ALARM MONITORING AND EVALUATION SYSTEMS AND METHODS

20250111282

18/899844

September 27, 2024

At least one processor may receive vent data describing a plurality of events related to equipment managed by a building management system. The at least one processor may process the event data using at least one machine learning model. Outputs of the at least one machine learning model may include at least a priority label and a probability score for each respective event in the event data. The at least one processor may generate a user interface within the building management system. The user interface may indicate at least the priority label and the probability score for at least one of the events.

CBRE, INC. (DALLAS, TX, US)

1. A method comprising: receiving, by at least one processor, event data describing a plurality of events related to equipment managed by a building management system (BMS); processing, by the at least one processor, the event data using at least one machine learning (ML) model, wherein outputs of the at least one ML model include at least a priority label and a probability score for each respective event in the event data; generating, by the at least one processor, a user interface within the BMS, the user interface indicating at least the priority label and the probability score for at least one of the events; and causing, by the at least one processor, display of the user interface.

2. The method of claim 1, further comprising clustering, by the at least one processor, the event data to correlate indications of at least one specific event prior to the processing and produce at least an alarm count for the at least one specific event.

3. The method of claim 2, wherein the clustering comprises at least one of applying a clustering rule and processing the event data using a ML clustering algorithm.

4. The method of claim 1, wherein the event data includes at least one of alarm name, alarm site, alarm priority, alarm timestamp, alarm count, and alarm frequency.

5. The method of claim 1, further comprising reranking, by the at least one processor, at least one of the events prior to the generating.

6. The method of claim 5, wherein the reranking comprises overriding a priority label for at least one of an event with an existing work order and an event for equipment having a critical status.

7. The method of claim 1, further comprising generating, by the at least one processor, a work order within the BMS in response to a priority label having a high status and a probability score being above a threshold value for at least one of the events.

8. The method of claim 1, wherein the user interface displays data for events having a high status and a probability score above a threshold value while suppressing display of data for events having a low status.

9. The method of claim 1, further comprising tuning, by the at least one processor, the at least one ML model to weight respective categories of event data.

10. The method of claim 1, further comprising training, by the at least one processor, the at least one ML model using labeled historical and/or simulated event data.

11. A system comprising: at least one processor; and at least one non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform processing comprising: processing event data describing a plurality of events related to equipment managed by a building management system (BMS) using at least one machine learning (ML) model, wherein outputs of the at least one ML model include at least a priority label and a probability score for each respective event in the event data; generating a user interface within the BMS, the user interface indicating at least the priority label and the probability score for at least one of the events; and causing display of the user interface.

12. The system of claim 11, wherein the processing further comprises clustering the event data to correlate indications of at least one specific event prior to the processing and produce at least an alarm count for the at least one specific event.

13. The system of claim 12, wherein the clustering comprises at least one of applying a clustering rule and processing the event data using a ML clustering algorithm.

14. The system of claim 11, wherein the event data includes at least one of alarm name, alarm site, alarm priority, alarm timestamp, alarm count, and alarm frequency.

15. The system of claim 11, wherein the processing further comprises reranking at least one of the events prior to the generating.

16. The system of claim 15, wherein the reranking comprises overriding a priority label for at least one of an event with an existing work order and an event for equipment having a critical status.

17. The system of claim 11, wherein the processing further comprises generating a work order within the BMS in response to a priority label having a high status and a probability score being above a threshold value for at least one of the events.

18. The system of claim 11, wherein the user interface displays data for events having a high status and a probability score above a threshold value while suppressing display of data for events having a low status.

19. The system of claim 11, wherein the processing further comprises tuning the at least one ML model to weight respective categories of event data.

20. The system of claim 11, wherein the processing further comprises training the at least one ML model using labeled historical and/or simulated event data.

06; 06; 06

edspap.20250111282