Generating event device optimization analytics in event system

By using machine learning models in event systems to optimize the detection status and configuration of event devices, the false alarm and delayed alarm problems caused by poor event system design in the prior art are solved, and the accuracy and security of event detection are improved, and the accuracy and security of event detection are reduced. The cost.

CN119067246APending Publication Date: 2024-12-03HONEYWELL INTERNATIONAL INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410497571.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-26
Filing Date
2024-04-24
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing event system is poorly designed, resulting in improper detector setup and inability to correctly identify emergencies, which may lead to false alarms or delayed alarms, affecting the safety and trust of residents in the facility.

Method used

Receive data from event equipment and environmental monitoring systems through computing devices, generate event equipment optimization analysis using machine learning models, and provide suggestions for detector detection status, alternative event equipment types and engineering configuration to optimize the performance of event systems.

Benefits of technology

Improves the early warning capabilities of the incident system for emergencies, reduces false alarms and nuisance events, enhances the trust of residents in the facility, and reduces unnecessary responses to emergency services, achieving safer and more cost-effective event detection process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067246A_ABST
    Figure CN119067246A_ABST
Patent Text Reader

Abstract

Devices, systems, and methods for generating event device optimization analytics in an event system are described herein. In some examples, one or more embodiments include a computing device including a memory and a processor to execute instructions stored in the memory to receive building system information from a plurality of event devices of an event system in a facility, an event device optimization analysis is generated via a machine learning model using building system information from a plurality of event devices, and the event device optimization analysis is caused to be displayed via a user interface.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to devices, systems, and methods for generating event device optimization analysis in an event system. Background Art

[0002] Facilities, such as commercial facilities, office buildings, hospitals, campuses (e.g., including buildings and outdoor spaces), etc., may have an event system that can be triggered during an event (such as an emergency, e.g., a fire) to warn occupants to evacuate. Such an event system may include an alarm system having a control panel and many event devices (e.g., sensors, sounders, pull-type fire alarm boxes, etc.) located throughout the facility (e.g., on different floors and / or in different rooms of the facility) that can perform actions when an event (e.g., a hazardous event, a fault event, etc.) occurs in the facility. In the example of an event, many of the event devices can provide notification of the event to occupants of the facility via alarms and / or other mechanisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Figure 1 is an example of a system for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure.

[0004] Figure 2 is an example of a computing device with a machine learning model for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure.

[0005] Figure 3 is an example of a report in an event device optimization analysis according to one or more embodiments of the present disclosure.

[0006] Figure 4 is an example of a computing device for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0007] Devices, systems, and methods for generating event device optimization analysis in an event system are described herein. In some examples, one or more embodiments include a computing device including a memory and a processor for executing instructions stored in the memory to receive building system information from a plurality of event devices of an event system in a facility, generate an event device optimization analysis via a machine learning model using the building system information from the plurality of event devices, and cause the event device optimization analysis to be displayed via a user interface.

[0008] Facilities can use event systems to warn residents of facilities of emergency events, such as fires. An event system can be a system of devices that operate to collect information about a facility and provide the collected information for analysis. Such an event system can also take actions based on the collected information, such as providing auditory and / or visual warnings in emergency events. For example, an event system can use event devices to warn residents of emergency events, such as fires, that occur in a space. As used herein, the term "event device" refers to a device that can receive inputs related to an event and / or generate outputs related to an event. Such event devices can be part of an event system for a space within / throughout a facility, and can include devices such as fire sensors, smoke detectors, heat detectors, carbon monoxide (CO) detectors, or combinations of these devices; air quality sensors; interfaces; manual call points (MCPs); pull-type fire alarm boxes; input / output modules; aspirated devices; and / or auditory / visual devices (e.g., speakers, sounders, flashers, buzzers, microphones, cameras, video displays, video screens, etc.), relay output modules, and other types of event devices.

[0009] The detection states of detectors in the event devices of an event system are typically set when the event system is first installed and / or commissioned in a facility. However, in some cases, the setting and commissioning of the detectors may not take into account how the facility will operate when occupied by occupants.

[0010] Additionally, in some examples, some facilities may have a poor initial event system design. For example, alternative event equipment types and / or alternative engineering configurations may not have been considered in the poorly designed event system. Additionally, the poorly designed event system may not include a feedback loop for determining whether the correct event equipment type is being utilized in the facility.

[0011] When detector / event devices are not properly configured and / or the event system is poorly designed, various problems may arise. For example, the event system may not properly reject potential nuisance events and / or false alarm events, while there may be delays in initiating alarms for true emergencies.

[0012] If the event system is poorly designed and / or the event devices are improperly selected and / or set up, too many unwanted events (such as nuisance events and / or false alarm events) will be detected, which may undermine occupants' trust in the event system. However, erroneously reducing the sensitivity of detectors in event devices in the event system may inhibit the event system's ability to provide early warning detection of true emergencies, which is critical to alerting occupants within the facility.

