Systems and methods for automating conversion of drawings to indoor maps and plans

1. A computer-implemented method of creating an indoor map from a CAD drawing, the method comprising:

preprocessing, by a device, an original CAD drawing to create a modified CAD drawing, a text database containing text from the original CAD drawing, a CAD vector-image of the modified CAD drawing, and a CAD raster-image of the modified CAD drawing;

determining, by a device, a floor depicted in the CAD drawing, the determining results in a floor-level bounding line;

sensing, by a device, furniture depicted on the floor by applying the floor-level bounding line, the CAD vector-image, and the text database to machine-learning algorithms, the sensing results in a plurality of furniture entities and associated location information;

identifying, by a device, each room depicted in the CAD drawing within the floor-level bounding line, the identifying results in a plurality of room outlines; and

creating, by a device, an indoor map for the floor by combining the plurality of furniture entities and associated location information with the plurality of room outlines.

2. The computer-implemented method of claim 1 wherein identifying each room depicted in the CAD drawing further comprises identifying based on the plurality of furniture identities and associated location information.

3. The computer-implemented method of claim 1 wherein sensing the furniture depicted on the floor further comprises:

providing the floor-level bounding line and the CAD vector-image to a furniture-level machine-learning algorithm, the furniture-level machine-learning algorithm generates furniture bounding lines;

administering a parsed version of the text database to a text-level machine-learning algorithm, the text-level machine-learning algorithm generates intermediate furniture identities with associated intermediate location information; and

applying the furniture bounding lines and the intermediate furniture identities to an ensemble machine-learning algorithm, the ensemble machine-learning algorithm selects final-furniture bounding lines and identity information; and

post processing the final-furniture bounding lines and identity information, the post processing generates the furniture entities and the associated location information.

4. The computer-implemented method of claim 3 wherein the furniture bounding lines includes at least one bounding line identifying a door.

5. The computer-implemented method of claim 3 :

wherein, prior to the providing, the method further comprises:

reading, by a device, scale information from the original CAD drawing;

gridding, by a device, a portion of the CAD vector-image identified by the floor-level bounding line into a plurality of grids having a predetermined size based on the scale information; and

wherein providing further comprises providing the plurality of grids to the furniture-level machine-learning algorithm;

wherein post processing further comprises removing duplicate furniture detections from the furniture entities.

6. The computer-implemented method of claim 5 wherein gridding further comprises selecting plurality of grids, each grid of the plurality defines an area that overlaps at least one neighboring grid by a predetermined percentage.

7. The computer-implemented method of claim 3 wherein post processing further comprises replacing, within the modified CAD drawing, the furniture entities with predetermined furniture entities.

8. A computer system for creating an indoor map from a CAD drawing, the computer system comprising:

a processor;

a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to:

preprocess an original CAD drawing to create a modified CAD drawing, a text database containing text from the original CAD drawing, a CAD vector-image of the modified CAD drawing, and a CAD raster-image of the modified CAD drawing;

determine a floor depicted in the CAD drawing, the determination results in a floor-level bounding line;

sense furniture depicted on the floor by applying the floor-level bounding line, the CAD vector-image, and the text database to machine-learning algorithms, the sensing results in a plurality of furniture entities and associated location information;

identify each room depicted in the CAD drawing within the floor-level bounding line, the identifying results in a plurality of room outlines; and

create an indoor map for the floor by combining the plurality of furniture entities and associated location information with the plurality of room outlines.

9. The computer system of claim 8 wherein when the processor identifies each room depicted in the CAD drawing, the instructions further cause the processor to identify based on the plurality of furniture identities and associated location information.

10. The computer system of claim 8 wherein when the processor senses the furniture depicted on the floor, the instructions further cause the processor to:

provide the floor-level bounding line and the CAD vector-image to a furniture-level machine-learning algorithm, the furniture-level machine-learning algorithm generates furniture bounding lines;

administer a parsed version of the text database to a text-level machine-learning algorithm, the text-level machine-learning algorithm generates intermediate furniture identities with associated intermediate location information; and

apply the furniture bounding lines and the intermediate furniture identities to an ensemble machine-learning algorithm, the ensemble machine-learning algorithm selects final-furniture bounding lines and identity information; and

post process the final-furniture bounding lines and identity information, the post processing generates the furniture entities and the associated location information.

11. The computer system of claim 10 wherein the furniture bounding lines includes at least one bounding line identifying a door.

12. The computer system of claim 10 :

wherein, prior to the when the processor provides, the instruction further cause the processor to:

read scale information from the original CAD drawing;

grid a portion of the CAD vector-image identified by the floor-level bounding line into a plurality of grids having a predetermined size based on the scale information; and

wherein when the processor provides, the instructions further cause the processor to provide the plurality of grids to the furniture-level machine-learning algorithm;

wherein when the processor post processes, the instructions further cause the processor to remove duplicate furniture detections from the furniture entities.

13. The computer system of claim 12 wherein when the processor grids, the instructions further cause the processor to select a plurality of grids, each grid of the plurality defines an area that overlaps at least one neighboring grid by a predetermined percentage.

14. The computer system of claim 10 wherein when the processor post processes, the instruction further cause the processor to replace, within the modified CAD drawing, the furniture entities with predetermined furniture entities.

15. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to:

preprocess an original CAD drawing to create a modified CAD drawing, a text database containing text from the original CAD drawing, a CAD vector-image of the modified CAD drawing, and a CAD raster-image of the modified CAD drawing;

determine a floor depicted in the CAD drawing, the determination results in a floor-level bounding line;

sense furniture depicted on the floor by applying the floor-level bounding line, the CAD vector-image, and the text database to machine-learning algorithms, the sensing results in a plurality of furniture entities and associated location information;

identify each room depicted in the CAD drawing within the floor-level bounding line, the identifying results in a plurality of room outlines; and

create an indoor map for the floor by combining the plurality of furniture entities and associated location information with the plurality of room outlines.

16. The computer-readable medium of claim 15 wherein when the processor senses the furniture depicted on the floor, the instructions further cause the processor to:

provide the floor-level bounding line and the CAD vector-image to a furniture-level machine-learning algorithm, the furniture-level machine-learning algorithm generates furniture bounding lines;

administer a parsed version of the text database to a text-level machine-learning algorithm, the text-level machine-learning algorithm generates intermediate furniture identities with associated intermediate location information; and

apply the furniture bounding lines and the intermediate furniture identities to an ensemble machine-learning algorithm, the ensemble machine-learning algorithm selects final-furniture bounding lines and identity information; and

post process the final-furniture bounding lines and identity information, the post processing generates the furniture entities and the associated location information.

17. The computer-readable medium of claim 16 wherein the furniture bounding lines includes at least one bounding line identifying a door.

18. The computer-readable medium of claim 16 :

wherein, prior to the when the processor provides, the instruction further cause the processor to:

read scale information from the original CAD drawing;

grid a portion of the CAD vector-image identified by the floor-level bounding line into a plurality of grids having a predetermined size based on the scale information; and

wherein when the processor provides, the instructions further cause the processor to provide the plurality of grids to the furniture-level machine-learning algorithm;

wherein when the processor post processes, the instructions further cause the processor to remove duplicate furniture detections from the furniture entities.

19. The computer-readable medium of claim 18 wherein when the processor grids, the instructions further cause the processor to select a plurality of grids, each grid of the plurality defines an area that overlaps at least one neighboring grid by a predetermined percentage.

20. The computer-readable medium of claim 16 wherein when the processor post processes, the instruction further cause the processor to replace, within the modified CAD drawing, the furniture entities with predetermined furniture entities.