Granted Patent B2

US 12,711,288 · App. 17/855,607 · Granted Aug 18, 2026

Inventors: Rajiv Ramanasankaran (San Jose, CA); Chenlu Zhang (Milwaukee, WI); Ambuj Shatdal (Madison, WI); Young Lee (Milwaukee, WI); Jonathan D. Douglas (Mequon, WI)

Assignee: TYCO FIRE & SECURITY GMBH

G06F30/20G06F30/12

Abstract

Claims (52)

1 . A building system of a building comprising one or more non-transitory storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:

retrieve historical data values of a plurality of data points for a plurality of historical times from a knowledge graph of a digital twin of the building;

execute an artificial intelligence to generate a plurality of inference values of the plurality of data points for a plurality of future times based on the retrieved historical data values and store the plurality of inference values in the knowledge graph of the digital twin;

generate user interface data causing a user device to display a user interface comprising a graphic representation of the building based on a model of the building, the user interface including a selectable element providing selections of the plurality of historical times and the plurality of future times;

receive a selection from the user device via the selectable element of a future time of the plurality of future times;

responsive to the selection, retrieve the plurality of inference values from the knowledge graph of the digital twin and insert the plurality of inference values into data of the model; and

cause the user device to display the graphic representation of the building with a plurality of states based on the plurality of inference values of the plurality of data points for the plurality of future times.

2 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

store the digital twin of the building in the one or more non-transitory storage devices, the digital twin comprising a virtual representation of the building with a plurality of entities of the building, the plurality of data points, and interrelationships between the plurality of entities of the building and the plurality of data points, wherein the digital twin further includes the artificial intelligence configured to generate the plurality of inference values.

3 . The building system of claim 2 , wherein the digital twin includes a building graph data structure including a plurality of nodes representing the plurality of entities of the building and a plurality of edges between the plurality of nodes representing the interrelationships between the plurality of entities of the building.

4 . The building system of claim 2 , wherein the digital twin generates one or more predicted future states or one or more simulated past states of a building space represented within the digital twin.

5 . The building system of claim 4 , wherein the instructions cause the one or more processors to:

generate a space indicator that describes the one or more predicted future states or the one or more simulated past states of the building space using one or more colors.

6 . The building system of claim 5 , wherein the space indicator is a graphic representation that highlights the building space to indicate the one or more predicted future states or the one or more simulated past states of the building space.

7 . The building system of claim 5 , wherein the one or more colors indicate an identity of infectious disease in the building space.

8 . The building system of claim 4 , wherein the one or more predicted future states of the building include at least one of:

a predicted occupant level, a predicted air quality level, or a predicted reproductive number.

9 . The building system of claim 8 , wherein the predicted occupant level is an inference value that predicts an amount of occupants in the building, the predicted air quality level is an inference value that predicts air quality of the building, and the predicted reproductive number is an inference value that predicts a spread of an infectious disease of the building.

10 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

cause the user device to display the selectable element comprising representations of a plurality of historical days and a plurality of future days.

11 . The building system of claim 10 , wherein the instructions cause the one or more processors to:

receive a second selection of a historical day of the plurality of historical days via the selectable element; and

cause the graphic representation to include a predicted historical state of the building for the historical day responsive to a reception of the second selection for the historical day via the selectable element.

12 . The building system of claim 10 , wherein the instructions cause the one or more processors to:

receive the selection of a future day of the plurality of future days via the selectable element; and

cause the graphic representation to include a predicted future state of the building for the future day responsive to a reception of the selection of the future day via the selectable element.

13 . A method comprising:

retrieving historical data values of a plurality of data points for a plurality of historical times from a knowledge graph of a digital twin of a building;

executing an artificial intelligence to generate a plurality of inference values of the plurality of data points for a plurality of future times based on the retrieved historical data values and store the plurality of inference values in the knowledge graph of the digital twin;

generating user interface data causing a user device to display a graphic representation of the building based on a model of the building, the user interface including a selectable element providing selections of the plurality of historical times and the plurality of future times;

receiving a selection from the user device via the selectable element of a future time of the plurality of future times;

responsive to the selection, retrieving the plurality of inference values from the knowledge graph of the digital twin and insert the plurality of inference values into data of the model; and

causing the user device to display the graphic representation of the building with a plurality of states based on the plurality of inference values of the plurality of data points for the plurality of future times.

14 . The method of claim 13 , further comprising storing the digital twin of the building in one or more storage devices, the digital twin comprising a virtual representation of the building with a plurality of entities of the building, the plurality of data points, and interrelationships between the plurality of entities of the building and the plurality of data points, wherein the digital twin further includes the artificial intelligence configured to generate the plurality of inference values.

15 . The method of claim 14 , further comprising generating, by the digital twin, one or more predicted future states or one or more simulated past states of a building space represented within the digital twin.

16 . The method of claim 15 , further comprising generating a space indicator that describes the one or more predicted future states or the one or more simulated past states of the building space using one or more colors.

17 . The method of claim 13 , further comprising causing the user device to display the selectable element, the selectable element comprising representations of a plurality of historical days and a plurality of future days.

18 . The method of claim 17 , further comprising:

receiving a second selection of a historical day of the plurality of historical days via the selectable element; and

causing the graphic representation to include a predicted historical state of the building for the historical day responsive to a reception of the selection for the historical day via the selectable element.

19 . One or more non-transitory computer readable media containing program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

retrieving historical data values of a plurality of data points for a plurality of historical times from a knowledge graph of a digital twin of a building;

executing an artificial intelligence to generate a plurality of inference values of the plurality of data points for a plurality of future times based on the retrieved historical data values and store the plurality of inference values in the knowledge graph of the digital twin;

generating user interface data causing a user device to display a user interface comprising a graphic representation of the building based on a model of the building, the user interface including a selectable element providing selections of the plurality of historical times and the plurality of future times;

receiving a selection from the user device via the selectable element of a future time of the plurality of future times;

generating predicted future states for the future time, wherein one of the predicted future states is generated from a combination of the plurality of inference values of the plurality of data points for the future time;

responsive to the selection, retrieving the plurality of inference values from the knowledge graph of the digital twin and insert the plurality of inference values into data of the model; and

causing the user device to display the graphic representation of the building with at least the one of the predicted future states for the future time.

20 . The one or more non-transitory computer readable media of claim 19 , wherein the program instructions further cause the one or more processors to store the digital twin of the building in the one or more non-transitory computer readable media, the digital twin comprising a virtual representation of the building with a plurality of entities of the building, the plurality of data points, and interrelationships between the plurality of entities of the building and the plurality of data points, wherein the digital twin further includes the artificial intelligence configured to generate the plurality of inference values.

21 . The one or more non-transitory computer readable media of claim 19 , wherein the program instructions further cause the one or more processors to:

receive a second selection of a historical day of historical days via the selectable element; and

cause the graphic representation to include a predicted historical state of the building for the historical day responsive to a reception of the selection for the historical day via the selectable element.

Assignments (2)

Continuity (2)

References Cited (400)