System and method for generating an alternative product recommendation

• US 20080215349A1
• Filed: 07/17/2007
• Published: 09/04/2008
• Est. Priority Date: 05/07/2003
• Status: Active Grant

• Current Assignee: CBS Interactive Inc. (Paramount Global (f/k/a ViacomCBS Inc.))
• Original Assignee: CNET Networks Incorporated (Paramount Global (f/k/a ViacomCBS Inc.))
• Inventors: Baran, Daniel R., Walsh, Robin Hiroko, Musgrove, Timothy Allen
• Granted Patent: US 8,019,656 B2
• Time in Patent Office: Days
• US Class Current: 705/1
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers

Abstract

A method and system for automatically generating a self-updating naturally-reading narrative product summary including assertions about a selected product. In one embodiment, the system and method includes evaluating an existing narrative product summary, comparing an existing attribute name, attribute value, attribute unit, and assertion model, respectively, to a current attribute name, attribute value, attribute unit, and assertion model to determine if one of the comparisons shows a change. The system and method further determines a new attribute associated with the selected product, selects an alternative product, retrieves a new assertion model with assertions that describe the selected product and identify an alternative product in a natural manner. The system and method then generates a naturally-reading narrative product summary by combining the new attribute with the new retrieved assertion model, and by combining the selected alternative product with another retrieved assertion model to recommend the selected alternative product in the narrative.

Claims

1. A computer-implemented method of automatically generating a self-updating naturally-reading narrative product summary, the method comprising:

determining if a narrative product summary exists for a selected product; and

if a narrative product summary exists for a product,

reconciling the existing narrative product summary into an existing attribute associated with the selected product, the existing attribute including at least one of an existing attribute name, an existing attribute value, or an existing attribute unit; and

resolving defined forms in which an assertion describes the selected product to an existing assertion model;

then

comparing at least one of the existing attribute name, the existing attribute value, the existing attribute unit, and the existing assertion model, respectively, to at least one of a current attribute name, a current attribute value, a current attribute unit, and a current assertion model to determine if at least one of the comparisons shows a change in the attribute name, the attribute value, the attribute unit, or the assertion model; and

if a change is evident;

determining at least one new attribute associated with the selected product, the at least one new attribute including at least one of a changed attribute name, a changed attribute value, or a changed attribute unit;

retrieving a new assertion model defining changed forms in which a new assertion is used to describe the product in a natural manner; and

generating an updated naturally reading narrative by combining the new attribute with the retrieved new assertion model.

2. A computer-implemented method of automatically generating a self-updating naturally-reading narrative product summary about a selected product, the method comprising:

evaluating an existing narrative product summary including;

reconciling the existing narrative product summary into an existing attribute associated with the selected product, the existing attribute including at least one of an existing attribute name, an existing attribute value, or an existing attribute unit, and

resolving forms in the existing narrative product summary to an existing assertion model;

comparing at least one of the existing attribute name, the existing attribute value, the existing attribute unit, and the existing assertion model, respectively, to at least one of a current attribute name, a current attribute value, a current attribute unit, and a current assertion model to determine if at least one of the comparisons shows a change in the attribute name, the attribute value, the attribute unit, or the assertion model;

determining at least one new attribute associated with the selected product, the at least one new attribute including at least one of a changed attribute name, a changed attribute value, or a changed attribute unit;

selecting an alternative product;

retrieving new assertion models defining forms in which assertions describe the selected product and identify the alternative product in a natural manner; and

generating a naturally-reading narrative product summary by combining the at least one new attribute with a new retrieved assertion model, and combining the selected alternative product with another retrieved assertion model to recommend the selected alternative product in the narrative.

3. The method of claim 2, wherein the at least one new attribute associated with the selected product includes an indication of the length of time the selected product has been offered for sale.

4. The method of claim 2, wherein the new assertion models define forms in which the assertions include an indication of the length of time the selected product has been offered for sale.

5. The method of claim 2, wherein the existing attribute value of the selected product is ordered within an evaluative scale of alternative products.

6. The method of claim 5, wherein the existing attribute value of the selected product ordered within the evaluative scale of alternative products changes over time with respect to the alternative products.

7. The method of claim 2, further comprising notifying a user that an update has taken place of the self-updating naturally-reading narrative product summary.

8. The method of claim 7, wherein the user is notified by email or RSS feed that an update has taken place of the self-updating naturally-reading narrative product summary.

9. The method of claim 2, wherein the selected alternative product is selected from a product category of a class of peer products.

10. The method of claim 9, wherein characteristics of peer products in the class of peer products cause a change in a scalarization range of the existing attribute value of the selected product, thereby introducing a new assertion based upon a changed relative position of the selected product in the peer class.

11. The method of claim 10, wherein the characteristics of peer products in the class of peer products includes the number or type of peer products.

12. The method of claim 11, wherein the characteristic of number or type of peer product in the class of peer products causes a change in dollar value of the selected product.

13. The method of claim 2, wherein the selected alternative product is ranked within a predetermined near-rank margin of the selected product.

14. The method of claim 2, wherein the selected alternative product has a price that is substantially the same as a price of the selected product.

15. The method of claim 2, wherein the selected alternative product has a price within a predetermined near-price margin of the selected product.

16. The method of claim 2, wherein the selected alternative product and the selected product have the same primary scenario.