[0013] According to the present disclosure, generating an event device optimization analysis in an event system can optimize the detection status of detectors of event devices in the event system, and can also generate recommendations for alternative event device types and / or alternative engineering configurations for event devices in the facility, all based on real data from the facility. Compared to previous methods, this method can provide comprehensive analytical information for more proactive management of event systems in the facility, thereby facilitating a safer and less costly event detection process in the facility. In addition, this method can reduce unnecessary responses to the facility from local emergency services due to false alarm events and / or nuisance events. In addition, compared to previous methods, this method can increase the reliance of occupants of the facility on the event system, especially in the event of a real emergency.

[0014] In the following Detailed Description, reference is made to the accompanying drawings which form part of the present Detailed Description. The drawings show, by way of illustration, the manner in which one or more embodiments of the present disclosure may be practiced.

[0015] These embodiments are described in sufficient detail to enable one of ordinary skill in the art to practice one or more embodiments of the present disclosure. It is to be understood that other embodiments may be utilized and process, electrical and / or structural changes may be made without departing from the scope of the present disclosure.

[0016] It should be understood that the elements shown in the various embodiments herein may be added, exchanged, combined and / or eliminated to provide multiple additional embodiments of the present disclosure. The proportions and relative sizes of the elements provided in the drawings are intended to illustrate embodiments of the present disclosure and should not be limiting.

[0017] The figures herein follow the following numbering convention: the first digit or digits correspond to the figure number, and the remaining digits identify the element or component in the figure. Similar elements or components between different figures may be identified by using similar numerals. For example, 102 may refer to Figure 1 Component "02" in , and Figure 2 Similar elements in can be referenced as 202.

[0018] As used herein, "a" or "a number of" things may refer to one or more such things, and "a number of" things may refer to more than one such things. For example, "a number of components" may refer to one or more components, and "a number of components" may refer to more than one component.

[0019] Figure 11 is an example of a system 100 for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure. The system 100 may include a computing device 102, an environmental monitoring system (EMS) 104, event devices (106-1, 106-2, 106-N), a control panel 108, a gateway 110, and a mobile device 114.

[0020] As described above, the system 100 may be included in a facility, a space in a facility, etc. The system 100 may include a device / series of devices to detect events and / or process and / or analyze detected events to determine whether to generate an alarm for occupants of the facility.

[0021] For example, the system 100 may include event devices 106-1, 106-2, 106-N (collectively referred to herein as event devices 106). Event devices 106 may be devices that detect events and transmit the detected events for processing and / or analysis. As described above, event devices 106 may include, for example, cameras, motion sensors, fire sensors, smoke detectors, heat detectors, carbon monoxide (CO) detectors, fixed gas and / or flame detectors, aspirating smoke detectors, beam smoke detectors, or combinations of these devices; air quality sensors; interfaces; manual call points (MCPs); pull alarm boxes; input / output modules; aspirating devices; sprinkler controls; and / or audio / visual devices (e.g., speakers, microphones, cameras, video displays, video screens, etc.), relay output modules, and other types of event devices.

[0022] Such event devices 106 may include detectors. As used herein, the term "detector" refers to a device that measures events and / or changes in its environment and transmits the detected events and / or changes for processing and / or analysis. For example, event device 106-1 may be a smoke detector and may include a detector that measures the amount of smoke in a sample.

[0023] The system 100 may also include a control panel 108. The control panel 108 may be used to control the various event devices 106 included in the system 100.

[0024] The control panel 108 may be connected to the event device 106 and the gateway 110. The gateway 110 may be a device (e.g., a building system gateway) that provides a communication link between the control panel 108 and other devices, such as the computing device 102 and the mobile device 112. For example, the gateway 110 may enable data (e.g., system device data, activation signals, etc.) to be transmitted from the event device 106 to the computing device 102 and / or the mobile device 112 via the control panel 108, and vice versa.

[0025] The facility may also include an environmental monitoring system (EMS) 104. The environmental monitoring system may include equipment that monitors and / or detects conditions in a certain area. For example, the environmental monitoring system may include sensors or other equipment that can detect events that occur (e.g., door opening, window closing, temperature of space, flow rate of air ducts, etc.). In some examples, the environmental monitoring system may include a building management system (BMS). As used herein, the term "building management system" refers to a computing-based automation and control system used in a facility to monitor, regulate and / or control electrical and mechanical equipment of a facility, including power, lighting and ventilation, and other types of equipment in the facility. The building management system may utilize a building information model with data associated with the facility (e.g., data associated with components, equipment and / or attributes of the facility). For example, the building information model data may include data from equipment associated with components and / or equipment associated with any other system in the building, machinery, electrical conduits, sanitation and / or facilities. Additionally, building information model data may include architectural, mechanical, electrical, plumbing, sanitary, fire and / or geometric information associated with a building via various floor plans of the facility and may be represented in two-dimensional (2D) and / or three-dimensional (3D) plans.

[0026] Also included in the system 100 is a mobile device 112. The mobile device 112 may be utilized by occupants of the facility, such as building managers, engineers, maintenance personnel.

