Meaning-based advertising and document relevance determination

• US 7,698,266 B1
• Filed: 03/24/2004
• Issued: 04/13/2010
• Est. Priority Date: 11/01/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Elbaz, Gilad Israel, Weissman, Adam J
• Primary Examiner(s): Wassum; Luke S
• Application Number:
  US10/807,264
• Time in Patent Office: 2,211 Days
• Field of Search: 705/5
• US Class Current: 1/1
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method for advertising on electronic data networks based upon semantic differentiation.

Claims

1. A method, comprising:

organizing advertisements according to their meaning into a lexicon, the lexicon defining elements of a semantic space represented by a network of interconnected meanings;

receiving a concept;

determining one or more concepts close in meaning to the received concept;

identifying one or more advertisements in the semantic space related to the received concept and the one or more concepts close in meaning to the received concept based on meanings of the advertisements; and

transmitting for display the one or more advertisements based on an order, the order corresponding to a relationship between monetary values determined for each of the one or more advertisements identified as related to the received concept and the one or more concepts close in meaning to the received concept.

2. The method of claim 1, wherein the order is additionally based on a predicted relevance of the one or more advertisements to the received concept.

3. The method of claim 1, wherein the order is additionally based on a descending predicted relevance of the one or more advertisements to the received concept.

4. The method of claim 1, wherein the monetary values are prices associated with viewings of the one or more advertisements.

5. The method of claim 1, wherein the order is additionally based on a semantic distance from the one or more advertisements to a meaning in the semantic space associated with a received concept.

6. The method of claim 1, wherein the order is additionally based on a degree of closeness in meaning of the one or more advertisements to the received concept.

7. The method of claim 1, wherein the order is additionally based on a degree of closeness in context of the one or more advertisements to the received concept.

8. A method comprising:

organizing advertisements according to their meaning into a lexicon, the lexicon defining elements of a semantic space and represented by a network of interconnected meanings;

receiving an input term;

identifying a first point in the semantic space associated with the input term based on an interpretation of potential meanings of the input term;

determining a first semantic sub-space that includes all of the elements of the semantic space within a predetermined radius of the first point;

identifying, in the first semantic sub-space, an advertisement proximate in semantic distance to the input term, wherein the semantic distance identifies how closely related the advertisement is to the input term; and

providing the advertisement in response to the input term.

9. The method of claim 8, further comprising:

receiving an indication of a particular meaning;

identifying a second point in the semantic space associated with a particular meaning;

determining a second semantic sub-space that includes all of the elements of the semantic space within the predetermined radius of the second point;

identifying one or more advertisements in the second semantic sub-space; and

providing the one or more advertisements in response to the input term.

10. The method of claim 8, further comprising:

identifying keywords and meanings associated with the first semantic sub-space; and

providing the keywords and meanings to a user.

11. The method of claim 8, further comprising:

receiving an indication of a meaning to associate with each advertisement from an advertiser associated with each advertisement;

receiving a cost-per-impression amount associated with the meaning from the advertiser; and

charging each advertiser the cost-per-impression amount associated with the meaning if the advertisement is provided in response to an input term.

12. The method of claim of claim 11, further comprising:

modifying the cost-per-impression amount associated with the meaning for the advertisement based on the semantic distance between a location in semantic space of the meaning and the input term.

13. The method of claim 12, wherein the semantic distance is inversely proportional to the cost-per-impression amount.

14. A system, comprising:

one or more computers; and

a storage device coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising;

organizing advertisements according to their meaning into a lexicon, the lexicon defining elements of a semantic space and represented by a network of interconnected meanings;

receiving an input term;

identifying a first point in the semantic space associated with the input term based on an interpretation of potential meanings of the input term;

determining a first semantic sub-space that includes all of the elements of the semantic space within a predetermined radius of the first point;

identifying, in the first semantic sub-space, an advertisement proximate in semantic distance to the input term, wherein the semantic distance identifies how closely related the advertisement is to the input term; and

providing the advertisement in response to the input term.

15. The system of claim 14, wherein the operations further comprise:

receiving an indication of a particular meaning;

identifying a second point in the semantic space associated with particular meaning;

determining a second semantic sub-space that includes all of the elements of the semantic space within the predetermined radius of the second point;

identifying one or more advertisements in the second semantic sub-space; and

providing the one or more advertisements in response to the input term.

16. The system of claim 14, wherein the operations further comprise:

identifying keywords and meanings associated with the first semantic sub-space; and

providing the keywords and meanings to a user.

17. The system of claim 14, wherein the operations further comprise:

receiving an indication of a meaning to associate with each advertisement from an advertiser associated with each advertisement;

receiving a cost-per-impression amount associated with the meaning from the advertiser; and

charging each advertiser the cost-per-impression amount associated with the meaning if the advertisement is provided in response to an input term.

18. The system of claim of claim 17, wherein the operations further comprise:

modifying the cost-per-impression amount associated with the meaning for the advertisement based on the semantic distance between a location in semantic space of the meaning and the input term.

19. The system of claim 18, wherein the semantic distance is inversely proportional to the cost-per-impression amount.