An event rule mining method and device for fire protection system

Abstract

The present invention relates to a method and apparatus for mining event rules for fire protection systems. The method comprises: obtaining equipment data for N fire protection equipment detected in real time in the fire protection system, where N is a positive integer; extracting a target event in the fire protection system based on the equipment data; determining M first predicted events associated with the target event based on the fire protection system topology and event similarity, where M is a positive integer; monitoring the target event, and obtaining event rule mining results for the fire protection system based on the relationship between the next occurrence of the target event and the M first predicted events. This method can effectively determine whether there are unknown representations of known events or completely unknown events, thereby improving the comprehensiveness of fire protection system status analysis.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an event rule mining method and device for a fire protection system. Background Art

[0002] With the continuous advancement of sensor technology, firefighting methods have gradually evolved from manual operation of handheld fire extinguishers and fire hydrants to intelligent firefighting systems with autonomous sensing and firefighting capabilities. These intelligent firefighting systems integrate multiple devices, including sensors, monitoring equipment, and alarm systems. These devices generate vast amounts of data, containing a wide range of information about fires. By mining and analyzing events occurring in firefighting systems, we can better understand the causes, spread, and extinguishing processes of fires, predict fire trends, and proactively prevent fires, thereby improving the response speed and effectiveness of firefighting systems. Furthermore, the vast amount of data accumulated in firefighting systems can provide a valuable basis for fire investigation and analysis, helping to improve firefighting facilities and preventive measures, and enhancing fire safety management. Therefore, event mining in firefighting systems has significant practical significance and application value.

[0003] Classic methods for event mining in fire protection systems rely primarily on template matching, which compares data features with those of existing event data. With the continuous development of deep learning and machine learning, novel methods have emerged, such as sequential pattern mining and time series analysis. These techniques can uncover hidden patterns and regularities in event data, helping users better understand the causes and mechanisms behind events. They can also provide predictions and decision support for event occurrences, helping users make more accurate decisions. However, these techniques share a common flaw: they can only assess data within the context of a single task's rules. For example, in a fire warning task, the relevant rules must be used to determine whether data collected by sensors in an intelligent fire protection system is indicative of a fire (predicting a fire or not). While existing technologies have achieved good performance, these flaws present two weaknesses: first, they cannot fully explore data within a single task (the rules are fixed, but some rules that could represent other hidden features remain undiscovered); and second, they lack multi-task capabilities (a single model or technique can only solve a single task). Summary of the Invention

[0004] In order to solve the above-mentioned problems in the prior art, the present invention provides a method and device for mining event rules for fire protection systems.

[0005] In the first aspect, an embodiment of the present application provides an event rule mining method for a fire protection system, comprising: obtaining equipment data of N fire protection equipment detected in real time in the fire protection system; N is a positive integer; extracting a target event in the fire protection system based on the equipment data; determining M first predicted events associated with the target event based on the fire protection system topology and event similarity of the fire protection system; M is a positive integer; monitoring the target event, and obtaining the event rule mining results of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events.

[0006] In an optional implementation of the first aspect, the equipment data detected by each fire-fighting equipment includes at least one of operation data and perception data; the operation data is data detected on the operation of the fire-fighting equipment itself; and the perception data is data obtained by the fire-fighting equipment sensing the environment.

[0007] In an optional implementation of the first aspect, the extracting the target event in the fire protection system based on the equipment data includes: inputting the operation data and the perception data into an autoencoder, projecting the perception data to the same dimension as the operation data through the autoencoder, and performing event recognition to extract the target event.

[0008] In an optional implementation of the first aspect, the autoencoder is a two-stage network, comprising a projection network and a visual self-attention network; the projection network is used to project the perception data into the same dimension as the operational data; the visual self-attention network is used to perform event recognition based on the perception data and operational data of the same dimension to extract the target event; the loss function of the projection network is based on KL divergence; the loss function expression of the projection network includes: ;in, represents the loss function of the projection network; represents the KL divergence; representing the sensory data; indicating the operating data; Data representing dimension alignment in the perception data; Data representing dimension alignment in the operating data; represents the projection network; the loss function expression of the visual self-attention network includes: ;in, represents the loss function of the visual self-attention network; Indicates the number of fire-fighting equipment; representing event indicators related to the operational data; representing an event indicator regarding the sensory data; Represents the visual self-attention network.

