesis operation performed on the knowledge representation.
3. The computer-implemented method of claim 1 , wherein the knowledge representation comprises a semantic network.
4. The computer-implemented method of claim 1 , wherein identifying the second concept comprises:
obtaining a plurality of concepts semantically relevant to the first concept;
computing, for each of one or more concepts in the plurality of concepts, a score indicative of the semantic relevance of the respective concept to the first concept; and
selecting the second concept from the one or more concepts based on the computed scores.
5. The computer-implemented method of claim 1 , further comprising:
presenting the advertisement opportunity and/or the at least one advertising word or phrase, prior to the purchase, to the at least one purchaser.
6. The computer-implemented method of claim 1 , further comprising presenting the computed value to the at least one purchaser.
7. The computer-implemented method of claim 1 , wherein the purchasing is performed by an agent.
8. The computer-implemented method of claim 7 , further comprising performing, by the agent, at least one act selected from the group consisting of:
identifying the purchase price of the advertisement opportunity associated with the at least one advertising word or phrase;
requesting approval for the purchasing; and
reporting an imminent purchase or the purchasing of the advertisement opportunity.
9. The computer implemented method of claim 1 , wherein obtaining the purchaser-context information comprises receiving registration information from the at least one purchaser, purchaser website information, information typed in by the at least one purchaser and/or information highlighted by the at least one purchaser.
10. The computer-implemented method of claim 1 , wherein identifying the first concept in the knowledge representation comprises:
searching the knowledge representation for the first concept; and/or
generating the first concept and adding the generated first concept to the knowledge representation.
11. The computer-implemented method of claim 1 , wherein computing the value of the advertisement opportunity comprises allocating a portion of the at least one purchaser's purchasing budget determined based at least in part on the semantic relevance between the first and second concepts.
12. A system comprising:
at least one processor; and
at least one storage medium storing processor-executable instructions that, when executed by the at least one processor, perform a method for purchasing an advertisement opportunity based on a knowledge representation, the method comprising:
obtaining purchaser-context information associated with at least one purchaser;
computing a value, specific to the at least one purchaser, of an advertisement opportunity associated with at least one advertising word or phrase, the computing comprising:
identifying, in a knowledge representation encoded as a data structure, a first concept representing at least a portion of the purchaser-context information,
identifying, in the knowledge representation, a second concept with which the at least one advertising word or phrase shares at least one label,
determining a semantic relevance between the first concept and the second concept based at least in part on the first and second concepts' relative positions in a topology of the knowledge representation, and
computing the value of the advertisement opportunity as a function of the determined semantic relevance between the first and second concepts;
comparing the computed value to a purchase price of the advertisement opportunity; and
purchasing the advertisement opportunity in response to determining that the computed value exceeds the purchase price.
13. The system of claim 12 , wherein the method further comprises identifying the advertising word or phrase based on a retrieval operation or synthesis operation performed on the knowledge representation.
14. The system of claim 12 , wherein the knowledge representation comprises a semantic network.
15. The system of claim 12 , wherein identifying the second concept comprises:
obtaining a plurality of concepts semantically relevant to the first concept;
computing, for each of one or more concepts in the plurality of concepts, a score indicative of the semantic relevance of the respective concept to the first concept; and
selecting the second concept from the one or more concepts based on the computed scores.
16. The system of claim 12 , wherein the method further comprises presenting the advertisement opportunity and/or the at least one advertising word or phrase, prior to the purchase, to the at least one purchaser.
17. The system of claim 12 , wherein the method further comprises presenting the computed value to the at least one purchaser.
18. The system of claim 12 , wherein the purchasing is performed by an agent.
19. The system of claim 15 , wherein the method further comprises performing, by the agent, at least one act selected from the group consisting of:
identifying the purchase price of the advertisement opportunity associated with the at least one advertising word or phrase;
requesting approval for the purchasing; and
reporting an imminent purchase or the purchasing of the advertisement opportunity.
20. The system of claim 12 , wherein obtaining the purchaser-context information comprises receiving registration information from the at least one purchaser, purchaser website information, information typed in the by at least one purchaser and/or information highlighted by the at least one purchaser.
21. The system of claim 12 , wherein identifying the first concept in the knowledge representation comprises:
searching the knowledge representation for the first concept; and/or
generating the first concept and adding the generated first concept to the knowledge representation.
22. The system of claim 12 , wherein computing the value of the advertisement opportunity comprises allocating a portion of the at least one purchaser's purchasing budget determined based at least in part on the semantic relevance between the first and second concepts.
23. A non-transitory computer-readable medium storing code that, when executed on a computer device, adapts the device to perform a method for purchasing an advertisement opportunity based on a knowledge representation, the method comprising:
obtaining purchaser-context information associated with at least one purchaser;
computing a value, specific to the at least one purchaser, of an advertisement opportunity associated with at least one advertising word or phrase, the computing comprising:
identifying, in a knowledge representation encoded as a data structure, a first concept representing at least a portion of the purchaser-context information,
identifying, in the knowledge representation, a second concept with which the at least one advertising word or phrase shares at least one label,
determining a semantic relevance between the first concept and the second concept based at least in part on the first and second concepts' relative positions in a topology of the knowledge representation, and
computing the value of the advertisement opportunity as a function of the determined semantic relevance between the first and second concepts;
comparing the computed value to a purchase price of the advertisement opportunity; and
purchasing the advertisement opportunity in response to determining that the computed value exceeds the purchase price.
24. The non-transitory computer-readable medium of claim 23 , wherein the method further comprises identifying the advertising word or phrase based on a retrieval operation or synthesis operation performed on the knowledge representation.
25. The non-transitory computer-readable medium of claim 23 , wherein identifying the first concept in the knowledge representation comprises:
searching the knowledge representation for the first concept; and/or
generating the first concept and adding the generated first concept to the knowledge representation.
26. The non-transitory computer-readable medium of claim 23 , wherein computing the value of the advertisement opportunity comprises allocating a portion of the at least one purchaser's purchasing budget determined based at least in part on the semantic relevance between the first and second concepts.