Semantic enrichment of trajectory data

• US 10,430,805 B2
• Filed: 10/30/2015
• Issued: 10/01/2019
• Est. Priority Date: 12/10/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Soderberg, Joakim, Heredia, Edwin A., Kapanipathi, Pavan, Algie, Glenn, Messer, Alan
• Primary Examiner(s): Ellis, Matthew J
• Application Number:
  US14/928,599
• Publication Number:
  US 20160170994A1
• Time in Patent Office: 1,432 Days
• Field of Search: None
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Enriching trajectory data from a device may include determining, using a processor, enrichment data items related to points of presence within trajectory data. The enrichment data items may be retrieved from a data source. Enriching trajectory data may also include determining, using the processor, ranking metrics for the enrichment data items and ranking, using the processor, the enrichment data items according to the ranking metrics. One or more ranked enrichment data items, in association with the related point of presence of the trajectory data, may be provided to a device using the processor.

Claims

1. A method, comprising:

in response to receiving user generated data including a plurality of visual assets and corresponding trajectory data from a first user device, determining, using a processor, enrichment data items related to a plurality of points of presence within the trajectory data, wherein the points of presence specify time and location data for the first user device;

determining, using the processor, ranking metrics for the enrichment data items;

ranking, using the processor, the enrichment data items according to the ranking metrics;

in response to determining a difference between properties of a first point of presence of the plurality of points of presence corresponding to a first visual asset of the plurality of visual assets and a second point of presence of the plurality of points of presence corresponding to a second visual asset of the plurality of visual assets, generating, using the processor, a connective message, wherein the connective message is synthetic text dialog describing the difference and generated using a finite state machine configured to prevent repetitiveness of connective messages and generate dialog linked to previous messages displayed in scenes of a multimedia composition;

generating, using the processor, a manifest specifying directives for generating the multimedia composition including the first visual asset linked to the second visual asset by the connective message and at least one ranked enrichment data item in association with the related plurality of points of presence; and

providing the manifest to a second user device, wherein the second user device implements the directives to generate the multimedia composition.

2. The method of claim 1, wherein the multimedia composition is interactive and specifies a plurality of concurrent non-linear storylines that are selectable during playback.

3. The method of claim 1, wherein the enrichment data items comprise facts, and wherein:

the determining the enrichment data items comprises;

for points of presence of the plurality of points of presence having an annotation, retrieving, from the external data source, descriptive text for named entities found in the annotation; and

separating the descriptive text into sentences, wherein each sentence is a fact; and

the ranking comprises ranking the facts according to a cost function that depends upon a measure of informativeness and sentence length.

4. The method of claim 3, further comprising:

determining the measure of informativeness by normalizing a number of the named entities in the fact by a length of the fact.

5. The method of claim 1, wherein the determining the enrichment data items comprises:

determining landmarks associated with the plurality of points of presence of the trajectory data according to distance of the landmarks from the plurality of points of presence and popularity of the landmarks.

6. The method of claim 1, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

determining a term describing an attribute of a selected point of presence from the plurality of points of presence within the trajectory data;

determining a synonym for the term;

responsive to submitting a query, wherein the query specifies a location of the selected point of presence, the term, and the synonym, receiving a plurality of visual assets and visual asset scores; and

excluding each visual asset that has a detectable face from the plurality of visual assets received;

wherein the ranking comprises ranking the plurality of visual assets according to the scores after the excluding.

7. The method of claim 1, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

responsive to submitting a query to a social networking system, wherein the query specifies a location of a selected point of presence from the plurality of points of presence within the trajectory data, receiving a plurality of visual assets and associated descriptions from the social networking system; and

excluding each visual asset that has a detectable face from the plurality of visual assets received from the social networking system;

wherein the ranking comprises ranking the plurality of visual assets according to relevance of the visual assets determined according to uniqueness of terms in the descriptions for the visual assets after the excluding.

8. A system, comprising:

a processor programmed to initiate executable operations including;

in response to receiving user generated data including a plurality of visual assets and corresponding trajectory data from a user first device, determining enrichment data items related to a plurality of points of presence within the trajectory data, wherein the points of presence specify time and location data for the first user device;

determining ranking metrics for the enrichment data items;

ranking the enrichment data items according to the ranking metrics;

in response to determining a difference between properties of a first point of presence of the plurality of points of presence corresponding to a first visual asset of the plurality of visual assets and a second point of presence of the plurality of points of presence corresponding to a second visual asset of the plurality of visual assets, generating a connective message, wherein the connective message is synthetic text dialog describing the difference and generated using a finite state machine configured to prevent repetitiveness of connective messages and generate dialog linked to previous messages displayed in scenes of a multimedia composition;

generating, a manifest specifying directives for generating the multimedia composition including the first visual asset linked to the second visual asset by the connective message and at least one ranked enrichment data item in association with the related plurality of points of presence; and

providing the manifest to a second user device, wherein the second user device implements the directives to generate the multimedia composition.

