METHOD AND APPARATUS FOR A RECOMMENDATION SYSTEM BASED ON TOKEN EXCHANGE

• US 20140059213A1
• Filed: 11/28/2012
• Published: 02/27/2014
• Est. Priority Date: 08/23/2012
• Status: Active Grant

• Current Assignee: Teknologian tutkimuskeskus VTT Oy
• Original Assignee: Teknologian tutkimuskeskus VTT Oy
• Inventors: OLLIKAINEN, Ville, LAUNONEN, Raimo, KORTEKANGAS, Atte
• Granted Patent: US 9,882,790 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• 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 43/00 Arrangements for monitoring or testing data switching networks

Abstract

Recommendation system based on the actions of a group of users, and not requiring prior metadata, is provided. The recommendation is not limited to from user-to-item (e.g. media recommendation) type; e.g. from user-to-user (e.g. social networking), from item-to-item (e.g. “see also” in internet shopping) and item-to-user (e.g. advertizing) recommendations are supported. The solution utilizes a set of identifiable tokens, associated with each entity, an entity being either a user or an item. Whenever there is an interaction between entities, either existing token sets are updated or new token sets are created such that after an interaction each interacting entity is associated with a token set which resembles more than before the token set(s) associated with the other interacting entity. Recommendation can be produced by searching best matching token sets on the user-to-item, user-to-user, from item-to-item or item-to-user basis.

Claims

1. A method for providing recommendations of entities to be executed by at least one electronic device optionally including a mobile terminal,

obtaining a first token set associated with a first entity, optionally a user of said at least one electronic device, wherein the first token set comprises a plurality of identifiable tokens,

adapting the first token set on the basis of interaction between the first entity and a second entity, optionally a resource available through a network accessible service, wherein based on a second token set associated with the second entity the first token set is altered to increasingly resemble the second set and based on the first token set the second token set is altered to increasingly resemble the first token set,

obtaining information regarding a plurality of token sets associated with a corresponding plurality of entities,

determining an indication of similarity between the first token set and each set in said plurality of token sets, and

based on the determined indications of similarity, establishing a recommendation regarding a sub-set of one or more entities from said plurality of entities.

2. The method according to claim 1, wherein the interaction involves information exchange between a first computing unit of the first entity and a second computing unit of the second entity, the first entity being a user of a terminal device and the second entity being associated with a unique uniform resource identifier relating to a network accessible service, further wherein the first and second computing units are capable of accessing the first and second token sets associated with the first and second entities, respectively, and the terminal device has access to a means for resolving universal resource locator of a second token process for processing the second token set in the second computing unit, and wherein the method comprises:

a. identifying the user of the terminal device,

b. detecting said user accessing the service, the access being related to the uniform resource identifier of the service,

c. giving said uniform resource identifier, requesting the universal resource locator of the second token process from the means for resolving the universal resource locator of a token process,

d. receiving the universal resource locator of the second token process as the response,

e. utilizing at least part of said universal resource locator of the second token process in requesting the first computing unit to exchange information with the second computing unit,

f. as a response to said request and utilizing the received universal resource locator of the second token process, requesting, by the first computing unit, from the second computing unit at least a part of the second token set associated with the second entity, and sending at least part of the first token set associated with the first entity to the second computing unit to enable said second computing unit, through utilization of at least part of the first token set received from the first computing unit, to adapt at least part of the second token set associated with the second entity,

g. receiving, at the first computing unit, from the second computing unit at least part of the second token set associated with the second entity, and

h. through utilization, at the first computing unit, of at least part of the second token set received from the second computing unit, adapting at least part of the first token set associated with the first entity.

3. The method according to claim 2, wherein said means for resolving universal resource locator of the second computing unit utilize as input a unique identifier of the second entity.

4. The method according to claim 2, wherein said means for resolving universal resource locator of the second computing unit utilize as input data transferred from the second entity to the terminal device.

5. The method according to claim 1, wherein token sets including the first and second token sets are comparable so as to enable measuring their mutual distance forming at least part of said indication of similarity.

6. The method according to claim 1, wherein the first and second token sets are represented in a mathematical space which enables measuring distance between the two token sets, optionally based on the similarity of the tokens'"'"' values in the sets, and adapting the first token set based on the second token set reduces such distance between them.