[0027] like Figure 1 As shown, event device 106 can be connected to computing device 102 and / or mobile device 112 (e.g., via control panel 108 and gateway 110). In addition, EMS 104 can be connected to computing device 102 and / or mobile device 112. Such devices can be connected via a network relationship. Examples of such network relationships can include a local area network (LAN), a wide area network (WAN), a personal area network (PAN), a distributed computing environment (e.g., a cloud computing environment), a storage area network (SAN), a metropolitan area network (MAN), a cellular communication network, long term evolution (LTE), visible light communication (VLC), Bluetooth, Worldwide Interoperability for Microwave Access (WiMAX), near field communication (NFC), infrared (IR) communication, a public switched telephone network (PSTN), radio waves and / or the Internet, as well as other types of network relationships.

[0028] As used herein, the term "computing device" refers to an electronic system with processing resources, memory resources, and / or an application-specific integrated circuit (ASIC) that can process information. Examples of computing devices may include, for example, laptop computers, notebook computers, desktop computers, all-in-one (AIO) computing devices, servers, networking equipment (e.g., routers, switches, etc.), and / or mobile devices, as well as other types of computing devices. As used herein, a mobile device may include a device that a user carries and / or wears (or can carry and / or wear by a user). For example, a mobile device may be a phone (e.g., a smart phone), a tablet computer, a personal digital assistant (PDA), smart glasses, and / or a wrist-worn device (e.g., a smart watch), as well as other types of mobile devices.

[0029] To generate the optimization analysis, computing device 102 may receive building system information from various entities in system 100. As used herein, the term "building system information" refers to data associated with the operation of a facility. Building system information may be received from event device 106, EMS 104, and / or from mobile device 112, as further described herein.

[0030] The computing device 102 may receive building system information from the event device 106. For example, the event device 106 may transmit the building system information to the computing device via the control panel 108 and the gateway 110. The building system information from the event device 106 may include any data that the event device 106 can measure. For example, the data from the event device 106 may include early warning data before the event device 106 detects the event, alarm data after the event device 106 detects the event, operational data not related to the event, spike events, etc. For example, the early warning data may include detector data relative to a detection threshold, an analog-to-digital value from the event device 106, etc. For example, the event device 106-1 may be a heat detector and transmits a heat level (e.g., temperature) relative to a threshold temperature to the computing device 102. Additionally, the event device 106-2 may be a smoke detector and transmits a smoke level relative to a threshold smoke amount, the event device 106-3 may be a CO detector and transmits a CO level relative to a threshold amount, and so on.

[0031] Additionally, in response to event device 106 detecting an event, event device 106 may transmit building system information including alarm data to computing device 102 after event device 106 detects the event. For example, event device 106-1 may detect an event (e.g., a detected temperature exceeding a threshold temperature), and event device 106-1 may transmit alarm data (e.g., the detected temperature) to computing device 102.

[0032] The computing device 102 may also receive building system information from the EMS 104 of the facility. As described above, the building system information from the EMS 104 may include environmental information, such as information from the device and building information model data of equipment associated with the component and / or any other system associated with the building, machinery, electrical plumbing, sanitation and / or facilities, and may also include information associated with the floor plan of the facility. In addition to the information detected by the event device 106, such building system information from the EMS 104 of the facility may also provide environmental data about the facility. For example, the building system information from the EMS 104 may provide contextual information about what is happening in the space before and when the event is detected. For example, if the event device 106-2 is an air quality sensor that detects a drop in air quality, the building system information from the EMS 104 may provide contextual information that the door of the space remains open (e.g., via a door sensor connected to the EMS 104), which may enable dirty air to interact with the event device 106-2. Such information may enable computing device 102 to determine steps to take regarding optimization analysis via a machine learning model, as further described herein.

[0033] The building system information may also include classification data regarding events detected by the event device 106. For example, in response to the event device 106 detecting an event, a query may be transmitted to the mobile device 112 that may enable a user to provide input to the mobile device 112 regarding the type of event. Thus, the classification data may be organized by event type based on the user input. For example, the event device 106-1 may detect an event, and the user of the mobile device 112 may determine whether the detected event is an unwanted alarm event or a real event. The query provided to the user of the mobile device may enable the user to specify whether the event is an unwanted alarm event or a real event. After providing input to the mobile device 112 that the detected event is an unwanted alarm event, the mobile device 112 may classify the detected event as an unwanted alarm event and transmit such information to the computing device 102 as the building system information.

[0034] As described above, event types may include unwanted alarm events and / or real events. An unwanted alarm event may be an event that results from (intentionally or unintentionally) creating an environmental condition that the event device is designed to detect but is not an emergency event. Such unwanted alarm events may be, for example, nuisance events, false alarm events, etc. For example, an occupant may be baking bread in an office kitchen. Although the smoke generated by the baking bread is unintentional and may cause the event device 106 to trigger, such an event is not an emergency event and may be considered an unwanted alarm event.

