# US 2024/0205518 A1 · Systems and methods for creating customized content

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

- Number: US 2024/0205518 A1
- Document ID: US20240205518A1
- Status: Published application
- Kind: A1
- Application number: 18/392,398
- Filed: 2023-12-21
- Published: 2024-06-20
- Earliest claimed: 2019-03-25
- Assignees: Rovi Guides, Inc.
- Applicants: Rovi Guides, Inc.
- Inventors: Alan Waterman
- Web page: https://patentgrep.com/patent/US20240205518A1

## CPC

- H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments}
- H04N 21/8543: using a description language, e.g. Multimedia and Hypermedia information coding Expert Group [MHEG], eXtensible Markup Language [XML] {(information retrieval of semistructured data, the underlying structure being taken into account, e.g. mark-up language structure data G06F16/80)}
- G06F 16/7847: {using low-level visual features of the video content}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06T 15/50: Lighting effects
- H04N 21/44004: {involving video buffer management, e.g. video decoder buffer or video display buffer}
- H04N 21/47205: {for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally}
- H04N 21/85406: {involving a specific file format, e.g. MP4 format}
- G06N 3/08: Learning methods
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and methods are disclosed for generating a content structure that can then be used as a content design building block. Specifically, new content can be automatically generated by combining, replacing or mixing and matching objects, actions, settings, effects, audio, etc., from any number of previously stored content structures to create a new content structure, which is then rendered as a new content segment. Content segments are then stitched together to generate a finished content stream. In this way, new and original content can be created without the traditionally expensive and labor-intensive filming or computer animation processes.

## Claims

### Claim at position 1

-60. (canceled)

### Claim 61

A method for creating new content based on deconstructed content, the method comprising:
receiving a first content portion that depicts a first object;
deconstructing the first content portion into a plurality of attributes and a plurality of attribute values associated with the first object;
generating first mappings that comprise the plurality of attribute values corresponding to the plurality of attributes;
generating a first content structure comprising the plurality of attributes and the first mappings;
accessing a data structure comprising at least a second attribute associated with a second object, wherein the second attribute corresponds to a second attribute value;
retrieving, from the data structure, second mappings that comprise the second attribute and the second attribute value;
determining a match between at least one of the first mappings and at least one of the second mappings;
generating a second content structure by selectively combining (i) the second attribute with the plurality of attributes and (ii) the second attribute value with the plurality of attribute values based on the determined match;
constructing, based on the second content structure, a second content portion to depict the first object with the second attribute and the second attribute value.

### Claim 62 (depends on 61)

The method of claim 61, wherein:
each one of the first mappings indicates at least one of a feature, state, action, audio or location mapping corresponding to the first object, wherein each one of the feature, state, action, audio or location mapping comprises at least one attribute and one corresponding attribute value; and
each one of the second mappings indicates at least one of a feature, state, action, audio or location mapping corresponding to the second object, wherein each one of the feature, state, action, audio or location mapping comprises at least one attribute and one corresponding attribute value.

### Claim 63 (depends on 62)

The method of claim 62, wherein the determining the match between at least one of the first mappings and at least one of the second mappings, comprises:
identifying a first attribute in the first mappings and the second attribute in the second mappings that indicate the same feature, state, action, audio, or location mapping of an object, wherein the first attribute corresponds to an undefined first attribute value and the second attribute corresponds to a defined second attribute value.

### Claim 64 (depends on 63)

The method of claim 63, wherein generating the second content structure comprises:
combining the defined second attribute value with the undefined first attribute value.

### Claim 65 (depends on 61)

The method of claim 61, wherein the deconstructing the first content portion comprises:
determining, based on using pattern recognition on the first content portion, a plurality of objects depicted in the first content portion; and
for each object of the plurality of objects:
determining, based on the depiction in the first content portion, attributes and associated attribute values; and
storing the attributes and the attribute values in an attribute table associated with each of the plurality of objects.

### Claim 66 (depends on 61)

The method of claim 61, wherein generating the first mappings comprises:
mapping the plurality of attribute values to a plurality of sub-portions within the first content portion during which the first object is depicted with the plurality of attributes corresponding to the plurality of attribute values; and
storing indicators for each of the plurality of sub-portions in association with the first object.

### Claim 67 (depends on 61)

The method of claim 61, wherein creating the second content structure comprises adjusting a time frame associated with the second attribute value to match a time frame associated with a first attribute value.

### Claim 68 (depends on 61)

The method of claim 61, wherein receiving the first content portion comprises:
receiving a content stream comprising the first content portion; and
extracting the first content portion.

