Methods and systems for on-device social grouping

• US 10,402,915 B2
• Filed: 05/09/2014
• Issued: 09/03/2019
• Est. Priority Date: 05/10/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Yang, Jun, Yan, Zhixian, Luo, Lu, Bao, Xuan, Zhang, Haipeng, Munguia Tapia, Emmanuel
• Primary Examiner(s): Casanova, Jorge A
• Application Number:
  US14/274,604
• Publication Number:
  US 20140337340A1
• Time in Patent Office: 1,943 Days
• Field of Search: 707737
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Methods, systems, and computer readable media for social grouping are provided to perform social grouping of a user'"'"'s contacts based on the user'"'"'s interactions with the contacts. A set of attributes associated with interactions between a user and a set of contacts may be determined by a first device. The set of attributes associated with the interactions may be related to the first device. The set of contacts may be organized into a set of groups based on the set of attributes.

Claims

1. A method, comprising:

obtaining records related to interactions between a user and a set of contacts;

processing the records to generate interaction data of the user with the set of contacts;

determining, by a first device, communication patterns that describe interactions between the user and the set of contacts, the communication patterns being recorded by at least the first device;

determining, by the first device, one or more sets of respective features from the communication patterns, the one or more sets of respective features capturing at least spatial relationships and temporal relationships in the interactions;

applying, by the first device, a multi-modal clustering to the one or more sets of respective features based upon the spatial and temporal relationships in the interactions between the user and the set of contacts, wherein each contact of the set of contacts is a multi-modal contact associated with different communication modalities;

for each multi-modal contact, generating a unique contact ID representing the different communication modalities of the multi-modal contact;

organizing, by the first device, the set of contacts into a set of groups based at least in part on the multi-modal clustering and the unique contact ID;

detecting a triggering event based upon a change of the user'"'"'s location and event data specific to an application, wherein the user'"'"'s location may be identified as a significant location based upon the multi-modal clustering; and

updating the set of groups based on the triggering event and the multi-modal clustering.

2. The method of claim 1, wherein:

the triggering event is associated with at least one communication pattern.

3. The method of claim 1, further comprising constructing a feature vector for a contact of the set of contacts, the feature vector representing the communication patterns associated with the interactions between the user and the contact.

4. The method of claim 1, further comprising determining a group characteristic for each group of the set of groups.

5. The method of claim 1, further comprising:

detecting group dynamics for the set of groups; and

organizing the set of contacts based on the group dynamics.

6. The method of claim 1, wherein the communication patterns are associated with interactions recorded on a second device between the user and the set of contacts.

7. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform;

obtaining records related to interactions between a user and a set of contacts;

processing the records to generate interaction data of the user with the set of contacts;

determining, by a first device, communication patterns that describe interactions between the user and the set of contacts, the communication patterns being recorded by at least the first device;

determining, by the first device, one or more sets of respective features from the communication patterns, the one or more sets of respective features capturing at least spatial relationships and temporal relationships in the interactions;

applying, by the first device, a multi-modal clustering to the one or more sets of respective features based upon the spatial relationships and the temporal relationships in the interactions between the user and the set of contacts, wherein each contact of the set of contacts is a multi-modal contact associated with different communication modalities;

for each multi-modal contact, generating a unique contact ID representing the different communication modalities of the multi-modal contact;

organizing, by the first device, the set of contacts into a set of groups based at least in part on the multi-modal clustering and the unique contact ID;

detecting a triggering event based upon a change of the user'"'"'s location and event data specific to an application, wherein the user'"'"'s location may be identified as a significant location based upon the multi-modal clustering; and

updating the set of groups based on the triggering event and the multi-modal clustering.

8. The system of claim 7, wherein:

the triggering event is associated with at least one communication pattern.

9. The system of claim 7, wherein the instructions, when executed by the at least one processor, cause the system to further perform constructing a feature vector for a contact of the set of contacts, the feature vector representing the communication patterns associated with the interactions between the user and the contact.

10. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform:

obtaining records related to interactions between a user and a set of contacts;

processing the records to generate interaction data of the user with the set of contacts;

determining, by a first device, communication patterns that describe interactions between the user and the set of contacts, the communication patterns being recorded by at least the first device;

determining, by the first device, one or more sets of respective features from the communication patterns, the one or more sets of respective features capturing at least spatial relationships and the temporal relationships in the interactions;

applying, by the first device, a multi-modal clustering to the one or more sets of respective features based upon the spatial relationships and the temporal relationships in the interactions between the user and the set of contacts;

wherein each contact of the set of contacts is a multi-modal contact associated with different communication modalities;

for each multi-modal contact, generating a unique contact ID representing the different communication modalities of the multi-modal contact;

organizing, by the first device, the set of contacts into a set of groups based at least in part on the multi-modal attributes and the unique contact ID;

detecting a triggering event based upon a change of the user'"'"'s location and event data specific to an application, wherein the user'"'"'s location may be identified as a significant location based upon the multi-modal clustering; and

updating the set of groups based on the triggering event and the multi-modal clustering.

11. The non-transitory computer-readable storage medium of claim 10, wherein the triggering event is associated with at least one communication pattern.