[0035] Another example of an unwanted alarm event may be a false alarm event. For example, the event device 106 may be a heat detector located near a steam pipe (e.g., due to installation error or poor event system design), wherein the event device 106 may falsely trigger when the temperature of the steam pipe is high enough (e.g., intentionally due to facility operation) that the event device 106 detects heat generated by the steam pipe. As further described herein, event device optimization analysis according to the present disclosure may provide a facility manager or other user options to make various changes in a facility to use building system information to try and prevent unwanted alarm events (such as nuisance events and false alarm events).

[0036] In addition, the event type may also include a real event. As used herein, the term "real event" refers to an emergency event. For example, the event device 106 may be a smoke detector that detects smoke generated by a fire in a facility. As further described herein, the event device optimization analysis may assure occupants of the facility that a fire within the facility can be properly detected and that a timely warning is issued to the occupants to initiate safe emergency procedures.

[0037] As described above, computing device 102 can receive building system information from event device 106 (e.g., including early warning data and alarm data), mobile device 112 (e.g., including classification data about events, past events, etc.), and from EMS 104 (e.g., including environmental information data). Computing device 102 can use the building system information from event device 106, EMS 104, and / or mobile device 112 to generate event device optimization analysis via a machine learning model.

[0038] A machine learning model can be an algorithm that utilizes sample data (e.g., training data) to generate a set of rules that enables the algorithm to make predictions about new data fed to the model. For example, computing device 102 can utilize received building system information to generate an event device optimization analysis to determine an optimal detection state for a detector of an event device, whether an alternative event device type may be more suitable, whether an alternative engineering configuration may be more suitable, whether to unlock locked detector features for use, and / or a combination thereof. For example, utilizing building system information, computing device 102 (e.g., via a machine learning model) can select event device 106-1 because the building system information can indicate that event device 106-1 can be optimized by modifying the detection state of a detector of event device 106-1, indicating that an alternative event device type may be more suitable for the location in the facility where event device 106-1 is located, indicating that an alternative engineering configuration for event device 106-1 may be more desirable, and / or indicating whether to unlock detector features in the event device, as further described herein. In addition, the machine learning model can utilize building system information, past event equipment optimization analyses, and / or past inputs in response to past event equipment optimization analyses to determine a propensity rating for event equipment optimization analysis options for user consideration, as further described herein.

[0039] In one example, generating an event device optimization analysis may include determining an optimal detection state of a detector of event device 106-1 via a machine learning model. In some examples, event device 106-1 may include multiple operating states, each operating state having a sensitivity level that can vary within each state. For example, event device 106-1 may be a detector that can detect multiple fire phenomena such as heat and CO (e.g., event device 106-1 may be a dual optical thermal CO detector). Such a device type may have a higher sensitivity than, for example, a device that detects a single fire phenomenon (e.g., a smoke detector). The machine learning model may determine that event device 106-1 detects too many false alarm events because event device 106-1 is too close to a steam pipe in a space in a facility that discharges engine exhaust, causing event device 106-1 to detect heat and exhaust from the steam pipe, thereby interacting with event device 106-1. In this case, the machine learning model may determine that the detection state of event device 106-1 may be modified and / or the sensitivity level within the detection state may be modified (e.g., reduced) to prevent event device 106-1 from being activated when the steam pipe is hot and discharges exhaust.

[0040] Additionally, the event device optimization analysis may include a propensity rating around a proposed detection state and / or optimal sensitivity level. For example, a machine learning model may determine that turning down the sensitivity level of a dual optical thermal CO detector device has a 60% propensity rating for preventing activation of event device 106-1 in situations where a steam pipe is hot and venting exhaust gases.

[0041] In another example, event device 106-1 may be a device that detects a single event phenomenon. The machine learning model may determine that event device 106-1 detects many false positive events because event device 106-1 is an air quality sensor that is too close to a door that is continuously in use (e.g., open), causing unclean air to continuously interact with event device 106-1. In this case, the machine learning model may determine that the detection state of event device 106-1 can be turned down to prevent event device 106-1 from being activated by too many false positives.

[0042] Additionally, the event device optimization analysis may include a propensity rating around a proposed optimal sensitivity level. For example, the machine learning model may determine that turning down the sensitivity level of the air quality sensor has an 80% propensity rating for preventing the event device 106-1 from being activated if the door is open and unclean air interacts with the event device 106-1.

[0043] In another example, generating an event device optimization analysis may include determining, via a machine learning model, an alternative event device type for event device 106-1. For example, event device 106-1 may be a heat detector that may be too close to a steam pipe (e.g., the temperature of which is provided to computing device 102 via building system information), and the machine learning model may determine that event device 106-1 detects too many false alarm events because event device 106-1 inadvertently detects heat from the steam pipe. In this case, the machine learning model may determine that the event device type of event device 106-1 (e.g., a heat detection device) should be replaced with an alternative event device type, such as a smoke detector event device. Thus, the smoke detector event device will provide fire detection capabilities without being triggered by the heat of the nearby steam pipe.

[0044] Additionally, the event device optimization analysis may include a propensity rating around proposed alternative event device types. For example, a machine learning model may determine that changing a heat detector to a smoke detector has a 98% propensity rating for preventing activation of event device 106-1 in the event that the steam pipe is hot.

