Building data platform with digital twin based inferences and predictions for a graphical building model

Patent metadata

Field	Value
Publication number	US-11714930-B2
Application number	US-202117537046-A
Country	US
Kind code	B2
Filing date	Nov 29, 2021
Priority date	Nov 29, 2021
Publication date	Aug 1, 2023
Grant date	Aug 1, 2023

Abstract

A building system including one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to receive an indication to execute an artificial intelligence (AI) agent, execute the AI agent based on the digital twin to generate an inference or a prediction, cause a graphical model of the building including graphical representations of the entities to include information based on the inference or the prediction, and cause a display device of a user device to display the graphical model.

First claim

What is claimed is:

1. A building system comprising one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:
receive an indication to execute an artificial intelligence (AI) agent;
execute the AI agent based on operational data of a building stored or linked in a knowledge graph to generate an inference or a prediction of a condition of a building, the knowledge graph including representations of entities of the building, relationships between the entities of the building, and one or more storage elements storing or linking the operational data;
store, by the AI agent, the inference or the prediction, or a link to the inference or the prediction, in the one or more data storage elements of the knowledge graph;
query the knowledge graph to retrieve the inference or the prediction from the knowledge graph;
update, responsive to the query, a graphical model of the building including graphical representations of the entities to include the inference or the prediction; and
cause a display device of a user device to display the updated graphical model.

2. The building system of claim 1 , wherein the graphical model of the building is a three dimensional building model of the building.

3. The building system of claim 1 , wherein the graphical model is a building information model (BIM).

4. The building system of claim 1 , wherein the entities of the building are at least one of a space, a device, or a person.

5. The building system of claim 1 , wherein the knowledge graph includes a graph data structure including a plurality of nodes representing the entities of the building and a plurality of edges between the plurality of nodes representing the relationships between the entities of the building;
wherein a first node of the plurality of nodes represents the entity;
wherein the instructions cause the one or more processors to:
identify one or more second nodes storing or identifying data for the entity, the one or more second nodes related to the first node by one or more edges of the plurality of edges;
retrieve the data for the entity from the one or more second nodes or based on the one or more second nodes; and
execute the AI agent based on the data for the entity to generate the inference or the prediction.

6. The building system of claim 1 , wherein the knowledge graph includes a graph data structure including a plurality of nodes representing the entities of the building and a plurality of edges between the plurality of nodes representing the relationships between the entities of the building;
wherein a first node of the plurality of nodes represents the entity;
wherein the instructions cause the one or more processors to:
identify a second node of the plurality of nodes for storing the inference or the prediction by identifying one or more edges of the plurality of edges between the first node and the second node; and
cause the second node of the plurality of nodes to store the inference or the prediction.

7. The building system of claim 1 , wherein the instructions cause the one or more processors to:
receive an input from the user device in the graphical model; and
execute the AI agent based on the knowledge graph to generate the inference or the prediction in response to receiving the input.

8. The building system of claim 1 , wherein the instructions cause the one or more processors to:
receive an interaction with a graphical representation of the entity of the graphical representations of the entities from the user device in the graphical model;
cause the graphical model of the building to include one or more inferences or one or more predictions associated with the entity; and
cause the display device of the user device to display the graphical model.

9. The building system of claim 1 , wherein a graphical representation of the entity is included within the graphical model of the building;
wherein the instructions cause the one or more processors to cause the graphical model of the building including the graphical representations of the entities to animate the graphical representation of the entity based on the inference or the prediction.

10. The building system of claim 1 , wherein the AI agent is at least one of:
a clean air optimization (CAO) agent configured to generate one or more operating parameters for an air handler unit of the building; or
an energy prediction model AI agent configured to predict an energy usage of a component of the building.

11. The building system of claim 1 , wherein the inference is at least one inferred operating value that causes one or more pieces of equipment of the building to achieve an operating goal;
wherein the prediction is at least one predicted value of a parameter at a future time.

12. The building system of claim 11 , wherein at least one of the inference or the prediction is a timeseries of time correlated data values.

13. The building system of claim 11 , wherein the instructions cause the one or more processors to:
cause the one or more pieces of equipment of the building to operate based on the inferred operating value to achieve the operating goal.

14. A method, comprising:
receiving, by one or more processing circuits, an indication to execute an artificial intelligence (AI) agent;
executing, by the one or more processing circuits, the AI agent based on operational data of a building stored or linked in a knowledge graph to generate an inference or a prediction of a condition of the building, the knowledge graph including representations of entities of the building, relationships between the entities of the building, and one or more storage elements storing or linking the operational data;
storing, by the AI agent, the inference or the prediction, or a link to the inference or the prediction, in the one or more data storage elements of the knowledge graph;
querying, by the one or more processing circuits, the knowledge graph to retrieve the inference or the prediction from the knowledge graph;
updating, responsive to the query, by the one or more processing circuits, a graphical model of the building including graphical representations of the entities to include the inference or the prediction; and
causing, by the one or more processing circuits, a display device of a user device to display the updated graphical model.

15. The method of claim 14 , wherein the graphical model of the building is a three dimensional building model of the building.

16. The method of claim 14 , wherein the knowledge graph includes a graph data structure including a plurality of nodes representing the entities of the building and a plurality of edges between the plurality of nodes representing the relationships between the entities of the building;
wherein the inference or the prediction is for an entity of the entities, wherein a first node of the plurality of nodes represents the entity;
wherein the method further comprises:
identifying, by the one or more processing circuits, one or more second nodes storing or identifying data for the entity, the one or more second nodes related to the first node by one or more edges of the plurality of edges;
retrieving, by the one or more processing circuits, the data for the entity from the one or more second nodes or based on the one or more second nodes; and
executing, by the one or more processing circuits, the AI agent based on the data for the entity to generate the inference or the prediction.

17. The method of claim 14 , wherein the knowledge graph include

Assignees

• Johnson Controls Tyco IP Holdings LLP

Inventors

• Ramanasankaran Rajiv
• Zhang Chenlu
• Shatdal Ambuj
• Lee Young

Classifications

• G06F30/13 Primary

  Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads · CPC title

• G06F30/27 Primary

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N3/092

  Reinforcement learning · CPC title