Abstract: A method includes fine-tuning at least one large language model (LLM) using building domain data comprising information regarding equipment types, equipment parameters, and output conditions, facilitating generation of an input query for the at least one LLM by providing an interactive interface configured to guide input of a relevant equipment type, a relevant equipment parameter, a relevant output condition, and a request type by a user and generating the input query based on the input of the relevant equipment type, the relevant equipment parameter, the relevant output condition, and the request type, and providing a response to the input query as an output of the at least one LLM by using the input query as an input to the LLM.

Abstract: Systems and methods are disclosed relating to building management systems with 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.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed by one or more processors, cause the one or more processors to receive training data including acronym strings and tag strings, train a sequence to sequence neural network based on the training data, receive an acronym string for labeling, the acronym string comprising a particular plurality of acronyms, and generate a tag string for the acronym string with the sequence to sequence neural network, wherein the sequence to sequence neural network outputs a tag of the tag string for one acronym of the particular plurality of acronyms based on the one acronym and contextual information of the acronym string, wherein the contextual information includes other acronyms of the particular plurality of acronyms.

Abstract: 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.

Abstract: A method includes receiving, by one or more processors, a plurality of first unstructured service reports corresponding to a plurality of first service requests handled by technicians for servicing building equipment. The plurality of first unstructured service reports may include unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats. The method may include training, by the one or more processors, a generative AI model using the plurality of first unstructured service reports. The method may include performing, by the one or more processors using the trained generative AI model, one or more actions with respect a second service request subsequent to training the generative AI model.

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 extracting, by the one or more processors, a set of standards from one or more technical documents associated with the building equipment. 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. Generating the structured service report may include standardizing the structured service report to comply with the set of standards extracted from the one or more technical documents associated with the building equipment.

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.

Abstract: A method including training, by one or more processors, a generative AI model using first operating data from building equipment and a plurality of first service reports indicating a plurality of first problems associated with the building equipment. The method may include predicting, by the one or more processors using the generative AI model, one or more future problems likely to occur with the building equipment based on second operating data from the building equipment. The method may include automatically initiating, by the one or more processors, one or more actions to prevent the one or more future problems from occurring or mitigate an effect of the one or more future problems.

Abstract: 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.

Abstract: A method includes receiving, by one or more processors, unstructured service data corresponding to one or more service requests handled by technicians for servicing building equipment of a building. The method may include detecting, by the one or more processors, an identifier of the building equipment, a space of the building, or a customer associated with the building using the unstructured service data. The method may include retrieving, by the one or more processors based on the identifier of the building equipment, the space, or the customer, additional data associated with the building equipment, the space, or the customer from one or more additional data sources separate from the unstructured service data. The method may include training, by the one or more processors, a generative AI model using training data including the unstructured service data and the additional data.

Abstract: A method including training, by one or more processors, a generative AI model using a plurality of first unstructured service reports corresponding to a plurality of first service requests handled by technicians for servicing building equipment. The plurality of first unstructured service reports include unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats. The method includes receiving, by the processors, a second service request for servicing building equipment. The method includes generating, by the processors using the generative AI model, a user interface prompting a user to provide information about a problem leading to the second service request as unstructured data not conforming to the predetermined format or conforming to the plurality of different predetermined formats.

Abstract: A method includes training, by one or more processors, a generative AI model using training data including a plurality of first service requests indicating a plurality of first problems associated with building equipment and a plurality of first actions performed in response to the plurality of first service requests. The method may include receiving, by the one or more processors, a second service request indicating a second problem associated with building equipment. The method may include automatically determining, by the one or more processors using the generative AI model, one or more second actions to perform based on characteristics of the second service request. The method may include automatically initiating, by the one or more processors, the one or more second actions to address the second problem associated with the building equipment.

Abstract: A building management system for a building including one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to ingest event information from at least one of a building system or an external computing system, enrich the event information based on a digital twin associated with the event information, wherein enriching the event information includes adding contextual information to the event information based on the digital twin to generate enriched event information, generate a predicted parameter that will result from a control decision for operating at least one of the building system or a different building system based on the enriched event information, and modify the control decision based on the predicted parameter.

Abstract: A building system of a building including one or more memory devices having instructions thereon, that, when executed by one or more processors, cause the one or more processors to receive tags describing points of the building. The instructions cause the one or more processors to map the tags to classes of a schema of a graph data structure, perform clustering to generate clusters of the points. The instructions cause the one or more processors to identify, based on the clusters, relationships in the schema of the graph data structure between the tags mapped to the classes of the schema of the graph data structure. The instructions cause the one or more processors to construct the graph data structure in the schema based on the tags mapped to the classes and the relationships in the schema of the graph data structure.

Abstract: A model management system for building equipment includes one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to determine whether fault data exists in equipment data used to generate a plurality of shutdown prediction models for the building equipment, generate a first performance evaluation value for each of the plurality of shutdown prediction models using a first evaluation technique in response to a determination that the fault data exists in the equipment data, generate a second performance evaluation value for each of the plurality of shutdown prediction models using a second evaluation technique in response to a determination that the fault data does not exist in the equipment data, and select one of the plurality of shutdown prediction models based on the first performance evaluation value and the second performance evaluation value.

Abstract: A method is provided for achieving a net energy goal for building operations for a time period including a first subperiod before a current time and a second subperiod from the current time to an end of the time period. The method includes generating first forecasted ranges for amounts of energy consumption for a plurality of time steps in the second subperiod, generating second forecasted ranges for amounts of energy production for the plurality of time steps in the second subperiod, and generating third forecasted ranges for amounts of net energy for the plurality of time steps in the second subperiod. The amounts of net energy are based on differences between the amounts of energy consumption and the amounts of energy production.

Abstract: A system located in a building. The system including a processing circuit configured to receive tags describing points of a piece of building equipment, the piece of building equipment connected to the system. The processing circuit configured to map the tags to classes of a schema of a graph data structure. The processing circuit configured to perform clustering to generate clusters of the points. The processing circuit configured to identify, based on the clusters, relationships in the schema of the graph data structure between the tags mapped to the classes of the schema of the graph data structure. The processing circuit configured to communicate data to a second system based at least in part on the tags mapped to the classes and the relationships.

Abstract: A method for generating a training data set includes receiving, by a processing circuit, warranty claim data associated with one or more building devices or building device components; processing, by the processing circuit, the warranty claim data using natural language processing to generate a training data set comprising one or more causes and solutions associated with failure of the one or more building devices or the building device components; and training, by the processing circuit, a component reliability model using the training data set to produce a trained model.

Abstract: A method for training a fault probability model using warranty claim data includes obtaining, by a processing circuit, a first data set for failed building devices based on warranty claim data associated with the building devices; receiving, by the processing circuit, design change data associated with the building devices and determining a design change date based on the design change data; comparing, by the processing circuit, a manufacturing date for each of the failed building devices with the design change date; removing, by the processing circuit, any building devices from the first data set in response to the manufacturing date preceding the design change date to create an updated first data set; generating, by the processing circuit, a training data set comprising the updated first data set; and training, by the processing circuit, a fault probability model using the training data set to produce a trained model.

Abstract: A system including a processing circuit configured to receive tags describing points of a piece of equipment, the piece of equipment connected to the system. The processing circuit configured to map the tags to classes of a schema of a graph data structure. The processing circuit configured to perform clustering to generate clusters of the points. The processing circuit configured to identify, based on the clusters, relationships in the schema of the graph data structure between the tags mapped to the classes of the schema of the graph data structure. The processing circuit configured to communicate data to a second system based at least in part on the tags mapped to the classes and the relationships.