[0045] In another example, generating an event device optimization analysis may include determining an alternative engineering configuration for event device 106-1 via a machine learning model. Similar to the previous example, event device 106-1 may be a thermal detector that may be too close to a steam pipe (e.g., its temperature determined by a sensor provided to computing device 102 from EMS 104 via building system information), and the machine learning model may determine that event device 106-1 detects too many false positive events because event device 106-1 inadvertently detects heat from the steam pipe. In this case, the machine learning model may determine that event device 106-1 (e.g., a thermal detection device) should include a simultaneous detection mechanism so that event device 106-1 is not activated even when an event is detected (e.g., a temperature exceeding a threshold temperature is detected) unless event device 106-2 also detects an event. For example, if event device 106-1 detects an event, and event device 106-2 is also a thermal detector that detects heat and is not close to a steam pipe, event devices 106-1 and 106-2 may be activated. As another example, if event device 106-1 detects an event and event device 106-2 is a smoke detector that detects smoke, event devices 106-1 and 106-2 may activate. As another example, if event device 106-1 detects an event and event device 106-2 is also a heat detector that does not detect heat and is not near a steam pipe, event devices 106-1 and 106-2 do not activate.

[0046] Additionally, the event device optimization analysis may include a propensity rating around the proposed alternative engineering configurations. For example, the machine learning model may determine that including co-occurrence detection has a 95% propensity rating for the likelihood of preventing activation of event device 106-1 when the steam pipe is hot.

[0047] Although determining an alternative engineering configuration is described above as including simultaneous detection, embodiments of the present disclosure are not limited thereto. For example, the alternative engineering configuration may also include a day and night detection module, an alarm delay process, and the like.

[0048] In another example, generating an event device optimization analysis may include determining, via a machine learning model, whether to unlock a detector feature of event device 106-1. For example, event device 106-1 may be a detector that can detect multiple fire phenomena such as heat and CO (e.g., event device 106-1 may be a dual optical thermal CO detector). However, the firmware of event device 106-1 may only allow the use of a thermal detector. The machine learning model may determine that event device 106-1 detects too many false alarm events using only a thermal detector because event device 106-1 is too close to a steam pipe, causing event device 106-1 to detect heat from the steam pipe. In this case, the machine learning model may determine that the CO detector feature of event device 106-1 may be unlocked for use, such that event device 106-1 must detect both heat and CO to activate event device 106-1. Such feature unlocking may prevent event device 106-1 from being activated when the steam pipe is hot.

[0049] Additionally, the event device optimization analysis may include a propensity rating around a proposed feature unlock. For example, a machine learning model may determine that unlocking a locked feature has an 85% propensity rating for the likelihood of preventing activation of event device 106-1 when the steam pipe is hot.

[0050] In addition, although generating an event device optimization analysis is described above as including determining an optimal detection state, determining an alternative event device type, and determining an alternative engineering configuration, the embodiments of the present disclosure are not limited thereto. For example, generating an event device optimization analysis may also include determining that another event device should be included, that the location of the event device in the facility should be changed, and the like. In addition, the event device optimization analysis may include a combination of an optimal detection state, an alternative event device type, and an alternative engineering configuration. For example, the event device optimization analysis may include changing the sensitivity of a detector of an event device 106-1 having a propensity rating of 60% and changing an alternative event device type of an event device 106-1 having a propensity rating of 98%. Therefore, a user viewing the event device optimization analysis may utilize the propensity rating as a factor in determining which approach to take to reduce false alarm events of the event device 106-1 around the steam pipe.

[0051] After generating the event device optimization analysis, computing device 102 can transmit the event device optimization analysis to another computing device. For example, computing device 102 can transmit the event device optimization analysis to mobile device 112 and / or any other computing device to display the event device optimization analysis via a user interface.

[0052] For example, mobile device 112 may include a user interface that may display the event device optimization analysis received from computing device 102. Event device optimization analysis may be used to do a variety of things, as further described herein.

[0053] The event device optimization analysis may include a report that summarizes the event device optimization analysis, including event devices 106 of interest, possible recommendations for event devices 106, and the like.

[0054] In some examples, the report may include a recommendation to change the detection state of the detector of the event device 106 to an optimal detection state. For example, the event device 106-1 may be an air quality sensor having a sensitivity level of 8. The event device optimization analysis may determine that the optimal sensitivity level is 7 based on the event device 106-1 having too many false alarms (e.g., due to exposure to unclean air from a continuously open door), and may include a recommendation to change the sensitivity level from sensitivity level 8 to an optimal sensitivity level (e.g., sensitivity level 7). Additionally, the event device optimization analysis may include a propensity rating associated with the recommendation to change the detection state.

[0055] In some examples, the report may include a recommendation to change event device 106 to an alternate event device type. For example, event device 106-1 may be a heat detector that is too close to a steam pipe. The event device optimization analysis may determine that the heat detector detects too many false positive events because event device 106-1 inadvertently detects heat from the steam pipe, and may determine that the event device type of event device 106-1 should be replaced with a smoke detector event device type. The report may accordingly include a recommendation to change event device 106-1 from a heat detector to a smoke detector. Additionally, the event device optimization analysis may include a propensity rating associated with the recommendation to change event device 106 to an alternate event device type.

