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

• US 10,467,677 B2
• Filed: 04/15/2015
• Issued: 11/05/2019
• 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., Eisert, Evan Favermann, Eggers, Jana B., Plante, Raymond J., Houle, Michael D.
• Primary Examiner(s): Hill, Stanley K.
• Application Number:
  US14/687,742
• Publication Number:
  US 20150220836A1
• Time in Patent Office: 1,665 Days
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• 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: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/21 for social networking applications

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 system for generating customized venue recommendations for users from data networks, the system comprising:

processing circuitry; and

a non-transitory computer readable memory coupled to the processing circuitry, the memory storing machine-executable instructions, wherein the machine-executable instructions, when executed on the processing circuitry, cause the processing circuitry to

receive, from a remote computing device of a user via a network, a request for venue recommendations at a first location, wherein

the first location corresponds to a destination that is remote from a current location of the user, and

the request includes venue attribute preferences of the user,

access, from a non-transitory storage medium, a first data network corresponding to the first location and a second data network corresponding to the current location of the user, wherein

each of the first data network and second data network comprise

a plurality of nodes, each node of the plurality of nodes representing a venue of a plurality of venues in the respective location having one or more common attributes with the venue attribute preferences of the user, and

connections between one or more of the plurality of nodes within the respective data network, wherein the connections represent interrelationships between one or more of the plurality of nodes,

identify, based in part on the first data network for the first location having fewer nodes and connections than the second data network, an information deficit in the first data network, wherein

the information deficit indicates an insufficiency of the first data network to produce customized venue recommendations for the user at the first location,

generate, responsive to identification of the information deficit in the first data network, an augmented data network incorporating additional nodes from the second data network into the first data network based in part on commonalities between the plurality of nodes in each of the first data network and second data network,

determine, based on connection strengths representing interrelationships between nodes in the augmented data network, one or more customized venue recommendations for the user, and

present, within a user interface screen at the remote computing device of the user responsive to receiving the request, the one or more customized venue recommendations.

2. The system of claim 1, wherein the plurality of venues include at least one of restaurants, hotels, and theaters.

3. The system of claim 1, wherein the venue attribute preferences of the user include at least one of venue type, cuisine type, attire type, price point, and ability to accommodate children.

4. The system of claim 1, wherein generating the augmented data network comprises connecting one or more nodes of the first data network with one or more nodes of the second network based in part on commonalities between the plurality of nodes in each of the first data network and second data network, wherein the connections between nodes in the augmented data network include connection strengths indicating an amount of commonality between a pair of connected nodes.

5. The system of claim 4, wherein the machine-executable instructions, when executed on the processing circuitry, further cause the processing circuitry to:

access, from the non-transitory storage medium, review data for the plurality of venues represented by the plurality of nodes in the first data network and second data network,

identify a first venue represented by a first node in the first data network and a second venue represented by a second node in the second data network, wherein the first venue and the second venue have at least one shared reviewer, and

apply, based in part on a comparison of respective reviews for each of the first venue and second venue by the reviewer, a respective connection strength to a connection in the augmented data network connecting the first venue and second venue.

6. The system of claim 5, wherein applying the respective connection strength to the connection in the augmented data network connecting the first venue and second venue includes applying a negative value to the connection strength based on the reviewer having opposite affinities for the first venue and the second venue.

7. The system of claim 5, wherein applying the respective connection strength to the connection in the augmented data network connecting the first venue and second venue includes applying a positive value to the connection strength based on the reviewer having substantially similar affinities for the first venue and the second venue.

8. The system of claim 1, wherein the venue attribute preferences of the user include at least one preferred venue of the user at the current location.

9. The system of claim 8, wherein the second data network includes respective nodes for the at least one preferred venue of the user.

10. The system of claim 1, wherein generating the augmented data network comprises:

identifying, responsive to identification of the information deficit in the first data network, one or more venue clones within at first location, wherein the one or more venue clones share one or more attributes with one or more preferred venues of the user at the second location; and

augmenting the first data network with clone nodes representing the one or more identified venue clones and respective connections between the clone nodes and other nodes within the first data network to form the augmented data network.

11. The system of claim 10, wherein identifying the one or more venue clones includes calculating a congruency factor for one or more of the venues in the first location, wherein the congruency factor indicates an amount of similarity between a respective venue in the first location and the one or more preferred venues of the user at the second location.

12. A method comprising:

receiving, from a user at a remote computing device, a request for venue recommendations at a first location, wherein the first location corresponds to a destination that is remote from a current location of the user, and the request includes venue attribute preferences of the user;

accessing, from a data repository, a first data network corresponding to the first location and a second data network corresponding to the current location, wherein each of the first data network and second data network comprise a plurality of nodes, each node of the plurality of nodes representing a venue of a plurality of venues in the respective location having one or more common attributes with the venue attribute preferences of the user, and links between one or more of the plurality of nodes within the respective data network, wherein the links represent interrelationships between one or more of the plurality of nodes;

identifying, based in part on the first data network for the first location having fewer nodes and links than the second data network, an information deficit in the first data network, wherein the information deficit indicates an insufficiency of the first data network to produce customized venue recommendations for the user at the first location;

identifying, responsive to identification of the information deficit in the first data network, one or more venue clones at the first location, wherein the one or more venue clones share one or more attributes with one or more preferred venues of the user at the second location; and

augmenting the first data network with clone nodes representing the one or more identified venue clones and respective links between the clone nodes and other nodes within the first data network to form an augmented data network;

determining, based on link strengths representing interrelationships between nodes in the augmented data network, one or more customized venue recommendations for the user; and

presenting, within a user interface screen at the remote computing device of the user responsive to receiving the request, the one or more customized venue recommendations.

13. The method of claim 12, wherein identifying the one or more venue clones comprises calculating a congruency factor for one or more of the venues in the first location, wherein the congruency factor indicates an amount of similarity between a respective venue in the first location and the one or more preferred venues of the user at the second location.

14. The method of claim 12, wherein the plurality of venues include at least one of restaurants, hotels, and theaters.

15. The method of claim 12, wherein the venue attribute preferences of the user include at least one of venue type, cuisine type, attire type, price point, and ability to accommodate children.

16. The method of claim 12, further comprising:

generating, responsive to identification of the information deficit in the first data network, the augmented data network incorporating additional nodes from the second data network into the first data network based in part on commonalities between the plurality of nodes in each of the first data network and second data network.

17. The method of claim 16, wherein generating the augmented data network comprises linking one or more nodes of the first data network with one or more nodes of the second network based in part on commonalities between the plurality of nodes in each of the first data network and second data network, wherein

the links between nodes in the augmented data network include link strengths indicating an amount of commonality between a pair of linked nodes.

18. The method of claim 17, further comprising:

accessing, from the data repository, review data for the plurality of venues represented by the plurality of nodes in the first data network and second data network;

identifying a first venue represented by a first node in the first data network and a second venue represented by a second node in the second data network, wherein the first venue and the second venue have at least one shared reviewer; and

applying, based in part on a comparison of respective reviews for each of the first venue and second venue by the reviewer, a respective link strength to a link in the augmented data network connecting the first venue and second venue.

19. The method of claim 18, wherein applying the respective link strength to the link in the augmented data network linking the first venue and second venue comprises applying a negative value to the link strength based on the reviewer having opposite affinities for the first venue and the second venue.

20. The method of claim 18, wherein applying the respective link strength to the link in the augmented data network linking the first venue and second venue comprises applying a positive value to the link strength based on the reviewer having substantially similar affinities for the first venue and the second venue.