Organizing multimedia content

Patent metadata

Field	Value
Publication number	US-9495439-B2
Application number	US-201314048801-A
Country	US
Kind code	B2
Filing date	Oct 8, 2013
Priority date	Oct 8, 2013
Publication date	Nov 15, 2016
Grant date	Nov 15, 2016

Abstract

In one embodiment, a method includes receiving digital media content files. The digital media content has at least one property associated with it. Topically related segments are determined from received content in accordance with one or more property. Topic clusters are generated based on similarities between segments. Topic clusters are compared and clustered from multiple files of the plurality into cluster groups in accordance with a comparison. Cluster groups are associatively stored in a data storage. A search for topic clusters relevant to a particular need is made, and a series of related segments associated with the search are generated for serial display.

First claim

The invention claimed is:

1. A method comprising:
receiving a plurality of video recordings, wherein each of the video recordings comprise a recording of a respective meeting of a plurality of meetings, wherein the video recordings are stored as digital media content files;
identifying a set of properties of the video recordings, wherein the set of properties of each respective video recording comprises: (i) a presenter at the respective meeting, (ii) an attendee at the respective meeting, (iii) a topic of the respective meeting, and (iv) a time the respective meeting occurred;
associating at least two topically related segments of at least two of the plurality of video recordings based on the respective sets of properties;
generating topic clusters based on similarities between the at least two topically related segments, wherein the topic clusters comprise the at least two topically related segments of the at least two of the plurality of video recordings;
generating speaker clusters based on the topic clusters, wherein the speaker clusters associate the presenters at each of the meetings corresponding to the at least two topically related segments of the at least two of the plurality of video recordings;
comparing the topic clusters based on the set of properties of each video recording;
associating the topic clusters from the at least two of the plurality of video recordings into cluster groups based on the comparing of the topic clusters;
associatively storing the cluster groups in a data storage; and
generating a time line series corresponding to the at least two topically related segments in each cluster group.

2. The method of claim 1 , further comprising:
storing each time line series associatively with each corresponding topically related segment in the data storage.

3. The method of claim 2 , further comprising:
receiving query data specifying at least one of a topic and a speaker; and
retrieving at least one of a topic cluster and a speaker cluster from the data storage based on the received query data.

4. The method of claim 3 , further comprising:
displaying the at least one cluster group on an associated display in a display sequence corresponding to the time line series associated therewith.

5. The method of claim 2 , further comprising:
receiving query data; and
associating topically homogeneous segments in accordance with the received query data.

6. A non-transitory computer-readable storage medium storing instructions, which when executed by a processor, performs an operation comprising:
receiving a plurality of video recordings, wherein each of the video recordings comprise a recording of a respective meeting of a plurality of meetings, wherein the video recordings are stored as digital media content files;
identifying a set of properties of the video recordings, wherein the set of properties of each respective video recording comprises: (i) a presenter at the respective meeting, (ii) an attendee at the respective meeting, (iii) a topic of the respective meeting, and (iv) a time the respective meeting occurred;
associating at least two topically related segments of at least two of the plurality of video recordings based on the respective sets of properties;
generating topic clusters based on similarities between the at least two topically related segments, wherein the topic clusters comprise the at least two topically related segments of the at least two of the plurality of video recordings;
generating speaker clusters based on the topic clusters, wherein the speaker clusters associate the presenters at each of the meetings corresponding to the at least two topically related segments of the at least two of the plurality of video recordings;
comparing the topic clusters based on the set of properties of each video recording;
associating the topic clusters from the at least two of the plurality of video recordings into cluster groups based on the comparing of the topic clusters;
associatively storing the cluster groups in a data storage; and
generating a time line series corresponding to the at least two topically related segments in each cluster group.

7. The non-transitory computer-readable storage medium of claim 6 , the operation further comprising:
storing each time line series associatively with each corresponding topically related segment in the data storage.

8. The non-transitory computer-readable storage medium of claim 7 , the operation further comprising:
receiving a query specifying a first topic and a first speaker;
retrieving at least one cluster group based on the set of properties of the at least one cluster group matching the first topic;
retrieving a first speaker group based on the presenter of the first speaker group matching the first speaker; and
returning the at least one cluster group and the first speaker group as responsive to the query.

9. The non-transitory computer-readable storage medium of claim 8 , the operation further comprising:
displaying the at least one cluster group on an associated display in a sequence corresponding to the time line series.

10. The non-transitory computer-readable storage medium of claim 7 , the operation further comprising:
receiving a query; and
associating topically homogeneous segments in accordance with the query.

11. A system, comprising:
one or more computer processors; and
a memory containing a program, which when executed by the processors, performs an operation comprising:
receiving a plurality of video recordings, wherein each of the video recordings comprise a recording of a respective meeting of a plurality of meetings, wherein the video recordings are stored as digital media content files;
identifying a set of properties of the video recordings, wherein the set of properties of each respective video recording comprises: (i) a presenter at the respective meeting, (ii) an attendee at the respective meeting, (iii) a topic of the respective meeting, and (iv) a time the respective meeting occurred;
associating at least two topically related segments of at least two of the plurality of video recordings based on the respective sets of properties;
generating topic clusters based on similarities between the at least two topically related segments, wherein the topic clusters comprise the at least two topically related segments of the at least two of the plurality of video recordings;
generating speaker clusters based on the topic clusters, wherein the speaker clusters associate the presenters at each of the meetings corresponding to the at least two topically related segments of the at least two of the plurality of video recordings;
comparing the topic clusters based on the set of properties of each video recording;
associating the topic clusters from the at least two of the plurality of video recordings into cluster groups based on the comparing of the topic clusters;
associatively storing the cluster groups in a data storage; and
generating a time line series corresponding to the at least two topically related segments in each cluster group.

12. The system of claim 11 , the operation further comprising:
storing each time line series associatively with each corresponding topically related segment in the data storage.

13. The system of claim 12 , the operation further comprising:
receiving a query specifying a first topic and a first speaker;
retrieving at least one cluster group based on the set of properties of the at least one cluster group matching the first topic;
retrieving a first speaker group based on the presenter of the first speaker group matching the first speaker; and
returning the at least o

Assignees

• Cisco Tech Inc

Inventors

• Xi Yongxin
• Sen Mainak

Classifications

• G06F16/783

  using metadata automatically derived from the content · CPC title

• G06F16/43

  Querying · CPC title

• G06F16/285 Primary

  Clustering or classification · CPC title

• G06F17/30598 Primary

  Physics · mapped topic

• G06F17/30784

  Physics · mapped topic