7. The method according to claim 1, wherein said adapting contains at least one element selected from the group consisting of:

copying at least one token from the second token set into the first token set, replacing a token in the first set with a token from the second set, modifying a token in the first set based on the value of at least one token in the second set, deleting a token from the first set.

8. The method according to claim 1, wherein the extent of adaptation relating to the first token set, optionally copy percentage of data from other token set such as the second set to the first set, is reduced according to predetermined logic in response to each executed adaptation round.

9. The method according to claim 1, wherein said determining and establishing comprise:

a. calculating distances between the first token set and each set in said plurality,

b. memorizing the smallest distances and the entities associated with them, and

c. returning the list of entities associated with the token sets with smallest distances to the first token set.

10. The method according to claim 1, wherein each token set is associated with at least one indication selected from the group consisting of:

indication of how many times it has been updated, timestamp or other temporal indication of creation, timestamp or other temporal indication of last access, and timestamp or other temporal indication of last update, wherein the at least one indication is preferably utilized in the adaptation.

11. The method according to claim 1 wherein said plurality of entities includes at least one entity selected from the group consisting of:

media content, user, service, and item for sale.

12. The method according to claim 1, wherein at least the first token set is stored in a database hosted by at least one network server accessible via the Internet for retrieval by terminal device and subsequent use in connection with network accessible services.

13. The method according to claim 1, executed by a terminal device comprising at least one element optionally selected from the group consisting of:

cellular phone, smartphone, PDA (personal digital assistant), wristop computer, tablet, laptop computer, and desktop computer.

14. The method according to claim 1, executed by at least one network element such as a server.

15. The method according to claim 1, wherein the first entity is associated with multiple token sets, each preferably targeted for different use context.

16. The method according to claim 1, triggered by a terminal device in response to reading an optical code, such as QR (Quick Response)code, or communication with an NFC (Near-Field Communication) tag.

17. An electronic terminal device, optionally a smartphone, tablet, laptop or desktop computer, comprising a processing element and memory element for processing and storing data, respectively, and a data interface for transferring data, configured to execute:

obtaining a first token set associated with a first entity, optionally a user of said at least one electronic device, wherein the first token set comprises a plurality of identifiable tokens,

adapting the first token set on the basis of interaction between the first entity and a second entity, optionally a resource available through a network accessible service, wherein based on a second token set associated with the second entity the first token set is altered to increasingly resemble the second set and based on the first token set the second token set is altered to increasingly resemble the first token set,

obtaining information regarding a plurality of token sets associated with a corresponding plurality of entities,

determining an indication of similarity between the first token set and each set in said plurality of token sets, and

based on the determined indications of similarity, establishing a recommendation regarding a sub-set of one or more entities from said plurality of entities.

18. A system comprising at least one network server and optionally an electronic terminal device, comprising a processing element and memory element for processing and storing data, respectively, and a data interface for transferring data, configured to execute:

obtaining a first token set associated with a first entity, optionally a user of said at least one electronic device, wherein the first token set comprises a plurality of identifiable tokens,

adapting the first token set on the basis of interaction between the first entity and a second entity, optionally a resource available through a network accessible service, wherein based on a second token set associated with the second entity the first token set is altered to increasingly resemble the second set and based on the first token set the second token set is altered to increasingly resemble the first token set,

obtaining information regarding a plurality of token sets associated with a corresponding plurality of entities,

determining an indication of similarity between the first token set and each set in said plurality of token sets, and

based on the determined indications of similarity, establishing a recommendation regarding a sub-set of one or more entities from said plurality of entities.

19. A computer program product comprising a computer-readable medium having computer readable program code embodied therein for providing recommendations of entities, said computer program code comprising instructions for

obtaining a first token set associated with a first entity, optionally a user of said at least one electronic device, wherein the first token set comprises a plurality of identifiable tokens,

adapting the first token set on the basis of interaction between the first entity and a second entity, optionally a resource available through a network accessible service, wherein based on a second token set associated with the second entity the first token set is altered to increasingly resemble the second set and based on the first token set the second token set is altered to increasingly resemble the first token set,

obtaining information regarding a plurality of token sets associated with a corresponding plurality of entities,

determining an indication of similarity between the first token set and each set in said plurality of token sets, and

based on the determined indications of similarity, establishing a recommendation regarding a sub-set of one or more entities from said plurality of entities.