### Claim 69 (depends on 67)

The method of claim 67, wherein the first content portion is extracted based on at least one of a predetermined duration, a portion definition indicator, a pause in audio, and closed caption data.

### Claim 70 (depends on 61)

The method of claim 61, wherein the first content portion comprises a sequence of video frames, and wherein the method further comprises:
identifying an object in the first content portion that appears in each video frame of the sequence of video frames;
tracking, for the identified object, a changing attribute in the sequence, wherein tracking the changing attribute comprises determining, for the changing attribute of the identified object, attribute values corresponding to each video frame of the sequence; and
wherein the first mappings comprise the changing attribute mapped to the sequence based on the determined attribute values.

### Claim 71

A system for creating new content based on deconstructed content, the method comprising:
input/output circuitry configured to:
receive a first content portion that depicts a first object; and control circuitry configured to:
deconstruct the first content portion into a plurality of attributes and a plurality of attribute values associated with the first object;
generate first mappings that comprise the plurality of attribute values corresponding to the plurality of attributes;
generate a first content structure comprising the plurality of attributes and the first mappings;
access a data structure comprising at least a second attribute associated with a second object, wherein the second attribute corresponds to a second attribute value;
retrieve, from the data structure, second mappings that comprise the second attribute and the second attribute value;
determine a match between at least one of the first mappings and at least one of the second mappings;
generate a second content structure by selectively combining (i) the second attribute with the plurality of attributes and (ii) the second attribute value with the plurality of attribute values based on the determined match;
construct, based on the second content structure, a second content portion to depict the first object with the second attribute and the second attribute value.

### Claim 72 (depends on 71)

The system of claim 71, wherein:
each one of the first mappings indicates at least one of a feature, state, action, audio or location mapping corresponding to the first object, wherein each one of the feature, state, action, audio or location mapping comprises at least one attribute and one corresponding attribute value; and
each one of the second mappings indicates at least one of a feature, state, action, audio or location mapping corresponding to the second object, wherein each one of the feature, state, action, audio or location mapping comprises at least one attribute and one corresponding attribute value.

### Claim 73 (depends on 72)

The system of claim 72, wherein the control circuitry is configured to determine the match between at least one of the first mappings and at least one of the second mappings, by:
identifying a first attribute in the first mappings and the second attribute in the second mappings that indicate the same feature, state, action, audio, or location mapping of an object, wherein the first attribute corresponds to an undefined first attribute value and the second attribute corresponds to a defined second attribute value.

### Claim 74 (depends on 73)

The system of claim 73, wherein the control circuitry is configured to generate the second content structure by:
combining the defined second attribute value with the undefined first attribute value.

### Claim 75 (depends on 71)

The system of claim 71, wherein the control circuitry is configured to deconstruct the first content portion by:
determining, based on using pattern recognition on the first content portion, a plurality of objects depicted in the first content portion; and
for each object of the plurality of objects:
determining, based on the depiction in the first content portion, attributes and associated attribute values; and
storing the attributes and the attribute values in an attribute table associated with each of the plurality of objects.

### Claim 76 (depends on 71)

The system of claim 71, wherein the control circuitry is configured to generate the first mappings by:
mapping the plurality of attribute values to a plurality of sub-portions within the first content portion during which the first object is depicted with the plurality of attributes corresponding to the plurality of attribute values; and
storing indicators for each of the plurality of sub-portions in association with the first object.

### Claim 77 (depends on 71)

The system of claim 71, wherein the control circuitry is configured to create the second content structure by adjusting a time frame associated with the second attribute value to match a time frame associated with a first attribute value.

### Claim 78 (depends on 71)

The system of claim 71, wherein the control circuitry is configured to receive the first content portion by:
receiving a content stream comprising the first content portion; and
extracting the first content portion.

### Claim 79 (depends on 77)

The system of claim 77, wherein the control circuitry is configured to extract the first content portion based on at least one of a predetermined duration, a portion definition indicator, a pause in audio, and closed caption data.

### Claim 80 (depends on 71)

The system of claim 71, wherein the first content portion comprises a sequence of video frames, and wherein the control circuitry is further configured to:
identify an object in the first content portion that appears in each video frame of the sequence of video frames;
track, for the identified object, a changing attribute in the sequence, wherein tracking the changing attribute comprises determining, for the changing attribute of the identified object, attribute values corresponding to each video frame of the sequence; and
wherein the first mappings comprise the changing attribute mapped to the sequence based on the determined attribute values.
