Method and apparatus for motion description

1. An apparatus configured to transform an input data stream comprising spatio-temporal data that is expressed at least in part in a non-linguistic format into a format that can be expressed at least in part via a linguistic representation in a textual output, the apparatus comprising a memory coupled to at least one processor and the at least one processor, the apparatus configured to:

receive the input data stream comprising a spatio-temporal data set, the spatio-temporal data set comprising the spatio-temporal data and associated with a particular region and a particular time period;

organize the spatio-temporal data set according to a domain model comprising an importance rules set for one or more spatio-temporal data subsets of the spatio-temporal data set;

wherein organizing the spatio-temporal data set comprises:

determining an importance score for one or more spatio-temporal data subsets of the spatio-temporal data set using the domain model, wherein the importance score is determined based on one or more of an externally specified importance value for an spatio-temporal data subset type, a number of spatial points in the spatio-temporal data subset, and a time period of the spatio-temporal data subset; and

organizing the spatio-temporal data set according to the importance scores; and

generate a document plan using the organized spatio-temporal data set, the document plan generated with one or more messages that describe each spatio-temporal data subset of the organized spatio-temporal data set; and

generate a linguistic representation of the one or more messages using the document plan, wherein the linguistic representation of the one or more messages is displayable via a user interface.

2. The apparatus of claim 1 , wherein a spatio-temporal data subset describes at least one of a domain event and a domain state.

3. The apparatus of claim 1 , further configured to:

filter out one or more spatio-temporal data subsets;

partition one or more spatio-temporal data subsets into a portion of the particular region; and

ordering the spatio-temporal data set into a particular order.

4. The apparatus of claim 1 , wherein the particular region is a geographic region.

5. The apparatus of claim 1 , further configured to:

organize the spatio-temporal data set based on the importance scores by placing a most important spatio-temporal data subset first in the document plan.

6. The apparatus of claim 5 , wherein the most important spatio-temporal data subset is placed first in the document plan in response to determining that a difference in an importance score between the most important spatio-temporal data subset's importance score and a next most important spatio-temporal data subset's importance score is greater than a threshold importance score value.

7. The apparatus of claim 1 , wherein a domain of the spatio-temporal data set is at least one of weather data, traffic data, medical data, scientific data, and computer network data.

8. The apparatus of claim 1 , wherein organizing the spatio-temporal data set further comprises ordering the spatio-temporal data set based on a start time of the one or more spatio-temporal data subsets.

9. The apparatus of claim 1 , further configured to generate the linguistic representation by:

generating a set of messages from the organized spatio-temporal data set; and

conducting document planning, microplanning, and realization using the set of messages and the document plan to result in an output text.

10. A non-transitory computer readable storage medium configured to transform an input data stream comprising spatio-temporal data that is expressed at least in part in a non-linguistic format into a format that can be expressed at least in part via a linguistic representation in a textual output, the non-transitory computer readable storage medium comprising instructions, that, when executed by a processor, configure the processor to:

receive the input data stream comprising a spatio-temporal data set, the spatio-temporal data set comprising the spatio-temporal data and associated with a particular region and a particular time period;

organize the spatio-temporal data set according to a domain model comprising an importance rules set for one or more spatio-temporal data subsets of the spatio-temporal data set;

wherein organizing the spatio-temporal data set comprises:

determining an importance score for one or more spatio-temporal data subsets of the spatio-temporal data set using the domain model, wherein the importance score is determined based on one or more of an externally specified importance value for an spatio-temporal data subset type, a number of spatial points in the spatio-temporal data subset, and a time period of the spatio-temporal data subset; and

organizing the spatio-temporal data set according to the importance scores; and

generate a document plan using the organized spatio-temporal data set, the document plan generated with one or more messages that described each spatio-temporal data subset of the organized spatio-temporal data set; and

generate a linguistic representation of the one or more messages using the document plan wherein the linguistic representation of the one or more messages is displayable via a user interface.

11. The non-transitory computer readable storage medium of claim 10 , wherein a spatio-temporal data subset describes at least one of a domain event and a domain state.

12. The non-transitory computer readable storage medium of claim 10 , comprising instructions, that, when executed by a processor, further configure the processor to:

filter out one or more spatio-temporal data subsets;

partition one or more spatio-temporal data subsets into a portion of the particular region; and

ordering the spatio-temporal data set into a particular order.

13. The non-transitory computer readable storage medium of claim 10 , wherein the particular region is a geographic region.

14. The non-transitory computer readable storage medium of claim 10 , comprising instructions, that, when executed by a processor, further configure the processor to:

organize the spatio-temporal data set based on the importance scores by placing a most important spatio-temporal data subset first in the document plan.

15. The non-transitory computer readable storage medium of claim 14 , wherein the most important spatio-temporal data subset is placed first in the document plan in response to determining that a difference in an importance score between the most important spatio-temporal data subset's importance score and a next most important spatio-temporal data subset's importance score is greater than a threshold importance score value.

16. The non-transitory computer readable storage medium of claim 10 , wherein a domain of the spatio-temporal data set is at least one of weather data, traffic data, medical data, scientific data, and computer network data.

17. The non-transitory computer readable storage medium of claim 10 , wherein organizing the spatio-temporal data set further comprises ordering the spatio-temporal data set based on a start time of the one or more spatio-temporal data subsets.

18. The non-transitory computer readable storage medium of claim 10 , comprising instructions, that, when executed by a processor, further configure the processor to generate the linguistic representation by:

generating a set of messages from the organized spatio-temporal data set; and

conducting document planning, microplanning, and realization using the set of messages and the document plan to result in an output text.

19. A computer-implemented method for transforming an input data stream comprising spatio-temporal data that is expressed at least in part in a non-linguistic format into a format that can be expressed at least in part via a linguistic representation in a textual output, the method comprising:

receiving, by a processor, the input data stream comprising a spatio-temporal data set, the spatio-temporal data set comprising the spatio-temporal data and associated with a particular region and a particular time period;

organizing, by the processor, the spatio-temporal data set according to a domain model comprising an importance rules set for one or more spatio-temporal data subsets of the spatio-temporal data set;

wherein organizing the spatio-temporal data set comprises:

determining, by the processor, an importance score for one or more spatio-temporal data subsets of the spatio-temporal data set using the domain model, wherein the importance score is determined based on one or more of an externally specified importance value for an spatio-temporal data subset type, a number of spatial points in the spatio-temporal data subset, and a time period of the spatio-temporal data subset; and

organizing, by the processor, the spatio-temporal data set according to the importance scores; and

generating, by the processor, a document plan using the organized spatio-temporal data set, the document plan generated with one or more messages that describe each spatio-temporal data subset of the organized spatio-temporal data set; and

generate a linguistic representation of the one or more messages using the document plan, wherein the linguistic representation of the one or more messages is displayable via a user interface.