[0056] In some examples, the report may include a recommendation to change the engineering configuration of event device 106 to an alternative engineering configuration. For example, event device 106-1 may be a heat detector that is too close to a steam pipe. The event device optimization analysis may determine that the heat detector detects too many false positive events because event device 106-1 inadvertently detects heat from the steam pipe, and may determine that event device 106-1 (e.g., a heat detection device) should include a simultaneous detection mechanism so that event device 106-1 is not activated even when an event is detected (e.g., a temperature exceeding a threshold temperature is detected) unless event device 106-2 also detects an event. The report may accordingly include a recommendation to include an alternative engineering configuration for event device 106-1. In addition, the event device optimization analysis may include a propensity rating associated with a recommendation to change the engineering configuration of event device 106 to an alternative engineering configuration.

[0057] In some examples, the report may include a recommendation to unlock the detector feature in the event device 106. For example, the event device 106-1 may be a combination heat and CO detector, and the CO detector has been locked in the firmware of the event device 106-1, where the event device 106-1 is too close to a steam pipe. The event device optimization analysis may determine that the heat detector detects too many false positive events because the event device 106-1 inadvertently detects heat from the steam pipe, and may determine that the event device 106-1 (e.g., the heat detection device) should unlock the CO detection feature so that the event device 106-1 is not activated even when the heat detector detects an event (e.g., detects a temperature exceeding a threshold temperature) unless the CO detector also detects an event (e.g., CO associated with the event). The report may accordingly include a recommendation to unlock the detector feature of the event device 106-1. In addition, the event device optimization analysis may include a propensity rating associated with unlocking the detector feature of the event device 106.

[0058] In some examples, computing device 102 may cause event device 106-1 to change a detection state. For example, a report including a recommendation to change the detection state of a detector of event device 106 to an optimal detection state may include displaying to a user (e.g., via mobile device 112) an inquiry as to whether to accept the recommendation. In response to mobile device 112 receiving input accepting the recommendation to change the detection state of the detector, computing device 102 may cause event device 106-1 to change the detection state of the detector to an optimal detection state. For example, computing device 102 may transmit a signal to event device 106-1 that may modify the firmware of event device 106-1 so that the detection state of the detector of event device 106-1 changes.

[0059] Although computing device 102 is described above as changing the detection state of the detector of event device 106 in response to user input, the embodiments of the present disclosure are not limited to this. For example, in some cases, computing device 102 may cause the detector to automatically change the detection state to an optimal detection state based on an event device optimization analysis. For example, based on an event device optimization analysis that indicates a change in the detection state of the detector, computing device 102 may cause event device 106-1 to change the detection state of the detector to an optimal detection state. For example, computing device 102 may automatically transmit a signal to event device 106-1 that may modify the firmware of event device 106-1 so that the detection state of the detector of event device 106-1 is changed to an optimal detection state determined by the event device optimization analysis.

[0060] In addition, in some examples, computing device 102 may cause event device 106-1 to change the engineering configuration to an alternative engineering configuration. For example, a report including a suggestion to change the engineering configuration of a detector of event device 106 to an alternative engineering configuration may include displaying to the user (e.g., via mobile device 112) an inquiry as to whether to accept the suggestion. In response to mobile device 112 receiving input accepting the suggestion to change the engineering configuration of event device 106, computing device 102 may cause event device 106-1 to change the engineering configuration of the detector to an alternative engineering configuration. For example, computing device 102 may transmit a signal to event device 106-1 that may modify the firmware of event device 106-1 so that the engineering configuration of the detector of event device 106-1 is changed.

[0061] In addition, although the computing device 102 is described above as changing the engineering configuration of the detector of the event device 106 in response to user input, the embodiments of the present disclosure are not limited to this. For example, in some cases, the computing device 102 may cause the detector to automatically change the engineering configuration to an alternative engineering configuration based on the event device optimization analysis. For example, based on the event device optimization analysis indicating a change in the engineering configuration of the detector, the computing device 102 may cause the event device 106-1 to change the engineering configuration of the detector to an alternative engineering configuration. For example, the computing device 102 may automatically transmit a signal to the event device 106-1, which may modify the firmware of the event device 106-1 so that the engineering configuration of the detector of the event device 106-1 is changed to an alternative engineering configuration determined by the event device optimization analysis.

[0062] Additionally, in some examples, computing device 102 may cause event device 106-1 to unlock the detector feature. For example, a report including a suggestion to unlock the detector feature in event device 106 may include displaying to the user (e.g., via mobile device 112) an inquiry as to whether to accept the suggestion. In response to mobile device 112 receiving input accepting the suggestion to unlock the detector feature of event device 106, computing device 102 may cause event device 106-1 to unlock the detector feature. For example, computing device 102 may transmit a signal to event device 106-1 that may modify the firmware of event device 106-1 to unlock the detector feature.

