Granted Patent B2

US 12,505,399 · App. 18/207,515 · Granted Dec 23, 2025

Inventors: Thomas Neal Steinhoff (San Gabriel, CA); Bryan Andrew Ackermann (Scottsdale, AZ); Rajesh Mandyam (Granada Hills, CA)

Assignee: Korn Ferry

G06Q10/0639G06F3/0482G06F3/0483G06F3/04845G06F3/167

Abstract

Claims (92)

1 . A computer-implemented method for generating and presenting a user-specific personal assessment report, comprising:

receiving, from a user, a plurality of answers corresponding to a plurality of predetermined questions in a personal assessment questionnaire;

generating, based on the plurality of answers, the user-specific personal assessment report comprising a plurality of static pages;

displaying a user interface for presenting the user-specific personal assessment report, the user interface comprising:

a report region for displaying a page of the plurality of static pages;

an avatar region for presenting a video of an avatar, wherein:

one or more images of the video of the avatar are generated according to a first output from a first machine-learning model,

the first machine-learning model is trained, using a plurality of images corresponding to an appearance of the avatar, to provide the first output,

the avatar is configured to be partially overlaid on the report region, and

a first location and a first size of the avatar are determined based on content displayed on the page;

receiving the user input initiating playback of the user interface;

in response to receiving the user input, initiating playback of the video of the avatar providing speech in the avatar region, wherein the speech of the avatar comprises an audio paraphrase of the page, wherein:

the audio of the paraphrase is generated according to a second output from a second machine-learning model, and

the second machine-learning model receives the plurality of answers and provides the second output according to the received plurality of answers;

receiving a user input indicative of resizing a window of the user interface from a first size to a second size; and

determining a second location and a second size of the avatar based on the second size of the user interface and a reduction of an overlap between the avatar and the content displayed on the user interface at the second size.

2 . The method of claim 1 , further comprising:

obtaining a plurality of scores based on the plurality of answers;

selecting one or more speech segments according to the plurality of scores;

generating a script based on the selected one or more speech segments; and

selecting one or more of video segments of the avatar from a video repository according to the plurality of scores, wherein the video of the avatar is generated further based on the selected one or more video segments.

3 . The method of claim 2 , wherein the video repository comprises a plurality of pre-generated videos of the avatar.

4 . The method of claim 3 , further comprising obtaining the plurality of pre-generated videos of the avatar, wherein the plurality of pre-generated videos of the avatar are obtained using the first machine-learning model.

5 . The method of claim 1 , wherein the user interface further comprises a navigation region comprising a plurality of topics for navigating to the plurality of static pages.

6 . The method of claim 5 , wherein the page of the static pages is associated with a topic of the plurality of topics.

7 . The method of claim 5 , further comprising:

receiving a second user input indicative of a selection of a topic of the plurality of topics;

in response to receiving the second user input, displaying a second page of the static pages; and

initiating playback of a second video of the avatar in the avatar region, wherein the second video comprises an audio paraphrase of the second page.

8 . The method of claim 7 , further comprising receiving a third user input for initiating playback of the second video.

9 . The method of claim 1 , wherein the speech of the avatar comprises background information associated without reciting verbatim the textual content displayed on the page of the user-specific personal assessment report.

10 . The method of claim 1 , wherein a location of the avatar is determined based in part on a location of content displayed on the page.

11 . The method of claim 1 , further comprising highlighting a first portion of the page displayed in the report region based on the speech of the avatar.

12 . The method of claim 1 , further comprising:

determining a first shape and a first level of transparency of the avatar region based on the content displayed on the user interface at the first size of the window, and

determining a second shape and a second level of transparency of the avatar region based on the content displayed on the user interface at the second size of the window.

13 . The method of claim 1 , further comprising: in accordance with the playback of the video of the avatar, automatically updating displaying of the user interface, comprising:

displaying second content on the user interface, and

displaying the avatar at a third location on the user interface and at a third size, wherein the third location and the third size of the avatar are automatically determined according to size and location of the second content on the user interface.

14 . The method of claim 1 , wherein the second location and the second size of the avatar are determined to minimize the overlap between the avatar and the content displayed on the user interface at the second size.

15 . The method of claim 1 , further comprising:

obtaining a plurality of scores based on the plurality of answers; and

determining whether a score of the plurality of scores meets a condition, wherein the condition comprises the score being lower than a score threshold, the score being higher than the score threshold, or the score being within a score range, wherein:

in accordance with a determination that the score meets the condition, the playback of the video does not comprise video associated with the score and further does not comprise audio associated with the score.