[0009] In an optional implementation of the first aspect, determining the M first predicted events associated with the target event based on the fire protection system topology and event similarity of the fire protection system includes: obtaining G known events in the fire protection system; calculating the correlation between each known event and the target event based on the fire protection system topology of the fire protection system and the event similarity between each known event and the target event; and extracting the M first predicted events from the G known events based on the correlation between each known event and the target event.

[0010] In an optional implementation of the first aspect, the calculation formula for the correlation between each known event and the target event includes: ;in, represents the target event; represents any of the known events; Indicates the correlation between the target event and the known event; represents the path length between the target event and the known event in the fire protection system topology diagram; Indicates the similarity between the target event and the known event at the data level.

[0011] In an optional implementation of the first aspect, the event rule mining result of the fire protection system is obtained based on the relationship between the next occurrence event of the target event and the M first predicted events, including: if the first event is not one of the M first predicted events, then determining M second predicted events associated with each of the first predicted events according to the fire protection system topology and event similarity of the fire protection system; wherein the first event is the next occurrence event of the target event; the total number of the second predicted events is If the second event is If one of the second predicted events is found, it is determined that the second event is a hidden representation of the first event; wherein, the second event is the next occurrence event of the first event; and the event rule mining result of the fire protection system includes that the second event is a hidden representation of the first event.

[0012] In an optional implementation of the first aspect, the method further includes: if the second event is not the one of the second predicted events, then determining a new event rule based on the target event, the first event and the second event; wherein the event rule mining result of the fire protection system includes the new event rule.

[0013] In an optional implementation of the first aspect, the method also includes: if the first event is one of the M first predicted events, determining M third predicted events associated with the first event based on the fire protection system topology and event similarity of the fire protection system; M is a positive integer; monitoring the first event, and obtaining the event rule mining results of the fire protection system based on the relationship between the next occurrence event of the first event and the M third predicted events.

[0014] In the second aspect, an embodiment of the present application provides an event rule mining device for a fire protection system, comprising: a data acquisition module for acquiring equipment data of N fire protection equipment detected in real time in the fire protection system; N is a positive integer; an event extraction module for extracting target events in the fire protection system based on the equipment data; an activity model correlation module for determining M first predicted events associated with the target event based on the fire protection system topology and event similarity of the fire protection system; M is a positive integer; a rule mining module for monitoring the target event, and obtaining event rule mining results of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events.

[0015] The beneficial effects of the present invention include: the embodiment of the present application provides an event rule mining method for a fire protection system, first, obtaining the equipment data of N fire protection equipment detected in real time in the fire protection system; then, extracting the target event in the fire protection system based on the equipment data; then, determining M first predicted events associated with the target event based on the fire protection system topology and event similarity of the fire protection system; finally, monitoring the target event, and based on the relationship between the next occurrence event of the target event and the M first predicted events, obtaining the event rule mining results of the fire protection system. That is, the embodiment of the present application proposes a new rule mining method, which uses the equipment data of N fire protection equipment in the fire protection system to extract the target event, and combines the correlation of the events for prediction, and uses the prediction results and the actual monitoring situation for rule mining. In this way, it can be determined whether there are unknown representations of known events or completely unknown events, thereby improving the comprehensiveness of the analysis of the fire protection system status. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for mining event rules for a fire protection system provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of a module of a fire protection system provided by an embodiment of the present invention;

[0018] Figure 3 This is a module block diagram of an event rule mining device for a fire protection system provided by an embodiment of the present invention;

[0019] Figure 4 This is a module block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0021] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0022] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context.