[0063] In addition, although computing device 102 is described above as unlocking the detector feature of the detector of event device 106 in response to user input, the embodiments of the present disclosure are not limited to this. For example, in some cases, computing device 102 may cause the detector to automatically unlock the detector feature based on the event device optimization analysis. For example, based on the event device optimization analysis indicating that the detector feature should be unlocked, computing device 102 may cause event device 106-1 to unlock the detector feature. For example, computing device 102 may automatically transmit a signal to event device 106-1, which may modify the firmware of event device 106-1 so as to unlock the detector feature of event device 106-1.

[0064] As described above, computing device 102 may use building system information to generate event device optimization analysis via a machine learning model. Such information may be received from a variety of sources, such as in conjunction with Figure 2 Further described.

[0065] Figure 2 is an example of a computing device 202 with a machine learning model 214 for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure. The computing device 202 can receive building system information from a BMS 204, an event device 206, and a mobile device 212.

[0066] As previously combined Figure 1 As mentioned, the computing device 202 can utilize the machine learning model 214 to generate an event device optimization analysis. The computing device 202 can also generate a machine learning model 214 to generate such an optimization analysis. For example, the computing device 202 can utilize training data and / or test data consisting of site data from a facility to generate a decision rule for generating an event device optimization analysis. Such a decision rule can be generated based on training and test data and can be used when generating an event device optimization analysis. For example, the training and test data can provide information for the decision rule so that in certain circumstances (e.g., if the number of unwanted alarm events encountered by the event device under certain environmental conditions exceeds a threshold number, which can be determined based on building system information from the BMS204), recommendations about detection status, alternative event device types, alternative engineering configurations, and / or unlocking detector features can be generated.

[0067] like Figure 2 As shown, computing device 202 may receive building system information including early warning data and alarm data from event device 206. Early warning data may be data from event device 206 before an event is detected. Additionally, alarm data may be data from event device 206 after an event is detected.

[0068] Additionally, computing device 202 may receive environmental information data from EMS 204. Such data from EMS 204 may include data from equipment associated with components and / or equipment associated with architectural, mechanical, electrical plumbing, sanitary, and / or any other systems in the facility, and may also include information associated with a floor plan of the facility.

[0069] Additionally, computing device 202 may receive classification data regarding events detected by event device 206 from mobile device 212. For example, in response to event device 206 detecting an event, a query may be transmitted to mobile device 212 that may enable a user to provide input regarding a type of event to mobile device 212. Such event types may include unwanted alarm events and / or real events.

[0070] The machine learning model 214 included in the computing device 202 can receive the classification data, environmental information, warning data, and / or alarm data. Therefore, the computing device 202 can use the above building system information to generate event device optimization analysis via the machine learning model 214, as previously described in conjunction with Figure 1 Such information can be presented in reports, as previously described in conjunction with Figure 1 as described, and as Figure 3 As further shown in .

[0071] Figure 3 316 is an example of a report 316 in an event device optimization analysis according to one or more embodiments of the present disclosure. The report 316 can include various recommendations 318.

[0072] As previously combined Figure 1 As depicted, the event device optimization analysis may include a report 316. The report 316 may summarize the event device optimization analysis, including event devices of interest, possible recommendations 318 for the event devices, and the like.

[0073] For example, report 316 may include a recommendation 318-1 for optimal detection states of detectors of the event device. For example, recommendation 318-1 may include that detectors 3, 7, and 12 should change fire detection states.

[0074] Additionally, report 316 may include a suggestion 318-2 for an alternative event device type for the event device. For example, suggestion 318-2 may include that the sensitivity level of detector 11 should be changed to sensitivity level 7 and be a heat detector and / or a CO detector.

[0075] In addition, report 316 may include recommendations 318-3 for alternative engineering configurations of the event device. For example, recommendation 318-3 may include that detectors 27 and 28 should be linked for simultaneous detection, and that detector 27 should change sensitivity state.

[0076] As previously in Figure 1 As mentioned in , the report 316 and the recommendation 318 can be transmitted to the user's mobile device. The mobile device can provide the user with a query 318 as to whether to accept such recommendations.

[0077] For example, the mobile device may provide a query to the user as to whether to accept the recommendation 318-1. In response to the mobile device receiving input accepting the recommendation for the optimal detection state, the computing device may generate a revised report 316. The revised report 316 may include a task to change the detection state to the optimal detection state. Such a revised report 316 may be generated and displayed to the user when the computing device does not modify the detection state (e.g., in response to user input or automatically without user input).

[0078] Similarly, the mobile device may provide a query to the user as to whether to accept suggestion 318-2. In response to the mobile device receiving input accepting the suggestion to change to an alternate event device type, the computing device may generate a revised report 316. Revised report 316 may include a task to change the event device type to an alternate event device type.

[0079] Finally, the mobile device may provide a query 318-3 to the user as to whether to accept the suggestion. In response to the mobile device receiving input accepting the suggestion of the link detectors 27 and 28, the computing device may generate a revised report 316. The revised report 316 may include the tasks of the link detectors 27 and 28. When the computing device does not link the detectors 27 and 28 (e.g., in response to user input or automatically without user input), such a revised report 316 may be generated and displayed to the user.

