Abstract: Controlling a fresh air intake includes determining a fresh air intake damper position based on the supply air flowrate, a measure of energy delivered to the supply air flow, or a measure of humidity of the supply air flow. Determining the fresh air intake damper position is subject to a constraint that the AHU maintains one or more comfort conditions in the building space and one or more of a constraint regarding maintaining one or more Indoor Air Quality (IAQ) contaminants in the building space below one or more IAQ thresholds, minimizing energy consumption of the AHU, and maximizing the fresh air ventilation air flow into the building space. Various parameters used to determine the fresh air intake damper position may be derived from available sensed conditions so as to reduce the number of physical sensors that are required.

Abstract: Anomalies may be detected in a video feed that is captured by a video camera of a video surveillance system. At least part of the video feed may be fed to a Generative Multimodal Model (GMM) along with a prompt that prompts the GMM to look for anomalies occurring in at least part of the video feed. The video feed is processed by the GMM using the prompt to identify one or more anomalies occurring in the at least part of the video feed. The one or more anomalies identified by the GMM in at least part of the video feed are reported.

Abstract: A list of equipment to implement a proposed building automation system may be generated based at least in part on a sequence of operation that describes how the proposed building automation system is to operate. A master standard library of different building automation system components includes a sequence of operation and an IO table for each of the different building automation system components. The sequence of operation that describes how the proposed building automation system is to operate, along with the master standard library of different building automation system components, are provided to a Large Language Model, which is prompted to generate the list of equipment based at least in part on the sequence of operation that describes how the proposed building automation system is to operate and the master standard library of different building automation system components. The list of equipment is outputted.

Abstract: Devices, systems, and methods for fire system floor plan layout generation are described herein. In some examples, one or more embodiments include a computing device comprising a memory and a processor to execute instructions stored in the memory to receive a floor plan layout of a space, define, via an object placement model utilizing the floor plan layout, placement locations of fire system objects for the floor plan layout, and generate, using the object placement model, a fire system floor plan for a fire system for the space including the fire system objects, wherein the fire system objects are located in the defined placement locations on the fire system floor plan from the floor plan layout.

Abstract: Devices, systems, and methods for providing predictive analytics of fire systems are described herein. One fire system maintenance system, includes fire system detectors, a fire system control panel, and a gateway device positioned within the facility and in communication with at least one of the fire system control panel or fire system detectors, the gateway having instructions to: collect fire system device health data associated with one or more fire or smoke detector devices and to send this fire system device health data to a remote device; the remote device having instructions to: analyze the collected fire system device health data to predict if the data contains any anomalies or deviations from an expected behavior; and a fire system maintenance solution application that identifies a nearest scheduled maintenance visit and associates a service item with the scheduled maintenance visit.

Abstract: A Building Management System (BMS) may be controlled in accordance with predicted occupancy using a trained model. A model is trained by providing the model with time stamped environmental data and corresponding time stamped occupancy data pertaining to a training building, wherein the time stamped environmental data is derived from one or more environmental sensors of the training building and the corresponding time stamped occupancy data is derived from one or more occupancy sensors of the training building. Once trained, the trained model is provided with time stamped environmental data for a use building that is derived from one or more environmental sensors of the use building. The trained model outputs a predicted occupancy value that represents a predicted occupancy count in the use building, and the BMS of the use building is controlled based at least in part on the predicted occupancy value.

Abstract: Methods and systems for interacting with users via a chatbot. A natural language query is received and processed by submitting a search query to a search engine. The search engine identifies relevant information including textual information and images for formulating a response. The identified information and query are submitted to a Large Language Model which generates a response displayed via the chatbot. The response may include textual information and relevant images. The system can extract text from images of documents and convert textual information into numerical vector representations for processing. Selectable options based on clustered relevant information can be provided to users for query refinement when appropriate. The chatbot interface enables natural language interactions while leveraging search capabilities and Artificial Intelligence to provide informative and helpful responses with both text and visual elements.

Abstract: A method and system for interacting with a building management system via a chatbot includes receiving a natural language query and processing it to identify tools and arguments needed to collect information from data sources associated with the building management system. The identified tools are executed with corresponding arguments to collect information from the data sources. The collected information and natural language query are submitted to a Large Language Model, which generates a natural language response based on the query and collected information.

Abstract: A natural language query is received via a chatbot to monitor and/or control one or more security devices of the security system. The natural language query is processed to identify one or more descriptors of one or more security system devices that are a subject of the natural language query and to identify a desired result of the natural language query. One or more security system commands are assembled and submitted to the security system to identify one or more specific security system devices of the security system that correspond to the natural language query. One or more security system commands are assembled and submitted to each of the specific security system devices of the security system that are tailored to achieve the desired result. Confirmation from the security system is received.

Abstract: Methods for improving operational efficiency include methods for improving inspection efficiency and methods for improving operator efficiency. A method includes determining an inspection efficiency of a plurality of inspectors inspecting devices of a building. A method includes determining an operator efficiency of a plurality of operators in resolving alarms generated by devices in a building. A method includes determining a device inspection score.

Abstract: Devices, systems, and methods for providing fire events pattern analysis and cross-building data analytics are described herein. One fire system maintenance system, includes a number of fire system detectors, a fire system control panel, and a gateway device all positioned within the facility, the gateway device having instructions to: collect fire system device health data associated with one or more fire or smoke detector devices and to send this fire system device health data to a remote device, the remote device having instructions to: analyze the collected fire system device health data to determine an event type for each device health event recorded in the collected data, predict future device health events, categorize the device health events based on their determined event type, and prioritize the categorized device health events based on the quantity of events categorized in each event type.

