Building management system with generative AI-based root cause prediction
A method including training, by one or more processors, a generative AI model using a plurality of first service requests handled by technicians for servicing building equipment. The generative AI model may be trained to predict root causes of a plurality of first problems corresponding to the plurality of first service requests. The method may include receiving, by the one or more processors, a second service request for servicing building equipment. The method may include predicting, by the one or more processors using the generative AI model, a root cause of a second problem corresponding to the second service request based on characteristics of the second service request and one or more patterns or trends identified from the plurality of first service requests using the generative AI model.
1. A method comprising:
training, by one or more processors, a generative AI model using a plurality of first service requests handled by technicians for servicing building equipment, the generative AI model trained to predict root causes of a plurality of first problems corresponding to the plurality of first service requests;
receiving, by the one or more processors, outcome data indicating whether the predicted root causes of the plurality of first problems using the generative AI model were determined to be actual root causes of the plurality of first problems after performing service on the building equipment in response to the plurality of first service requests;
retraining the generative AI model using the outcome data;
receiving, by the one or more processors, a second service request for servicing building equipment; and
predicting, by the one or more processors using the generative AI model, a root cause of a second problem corresponding to the second service request based on characteristics of the second service request and one or more patterns or trends identified from the plurality of first service requests using the generative AI model.
2. The method of claim 1 , wherein training the generative AI model comprises:
receiving a plurality of first unstructured service reports corresponding to the plurality of first service requests, the plurality of first unstructured service reports comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats; and
training the generative AI model using the plurality of first unstructured service reports.
3. The method of claim 1 , wherein training the generative AI model comprises:
generating, by the one or more processors using the generative AI model, a plurality of structured service reports corresponding to the plurality of first service requests, the plurality of structured service reports comprising structured data having a predetermined format; and
training the generative AI model using the plurality of structured service reports.
4. The method of claim 1 , further comprising receiving, by the one or more processors, outcome data indicating outcomes of the plurality of first service requests;
wherein the generative AI model is trained to identify the one or more patterns or trends between the plurality of first problems corresponding to the plurality of first service requests and the outcome data indicating the outcomes of the plurality of first service requests.
5. The method of claim 1 , further comprising receiving, by the one or more processors, additional data comprising engineering data indicating characteristics of the building equipment, the engineering data comprising one or more user manuals, operating guides, engineering drawings, process flow diagrams, or equipment specifications describing the building equipment or operation thereof;
wherein predicting the root cause of the second problem comprises using the engineering data in combination with data from the second service request to determine one or more potential root causes of the second problem.
6. The method of claim 1 , further comprising receiving, by the one or more processors, additional data comprising operational data generated during operation of the building equipment or based on data generated during operation of the building equipment, the operational data comprising one or more of timeseries data, sensor data, logged data, user reports, technician reports, service tickets, work orders, billing records, time sheets, or event data associated with the building equipment;
wherein predicting the root cause of the second problem comprises using the operational data in combination with data from the second service request to determine one or more potential root causes of the second problem.
7. The method of claim 1 , further comprising obtaining, by the one or more processors, one or more diagnostic models configured to predict one or more potential root causes of the second problem based on a set of structured data inputs;
wherein predicting the root cause of the second problem comprises (i) using the generative AI model to transform unstructured data corresponding to the second service request into the set of structured data inputs and (ii) providing the set of structured data inputs as inputs to the one or more diagnostic models.
8. The method of claim 1 , further comprising automatically determining, by the one or more processors using the generative AI model, one or more responses to the second service request based on the root cause of the second problem predicted by the generative AI model.
9. The method of claim 1 , wherein the second service request comprises one or more attributes included in the plurality of first services requests.
10. The method of claim 1 , further comprising identifying, by the one or more processors, information not yet provided that would allow the generative AI model to exclude or confirm one or more potential root causes as the root cause of the second problem predicted by the generative AI model if the information were provided.
11. The method of claim 1 , wherein the generative AI model comprises at least one of a transformer, an encoder, or a generative adversarial network.
12. A method comprising:
obtaining, by one or more processors, a generative AI model trained to predict root causes of a plurality of first problems corresponding to a plurality of first service requests handled by technicians for servicing building equipment;
receiving, by the one or more processors, outcome data indicating whether the predicted root causes of the plurality of first problems using the generative AI model were determined to be actual root causes of the plurality of first problems after performing service on the building equipment in response to the plurality of first service requests;
training, by the one or more processors, the generative AI model using the outcome data;
receiving, by the one or more processors, a second service request for servicing building equipment; and
predicting, by the one or more processors using the generative AI model, a root cause of a second problem corresponding to the second service request based on characteristics of the second service request and one or more patterns or trends identified from the plurality of first service requests using the generative AI model.
13. The method of claim 12 , wherein the generative AI model is trained to predict the root causes of the plurality of first problems based on a plurality of first unstructured service reports corresponding to the plurality of first service requests, the plurality of first unstructured service reports comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats.
