# US 11,907,508 B1 · Content analytics as part of content creation

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

- Number: US 11,907,508 B1
- Document ID: US11907508B1
- Status: Granted
- Kind: B1
- Application number: 18/133,725
- Filed: 2023-04-12
- Granted: 2024-02-20
- Earliest claimed: 2023-04-12
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: Yaman Kumar; Somesh Singh; William Brandon George; Timothy Chia-chi Liu; Suman Basetty; Pranjal Prasoon; Nikaash Puri; Mihir Naware; Mihai Corlan; Joshua Marshall Butikofer; Abhinav Chauhan; Kumar Mrityunjay Singh; James Patrick O'Reilly; Hyman Chung; Lauren Dest; Clinton Hansen Goudie-Nice; Brandon John Pack; Balaji Krishnamurthy; Kunal Kumar Jain; Alexander Klimetschek; Matthew William Rozen
- Web page: https://patentgrep.com/patent/US11907508B1

## CPC

- G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 3/04845: for image manipulation, e.g. dragging, rotation, expansion or change of colour
- G06F 18/241: relating to the classification model, e.g. parametric or non-parametric approaches
- G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F 40/151: Transformation
- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/30: Semantic analysis
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06T 11/26: Drawing of charts or graphs
- G06V 10/40: Extraction of image or video features
- G06V 10/764: using classification, e.g. of video objects
- G06T 2200/24: involving graphical user interfaces [GUIs]
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Content creation techniques are described that leverage content analytics to provide insight and guidance as part of content creation. To do so, content features are extracted by a content analytics system from a plurality of content and used by the content analytics system as a basis to generate a content dataset. Event data is also collected by the content analytics system from an event data source. Event data describes user interaction with respective items of content, including subsequent activities in both online and physical environments. The event data is then used to generate an event dataset. An analytics user interface is then generated by the content analytics system using the content dataset and the event dataset and is usable to guide subsequent content creation and editing.

## Claims

### Claim 1

A system comprising:
a content analytics module implemented using a processing device and configured to generate a content dataset including a plurality of content profiles having respective content identifiers and descriptions of a plurality of content features extracted, respectively, from the plurality of content using a plurality of machine-learning models configured as classifiers that are trained for identifying respective content features of the plurality of content features;
an event analytics module implemented using the processing device and configured to generate an event dataset from event data, the event dataset including respective content identifiers and performance indicators quantifying performance of the respective said content features towards achieving an action;
an analytics user interface module implemented using the processing device and configured to display an analytics user interface that is configured to:
receive an input via an analytics user interface as selecting an item of content from the plurality of content;
locate event data from the event dataset and a respective said content profile from the content dataset based on a respective said content identifier of the selected item of content; and
display in the analytics user interface a representation of the selected item of content, respective said content features from the located respective said content profile, and the performance indicators quantifying performance of the respective said content features towards achieving the action.

### Claim 2 (depends on 1)

The system as described in claim 1, further comprising a content processing source including theft plurality of machine-learning models configured to extract the plurality of content features from the plurality of content.

### Claim 3 (depends on 2)

The system as described in claim 2, wherein the plurality of machine-learning models is configured as classifiers that are trained for identifying respective content features of the plurality of content features.

### Claim 4 (depends on 1)

The system as described in claim 1, further comprising a content creation source configured to generate the plurality of content and extract one or more of the plurality of content features as part of generating the plurality of content.

### Claim 5 (depends on 4)

The system as described in claim 4, wherein the content creation source includes a content translation module configured to translate a digital document having text and a digital image into markup language content, automatically and without user intervention.

### Claim 6 (depends on 5)

The system as described in claim 5, wherein the markup language content is a webpage.

### Claim 7 (depends on 1)

The system as described in claim 1, wherein the action involves an outcome of user interaction with content having the respective said content features.

### Claim 8 (depends on 1)

The system as described in claim 1, wherein at least one said performance indicator quantifies a number of user interactions.

### Claim 9 (depends on 1)

The system as described in claim 1, wherein the plurality of content features are visual characteristics.

### Claim 10

A method comprising:
outputting, by a processing device, an analytics user interface including:
a representation of an item of content;
a plurality of options configured to support edits to the item of content;
a plurality of content features of the item of content extracted using a plurality of machine-learning models configured as classifiers that are trained for identifying respective content features of the plurality of content features; and
performance indicators associated with the content features, the performance indicators quantifying performance of the respective said content features towards achieving an action;
receiving, by the processing device, an input via the user interface to edit at least one said content feature of the item of content;
editing, by the processing device, the at least one said content feature of the item of content based on the input;
updating, by the processing device, the performance indicator quantifying performance of the at least one said content feature towards achieving the action based on the editing; and
outputting, by the processing device, the item of content having the edited feature and the updated performance indicator quantifying performance of the at least one said content feature towards achieving the action based on the editing for display in the analytics user interface.

### Claim 11 (depends on 10)

The method as described in claim 10, further comprising translating a digital document having text and a digital image into the item of content configured as markup language content, automatically and without user intervention.

### Claim 12 (depends on 10)

The method as described in claim 10, wherein the at least one said content feature is a visual characteristic of the item of content.

### Claim 13 (depends on 10)

The method as described in claim 10, wherein the item of content is a digital image.

### Claim 14 (depends on 10)

The method as described in claim 10, further comprising extracting the plurality of content features from the item of content, automatically and without user intervention.

### Claim 15 (depends on 14)

The method as described in claim 14, wherein the extracting is performed using a plurality of machine-learning models configured as classifiers that are trained for identifying respective content features of the plurality of content features.

### Claim 16

One or more computer-readable storage media having instructions stored thereon that, responsive to execution by a processing device, causes the processing device to perform operations including:
extracting a plurality of content features, respectively, from a plurality of content, the extracting performed using a plurality of machine-learning models configured as classifiers that are trained for identifying respective content features of the plurality of content features;
generating a content dataset including a plurality of content profiles having respective content identifiers and descriptions of the plurality of content features extracted from the plurality of content;
collecting event data from an event data source, the event data describing user interaction with respective items of content of the plurality of content;
generating an event dataset from the event data, the event dataset including respective content identifiers and descriptions of the user interaction, the event dataset includes at least one performance indicator, configured for display in an analytics user interface, quantifying performance of the respective said content features towards achieving an action; and
generating an item of content using generative artificial intelligence (AI) as implemented by a machine-learning model based on the content dataset and the event dataset.

### Claim 17 (depends on 16)

The one or more computer-readable storage media as described in claim 16, wherein the extracting is performed using the plurality of machine-learning models configured as classifiers that are trained for identifying respective content features of the plurality of content features.

### Claim 18 (depends on 16)

The one or more computer-readable storage media as described in claim 16, wherein the operations further comprise translating a plurality of digital documents having text and a digital image into the plurality of content configured using a markup language, automatically and without user intervention.

### Claim 19 (depends on 16)

The one or more computer-readable storage media as described in claim 16, wherein item of content is a digital image.

### Claim 20 (depends on 16)

The one or more computer-readable storage media as described in claim 16, wherein the action involves an outcome of user interaction with content having the respective said content features.