BUILDING MANAGEMENT SYSTEM WITH SPACE GRAPHS INCLUDING SOFTWARE COMPONENTS

1 . A building system, comprising:

one or more memory devices storing instructions thereon, that, when executed by one or more processors, cause the one or more processors to:

retrieve at least one node or at least one edge of a space graph, the space graph comprising a plurality of nodes representing a plurality of entities of a building and a plurality of edges between the plurality of nodes representing a plurality of relationships between the plurality of entities of the building;

execute, using at least one of the at least one node or the at least one edge, a machine learning model to classify a state of an entity of the plurality of entities of the building; and

update a current state of the entity using the classified state.

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

receive building data from one or more building data sources;

generate the plurality of edges between the plurality of nodes based on the building data, wherein the plurality of edges comprises a pair of edges between a first node representing the entity and a second node representing a second entity of the plurality of entities representing two different types of relationships, wherein the pair of edges comprises a first edge between the first node and the second node and a second edge between the second node and the first node; and

update the space graph by causing the space graph to store the plurality of nodes representing the plurality of entities and the plurality of edges between the plurality of nodes representing the plurality of relationships.

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

ingest data values into the space graph, the data values associated with the plurality of entities; and

execute, using at least a portion of the data values, the machine learning model to classify the state of the entity of the plurality of entities of the building.

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

receive new building data from one or more building data sources;

identify, based on the new building data, a new relationship between the entity and a second entity of the plurality of entities; and

update the space graph with the new relationship by causing the space graph to store a new edge between a first node of the plurality of nodes representing the entity and a second node of the plurality of nodes representing the second entity.

5 . The building system of claim 1 , wherein the plurality of nodes include a node representing a control algorithm;

wherein the plurality of edges include one or more particular edges between the node and a node of the plurality of nodes representing the machine learning model, the one or more particular edges indicating that the machine learning model operates based on the control algorithm.

6 . The building system of claim 1 , wherein the machine learning model is an artificial intelligence agent that performs artificial intelligence operations for at least one of a person, place, or piece of equipment of the building.

7 . The building system of claim 1 , wherein the machine learning model executes based on at least a portion of the plurality of nodes and a portion of the plurality of edges.

8 . The building system of claim 1 , wherein the entity is a space of the building;

wherein the instructions cause the one or more processors to classify the space as occupied or unoccupied.

9 . The building system of claim 1 , wherein the plurality of nodes include a second node representing one or more operating settings for the entity;

wherein the plurality of edges include one or more particular edges between the second node and a node of the machine learning model indicating that the machine learning model generates the one or more operating settings.

10 . The building system of claim 9 , wherein a fourth node of the plurality of nodes is linked by a particular edge of the plurality of edges to another node of the plurality of nodes that represents a device that operates based on the one or more operating settings.

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

store the space graph in a data storage device, wherein:

the plurality of nodes include a node representing the entity, wherein the entity is one of a person, place, or piece of equipment of the building; and

the plurality of nodes include a second node representing the machine learning model that operates outside the space graph, wherein the machine learning model performs operations for the person, place, or piece of equipment of the building indicated by one or more edges of the plurality of edges relating the node with the second node.

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

identify the one or more edges relating the node to the second node to determine that the machine learning model performs the operations for the person, place, or piece of equipment; and

cause the machine learning model to execute for the person, place, or piece of equipment.

13 . A method, comprising:

retrieving, by one or more processing circuits, at least one node or at least one edge of a space graph, the space graph comprising a plurality of nodes representing a plurality of entities of a building and a plurality of edges between the plurality of nodes representing a plurality of relationships between the plurality of entities of the building;

executing, by the one or more processing circuits, using at least one of the at least one node or the at least one edge, a machine learning model to classify a state of an entity of the plurality of entities of the building; and

updating, by the one or more processing circuits, a current state of the entity using the classified state.

14 . The method of claim 13 , comprising:

ingesting, by the one or more processing circuits, data values into the space graph, the data values associated with the plurality of entities; and

executing, by the one or more processing circuits, using at least a portion of the data values, the machine learning model to classify the state of the entity of the plurality of entities of the building.

15 . The method of claim 13 , wherein the machine learning model is an artificial intelligence agent that performs artificial intelligence operations for at least one of a person, place, or piece of equipment of the building.

16 . The method of claim 13 , wherein the entity is a space of the building;

the method comprising classifying, by the one or more processing circuits, the space as occupied or unoccupied.

17 . The method of claim 13 , comprising:

storing, by the one or more processing circuits, the space graph in a data storage device, wherein:

the plurality of nodes include a node representing the entity, wherein the entity is one of a person, place, or piece of equipment of the building; and

the plurality of nodes include a second node representing the machine learning model that operates outside the space graph, wherein the machine learning model performs operations for the person, place, or piece of equipment of the building indicated by one or more edges of the plurality of edges relating the node with the second node.

18 . The method of claim 17 , comprising:

identifying, by the one or more processing circuits, the one or more edges relating the node to the second node to determine that the machine learning model performs the operations for the person, place, or piece of equipment; and

causing, by the one or more processing circuits, the machine learning model to execute for the person, place, or piece of equipment.

19 . One or more non-transitory storage media storing instructions thereon, that, when executed by one or more processors, cause the one or more processors to perform operations, comprising:

retrieving at least one node or at least one edge of a space graph, the space graph comprising a plurality of nodes representing a plurality of entities of a building and a plurality of edges between the plurality of nodes representing a plurality of relationships between the plurality of entities of the building;

executing, using at least one of the at least one node or the at least one edge, a machine learning model to classify a state of an entity of the plurality of entities of the building; and

updating a current state of the entity using the classified state.

20 . The one or more non-transitory storage media of claim 19 , wherein the entity is a space of the building;

the operations further comprising classifying the space as occupied or unoccupied.