# US 2013/0276033 A1 · Method and system for syncronizing electronic program guides

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2013/0276033 A1
- Document ID: US20130276033A1
- Status: Published application
- Kind: A1
- Application number: 13/976,773
- Filed: 2010-12-29
- Published: 2013-10-17
- Earliest claimed: 2010-12-29
- Assignees: Telecom Italia S.p.A.
- Inventors: Gianluca Francini; Nicola Adami; Sergio Benini; Riccardo Leonardi
- Web page: https://patentgrep.com/patent/US20130276033A1

## CPC

- H04N 21/26283: {for associating distribution time parameters to content, e.g. to generate electronic programme guide data}
- H04N 21/23418: {involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)}
- H04N 21/2625: {for delaying content or additional data distribution, e.g. because of an extended sport event}
- H04N 21/47: End-user applications
- H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method for generating a time scheduling of a contents stream distributed to plural terminals. The contents stream is segmented in consecutive segments, each segment defining a corresponding program. The method includes: receiving auxiliary metadata including a planned time scheduling of the content stream which has been set in advance and monitoring at least a portion of a segment of the contents stream to extract corresponding content features therefrom, generating a corresponding fingerprint based on the extracted content features and assessing at least one among an actual start time and an actual end time of such segment based on a comparison between the fingerprint and a reference fingerprint associated with such segment, and updating the planned time scheduling based on the assessed at least one among the actual start time and actual end time to generate a time scheduling synchronized with the contents stream.

## Claims

### Claim 1

A method for generating a time scheduling of a contents stream distributed to a plurality of terminals, the contents stream being segmented in consecutive segments, each segment defining a corresponding program, the method including:
receiving auxiliary metadata comprising a planned time scheduling of the content stream which has been set in advance;
monitoring at least a portion of a segment of the contents stream to extract corresponding content features therefrom;
generating a corresponding fingerprint based on the extracted content features;
assessing at least one among an actual start time and an actual end time of such segment based on a comparison between said fingerprint and a reference fingerprint associated with such segment, and
updating the planned time scheduling based on the assessed at least one among the actual start time and the actual end time so as to generate a time scheduling synchronized with the contents stream.

### Claim 2 (depends on 1)

The method of claim 1, further including:
partitioning each segment over time into a corresponding plurality of portions,
generating said fingerprint based on content features extracted from a selected subset of portions among the corresponding plurality of portions.

### Claim 3 (depends on 2)

The method of claim 2, wherein the portions of said selected subset are localized in time adjacent to at least one among the start time and the end time of the corresponding segment.

### Claim 4 (depends on 2)

The method of claim 2, wherein said generating the fingerprint includes gathering a respective collection of content features for each portion of the selected subset, said comparison between said fingerprint and said reference fingerprint including calculating a distance between the content features of each collection and corresponding reference content features.

### Claim 5 (depends on 4)

The method of claim 4, wherein said assessing at least one among an actual start time and an actual end time includes comparing said calculated distance with a predetermined threshold.

### Claim 6 (depends on 1)

The method of any one among-the preceding claims claim 1, wherein said contents stream includes a video stream, said content features of the corresponding segment including at least one among:
opening credits of the segment;
a title sequence of the segment;
a logo of the segment;
closing credits of the segment;
a duration of the portions of the segment;
a visual codebook of the segment;
activity levels of the segment, and
text extracted from the segment.

### Claim 7 (depends on 6)

The method of claim 6, wherein said content features of the corresponding segment include at least one among the opening credits and the closing credits of the segment, and said assessing at least one among the actual start time and the actual end time of the segment comprises comparing said at least one among the opening credits and the closing credits with text extracted from the received auxiliary metadata.

### Claim 8 (depends on 1)

The method of claim 1, wherein said contents stream includes an audio stream, said content features of the corresponding segment including at least one among:
a duration of the portions of the segment;
audio classes of the segment, and
an average array of spectrogram's coefficients of the segment.

### Claim 9 (depends on 1)

The method of claim 1, wherein said auxiliary metadata are arranged in the form of an electronic program guide.

### Claim 10

A communication network including:
a transmission center for the distribution of
a contents stream segmented in consecutive segments, each segment defining a corresponding program, and
a time scheduling of the contents stream distribution to a plurality of terminals, and
a unit for updating a planned time scheduling for generating the time scheduling synchronized with the contents stream distributed by the transmission center, said unit for updating comprises:
a feature extractor for monitoring at least a portion of a segment of the contents stream to extract corresponding content features therefrom;
a fingerprint generator for generating a corresponding fingerprint based on the extracted content features;
a distance estimator for comparing said fingerprint with a reference fingerprint associated with such segment;
an updater unit for assessing at least one among an actual start time and an actual end time of such segment based on said comparison, and updating the planned time scheduling based on the assessed at least one among the actual start time and the actual end time for generating the time scheduling synchronized with the contents stream.

### Claim 11 (depends on 7)

The communication network of claim 7, wherein said feature extractor, said fingerprint generator, said distance estimator, and said updater unit are included in the transmission center.

### Claim 12 (depends on 7)

The communication network of claim 7, wherein said feature extractor, said fingerprint generator, said distance estimator, and said updater unit are included in the terminals.

### Claim 13 (depends on 10)

The communication network of claim 10, wherein the transmission center is a broadcasting center.

### Claim 14 (depends on 10)

The communication network of claim 10, wherein said terminals include at least one among set-top box systems, digital media receivers, media centers, decoders, personal video recorders, and personal computers.

### Claim 15 (depends on 1)

A non-transitory readable medium including computer executable instructions configured to run on a processing unit of a communication network for performing the method of claim 1.
