Recommending mobile device activities

• US 9,405,848 B2
• Filed: 09/15/2011
• Issued: 08/02/2016
• Est. Priority Date: 09/15/2010
• Status: Active Grant

• Current Assignee: VCVC III LLC (Vulcan, Inc.)
• Original Assignee: VCVC III LLC (Vulcan, Inc.)
• Inventors: Liang, Jisheng, Hunsinger, Will, Bhatti, Satish
• Primary Examiner(s): Saeed, Usmaan
• Assistant Examiner(s): Kim, Paul
• Application Number:
  US13/233,879
• Publication Number:
  US 20120084292A1
• Time in Patent Office: 1,783 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation

Abstract

Techniques for recommending mobile device activities, such as accessing mobile applications and/or mobile Web pages, are described. Some embodiments provide an Activity Recommendation System (“ARS”) configured to recommend relevant activities for a user to perform with a mobile device, based on context of the mobile device. In one embodiment, the ARS recommends mobile applications based content items (e.g., Web pages, images, videos) that are being currently accessed via the mobile device. The ARS may process information about mobile applications and content items to determine semantic information, such as entities and/or categories referenced or associated therewith. The ARS may then use the semantic information to determine mobile applications that have semantic information that is at least similar to that of a content item accessed via a mobile device.

Claims

1. A method for recommending mobile device activities, the method comprising:

receiving an indication of a content item contained on a Web page that is currently presented by a mobile device;

determining semantic information about the indicated content item, including accessing a semantic network that is a graph data structure that includes multiple entities that each have is-a and/or member-of relations to other entities or categories of the semantic network, wherein the is-a and/or member-of relations are represented as links between the entities or categories of the semantic network, to;

identify one or more entities in the semantic network that are referenced by the indicated content item and relationships relating to the identified entities;

identify one or more entities in the semantic network that are related to the identified one or more entities; and

identify one or more categories in the semantic network that are associated with the identified one or more entities and/or the related one or more entities, wherein the identified one or more categories are part of a taxonomic hierarchy in which each of the identified one or more categories is part of a corresponding taxonomic path that includes multiple categories related to one another via is-a relations, wherein the one or more categories are identified by traversing the links representing relations within the semantic network by traversing at most N taxonomic paths within the semantic network, where N is determined by user setting or data mining;

determining a plurality of mobile device activities, wherein each activity has one or more associated entities and/or categories in common with the determined semantic information; and

transmitting information about the determined plurality of activities.

2. The method of claim 1 wherein determining the semantic information about the indicated content item includes processing text of the Web page to identify the one or more entities referenced by the indicated content item.

3. The method of claim 1 wherein determining the semantic information about the indicated content item includes accessing the semantic network to identify the one or more entities related to the identified one or more entities referenced by the indicated content item.

4. The method of claim 1 wherein determining the semantic information about the indicated content item includes accessing the semantic network to identify the one or more categories associated with the identified one or more entities and/or the related one or more entities.

5. The method of claim 1, further comprising:

processing a corpus of text documents to generate the semantic network that represents a plurality of entities, relationships between entities of the plurality of entities, and categories associated with entities of the plurality of entities.

6. The method of claim 1 wherein determining the plurality of activities includes determining a mobile application that is configured to be executed on the mobile device and that provides functions that are related to the content item.

7. The method of claim 1, further comprising:

determining entities and categories associated with the plurality of mobile device activities by processing information about a plurality of mobile device applications, the information including at least one of a name, a summary, a description, a review, a rating, and an identifier; and

determining whether the determined semantic information about the indicated content item includes one or more of the determined entities and categories associated with the plurality of mobile device applications.

8. The method of claim 1 wherein determining the plurality of mobile device activities includes determining at least one mobile Website that is configured to be accessed by the mobile device and that provides functions related to the content item.

9. The method of claim 1 wherein the determining the plurality of mobile device activities includes accessing at least one mobile Website, and further comprising:

determining entities and categories associated with a plurality of mobile Web sites by processing text content from the plurality of mobile Web sites; and

determining whether the determined semantic information about the indicated content item includes one or more of the determined entities and categories associated with the plurality of mobile Web sites.

