Automated architectural specification generation and hardware identification

Patent metadata

Field	Value
Publication number	US-11062541-B2
Application number	US-201916425777-A
Country	US
Kind code	B2
Filing date	May 29, 2019
Priority date	May 29, 2018
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

A method according to one embodiment includes determining, by a server, a location of a door in an architectural drawing and a room function of a room secured by the door based on an analysis of the architectural drawing, determining, by the server, proper access control hardware to be installed on the door based on the room function, a category of access control hardware, and a predictive machine learning model associated with the category of access control hardware, and generating, by the server, a specification based on the determined proper access control hardware.

First claim

What is claimed is:

1. A method, comprising:
determining, by a server, a location of a door in an architectural drawing and a room function of a room secured by the door based on an analysis of the architectural drawing;
determining, by the server, proper access control hardware to be installed on the door based on the room function, a category of access control hardware, and a predictive machine learning model associated with the category of access control hardware; and
generating, by the server, a specification based on the determined proper access control hardware.

2. The method of claim 1 , wherein determining the location of the door and the room function comprises applying a plurality of morphological functions to the architectural drawing.

3. The method of claim 2 , wherein determining the location of the door and the room function comprises applying a Houghlines function to determine line endpoints of a line in the architectural drawing.

4. The method of claim 1 , wherein determining the location of the door and the room function comprises:
performing binary thresholding to the architectural drawing to generate a binary image; and
applying a plurality of morphological functions to the binary image.

5. The method of claim 1 , further comprising determining, by the server, locations at which to position a plurality of gateway devices based on an analysis of the architectural drawing.

6. The method of claim 1 , wherein the category of access control hardware is selected from a Door Hardware Institute (DHI) category of door hardware.

7. The method of claim 1 , further comprising monitoring a location of the determined proper access control hardware using a hardware tag secured to the proper access control hardware subsequent to acquisition of the proper access control hardware.

8. The method of claim 7 , wherein monitoring the location of the determined proper access control hardware comprises monitoring the location of the determined proper access control hardware via a base station when the determined proper access control hardware is between fifteen and twenty-five kilometers in distance from the base station.

9. A system, comprising:
at least one processor; and
at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to:
determine a location of a door in an architectural drawing and a room function of a room secured by the door based on an analysis of the architectural drawing;
determine proper access control hardware to be installed on the door based on the room function, a category of access control hardware, and a predictive machine learning model associated with the category of access control hardware; and
generate a specification based on the determined proper access control hardware.

10. The system of claim 9 , wherein to determine the location of the door and the room function comprises to:
perform binary thresholding to the architectural drawing to generate a binary image; and
apply a plurality of morphological functions to the binary image.

11. The system of claim 9 , wherein the plurality of instructions further causes the system to determine one or more locations at which to position one or more gateway devices based on an analysis of the architectural drawing.

12. The system of claim 9 , wherein the category of access control hardware is selected from a Door Hardware Institute (DHI) category of door hardware.

13. The system of claim 9 , wherein the plurality of instructions further causes the system to monitor a location of the determined proper access control hardware using a hardware tag secured to the proper access control hardware subsequent to acquisition of the proper access control hardware.

14. The system of claim 13 , further comprising a base station; and
wherein to monitor the location of the determined proper access control hardware comprises to monitor the location of the determined proper access control hardware via the base station using communication signals of a first frequency band when the determined proper access control hardware is between fifteen and twenty-five kilometers in distance from the base station.

15. At least one non-transitory machine-readable storage medium comprising a plurality of instructions stored thereon that, in response to execution by a system, causes the system to:
determine a location of a door in an architectural drawing and a room function of a room secured by the door based on an analysis of the architectural drawing;
determine proper access control hardware to be installed on the door based on the room function, a category of access control hardware, and a predictive machine learning model associated with the category of access control hardware; and
generate a specification based on the determined proper access control hardware.

16. The at least one non-transitory machine-readable storage medium of claim 15 , wherein the category of access control hardware is selected from a Door Hardware Institute (DHI) category of door hardware.

17. The at least one non-transitory machine-readable storage medium of claim 15 , wherein the plurality of instructions further causes the system to track a hardware tag secured to access control hardware using a distributed ledger.

18. The method of claim 1 , wherein determining the location of the door and the room function comprises:
identifying, by the server, text in the architectural drawing;
determining, by the server, coordinates of the identified text in the architectural drawing;
positioning a bounding box at the coordinates of the identified text; and
applying a door classifier at least one of within or around the bounding box to determine whether the identified text is associated with a door.

19. The method of claim 1 , wherein the architectural drawing comprises a flattened image.

20. The method of claim 3 , wherein determining the location of the door and the room function comprises determining a text label of the architectural drawing associated with the room function based on the line endpoints resulting from applying the Houghlines function.

Assignees

• Schlage Lock Co Llc

Inventors

• Prostko Robert S
• Martens Robert C
• Heitzman Nick
• Day Kristin
• Madsen Martin
• Kornaker Jason
• Langenberg Daniel
• Eickhoff Brian C
• Baxter Scott
• Baumgarte Joseph W
• Hopkins Benjamin
• Kottlowski Steve J
• Scheib Jacob

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title