Abstract: A current load on the AHU used to maintain one or more comfort conditions in the building space is determined, along with a remaining load capacity. A maximum additional fresh air ventilation air flow that could be admitted and conditioned using the remaining load capacity of the AHU such that the AHU could still maintain the one or more comfort conditions in the building space is determined. A fresh air intake damper position for the fresh air intake damper that increases the fresh air ventilation air flow through the fresh air intake damper by a fraction of the maximum additional fresh air ventilation air flow is determined. The fraction may be based at least in part on one or more of a temperature factor and an air quality factor. The fresh air intake damper is set to the determined fresh air intake damper position.

Abstract: Controlling a fresh air intake includes determining a fresh air intake damper position based on the supply air flowrate, a measure of energy delivered to the supply air flow, or a measure of humidity of the supply air flow. Determining the fresh air intake damper position is subject to a constraint that the AHU maintains one or more comfort conditions in the building space and one or more of a constraint regarding maintaining one or more Indoor Air Quality (IAQ) contaminants in the building space below one or more IAQ thresholds, minimizing energy consumption of the AHU, and maximizing the fresh air ventilation air flow into the building space. Various parameters used to determine the fresh air intake damper position may be derived from available sensed conditions so as to reduce the number of physical sensors that are required.

Abstract: Devices, systems, and methods for providing predictive analytics of fire systems are described herein. One fire system maintenance system, includes fire system detectors, a fire system control panel, and a gateway device positioned within the facility and in communication with at least one of the fire system control panel or fire system detectors, the gateway having instructions to: collect fire system device health data associated with one or more fire or smoke detector devices and to send this fire system device health data to a remote device; the remote device having instructions to: analyze the collected fire system device health data to predict if the data contains any anomalies or deviations from an expected behavior; and a fire system maintenance solution application that identifies a nearest scheduled maintenance visit and associates a service item with the scheduled maintenance visit.

Abstract: Devices, systems, and methods for providing fire events pattern analysis and cross-building data analytics are described herein. One fire system maintenance system, includes a number of fire system detectors, a fire system control panel, and a gateway device all positioned within the facility, the gateway device having instructions to: collect fire system device health data associated with one or more fire or smoke detector devices and to send this fire system device health data to a remote device, the remote device having instructions to: analyze the collected fire system device health data to determine an event type for each device health event recorded in the collected data, predict future device health events, categorize the device health events based on their determined event type, and prioritize the categorized device health events based on the quantity of events categorized in each event type.

Abstract: An occupancy count of the space of a building from each of a plurality of occupancy sensors may be monitored and an error parameter for each of the plurality of occupancy sensors may be identified, each error parameter representative of a difference between the occupancy count of the respective occupancy sensor and a ground truth occupancy count of the space, normalized over a period of time. An assigned weight for each of the plurality of occupancy sensors may be determined based at least in part on the respective error parameter. The estimated occupancy count of the space of the building is determined based at least in part on the occupancy count of each of the plurality of occupancy sensors and the assigned weight of each of the plurality of occupancy sensors. The BMS system is controlled based at least in part on the estimated occupancy count.

Abstract: Devices, systems, and methods for providing predictive analytics of fire systems are described herein. One fire system maintenance system, includes fire system detectors, a fire system control panel, and a gateway device positioned within the facility and in communication with at least one of the fire system control panel or fire system detectors, the gateway having instructions to: collect fire system device health data associated with one or more fire or smoke detector devices and to send this fire system device health data to a remote device; the remote device having instructions to: analyze the collected fire system device health data to predict if the data contains any anomalies or deviations from an expected behavior; and a fire system maintenance solution application that identifies a nearest scheduled maintenance visit and associates a service item with the scheduled maintenance visit.

Abstract: A Building Management System (BMS) may be controlled in accordance with predicted occupancy using a trained model. A model is trained by providing the model with time stamped environmental data and corresponding time stamped occupancy data pertaining to a training building, wherein the time stamped environmental data is derived from one or more environmental sensors of the training building and the corresponding time stamped occupancy data is derived from one or more occupancy sensors of the training building. Once trained, the trained model is provided with time stamped environmental data for a use building that is derived from one or more environmental sensors of the use building. Occupancy data for the use building is not required. The trained model outputs a predicted occupancy value that represents a predicted occupancy count in the use building, and the BMS of the use building is controlled based at least in part on the predicted occupancy value.

Abstract: Devices, systems, and methods for filter life prediction for an aspirating smoke detector are described herein. In some examples, one or more embodiments include a computing device comprising a memory and a processor to execute instructions stored in the memory to log operational data of the aspirating smoke detector for a first time period to generate an initial data set, fit a machine learning model to the initial data set, and determine, based on the machine learning model, a remaining useful life of the filter.

Abstract: Methods and systems for operating a Heating, Ventilating and Air Conditioning (HVAC) system in accordance with one of a plurality of operating modes. The plurality of operating modes include one or more of a health mode, an energy savings mode and a balanced mode. In some cases, the operating modes include two or more energy saving modes. The currently operating mode is selected based on the current operating conditions of the building and the desired goals of the building operator. The goals can include, for example, reducing energy usage, reducing pathogen risks, increasing air quality and/or a combination of these goals. In some cases, the operating modes are autonomously controlled. In some cases, the operating modes are manually controlled.