US-12619957-B2 - Building management system with generative AI-based automated flexible customer report generation

US12619957B2US 12619957 B2US12619957 B2US 12619957B2US-12619957-B2

Abstract

A method includes receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing building equipment. The unstructured service report may include unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats. The method may include automatically generating, by the one or more processors using a generative AI model, a structured service report in the predetermined format for delivery to a customer associated with the building equipment. The structured service report may include additional content generated by the generative AI model and not provided within the unstructured service report.

Inventors

Julie J. Brown
Miguel Galvez
Trent M. Swanson
John F. Kuchler
Deepak Budhiraja
Daniela M. Natali
Josip Lazarevski
Scott Deering
Gary W. Gavin
Kristen Sheppard-Guzelaydin
James Young
Young M. Lee
Prashanthi Sudhakar
Kaleb Luedtke
Karl F. Reichenberger
Wenwen Zhao
Adam R. Grabowski
Lauren C. Dern
Nicole A. Madison
Dana S. Petersen
Nevin L. Forry
Pedriant PENA
Rajiv Ramanasankaran
Ghassan R. Hamoudeh
Ryan G. Danielson
Sastry KM Malladi
Michael Tenbrock
Levent Tinaz
Samuel A. Girard
David S. Elario
Juliet A. Pagliaro Herman

Assignees

TYCO FIRE & SECURITY GMBH

Dates

Publication Date: 20260505
Application Date: 20240411

Claims (16)

