# US 2021/0342575 A1 · Cognitive enablement of presenters

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

- Number: US 2021/0342575 A1
- Document ID: US20210342575A1
- Status: Published application
- Kind: A1
- Application number: 17/133,633
- Filed: 2020-12-24
- Published: 2021-11-04
- Earliest claimed: 2020-05-01
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Raghuveer Prasad Nagar; Sarbajit K. Rakshit; Jagadesh Ramaswamy Hulugundi
- Web page: https://patentgrep.com/patent/US20210342575A1

## CPC

- G06V 40/172: {Classification, e.g. identification}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G02B 27/017: {Head mounted}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06V 10/46: Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features (colour feature extraction G06V10/56)
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/20: in augmented reality scenes
- G06V 40/174: {Facial expression recognition}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Cognitive enablement can include detecting sensor-generated signals received from one or more network-configured sensors, the sensor-generated signals corresponding to physical movement of an audience member during a presentation by a presenter. The sensor-generated signals can be converted to vectorized data structures for inputting to a classification model generated with machine learning. The physical movement can be classified as a prelude to a likely audience interaction, the classifying performed by the classification model based on the vectorized data structures. In response to the classifying, an audience member attribute associated with the audience member can be determined. An audience interaction can be predicted based on the audience member attribute using a prediction model generated with machine learning. A predictive alert corresponding to the predicted audience interaction can be generated. During the presentation, a user interface for displaying the predictive alert to the presenter can be generated using an electronic device.

## Claims

### Claim 1

A method, comprising:
detecting, with computer hardware, sensor-generated signals received from at least one of a plurality of dispersed network-configured sensors and corresponding to physical movement of a member of an audience during a presentation by a presenter;
converting the sensor-generated signals to vectorized data structures for inputting to a classification model generated with machine learning;
classifying the physical movement as a prelude to a likely audience interaction, the classifying performed by the classification model based on the vectorized data structures;
in response to the classifying, determining an audience member attribute associated with the member of the audience;
predicting an audience interaction based on the audience member attribute using a prediction model generated with machine learning;
generating a predictive alert corresponding to the audience interaction predicted; and
during the presentation, generating a user interface for displaying the predictive alert to the presenter using an electronic device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the network-configured sensors include at least one of an IoT motion sensor, mobile device sensor, wearable device sensor, or camera sensor.

### Claim 3 (depends on 1)

The method of claim 1, wherein the audience member attribute comprises an identity of the member of the audience, wherein the sensor-generated signals convey an image of the member of the audience, the image captured by a camera sensor, and wherein the identity of the member of the audience is determined by a facial recognition system based on the image conveyed.

### Claim 4 (depends on 1)

The method of claim 1, wherein the audience member attribute comprises biographical data corresponding to the member of the audience, and wherein the biographical data is obtained by searching a plurality of networked sites and retrieving the biographical data from at least one of the plurality of networked sites based on the identity of the member of the audience.

### Claim 5 (depends on 1)

The method of claim 1, wherein a mode of the presentation comprises an in-person presentation before the audience, wherein the electronic device is an augmented reality (AR) glasses worn by the presenter, and wherein the user interface is shown on the AR glasses and displays the predictive alert by highlighting the member of the audience as seen with the AR glasses and displaying text adjacent thereto indicating a topic of a predicted question or a predicted comment by the member of the audience.

### Claim 6 (depends on 1)

The method of claim 1, wherein a mode of the presentation comprises transmitting the presentation over a communications network, wherein the electronic device is a computing/communication device communicatively coupled to the communications network, and wherein the user interface displays the predictive alert by displaying an image of the member of the audience and displaying text adjacent to the image indicating a topic of a predicted question or a predicted comment.

### Claim 7 (depends on 1)

The method of claim 1, wherein the presentation is simultaneously presented via a data communications network to a first group of the audience online, including the audience member, and a second group of the audience in person, wherein the user interface displays the predictive alert by displaying an image of the member of the audience, the image received via the data communications network, and displaying text adjacent to the image indicating a topic of a predicted question or a predicted comment.

### Claim at position 8

8-20. (canceled)