Tyco Fire & Security GmbH (20240346459). BUILDING MANAGEMENT SYSTEM WITH GENERATIVE AI-BASED AUTOMATED MAINTENANCE SERVICE SCHEDULING AND MODIFICATION simplified abstract

BUILDING MANAGEMENT SYSTEM WITH GENERATIVE AI-BASED AUTOMATED MAINTENANCE SERVICE SCHEDULING AND MODIFICATION

Organization Name

Tyco Fire & Security GmbH

Inventor(s)

Julie J. Brown of Yardley PA (US)

Young M. Lee of Old Westbury NY (US)

Rajiv Ramanasankaran of San Jose CA (US)

Sastry KM Malladi of Fremont CA (US)

Michael Tenbrock of Dachsen (CH)

Levent Tinaz of Tampa Bay FL (US)

Samuel A. Girard of Kenosha WI (US)

David S. Elario of Hartland WI (US)

Juliet A. Pagliaro Herman of Waukesha WI (US)

Miguel Galvez of Westford MA (US)

Trent M. Swanson of Wellington FL (US)

John F. Kuchler of Muskego WI (US)

Deepak Budhiraja of Ashburn VA (US)

Daniela M. Natali of Kensington MD (US)

Josip Lazarevski of Zurich (CH)

Scott Deering of Milwaukee WI (US)

Gary W. Gavin of Franklin WI (US)

Kristen Sheppard-guzelaydin of West Chester PA (US)

James Young of Cork (IE)

Prashanthi Sudhakar of San Francisco CA (US)

Kaleb Luedtke of West Bend WI (US)

Karl F. Reichenberger of Mequon WI (US)

Wenwen Zhao of Santa Clara CA (US)

Adam R. Grabowski of Brookfield WI (US)

Lauren C. Dern of Fox Point WI (US)

Nicole A. Madison of Milwaukee WI (US)

Dana S. Petersen of Milwaukee WI (US)

Nevin L. Forry of York PA (US)

Pedriant Pena of Groveland MA (US)

Ghassan R. Hamoudeh of San Marcos CA (US)

Ryan G. Danielson of Castle Rock CO (US)

BUILDING MANAGEMENT SYSTEM WITH GENERATIVE AI-BASED AUTOMATED MAINTENANCE SERVICE SCHEDULING AND MODIFICATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240346459 titled 'BUILDING MANAGEMENT SYSTEM WITH GENERATIVE AI-BASED AUTOMATED MAINTENANCE SERVICE SCHEDULING AND MODIFICATION

The method described in the abstract involves training a generative AI model using data from service requests handled by technicians for building equipment maintenance, in order to predict outcomes based on request characteristics.

• Training a generative AI model with data from service requests
• Identifying patterns between request characteristics and outcomes
• Using the AI model to determine responses to new service requests
• Automating decision-making based on past data and trends

Potential Applications: - Predictive maintenance for building equipment - Optimizing technician response to service requests - Improving overall efficiency and effectiveness of maintenance operations

Problems Solved: - Enhancing decision-making in building equipment servicing - Streamlining maintenance processes - Reducing downtime and improving equipment reliability

Benefits: - Cost savings through predictive maintenance - Increased equipment uptime and longevity - Enhanced customer satisfaction through faster and more accurate service

Commercial Applications: Predictive maintenance software for building management companies, facility maintenance providers, and equipment manufacturers.

Questions about the technology: 1. How does the generative AI model improve decision-making in building equipment maintenance? 2. What are the key factors considered by the AI model when predicting outcomes of service requests?

Original Abstract Submitted

a method includes training, by one or more processors, a generative ai model using a plurality of first service requests handled by technicians for servicing building equipment and outcome data indicating outcomes of the plurality of first service requests. the generative ai model may be trained to identify one or more patterns or trends between characteristics of the plurality of first service requests and the outcomes of the plurality of first service requests. the method may include receiving a second service request for servicing building equipment. the method may include automatically determining, using the generative ai model, one or more responses to the second service request based on characteristics of the second service request and the one or more patterns or trends between the characteristics of the plurality of first service requests and the outcomes of the plurality of first service requests identified using the generative ai model.