# US 10,372,742 B2 · Apparatus and method for tagging topic to content

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

- Number: US 10,372,742 B2
- Document ID: US10372742B2
- Status: Granted
- Kind: B2
- Application number: 15/253,233
- Filed: 2016-08-31
- Published: 2017-03-02
- Granted: 2019-08-06
- Earliest claimed: 2015-09-01
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Jeong Woo Son; Sun Joong Kim; Won Joo Park; Sang Yun Lee; Won Ryu; Sang Kwon Kim; Seung Hee Kim; Woo Sug Jung
- Web page: https://patentgrep.com/patent/US10372742B2

## CPC

- G06F 16/353: into predefined classes
- G06F 16/7844: {using original textual content or text extracted from visual content or transcript of audio data}
- G06F 16/7867: {using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings}
- G11B 27/00: Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- H04N 21/25891: {being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)}
- H04N 21/4788: communicating with other users, e.g. chatting {(arrangements for providing for computer conferences, e.g. chat rooms, to substation in data switching networks H04L12/1813; distributed application using peer-to-peer [P2P] networks H04L67/104)}
- H04N 21/8405: represented by keywords
- H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Disclosed is an apparatus and method for tagging a topic to content. The apparatus may include an unstructured data-based topic generator configured to generate a topic model including an unstructured data-based topic based on content and unstructured data, a viewer group analyzer configured to analyze a characteristic of a viewer group including a viewer of the content based on a social network of the viewer and viewing situation information of the viewer, a multifaceted topic generator configured to generate a multifaceted topic based on the topic model and the characteristic of the viewer group, a content divider configured to divide the content into a plurality of scenes, and a tagger configured to tag the multifaceted topic to the scenes.

## Claims

### Claim 1

An apparatus for tagging a topic to content based on a viewing situation, the apparatus comprising:
an unstructured data-based topic generator configured to generate a topic model comprising an unstructured data-based topic based on the content and unstructured data, wherein the content includes at least one of content-related unstructured data and external unstructured data, the content-related unstructured data including subtitles and content dialogue, and the external unstructured data including a blog post and news;
a viewer group analyzer configured to analyze a characteristic of a viewer group comprising a viewer of the content based on a social network of the viewer and viewing situation information of the viewer;
a multifaceted topic generator configured to generate a multifaceted topic based on the topic model and the characteristic of the viewer group;
a content divider configured to divide the content into a plurality of scenes; and
a tagger configured to tag the multifaceted topic to a scene obtained through the division,
wherein the unstructured data-based topic generator, the viewer group analyzer, the multifaceted topic generator, the topic divider, and the tagger each comprise a processing unit including a processor running software to cause the processing unit to perform the functions of the unstructured data-based topic generator, the viewer group analyzer, the multifaceted topic generator, the topic divider, and the tagger, respectively.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the unstructured data-based topic generator comprises:
a content-related unstructured data collector configured to collect, from the content, content-related unstructured data associated with the content;
a keyword extractor configured to extract a first keyword and a second keyword from the content-related unstructured data; and
a topic model generator configured to generate the unstructured data-based topic on the content using the first keyword and the second keyword, and generate the topic model based on the unstructured data-based topic,
wherein the second keyword is determined among first keywords based on respective frequency numbers of the first keywords.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the unstructured data-based topic generator comprises:
an external unstructured data analyzer configured to extract a third keyword from external unstructured data; and
a model expander configured to expand the topic model based on the third keyword.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the viewer group analyzer comprises:
a social network generator configured to generate the social network based on online information of the viewer;
a proximity network generator configured to generate a proximity network from the viewing situation information;
a network integrator configured to integrate the social network and the proximity network; and
a group characteristic extractor configured to extract a common characteristic of the viewer group based on an integrated network obtained through the integration.

### Claim 5 (depends on 4)

The apparatus of claim 4, further comprising:
a viewer group extractor configured to extract the viewer group from the integrated network.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the multifaceted topic generator comprises:
a correlation analyzer configured to analyze a correlation between the unstructured data-based topic and the characteristic of the viewer group; and
a weight calculator configured to calculate a weight for each viewer group corresponding to the unstructured data-based topic based on the correlation, and apply the calculated weight to the topic model.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the multifaceted topic generator further comprises:
a topic model retrainer configured to change the topic model based on the correlation.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the tagger is configured to analyze a correlation between the viewer group and the scene and a correlation between the multifaceted topic and the scene, and
tag the multifaceted topic to the scene based on the correlation between the viewer group and the scene and the correlation between the multifaceted topic and the scene.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the correlation between the multifaceted topic and the scene is analyzed based on a correlation between a first keyword and the scene,
wherein the first keyword is extracted from content-related unstructured data associated with the content.

### Claim 10

A method of tagging a topic, comprising:
generating, by a processor, a topic of broadcast content based on characteristics of the broadcast content;
extracting, by the processor, a characteristic of a viewer group based on viewing information of a viewer of the broadcast content;
generating, by the processor, a multifaceted topic based on the topic of the broadcast content and the characteristic of the viewer group;
dividing the broadcast content into units of one or more scenes; and
tagging the multifaceted topic to the divided broadcast content.

### Claim 11 (depends on 10)

The method of claim 10, wherein the generating of the topic comprises:
collecting broadcast content-related unstructured data associated with the broadcast content;
extracting a first keyword based on the collected broadcast content-related unstructured data;
extracting a second keyword of the topic based on the extracted first keyword;
generating an unstructured data-based topic on the broadcast content using the first keyword and the second keyword, and generating a topic model based on the unstructured data-based topic; and
extracting a third keyword using the topic model and external unstructured data.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
storing information associated with the tagged multifaceted topic as metadata.

### Claim 13

A method of tagging a topic to content based on a viewing situation, the method comprising:
generating, by a processor, a topic model comprising an unstructured data-based topic based on the content and unstructured data, wherein the content includes at least one of content-related unstructured data including subtitles and content dialogue, and external unstructured data including a blog post and news;
analyzing a characteristic of a viewer group comprising a viewer of the content based on a social network of the viewer and viewing situation information of the viewer;
generating a multifaceted topic based on the topic model and the characteristic of the viewer group;
dividing the content into a plurality of scenes; and
tagging the multifaceted topic to a scene obtained through the division.

### Claim 14 (depends on 13)

The method of claim 13, wherein the generating of the topic model comprises:
collecting content-related unstructured data associated with the content;
extracting a first keyword and a second keyword from the content-related unstructured data; and
generating the unstructured data-based topic on the content using the first keyword and the second keyword, and generating the topic model based on the unstructured data-based topic.

### Claim 15 (depends on 14)

The method of claim 14, wherein the generating of the topic model comprises:
extracting a third keyword from external unstructured data; and
expanding the topic model based on the third keyword.