US 12,455,896 B2
Building management system with generative AI-based interactive service tool
Julie J. Brown, Yardley, PA (US); Young M. Lee, Old Westbury, NY (US); Rajiv Ramanasankaran, San Jose, CA (US); Sastry KM Malladi, Fremont, CA (US); Michael Tenbrock, Dachsen (CH); Levent Tinaz, Tampa Bay, FL (US); Samuel A. Girard, Kenosha, WI (US); David S. Elario, Hartland, WI (US); Juliet A. Pagliaro Herman, Waukesha, WI (US); Miguel Galvez, Westford, MA (US); Trent M. Swanson, Wellington, FL (US); John F. Kuchler, Muskego, WI (US); Deepak Budhiraja, Ashburn, VA (US); Daniela M. Natali, Kensington, MD (US); Josip Lazarevski, Zurich (CH); Scott Deering, Milwaukee, WI (US); Gary W. Gavin, Franklin, WI (US); Kristen Sheppard-Guzelaydin, West Chester, PA (US); James Young, Cork (IE); Prashanthi Sudhakar, San Francisco, CA (US); Kaleb Luedtke, West Bend, WI (US); Karl F. Reichenberger, Mequon, WI (US); Wenwen Zhao, Santa Clara, CA (US); Adam R. Grabowski, Brookfield, WI (US); Lauren C. Dern, Fox Point, WI (US); Nicole A. Madison, Milwaukee, WI (US); Dana S. Petersen, Milwaukee, WI (US); Nevin L. Forry, York, PA (US); Pedriant Pena, Groveland, MA (US); Ghassan R. Hamoudeh, San Marcos, CA (US); and Ryan G. Danielson, Castle Rock, CO (US)
Assigned to TYCO FIRE & SECURITY GMBH, Neuhausen am Rheinfall (CH)
Filed by Tyco Fire & Security GmbH, Neuhausen am Rheinfall (CH)
Filed on Jan. 22, 2024, as Appl. No. 18/419,449.
Claims priority of provisional application 63/470,120, filed on May 31, 2023.
Claims priority of provisional application 63/458,871, filed on Apr. 12, 2023.
Prior Publication US 2024/0346036 A1, Oct. 17, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 11/07 (2006.01); G06F 16/25 (2019.01); G06F 16/3329 (2025.01)
CPC G06F 16/258 (2019.01) [G06F 11/079 (2013.01); G06F 16/3329 (2019.01)] 24 Claims
OG exemplary drawing
 
1. A method comprising:
training, by one or more processors, a generative AI model using a plurality of first historical unstructured service reports corresponding to a plurality of first historical service requests handled by technicians for servicing building equipment and outcome data indicating whether historical service actions performed in response to the plurality of first historical service requests were successful in resolving historical problems leading to the plurality of first historical service requests, the plurality of first historical unstructured service reports comprising unstructured data not conforming to a first predetermined format comprising one or more predetermined fields or locations and one or more predetermined labels or identifiers characterizing the one or more predetermined fields or locations or conforming to a plurality of different predetermined formats other than the first predetermined format, wherein the training transforms the generative AI model into a trained generative AI model;
receiving, by the one or more processors after training the generative AI model, a new service request comprising a new request to perform service on building equipment;
generating, by the one or more processors using the trained generative AI model, a user interface prompting a user to provide information describing a new problem associated with the building equipment and leading to the new service request as unstructured data not conforming to the first predetermined format or conforming to the plurality of different predetermined formats;
determining, by the one or more processors using the trained generative AI model, one or more actions to address the new problem based on the information provided via the user interface, wherein using the trained generative AI model to determine the one or more actions comprises:
providing at least one of the new service request or the information provided via the user interface as input to the trained generative AI model,
executing the trained generative AI model to transform at least one of the new service request or the information provided via the user interface into the one or more actions to address the new problem leading to the new service request based on one or more patterns or correlations between the historical service actions performed in response to the plurality of historical service requests and respective outcomes of the historical service actions performed in response to the plurality of historical service requests indicated by the outcome data, wherein executing the trained generative AI model comprises (i) obtaining, by the one or more processors, one or more diagnostic models configured to predict one or more potential root causes of the new problem based on a set of structured data inputs, (ii) transforming the unstructured data received via the user interface into the set of structured data inputs and providing the set of structured data inputs as inputs to the one or more diagnostic models, (iii) receiving, by the one or more processors, a set of structured data outputs from the one or more diagnostic models configured to predict the one or more potential root causes of the new problem based on the set of structured data inputs, and (iv) transforming the structured data outputs from the one or more diagnostic models into a natural language response to the new service request and presenting the natural language response via the user interface, and
providing the natural language response comprising an indication of the one or more actions to address the new problem as output from the trained generative AI model; and
performing the one or more actions to address the new problem, the one or more actions comprising at least one of performing service on one or more components of the building equipment associated with the one or more potential root causes of the new problem, repairing or replacing the building equipment or the one or more components of the building equipment associated with the one or more potential root causes of the new problem, shutting down the building equipment to resolve the one or more potential root causes of the new problem, operating the building equipment using a different control strategy predicted to resolve the one or more potential root causes of the new problem, adjusting operation of the building equipment or other equipment to resolve the one or more potential root causes of the new problem, or installing new equipment to supplement or replace the building equipment to resolve the one or more potential root causes of the new problem.