Targeted e-commerce system
View Patent ↗A system for displaying products for purchase on any document displayed on any computer device, comprising conducting a statistical frequency analysis of the word occurrence in the document to determine the primary subject matter of the document and/or keywords in the document, selecting products which are relevant to the subject matter and keywords of the document, either by manual selection or by automatic selection. Automatic selection is accomplished by conducting a statistical frequency analysis of the word occurrence in the product descriptions to determine the keywords in the product descriptions and matching the keywords from the document with the keywords from the product descriptions.
1. A computer implemented method of selecting at least one file representing at least one product, the file relating to a web page on the World Wide Web, the method comprising:
receiving the web page having content therein;
analyzing the web page to detect a context for the web page using a statistical analysis of the web page content; and
selecting at least one file representing at least one product related to the detected context.
2. The method of claim 1 , wherein the selected file is at least one of a link, a document, or a thumbnail.
3. The method of claim 1 , further comprising:
receiving notice of a user request for the web page, said user request being received after the execution of said selecting.
4. The method of claim 1 , wherein said analyzing is executed to detect a plurality of contexts for the web page, and wherein said selecting is executed to select a plurality of products corresponding to the plurality of contexts, the method further comprising:
ranking the plurality of contexts and the plurality of products.
5. The method of claim 1 , further comprising:
receiving notice of a user request for the web page, said user request being received prior to the execution of said analyzing or said selecting.
6. The method of claim 1 , wherein said analyzing comprises:
parsing the content of the web page to discover one or more keywords published as part of the content; and
evaluating the one or more keywords to detect the context.
7. The method of claim 6 , wherein said parsing comprises:
performing a statistical word frequency analysis of the content to discover the one or more keywords.
8. The method of claim 6 , wherein said parsing comprises:
analyzing at least one metatag in the web page to discover the one or more keywords.
9. The method of claim 6 , wherein said evaluating comprises:
comparing the one or more keywords with a synonym to detect the context.
10. A method of selecting and displaying at least one file representing at least one product, the file relating to a web page on the World Wide Web, the method comprising:
receiving notice of a user request for a web page;
receiving the requested web page having content therein;
analyzing the requested web page to detect a context for the requested web page using a statistical analysis of the web page content;
selecting at least one file representing at least one product related to the detected context;
producing a second page including the requested web page and the file; and
displaying the second page to the user.
11. The method of claim 10 , wherein said analyzing is executed to detect a plurality of contexts for the requested web page, and wherein said selecting is executed to select a plurality of products corresponding to the plurality of contexts, the method further comprising:
ranking the plurality of contexts and the plurality of products, such that said displaying is executed to display the plurality of products in accordance with the ranking.
12. A computer readable storage medium including computer executable code for selecting at least one file representing at least one product, the file relating to a web page on the World Wide Web, the code enabling the steps of:
receiving the web page having content therein;
analyzing the web page to detect a context for the web page using a statistical analysis of the web page content; and
selecting at least one file representing at least one product related to the detected context.