1 . A method comprising: receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing building equipment comprising HVAC equipment, the unstructured service report comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats; analyzing, by the one or more processors, the unstructured data in the unstructured service report to extract an identifier of the HVAC equipment, a building space, or a customer from the unstructured data in the unstructured service report; obtaining, by the one or more processors, operating data generated by operating the HVAC equipment to affect a state of air within a building, the operating data obtained from one or more additional data sources separate from the unstructured service report and identified using the identifier of the HVAC equipment, the building space, or the customer extracted from the unstructured data in the unstructured service report; automatically generating, by the one or more processors using a generative AI model, a structured service report in the predetermined format for delivery to a customer associated with the HVAC equipment by transforming the unstructured service report into the structured service report, wherein the structured service report comprises additional content generated by the generative AI model based on the operating data and not provided within the unstructured service report, wherein automatically generating the structured service report comprises: cross-referencing metadata associated with two or more unstructured data elements of the unstructured service report to determine whether the two or more unstructured data elements are related, the metadata comprising timestamps indicating times at which the two or more unstructured data elements are generated or location attributes indicating spatial locations in a building or campus at which the two or more unstructured data elements are generated; generating two or more structured data elements of the structured service report based on the two or more unstructured data elements; and associating the two or more structured data elements with each other in the structured service report in response to determining that the two or more unstructured data elements are related by comparing the timestamps or the location attributes; and presenting, by the one or more processors, the structured service report in a graphical user interface including the additional content comprising trend information generated by the generative AI model based on time series data for a point associated with the HVAC equipment and included in the operating data.
2 . The method of claim 1 , wherein associating the two or more structured data elements with each other in the structured service report comprises placing the two or more structured data elements in proximity to each other in the structured service report.
3 . The method of claim 1 , wherein associating the two or more structured data elements with each other in the structured service report comprises adding a label to a first structured data element of the two or more structured data elements in the structured service report, the label referring to a second data element of the two or more structured data elements in the structured service report.
4 . The method of claim 1 , further comprising training, by the one or more processors, the generative AI model using training data comprising a plurality of unstructured service reports corresponding to a plurality of service requests handled by technicians for servicing the HVAC equipment, the training data not conforming to the predetermined format or conforming to the plurality of different predetermined formats.
5 . The method of claim 1 , wherein automatically generating the structured service report comprises: identifying a customer, a building, or a type of the HVAC equipment associated with the service request; selecting a predefined template for the structured service report from a set of multiple predefined templates based on the identified customer, building, or type of the HVAC equipment; and generating the structured service report to conform to the predefined template.
6 . The method of claim 1 , further comprising receiving, by the one or more processors, additional data from the one or more additional data sources separate from the unstructured service report; wherein automatically generating the structured service report comprises using the additional data to generate the additional content not provided within the unstructured service report.
7 . The method of claim 6 , wherein: the additional data comprise the operational data generated during operation of the HVAC equipment; and generating the additional content comprises using the operational data to construct the one or more charts, graphs, tables, or graphical data elements in the structured service report.
8 . The method of claim 1 , wherein automatically generating the structured service report comprises using the generative AI model to identify new correlations and/or patterns between two or more unstructured data elements of the unstructured service report.
9 . The method of claim 1 , further comprising: receiving, by the one or more processors, feedback indicating a quality of the structured service report; and configuring or updating, by the one or more processors, the generative AI model using the feedback.
10 . The method of claim 9 , wherein the feedback comprises user input from one or more subject matter experts, the user input comprising at least one of: binary feedback associating the structured service report with a predetermined binary category; technical feedback indicating whether the structured service report satisfies technical accuracy or precision criteria; score feedback assigning a score to the structured service report on a predetermined scale; or freeform feedback from the one or more subject matter experts.
11 . A method comprising: receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing HVAC equipment, the unstructured service report comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats; analyzing, by the one or more processors, the unstructured data in the unstructured service report to extract an identifier of the HVAC equipment, a building space, or a customer from the unstructured data in the unstructured service report; obtaining, by the one or more processors, operating data generated by operating the HVAC equipment to affect a state of air within a building, the operating data obtained from one or more additional data sources separate from the unstructured service report and identified using the identifier of the HVAC equipment, the building space, or the customer extracted from the unstructured data in the unstructured service report; automatically generating, by the one or more processors using a machine learning model, a structured service report in the predetermined format for delivery to a customer associated with the HVAC equipment by transforming the unstructured service report into the structured service report, wherein the structured service report comprises additional content generated by the machine learning model and not provided within the unstructured service report, wherein automatically generating the structured service report comprises: cross-referencing metadata associated with two or more unstructured data elements of the unstructured service report to determine whether the two or more unstructured data elements are related; generating two or more structured data elements of the structured service report based on the two or more unstructured data elements; and associating the two or more structured data elements with each other in the structured service report in response to determining that the two or more unstructured data elements are related by placing the two or more structured data elements in proximity to each other in the structured service report; and presenting, by the one or more processors, the structured service report in a graphical user interface including the additional content comprising trend information generated by the machine learning model based on time series data for a point associated with the HVAC equipment and included in the operating data.
12 . The method of claim 11 , wherein: the metadata comprise timestamps indicating times at which the two or more unstructured data elements are generated; and determining that the two or more unstructured data elements are related comprises comparing the timestamps.
13 . The method of claim 11 , wherein: the metadata comprise location attributes indicating spatial locations in a building or campus at which the two or more unstructured data elements are generated; and determining that the two or more unstructured data elements are related comprises comparing the location attributes.
14 . The method of claim 11 , wherein associating the two or more structured data elements with each other in the structured service report comprises adding a label to a first structured data element of the two or more structured data elements in the structured service report, the label referring to a second data element of the two or more structured data elements in the structured service report.
15 . The method of claim 11 , wherein automatically generating the structured service report comprises: identifying a customer, a building, or a type of the HVAC equipment associated with the service request; selecting a predefined template for the structured service report from a set of multiple predefined templates based on the identified customer, building, or type of the HVAC equipment; and generating the structured service report to conform to the predefined template.
16 . A method comprising: receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing building equipment comprising HVAC equipment, the unstructured service report comprising unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats; analyzing, by the one or more processors, the unstructured data in the unstructured service report to extract an identifier of the HVAC equipment, a building space, or a customer from the unstructured data in the unstructured service report; obtaining, by the one or more processors, operating data generated by operating the HVAC equipment to affect a state of air within a building, the operating data obtained from one or more additional data sources separate from the unstructured service report and identified using the identifier of the HVAC equipment, the building space, or the customer extracted from the unstructured data in the unstructured service report; automatically generating, by the one or more processors using a generative AI model, a structured service report in the predetermined format for delivery to a customer associated with the HVAC equipment by transforming the unstructured service report into the structured service report, wherein the structured service report comprises additional content generated by the generative AI model based on the operating data and not provided within the unstructured service report, wherein automatically generating the structured service report comprises: cross-referencing metadata associated with two or more unstructured data elements of the unstructured service report to determine whether the two or more unstructured data elements are related; generating two or more structured data elements of the structured service report based on the two or more unstructured data elements; and associating the two or more structured data elements with each other in the structured service report in response to determining that the two or more unstructured data elements are related by adding a label to a first structured data element of the two or more structured data elements in the structured service report, the label referring to a second data element of the two or more structured data elements in the structured service report; and presenting, by the one or more processors, the structured service report in a graphical user interface including the additional content comprising trend information generated by the generative AI model based on time series data for a point associated with the HVAC equipment and included in the operating data.

