# US 2025/0061270 A1 · Computer-assisted interactive content presentation and real-time assistance

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

- Number: US 2025/0061270 A1
- Document ID: US20250061270A1
- Status: Published application
- Kind: A1
- Application number: 18/452,408
- Filed: 2023-08-18
- Published: 2025-02-20
- Earliest claimed: 2023-08-18
- Assignees: Digital Media Innovations, LLC
- Applicants: Digital Media Innovations, LLC
- Inventors: David John Wippich; Michael Krax; Earl Hooper
- Web page: https://patentgrep.com/patent/US20250061270A1

## CPC

- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/30: Semantic analysis
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A presentation assistance system receives information about a presentation to be given and automatically provides feedback to improve the presentation either offline or in real time as the presentation unfolds using computer models, where a presentation is a collection of multi-media content, including but not limited to text, slides and graphics, and audio and video streams. The computer models may be trained based on prior presentations and performance metrics of relevant entities. In particular, the presentation includes interactions with audience members and computer models are used to generate likely participants and related interactions, such as questions or recommendations for improved interactions, relevant to the current presentation based on a set of machine learning and AI models, and, in particular, language models. The language model may be prompted with prior relevant questions to determine questions for the current presentation and evaluate the likelihood that the current presentation effectively answers them.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving a prepared set of presentation materials for an interactive presentation to an audience, the prepared set of presentation materials including a planned script;
determining a set of presentation characteristics with one or more language models;
identifying a set of reference external interactions from a set of other presentations based on the set of presentation characteristics;
determining a set of predicted external interactions for the interactive presentation based on a prompt to a language model using the set of reference external interactions;
determining one or more modifications to the planned script to increase the relevance of the planned script with respect to at least one of the set of predicted external interactions; and
providing the one or more modifications to a user device for display to a user.

### Claim 2 (depends on 1)

The method of claim 1, further comprising automatically modifying the planned script with the one or more modifications.

### Claim 3 (depends on 1)

The method of claim 1, further comprising determining a predicted participant based on the set of presentation metadata; and wherein determining the set of predicted external interactions is further based on the predicted participant.

### Claim 4 (depends on 1)

The method of claim 1, wherein the set of presentation metadata includes a summary of key points of the presentation materials and the set of reference external interactions is determined based in part on the summary of key points.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving a rehearsed presentation of the presentation; and
automatically determining one or more characteristics of a presentation delivery based on the rehearsed presentation.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
applying the one or more language models to determine a summary of a set of supplemental materials in the presentation materials; and
determining one or more further modifications to the planned script based on the summary.

### Claim 7

One or more non-transitory computer-readable media having instructions executable by one or more processors for:
receiving a prepared set of presentation materials for an interactive presentation to an audience, the prepared set of presentation materials including a planned script;
determining a set of presentation characteristics with one or more language models;
identifying a set of reference external interactions from a set of other presentations based on the set of presentation characteristics;
determining a set of predicted external interactions for the interactive presentation based on a prompt to a language model using the set of reference external interactions;
determining one or more modifications to the planned script to increase the relevance of the planned script with respect to at least one of the set of predicted external interactions; and
providing the one or more modifications to a user device for display to a user.

### Claim 8 (depends on 7)

The non-transitory computer-readable media of claim 7, wherein the instructions are further executable for automatically modifying the planned script with the one or more modifications.

### Claim 9 (depends on 7)

The non-transitory computer-readable media of claim 7, wherein the instructions are further executable for determining a predicted participant based on the set of presentation metadata; and wherein determining the set of predicted external interactions is further based on the predicted participant.

### Claim 10 (depends on 7)

The non-transitory computer-readable media of claim 7, wherein the set of presentation metadata includes a summary of key points of the presentation materials and the set of reference external interactions is determined based in part on the summary of key points.

### Claim 11 (depends on 7)

The non-transitory computer-readable media of claim 7, wherein the instructions are further executable for:
receiving a rehearsed presentation of the presentation; and
automatically determining one or more characteristics of a presentation delivery based on the rehearsed presentation.

### Claim 12 (depends on 7)

The non-transitory computer-readable media of claim 7, wherein the instructions are further executable for:
applying the one or more language models to determine a summary of a set of supplemental materials in the presentation materials; and
determining one or more further modifications to the planned script based on the summary.

### Claim 13

A computing system comprising:
one or more processors; and
one or more computer-readable media having instructions executable by the one or more processors for:
receiving a prepared set of presentation materials for an interactive presentation to an audience, the prepared set of presentation materials including a planned script;
determining a set of presentation characteristics with one or more language models;
identifying a set of reference external interactions from a set of other presentations based on the set of presentation characteristics;
determining a set of predicted external interactions for the interactive presentation based on a prompt to a language model using the set of reference external interactions;
determining one or more modifications to the planned script to increase the relevance of the planned script with respect to at least one of the set of predicted external interactions; and
providing the one or more modifications to a user device for display to a user.

### Claim 14 (depends on 13)

The computing system of claim 13, wherein the instructions are further executable for: automatically modifying the planned script with the one or more modifications.

### Claim 15 (depends on 13)

The computing system of claim 13, wherein the instructions are further executable for:
determining a predicted participant based on the set of presentation metadata; and
wherein determining the set of predicted external interactions is further based on the predicted participant.

### Claim 16 (depends on 13)

The computing system of claim 13, wherein the set of presentation metadata includes a summary of key points of the presentation materials and the set of reference external interactions is determined based in part on the summary of key points.

### Claim 17 (depends on 13)

The computing system of claim 13, wherein the instructions are further executable for:
receiving a rehearsed presentation of the presentation; and
automatically determining one or more characteristics of a presentation delivery based on the rehearsed presentation.

### Claim 18 (depends on 13)

The computing system of claim 13, wherein the instructions are further executable for:
applying the one or more language models to determine a summary of a set of supplemental materials in the presentation materials; and
determining one or more further modifications to the planned script based on the summary.
