Systems and methods for facilitating candidate interviews

Patent metadata

Field	Value
Publication number	US-12288193-B2
Application number	US-202318528895-A
Country	US
Kind code	B2
Filing date	Dec 5, 2023
Priority date	Mar 2, 2020
Publication date	Apr 29, 2025
Grant date	Apr 29, 2025

Abstract

A system for determining candidate answers during an interview. The system may include a memory storing executable instructions, and at least one processor configured to execute the instructions to perform operations. The operations may include capturing, by an image sensor, a plurality of images comprising a plurality of candidate answers; detecting, based on the captured images, a first bounding box comprising the plurality of the candidate answers; detecting, based on the captured images, a second bounding box comprising a plurality of alphanumeric characters, a first one of the alphanumeric characters being located on a line of software code; calculating a distance from a side of a first bounding box to a side of a second bounding box; and determining, based on the calculated distance, a source code alignment.

First claim

What is claimed is:

1. A system comprising:
a memory; and
a processor in communication with the memory, wherein the processor is configured to:
cause an image sensor to capture a plurality of images;
detect, based on the plurality of images, a first bounding box comprising a plurality of text characters;
detect, based on the plurality of images, a second bounding box comprising a plurality of alphanumeric characters;
calculate a distance from a side of the first bounding box to a side of the second bounding box; and
determine, based on the calculated distance, a software code alignment.

2. The system of claim 1 , wherein a first one of the plurality of alphanumeric characters is located on a line of software code.

3. The system of claim 2 , wherein the software code alignment comprises an indentation in the software code.

4. The system of claim 3 , wherein:
the indentation comprises a plurality of tabs; and
the plurality of tabs are indicative of software code within an algorithmic loop.

5. The system of claim 2 , wherein the processor is further configured to:
detect if an error exists in the software code; and
based on the detection, prompt interviewers to provide interview questions.

6. The system of claim 1 , wherein the image sensor comprises a camera positioned on a wall in a room.

7. The system of claim 1 , wherein:
the second bounding box comprises a height dimension and a width dimension; and
the processor is further configured to calculate an average size of the second bounding box, based on the height and width dimensions.

8. The system of claim 1 , wherein determining a software code alignment comprises automatically detecting a software code alignment across a plurality of lines of the software code.

9. The system of claim 1 , wherein the processor is further configured to:
compare the plurality of text characters to a plurality of candidate solutions stored in a database,
the plurality of candidate solutions comprising candidate solutions based on a plurality of interviews.

10. A method comprising:
causing, by a processor, an image sensor to capture a plurality of images;
detecting, by the processor based on the plurality of images, a first bounding box comprising a plurality of text characters;
detecting, by the processor based on the plurality of images, a second bounding box comprising a plurality of alphanumeric characters;
calculating, by the processor, a distance from a side of the first bounding box to a side of the second bounding box; and
determining, by the processor based on the calculated distance, a software code alignment.

11. The method of claim 10 , wherein:
the software code alignment comprises an indentation in a software code; and
the indentation comprises a plurality of tabs.

12. The method of claim 10 , further comprising:
determining, by the processor, whether the software code alignment comprises a tab, wherein an absence of the tab indicates software code placed outside of an algorithmic loop.

13. The method of claim 12 , wherein software code placed outside of an algorithmic loop indicates an incorrect candidate answer.

14. The method of claim 10 , further comprising:
detecting, by the processor, if an error exists in a software code; and
based on the detection, suggesting, by the processor, questions for interviewers to ask based on a plurality of stored candidate solutions.

15. The method of claim 14 , wherein the stored candidate solutions comprise candidate solutions based on a plurality of interviews.

16. The method of claim 10 , wherein the image sensor comprises a camera positioned on a laptop.

17. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
causing an image sensor to capture a plurality of images;
detecting, based on the plurality of images, a first bounding box comprising a plurality of text characters;
detecting, based on the plurality of images, a second bounding box comprising a plurality of alphanumeric characters;
calculating a distance from a side of the first bounding box to a side of the second bounding box; and
determining, based on the calculated distance, a software code alignment.

18. The non-transitory computer-readable medium of claim 17 , wherein:
the software code alignment comprises an indentation, and
the indentation is indicative of software code within an algorithmic loop.

19. The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:
detecting if an error exists in the software code, and
based on the detection, suggesting questions for interviewers to ask based on a plurality of stored candidate solutions.

20. The non-transitory computer-readable medium of claim 17 , wherein:
the second bounding box comprises a height dimension and a width dimension, and
the operations further comprise calculating an average size of the second bounding box based on the height and width dimensions.

Assignees

• Capital One Services Llc

Inventors

• Truong Anh
• Key Kate
• Rafferty Galen
• Farivar Reza
• Pham Vincent
• Walters Austin
• Watson Mark

Classifications

• G06V30/148

  Segmentation of character regions · CPC title

• G06V30/10

  Character recognition · CPC title

• G06V30/414

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06F11/3624

  by performing operations on the source code, e.g. via a compiler · CPC title

• G06Q10/105 Primary

  Human resources · CPC title