Systems and methods for providing recommendations based on collaborative and/or content-based nodal interrelationships

• US 9,208,443 B2
• Filed: 11/10/2014
• Issued: 12/08/2015
• Est. Priority Date: 09/28/2011
• Status: Active Grant

• Current Assignee: Nara Logics, Inc.
• Original Assignee: Nara Logics, Inc.
• Inventors: Wilson, Nathan R., Hueske, Emily A., Copeman, Thomas C.
• Primary Examiner(s): Hill, Stanley K
• Application Number:
  US14/537,319
• Publication Number:
  US 20150066830A1
• Time in Patent Office: 393 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 20/203 Inventory monitoring
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

In selected embodiments a recommendation generator builds a network of interrelationships between venues, reviewers and users based on their attributes and reviewer and user reviews of the venues. Each interrelationship or link may be positive or negative and may accumulate with other links (or anti-links) to provide nodal links the strength of which are based on commonality of attributes among the linked nodes and/or common preferences that one node, such as a reviewer, expresses for other nodes, such as venues. The links may be first order (based on a direct relationship between, for instance, a reviewer and a venue) or higher order (based on, for instance, the fact that two venue are both liked by a given reviewer). The recommendation engine in certain embodiments determines recommended venues based on user attributes and venue preferences by aggregating the link matrices and determining the venues which are most strongly coupled to the user.

Claims

1. A method comprising:

scanning, at at least one server, a network of data sources, thereby identifying item data for a plurality of items and review data from a plurality of reviewers for a plurality of the items;

prioritizing, at the at least one server, at least two data sources based in part on a predictive value of the review data identified via the scanning, the predictive value indicating a reliability of the review data;

harvesting, at the at least one server and in an order based on the prioritizing, the item data and the review data from the data sources;

generating, at the at least one server and based on the harvesting, a data network having nodes corresponding in part to the plurality of items and the plurality of reviewers.

2. The method according to claim 1, wherein the item data includes one or more attributes of the items and the review data reflects an affinity of a plurality of reviewers for the plurality of items.

3. The method according to claim 1, wherein the review data is harvested in part based on rating information from third party web sites.

4. The method according to claim 1, wherein the review data is harvested in part based on a purchase history of one or more users.

5. The method according to claim 1, wherein the review data is harvested in part based on a web browsing history of one or more users.

6. The method according to claim 1, wherein the review data is harvested in part based on a dwell time of one or more users at a location.

7. The method according to claim 1, wherein the predictive value of the review data is determined in part based on data sources having a predetermined number of items.

8. The method according to claim 1, wherein the predictive value of the review data is determined in part based on data sources providing a predetermined amount of reviews per item and/or reviews per reviewer.

9. The method according to claim 1, wherein the predictive value of the review data is determined in part based on a citation of the same review data on multiple data sources.

10. The method according to claim 1, wherein the predictive value of the review data is determined in part based on an alignment of review data from one data source with review data of one or more other data sources.

11. The method according to claim 1, wherein the harvesting includes in part dynamically generating a plurality of data source crawling modules and dynamically assigning one or more data source crawling modules to different data sources.

12. The method according to claim 11, wherein the data source crawling modules harvest data from the different data sources in an order based on the prioritizing.

13. The method according to claim 11, wherein the data source crawling modules are generated based on a data format of one or more data sources.

14. The method according to claim 1, wherein the harvesting further includes harvesting network link information.

15. The method according to claim 14, wherein the generating further includes generating, based on the harvesting, the data network having nodes corresponding in part to the plurality of items, the plurality of reviewers and the network link information.