17. The method of claim 2, wherein the recommendation is an advertisement, and further including the step of receiving compensation in exchange for recommending the selected alternative product.

18. The method of claim 17, wherein the amount of compensation is based on at least one of frequency of the recommendation and the number of recommended products sold that is attributable to the recommendation.

19. The method of claim 2, wherein the assertion models include a plurality of assertion templates, each assertion template including a natural sentence pattern and at least one field corresponding to the at least one attribute.

20. The method of claim 19, further including the step of assigning importance ratings to each of the at least one attributes.

21. The method of claim 20, further including the step of determining attribute ranks for each of the at least one attributes, and processing the attribute ranks together with the importance ratings to derive a severity value for each of the at least one attributes.

22. The method of claim 21, wherein the alternative product has the same primary scenario as the selected product and is selected based on at least one of a predetermined near-price margin, a predetermined near-rank margin, and a predetermined severity differential threshold.

23. A product summary generator for automatically generating a self-updating naturally-reading narrative product summary about a selected product, the product summary generator comprising:

a summary generation module adapted to evaluate an existing narrative product summary including;

reconciling the existing narrative product summary into an existing attribute associated with the selected product, the existing attribute including at least one of an existing attribute name, an existing attribute value, or an existing attribute unit, and

resolving forms in the existing narrative product summary to an existing assertion model;

an engine adapted to compare at least one of the existing attribute name, the existing attribute value, the existing attribute unit, and the existing assertion model, respectively, to at least one of a current attribute name, a current attribute value, a current attribute unit, and a current assertion model to determine if at least one of the comparisons shows a change in the attribute name, the attribute value, the attribute unit, or the assertion model;

a product attribute module adapted to obtain at least one new attribute associated with the selected product, the at least one new attribute including at least one of a changed attribute name, a changed attribute value, or a changed attribute unit,

an alternative product selection module adapted to select an alternative product;

an assertion model module adapted to retrieve new assertion models that define forms in which assertions describe the selected product and in which assertions describe the selected alternative product in a natural manner; and

the summary generation module further adapted to combine the at least one new attribute with a new retrieved assertion model to describe the selected product in the narrative and to combine the selected alternative product with another retrieved assertion model to recommend the selected alternative product in the narrative.

24. The product summary generator of claim 23, wherein the recommendation made by the summary generation module is an advertisement for which compensation is received in exchange for recommending the selected alternative product.

25. The product summary generator of claim 24, wherein the amount of compensation is based on at least one of frequency of the recommendation and number of recommended products sold that is attributable to the recommendation.

26. The product summary generator of claim 23, further comprising an alternative products database adapted to store a plurality of candidate alternative products and wherein the alternative product selection module selects the alternative product from the alternative products database.

27. A method of automatically generating a self-updating naturally-reading narrative product summary including assertions about a selected product, the method comprising:

evaluating an existing narrative product summary including;

reconciling the existing narrative product summary into an existing attribute associated with the selected product, the existing attribute including at least one of an existing attribute name, an existing attribute value, and an existing attribute unit, and

resolving forms in the existing narrative product summary into an existing assertion model;

comparing at least one of the existing attribute name, the existing attribute value, the existing attribute unit, and the existing assertion model, respectively, to at least one of a current attribute name, a current attribute value, a current attribute unit, and a current assertion model to determine if at least one of the comparisons shows a change in the attribute name, the attribute value, the attribute unit, or the assertion model;

determining at least one new attribute associated with the selected product, the at least one attribute including at least one of a changed attribute name, a changed attribute value, and a changed attribute unit;

retrieving assertion models defining forms in which an assertion can be manifested to describe the selected product, and to recommend an alternative product in a natural manner;

receiving a plurality of bids from manufacturers that indicate an amount of compensation each manufacturer is willing to pay to have at least one of the manufacturer'"'"'s product be recommended as the alternative product;

selecting the alternative product based on the plurality of bids; and

generating an updated naturally reading narrative by combining the at least one new attribute and the selected alternative product with the retrieved assertion models such that the generated narrative includes a recommendation of the selected alternative product.

28. The method of claim 27, wherein the amount of the compensation is based on at least one of frequency of the recommendation and number of recommended products sold that is attributable to the recommendation.

29. The method of claim 27, wherein the existing attribute value of the selected product is ordered within an evaluative scale of alternative products.

30. The method of claim 29, wherein the existing attribute value of the selected product ordered within the evaluative scale of alternative products changes over time with respect to the alternative products.

31. The method of claim 27, further comprising notifying a user that an update has taken place of the self-updating naturally-reading narrative product summary.

32. The method of claim 31, wherein the user is notified by email or RSS feed that an update has taken place of the self-updating naturally-reading narrative product summary.

33. The method of claim 27, wherein the selected alternative product is selected from a product category of a class of peer products.

34. The method of claim 33, wherein characteristics of peer products in the class of peer products cause a change in a scalarization range of the existing attribute value of the selected product, thereby introducing a new assertion based upon a changed relative position of the selected product in the peer class.

35. The method of claim 34, wherein the characteristics of peer products in the class of peer products includes the number or type of peer products.

36. The method of claim 35, wherein the characteristic of number or type of peer product in the class of peer products causes a change in dollar value of the selected product.