[0080] Therefore, generating event device optimization analysis in an event system according to the present disclosure can optimize event devices in the event system. Compared with previous methods, this method can use existing building information to build a machine learning model that can provide comprehensive analytical information for more proactively managing the event system in the facility, thereby promoting a safer and less costly event detection process in the facility.

[0081] Figure 4 is an example of a computing device 402 for generating event device optimization analysis in an event system according to one or more embodiments of the present disclosure. Figure 4As shown, computing device 402 may include memory 430 and processor 428 for generating event device optimization analysis in an event system according to the present disclosure.

[0082] The memory 430 may be any type of storage medium that can be accessed by the processor 428 to perform various examples of the present disclosure. For example, the memory 430 may be a non-transitory computer-readable medium having computer-readable instructions (e.g., executable instructions / computer program instructions) stored thereon that are executable by the processor 428 for generating event device optimization analysis in an event system according to the present disclosure.

[0083] The memory 430 may be a volatile memory or a non-volatile memory. The memory 430 may also be a removable (e.g., portable) memory or a non-removable (e.g., internal) memory. For example, the memory 430 may be a random access memory (RAM) (e.g., a dynamic random access memory (DRAM) and / or a phase change random access memory (PCRAM)), a read-only memory (ROM) (e.g., an electrically erasable programmable read-only memory (EEPROM) and / or a compact disc read-only memory (CD-ROM)), a flash memory, a laser disc, a digital versatile disc (DVD) or other optical storage device and / or a magnetic medium (such as a cassette, a tape or a disk), and other types of memory.

[0084] In addition, although the memory 430 is shown as being located within the computing device 402, the embodiments of the present disclosure are not limited thereto. For example, the memory 430 may also be located within another computing resource (e.g., enabling computer readable instructions to be downloaded via the Internet or another wired or wireless connection).

[0085] Processor 428 may be a central processing unit (CPU), a semiconductor-based microprocessor, and / or other hardware device suitable for retrieving and executing machine-readable instructions stored in memory 430 .

[0086] Although specific implementations have been illustrated and described herein, those of ordinary skill in the art will appreciate that any arrangement calculated to achieve the same technique may be substituted for the specific implementations shown. This disclosure is intended to cover any and all modifications or variations of various implementations of the present disclosure.

[0087] It should be understood that the above description is given in an illustrative rather than limiting manner.By reading the above description, combinations of the above embodiments, as well as other embodiments not specifically described herein, will be apparent to those skilled in the art.

[0088] The scope of the various embodiments of the present disclosure includes any other applications using the above-described structures and methods.The scope of the various embodiments of the present disclosure should therefore be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

[0089] In the above detailed description, various features are grouped together in the exemplary embodiments shown in the drawings for the purpose of simplifying the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the present disclosure require more features than are expressly recited in each claim.

[0090] Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment.Thus the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment.

Claims

1. A computing device (102, 202, 402) for generating an event device (106, 206) optimization analysis in an event system (100), the computing device comprising: Memory (430); and a processor (428) configured to execute executable instructions stored in the memory (430) to: From a plurality of event devices (106, 206) receiving building system information; generating an event device optimization analysis via a machine learning model (214) using the building system information from the plurality of event devices (106, 206); as well as Enables display of the event device optimization analysis via a user interface.

2. The computing device (102, 202, 402) of claim 1, wherein: Generating the event device optimization analysis includes determining, via the machine learning model (214), an optimal detection state for a detector of an event device (106, 206) among the plurality of event devices (106, 206).

3. The computing device (102, 202, 402) of claim 2, wherein: The processor (428) is configured to execute the instructions so that the detector changes the detection state of the detector to the optimal detection state.

4. The computing device (102, 202, 402) of claim 1, wherein: Generating the event device optimization analysis includes determining, via the machine learning model (214), an alternative event device (106, 206) type for an event device (106, 206) among the plurality of event devices (106, 206).

5. The computing device (102, 202, 402) of claim 1, wherein: Generating the event device optimization analysis includes determining, via the machine learning model (214), alternative engineering configurations for event devices (106, 206) among the plurality of event devices (106, 206).

6. The computing device (102, 202, 402) of claim 1, wherein: Generating the event device optimization analysis includes determining, via the machine learning model (214), detector features in an event device (106, 206) among the plurality of event devices (106, 206) that should be unlocked.

7. The computing device (102, 202, 402) of claim 6, wherein: The processor (428) is configured to execute the instructions to cause the detector to unlock the detector feature in the event device (106, 206).

8. The computing device (102, 202, 402) of claim 1, wherein: The processor (428) is configured to execute the instructions to generate the machine learning model (214) using training data consisting of site data in the facility and test data to generate decision rules for generating optimization analysis of the event device (106, 206).

9. The computing device (102, 202, 402) of claim 1, wherein: The building system information includes data measured by the plurality of event devices (106, 206).

10. The computing device (102, 202, 402) of claim 1, wherein: The building system information includes classification data regarding events detected by an event device (106, 206) of the plurality of event devices (106, 206).