14. The method of claim 12 , wherein the generative AI model is trained to predict the root causes of the plurality of first problems based on a plurality of structured service reports corresponding to the plurality of first service requests, the plurality of structured service reports comprising structured data having a predetermined format.
15. The method of claim 12 , further comprising receiving, by the one or more processors, outcome data indicating outcomes of the plurality of first service requests;
wherein the generative AI model is trained to identify the one or more patterns or trends between the plurality of first problems corresponding to the plurality of first service requests and the outcome data indicating the outcomes of the plurality of first service requests.
16. The method of claim 12 , further comprising receiving, by the one or more processors, additional data comprising operational data generated during operation of the building equipment or based on data generated during operation of the building equipment, the operational data comprising one or more of timeseries data, sensor data, logged data, user reports, technician reports, service tickets, work orders, billing records, time sheets, or event data associated with the building equipment;
wherein predicting the root cause of the second problem comprises using the operational data in combination with data from the second service request to determine one or more potential root causes of the second problem.
17. The method of claim 12 , further comprising obtaining, by the one or more processors, one or more diagnostic models configured to predict one or more potential root causes of the second problem based on a set of structured data inputs;
wherein predicting the root cause of the second problem comprises (i) using the generative AI model to transform unstructured data corresponding to the second service request into the set of structured data inputs and (ii) providing the set of structured data inputs as inputs to the one or more diagnostic models.
18. The method of claim 12 , further comprising automatically determining, by the one or more processors using the generative AI model, one or more responses to the second service request based on the root cause of the second problem predicted by the generative AI model.
19. A method comprising:
training, by one or more processors, a machine learning model using a plurality of first service requests handled by technicians for servicing building equipment, the machine learning model trained to predict root causes of a plurality of first problems corresponding to the plurality of first service requests;
receiving, by the one or more processors, outcome data indicating whether the predicted root causes of the plurality of first problems using the machine learning model were determined to be actual root causes of the plurality of first problems after performing service on the building equipment in response to the plurality of first service requests;
retraining the machine learning model using the outcome data;
receiving, by the one or more processors, a second service request for servicing building equipment; and
predicting, by the one or more processors using the machine learning model, a root cause of a second problem corresponding to the second service request based on characteristics of the second service request and one or more patterns or trends identified from the plurality of first service requests using the machine learning model.
20. The method of claim 19 , wherein training the machine learning model comprises:
receiving a plurality of first unstructured service reports corresponding to the plurality of first service requests, the plurality of first unstructured service reports comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats; and
training the machine learning model using the plurality of first unstructured service reports.
21. The method of claim 19 , wherein training the machine learning model comprises:
generating, by the one or more processors using the machine learning model, a plurality of structured service reports corresponding to the plurality of first service requests, the plurality of structured service reports comprising structured data having a predetermined format; and
training the machine learning model using the plurality of structured service reports.
22. The method of claim 19 , further comprising receiving, by the one or more processors, outcome data indicating outcomes of the plurality of first service requests;
wherein the machine learning model is trained to identify the one or more patterns or trends between the plurality of first problems corresponding to the plurality of first service requests and the outcome data indicating the outcomes of the plurality of first service requests.
23. The method of claim 19 , further comprising receiving, by the one or more processors, additional data comprising engineering data indicating characteristics of the building equipment, the engineering data comprising one or more user manuals, operating guides, engineering drawings, process flow diagrams, or equipment specifications describing the building equipment or operation thereof;
wherein predicting the root cause of the second problem comprises using the engineering data in combination with data from the second service request to determine one or more potential root causes of the second problem.
24. The method of claim 19 , further comprising receiving, by the one or more processors, additional data comprising operational data generated during operation of the building equipment or based on data generated during operation of the building equipment, the operational data comprising one or more of timeseries data, sensor data, logged data, user reports, technician reports, service tickets, work orders, billing records, time sheets, or event data associated with the building equipment;
wherein predicting the root cause of the second problem comprises using the operational data in combination with data from the second service request to determine one or more potential root causes of the second problem.
25. The method of claim 19 , further comprising receiving, by the one or more processors, additional data comprising parts data indicating parts usage associated with the building equipment, the parts data indicating one or more of parts of the building equipment; tools required to install, repair, or replace the parts; suppliers of the parts; or service providers capable of installing, repairing, or replacing the parts;
wherein predicting the root cause of the second problem comprises using the parts data in combination with data from the second service request to determine one or more potential root causes of the second problem.
26. The method of claim 19 , further comprising obtaining, by the one or more processors, one or more diagnostic models configured to predict one or more potential root causes of the second problem based on a set of structured data inputs;
wherein predicting the root cause of the second problem comprises (i) using the machine learning model to transform unstructured data corresponding to the second service request into the set of structured data inputs and (ii) providing the set of structured data inputs as inputs to the one or more diagnostic models.
27. The method of claim 19 , further comprising automatically determining, by the one or more processors using the machine learning model, one or more responses to the second service request based on the root cause of the second problem predicted by the machine learning model.