Autonomous Mobile Blogging

• US 20120150871A1
• Filed: 12/10/2010
• Published: 06/14/2012
• Est. Priority Date: 12/10/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Hua, Xian-Sheng, Li, Hongzhi, Li, Shipeng
• Granted Patent: US 8,655,889 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

An autonomous blog engine is implemented to enable the autonomous generation of a blog. The autonomous blog engine receives media objects that are captured by an electronic device during a trip session. The autonomous blog engine determines a place of interest based on photographs selected from the media objects. The autonomous blog engine then generates textual content using one or more pre-stored knowledge items that include information on the place of interest. The autonomous blog engine further autonomously publishes a blog entry on the place of interest that includes one or more photographs from the photograph cluster and the textual content.

Claims

1. A computer-readable medium storing computer-executable instructions that, when executed, cause one or more processors to perform operations comprising:

receiving a plurality of media objects that are captured by an electronic device during a trip session;

receiving one or more geolocations of the electronic device at periodic intervals during the trip session;

analyzing the one or more geolocations of the electronic device to determine a movement of the electronic device away from a visited site; and

publishing a blog entry for a place of interest that corresponds to the visited site, the blog entry including at least one media object and auto-generated textual content that is based at least on one or more pre-stored knowledge items that include information about the place of interest.

2. The computer-readable medium of claim 1, wherein the publishing includes publishing the blog entry on a blog website.

3. The computer-readable medium of claim 1, the operations further comprising:

clustering at least some photographs included in the plurality of media objects into a photograph cluster, the photograph cluster having a cluster center that is a mean of corresponding geolocations at which the at least some photographs are captured;

identifying a plurality of candidate sites with nearest physical distances to the cluster center; and

selecting a candidate site from the plurality of candidate sites as the place of interest when one or more first features depicted in a photograph of the photograph cluster match one or more second features depicted in a known photograph of the candidate site.

4. The computer-readable medium of claim 3, wherein the blog entry includes at least one photograph from the photograph cluster.

5. The computer-readable medium of claim 4, wherein the plurality of media objects further include at least one of a video clip, audio clip, or a multimedia clip, and wherein the publishing includes embedding a video clip, audio clip, or a multimedia clip in the at least one photograph.

6. The computer-readable medium of claim 1, the operations further comprising:

providing the textual content of the blog entry for display on the electronic device; and

receiving a modification to the textual content of the blog entry prior to the publishing,

wherein the publishing includes publishing the blog entry for the place of interest that includes the modification.

7. The computer-readable medium of claim of 1, the operations further comprising receiving an affection rating regarding the place of interest, wherein the publishing includes publishing the blog entry using the one or more pre-stored knowledge item with information that corresponds to the affection rating.

8. The computer-readable medium of claim 1, wherein the analyzing includes determining that the electronic device moved away from the visited site when a weight that reflects a moving state of the electronic device increases to a high value from an average value, maintains the high value, and then decreases from the high value to the average value.

9. The computer-readable medium of claim 1, wherein the publishing includes:

generating the textual content that relates to the place of interest using the pre-stored knowledge items;

composing the textual content with the at least one media object to generate a paragraph metadata object; and

publishing the paragraph metadata object as the blog entry according to a structure template and a presentation template.

10. The computer-readable medium of claim 1, wherein the publishing includes:

creating a paragraph metadata object that includes a textual content related to the place of interest and the at least one media object;

calculating a paragraph weight for the paragraph metadata object, the paragraph weight representing a relative importance of the paragraph metadata object; and

publishing the paragraph metadata object as the blog entry when the paragraph weight is higher than an additional paragraph weight of another paragraph metadata object.

11. The computer-readable medium of claim 1, wherein the publishing includes publishing the blog entry at least prior to the electronic device reaching another place of interest that follows the place of interest.

12. A method, comprising:

receiving a plurality of media objects that are captured by an electronic device during a trip session;

clustering a plurality of photographs included in the plurality of media objects into a photograph cluster;

determining a place of interest that corresponds to the photograph cluster; and

publishing a blog entry for the place of interest that includes at least one photograph from the photograph cluster and textual content that is generated using at least one or more pre-stored knowledge items that include information about the place of interest.

13. The method of claim 12, further comprising:

receiving an affection rating regarding the place of interest;

selecting the one or more pre-stored knowledge items from a plurality of knowledge items based at least on the affection rating; and

generating the textual content to include information in the one or more pre-stored knowledge items.

14. The method of claim 12, wherein the affection rating is one of a positive affection rating that indicates a positive user impression of the place of interest, a neutral affection rating that indicates a neutral user impression of the place of interest, or a negative affection rating that indicates a negative user impression of the place of interest.

15. The method of claim 12, wherein the determining the place of interest includes:

identifying a plurality of candidate sites with nearest physical distances to a cluster center of the photograph cluster, the cluster center being a mean of corresponding geolocations at which the plurality of photographs are captured; and

selecting a particular candidate site from the plurality of candidate sites as the place of interest when one or more first features depicted in a photograph of the photograph cluster match one or more second features depicted in a known photograph of the particular candidate site.

16. The method of claim 12, wherein the media objects further include at least one of a video clip, audio clip, or a multimedia clip, and wherein the publishing includes embedding a video clip, audio clip, or a multimedia clip in the at least one photograph.

17. The method of claim 12, wherein the publishing includes:

creating a paragraph metadata object that includes the textual content and the at least one photograph;

calculating a paragraph weight for the paragraph metadata object that represents a relative importance of the paragraph metadata object; and

publishing the paragraph metadata object as the blog entry when the paragraph weight is higher than an additional paragraph weight of another paragraph metadata object.

18. A system, comprising:

one or more processors; and

a memory that includes components that are executable by the one or more processors, the components comprising;

a device interface component to receive a plurality of media objects that are captured by an electronic device;

a state detection component to determine a movement of the electronic device away from a visited site;

a clustering component to cluster a plurality of photographs included in the media objects into a photograph cluster;

a cluster mapping component to map the photograph cluster to a place of interest that corresponds to the visited site; and

a blog publishing component to publish a blog entry about the place of interest that includes at least one photograph from the photograph cluster and textual content related to the place of interest.

19. The system of claim 18, further comprising a blog text generation module to select one or more pre-stored knowledge items from a plurality of knowledge items based at least on a received affection rating, and to create the textual content for the blog entry such that the textual content includes the information in the one or more pre-stored knowledge items.

20. The system of claim 18, wherein the affection rating is one of a positive affection rating that correlates with a positive user impression of the place of interest, a neutral affection rating that correlates with a neutral user impression of the place of interest, or a negative affection rating that correlates with negative user impression of the place of interest.