10. The method of claim 1 wherein the content item is at least one of a Web page, an audio item, and a video item.

11. The method of claim 1 wherein transmitting the information about the determined plurality of activities includes presenting an indication of one or more of the plurality of activities on a display of the mobile device.

15. The method of claim 1, further comprising:

traversing the links representing the is-a relations and member-of relations within the semantic network to identify the entity that is associated with the at least one activity and that is not directly referenced by the content item but that is in a relationship with the entity that is directly referenced by the content item.

16. The method of claim 1 wherein at least one of the activities has an associated category that is not the category of any entity that is directly referenced by the content item but that is the category of an entity that is in a relationship with an entity that is directly referenced by the content item.

17. The method of claim 16 further comprising:

traversing the links representing the is-a relations and member-of relations within the semantic network to identify the category that is associated with the at least one activity and that is not the category of any entity that is directly referenced by the content item but that is the category of the entity that is in a relationship with the entity that is directly referenced by the content item.

18. The method of claim 1 further comprising:

ranking the plurality of mobile device activities based at least in part on a location entity of the user matching a location entity associated with each activity.

19. The method of claim 2 further comprising:

presenting on the mobile device an activity recommender user interface that includes multiple user interface controls that are each configured to initiate one of the determined plurality of activities.

20. The method of claim 1 wherein the entities of the semantic network each have a corresponding entity type, and wherein the corresponding entity types include person, organization, location, concept, event, and product.

12. A non-transitory computer-readable medium having contents that, when executed by a computing system, enable the computing system to recommend mobile device activities, by performing a method comprising:

receiving an indication of a content item contained on a Web page that is currently presented by a mobile device;

determining semantic information about the indicated content item, including accessing a semantic network that is a graph data structure that includes multiple entities that each have is-a and/or member-of relations to other entities or categories of the semantic network, wherein the is-a and/or member-of relations are represented as links between the entities or categories of the semantic network, to;

identify one or more entities in the semantic network that are referenced by the indicated content item and relationships relating to the identified entities;

identify one or more entities in the semantic network that are related to the identified one or more entities; and

identify one or more categories in the semantic network that are associated with the identified one or more entities and/or the related one or more entities, wherein the identified one or more categories are part of a taxonomic hierarchy in which each of the identified one or more categories is part of a corresponding taxonomic path that includes multiple categories related to one another via is-a relations, wherein the one or more categories are identified by traversing the links representing relations within the semantic network by traversing at most N taxonomic paths within the semantic network, where N is determined by user setting or data mining;

determining a plurality of mobile device activities, wherein each activity has one or more associated entities and/or categories in common with the determined semantic information; and

transmitting information about the determined plurality of activities.

13. The computer-readable medium of claim 12 wherein the method further comprises:

determining entities and categories associated with the plurality of mobile device activities by processing information about a plurality of mobile device applications, the information including at least one of a name, a summary, a description, a review, a rating, and an identifier; and

determining whether the determined semantic information about the indicated content item includes one or more of the determined entities and categories associated with the plurality of mobile device applications.

14. A computing system configured to recommend content, comprising:

a memory;

a module that is stored on the memory and that is configured, when executed, to;

receive an indication of a content item contained on a Web page that is currently presented by a mobile device;

determine semantic information about the indicated content item, including accessing a semantic network that is a graph data structure that includes multiple entities that each have is-a and/or member-of relations to other entities or categories of the semantic network, wherein the is-a and/or member-of relations are represented as links between the entities or categories of the semantic network, to;

identify one or more entities in the semantic network that are referenced by the indicated content item and relationships relating to the identified entities;

identify one or more entities in the semantic network that are related to the identified one or more entities; and

identify one or more categories in the semantic network that are associated with the identified one or more entities and/or the related one or more entities, wherein the identified one or more categories are part of a taxonomic hierarchy in which each of the identified one or more categories is part of a corresponding taxonomic path that includes multiple categories related to one another via is-a relations, wherein the one or more categories are identified by traversing the links representing relations within the semantic network by traversing at most N taxonomic paths within the semantic network, where N is determined by user setting or data mining;

determine a plurality of mobile device activities, wherein each activity has one or more associated entities and/or categories in common with the determined semantic information; and

transmit information about the determined plurality of activities.