Description

CROSS-REFERENCE TO RELATED PATENT APPLICATIONS This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63/458,871 filed Apr. 12, 2023, and U.S. Provisional Patent Application No. 63/470,078 filed May 31, 2023, both of which are incorporated by reference herein in their entireties. BACKGROUND The present disclosure relates generally to a building system of a building. The present disclosure relates more particularly to systems for managing and processing data of the building system. Various interactions between building systems, components of building systems, users, technicians, and/or devices managed by users or technicians can rely on timely generation and presentation of data relating to the interactions, including for performing service operations. However, it can be difficult to generate the data elements to precisely identify proper response actions or sequences of response actions, as well as options for modified response actions, depending on various factors associated with items of equipment to be serviced, technical issues with the items of equipment, and the availability of timely, precise data to use for supporting the service operations. SUMMARY Implementations of the present disclosure relate to building management systems and methods that implement building equipment servicing. For example, a system can include at least one machine learning model configured using training data that includes at least one of unstructured data or structured data regarding items of equipment. The system can provide inputs, such as prompts, to the at least one machine learning model regarding an item of equipment, and generate, according to the inputs, responses regarding the item of equipment, such as responses for detecting a cause of an issue of the item of equipment, performing a service operation corresponding to the cause, or guiding a user through the service operation. The machine learning model can include various machine learning model architectures (e.g., networks, backbones, algorithms, etc.), including but not limited to language models, LLMs, attention-based neural networks, transformer-based neural networks, generative pretrained transformer (GPT) models, bidirectional encoder representations from transformers (BERT) models, encoder/decoder models, sequence to sequence models, autoencoder models, generative adversarial networks (GANs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), diffusion models (e.g., denoising diffusion probabilistic models (DDPMs)), or various combinations thereof. One implementation of the present disclosure is a method including receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing building equipment. The unstructured service report may include unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats. The method may include automatically generating, by the one or more processors using a generative AI model, a structured service report in the predetermined format for delivery to a customer associated with the building equipment. The structured service report may include additional content generated by the generative AI model and not provided within the unstructured service report. In some embodiments, automatically generating the structured service report includes cross-referencing metadata associated with two or more unstructured data elements of the unstructured service report to determine whether the two or more unstructured data elements are related, generating two or more structured data elements of the structured service report based on the two or more unstructured data elements, and associating the two or more structured data elements with each other in the structured service report in response to determining that the two or more unstructured data elements are related. In some embodiments, the metadata include timestamps indicating times at which the two or more unstructured data elements are generated. In some embodiments, determining that the two or more unstructured data elements are related includes comparing the timestamps. In some embodiments, the metadata include location attributes indicating spatial locations in a building or campus at which the two or more unstructured data elements are generated. In some embodiments, determining that the two or more unstructured data elements are related includes comparing the location attributes. In some embodiments, associating the two or more structured data elements with each other in the structured service report includes placing the two or more structured data elements in proximity to each other in the structured service report. In some embodiments, associating the two or more structured data elements with each other in the structured service report includes adding a label to a first structured