9. The system of claim 8, wherein the multimedia composition is interactive and specifies a plurality of concurrent non-linear storylines that are selectable during playback.

10. The system of claim 9, wherein the enrichment data items comprise facts, and wherein:

the determining the enrichment data items comprises;

for points of presence of the plurality of points of presence having an annotation, retrieving descriptive text for named entities found in the annotation; and

separating the descriptive text into sentences, wherein each sentence is a fact; and

the ranking comprises ranking the facts according to a cost function that depends upon a measure of informativeness and sentence length.

11. The system of claim 10, wherein the processor is further programmed to initiate executable operations comprising:

determining the measure of informativeness by normalizing a number of the named entities in the fact by a length of the fact.

12. The system of claim 9, wherein the determining the enrichment data items comprises:

determining landmarks associated with the plurality of points of presence of the trajectory data according to distance of the landmarks from the plurality of points of presence and popularity of the landmarks.

13. The system of claim 9, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

determining a term describing an attribute of a selected point of presence from the plurality of points of presence within the trajectory data;

determining a synonym for the term;

responsive to submitting a query, wherein the query specifies a location of the selected point of presence, the term, and the synonym, receiving a plurality of visual assets and visual asset scores; and

excluding each visual asset that has a detectable face from the plurality of visual assets received;

wherein the ranking comprises ranking the plurality of visual assets according to the scores after the excluding.

14. The system of claim 9, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

responsive to submitting a query to a social networking system, wherein the query specifies a location of a selected point of presence from the plurality of points of presence within the trajectory data, receiving a plurality of visual assets and associated descriptions from the social networking system; and

excluding each visual asset that has a detectable face from the plurality of visual assets received from the social networking system;

wherein the ranking comprises ranking the plurality of visual assets according to relevance of the visual assets determined according to uniqueness of terms in the descriptions for the visual assets after the excluding.

15. A computer program product comprising a computer readable storage medium having program code stored thereon for enriching trajectory data from a device, the program code executable by a processor to perform a method comprising:

in response to receiving user generated data including a plurality of visual assets and corresponding trajectory data from a first user device, determining, using the processor, enrichment data items related to a plurality of points of presence within the trajectory data, wherein the points of presence specify time and location data for the first user device;

determining, using the processor, ranking metrics for the enrichment data items;

ranking, using the processor, the enrichment data items according to the ranking metrics;

in response to determining a difference between properties of a first point of presence of the plurality of points of presence corresponding to a first visual asset of the plurality of visual assets and a second point of presence of the plurality of points of presence corresponding to a second visual asset of the plurality of visual assets, generating, using the processor, a connective message, wherein the connective message is synthetic text dialog describing the difference and generated using a finite state machine configured to prevent repetitiveness of connective messages and generate dialog linked to previous messages displayed in scenes of a multimedia composition;

generating, using the processor, a manifest specifying directives for generating the multimedia composition including the first visual asset linked to the second visual asset by the connective message and at least one ranked enrichment data item in association with the related plurality of points of presence; and

providing the manifest to a second user device, wherein the second user device implements the directives to generate the multimedia composition.

16. The computer program product of claim 15, wherein the multimedia composition is interactive and specifies a plurality of concurrent non-linear storylines that are selectable during playback.

17. The computer program product of claim 16, wherein the enrichment data items comprise facts, and wherein:

the determining the enrichment data items comprises;

for points of presence of the plurality of points of presence having an annotation, retrieving descriptive text for named entities found in the annotation; and

separating the descriptive text into sentences, wherein each sentence is a fact; and

the ranking comprises ranking the facts according to a cost function that depends upon a measure of informativeness and sentence length.

18. The computer program product of claim 15, wherein the determining enrichment data items comprises:

determining landmarks associated with the plurality of points of presence of the trajectory data according to distance of the landmarks from the plurality of points of presence and popularity of the landmarks.

19. The computer program product of claim 15, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

determining a term describing an attribute of a selected point of presence from the plurality of points of presence within the trajectory data;

determining a synonym for the term;

responsive to submitting a query, wherein the query specifies a location of the selected point of presence, the term, and the synonym, receiving a plurality of visual assets and visual asset scores; and

excluding each visual asset that has a detectable face from the plurality of visual assets received;

wherein the ranking comprises ranking the plurality of visual assets according to the scores after the excluding.

20. The computer program product of claim 15, wherein the enrichment data items comprise visual assets, and the determining the enrichment data items comprises:

responsive to submitting a query to a social networking system, wherein the query specifies a location of a selected point of presence from the plurality of points of presence within the trajectory data, receiving a plurality of visual assets and associated descriptions from the social networking system; and

excluding each visual asset that has a detectable face from the plurality of visual assets received from the social networking system;

wherein the ranking comprises ranking the plurality of visual assets according to relevance of the visual assets determined according to uniqueness of terms in the descriptions for the visual assets after the excluding.