16 . A system for generating and presenting a user-specific personal assessment report, comprising:

one or more processors; and

a memory communicatively coupled to the one or more processors and configured to store instructions that, when executed by the one or more processors, cause the system to:

receive, from a user, a plurality of answers corresponding to a plurality of predetermined questions in a personal assessment questionnaire;

generate, based on the plurality of answers, the user-specific personal assessment report comprising a plurality of static pages;

display a user interface for presenting the user-specific personal assessment report, the user interface comprising:

a report region for displaying a page of the plurality of static pages;

an avatar region for presenting a video of an avatar, wherein:

one or more images of the video of the avatar are generated according to a first output from a first machine-learning model,

the first machine-learning model is trained, using a plurality of images corresponding to an appearance of the avatar, to provide the first output,

the avatar is configured to be partially overlaid on the report region, and

a first location and a first size of the avatar are determined based on content displayed on the page;

receive the user input initiating playback of the user interface;

in response to receiving the user input, initiate playback of the video of the avatar providing speech in the avatar region, wherein the speech of the avatar comprises an audio paraphrase of the page, wherein:

the audio of the paraphrase is generated according to a second output from a second machine-learning model, and

the second machine-learning model receives the plurality of answers and provides the second output according to the received plurality of answers;

receive a user input indicative of resizing a window of the user interface from a first size to a second size; and

determine a second location and a second size of the avatar based on the second size of the user interface and a reduction of an overlap between the avatar and the content displayed on the user interface at the second size.

17 . The system of claim 16 , wherein the system is further caused to:

obtain a plurality of scores based on the plurality of answers;

select one or more speech segments according to the plurality of scores;

generate a script based on the selected one or more speech segments; and

select one or more of video segments of the avatar from a video repository according to the plurality of scores, wherein the video of the avatar is generated further based on the selected one or more video segments.

18 . The system of claim 16 , wherein the speech of the avatar comprises background information associated without reciting verbatim the textual content displayed on the page of the user-specific personal assessment report.

19 . The system of claim 16 , wherein the user interface further comprises a navigation region comprising a plurality of topics for navigating to the plurality of static pages.

20 . A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of a system, cause the system to perform a method comprising:

receiving, from a user, a plurality of answers corresponding to a plurality of predetermined questions in a personal assessment questionnaire;

generating, based on the plurality of answers, the user-specific personal assessment report comprising a plurality of static pages;

displaying a user interface for presenting the user-specific personal assessment report, the user interface comprising:

a report region for displaying a page of the plurality of static pages;

an avatar region for presenting a video of an avatar, wherein:

one or more images of the video of the avatar are generated according to a first output from a first machine-learning model,

the first machine-learning model is trained, using a plurality of images corresponding to an appearance of the avatar, to provide the first output,

the avatar is configured to be partially overlaid on the report region, and

a first location and a first size of the avatar are determined based on content displayed on the page;

receiving the user input initiating playback of the user interface;

in response to receiving the user input, initiating playback of the video of the avatar providing speech in the avatar region, wherein the speech of the avatar comprises an audio paraphrase of the page, wherein:

the audio of the paraphrase is generated according to a second output from a second model, and

the second machine-learning model receives the plurality of answers and provides the second output according to the received plurality of answers;

receiving a user input indicative of resizing a window of the user interface from a first size to a second size; and

determining a second location and a second size of the avatar based on the second size of the user interface and a reduction of an overlap between the avatar and the content displayed on the user interface at the second size.

21 . The non-transitory computer-readable storage medium of claim 20 , wherein the method further comprises:

obtaining a plurality of scores based on the plurality of answers;

selecting one or more speech segments according to the plurality of scores;

generating a script based on the selected one or more speech segments; and

selecting one or more of video segments of the avatar from a video repository according to the plurality of scores, wherein the video of the avatar is generated further based on the selected one or more video segments.

22 . The non-transitory computer-readable storage medium of claim 20 , wherein the speech of the avatar comprises background information associated without reciting verbatim the textual content displayed on the page of the user-specific personal assessment report.

23 . The non-transitory computer-readable storage medium of claim 20 , wherein the user interface further comprises a navigation region comprising a plurality of topics for navigating to the plurality of static pages.

Assignments (2)

Continuity (2)

References Cited (16)