[0024] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0026] Classic methods for event mining in fire protection systems rely primarily on template matching, which compares data features with those of existing event data. With the continuous development of deep learning and machine learning, novel methods have emerged, such as sequential pattern mining and time series analysis. These techniques can uncover hidden patterns and regularities in event data, helping users better understand the causes and mechanisms behind events. They can also provide predictions and decision support for event occurrences, helping users make more accurate decisions. However, these techniques share a common flaw: they can only assess data within the context of a single task's rules. For example, in a fire warning task, the relevant rules must be used to determine whether data collected by sensors in an intelligent fire protection system is indicative of a fire (predicting a fire or not). While existing technologies have achieved good performance, these flaws present two weaknesses: first, they cannot fully explore data within a single task (the rules are fixed, but some rules that could represent other hidden features remain undiscovered); and second, they lack multi-task capabilities (a single model or technique can only solve a single task).

[0027] In view of the above problems, the present application proposes the following embodiments to solve the above technical problems.

[0028] See also Figure 1 In a first aspect, an embodiment of the present application provides an event rule mining method for a fire protection system, the method comprising: steps 101 to 104.

[0029] Step 101: Obtain equipment data of N firefighting equipment detected in real time in a firefighting system; N is a positive integer.

[0030] First, all firefighting equipment in the firefighting system will be detected in real time to obtain their equipment data. Here, it is assumed that the firefighting system includes N firefighting equipment. The specific number N can be determined based on the actual configuration of the firefighting system.

[0031] See also Figure 2 , Figure 2The figure shows some firefighting equipment in the firefighting system. Firefighting equipment may include various sensors, monitoring equipment, and alarm equipment. For example, firefighting equipment may specifically include temperature sensors, smoke sensors, humidity sensors, cameras, gas detectors, fire pumps, sirens, etc. It should be noted that Figure 2 The firefighting equipment shown is only an example. In a specific application, the firefighting system may include Figure 2 More firefighting equipment shown, or with Figure 2 The present application does not limit the different fire-fighting equipment shown.

[0032] Step 102: Extract target events in the fire protection system based on the equipment data.

[0033] Here, target events in the fire protection system are extracted based on the equipment data, that is, the target events are obtained by analyzing and processing the equipment data.

[0034] It should be noted that an event can be understood as a definable event or situation that occurs in the fire protection system. Examples include camera overheating, smoke alarm current reaching zero (circuit fault), water pressure at a sprinkler falling below a threshold (insufficient water pressure), a fire with smoke but no flames, a fire with both smoke and flames, or no fire.

[0035] The operation of a fire protection system can be understood as a series of events arranged in chronological order. For example, as a fire spreads, Event 1 (CO concentration reaching 1.1%) transitions to Event 2 (CO concentration reaching 1.7%).

[0036] Step 103: Determine M first predicted events associated with the target event according to the fire protection system topology and event similarity of the fire protection system; M is a positive integer.

[0037] Then, a fire protection system topology of the fire protection system and known events in the fire protection system may be obtained, and M first predicted events associated with the target event may be determined based on the fire protection system topology of the fire protection system and event similarities with known events.

[0038] In the embodiment of the present application, M is 5. That is, 5 first predicted events associated with the target event are determined according to the fire protection system topology and event similarity of the fire protection system.

[0039] Of course, in other embodiments, M can also be 3, 7, 9, etc.

[0040] The above determination process may be to extract M first prediction events in order from the largest to the smallest degree of association.

[0041] Step 104: Monitor the target event, and obtain the event rule mining result of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events.

[0042] Finally, the target event occurring at the current moment is monitored, and when the target event transitions to the next event, the relationship between the next event and the M first predicted events is determined, thereby obtaining the event rule mining results of the fire protection system.

[0043] In summary, the embodiment of the present application provides an event rule mining method for a fire protection system. First, the equipment data of N fire protection equipment detected in real time in the fire protection system is obtained; then, the target event in the fire protection system is extracted based on the equipment data; then, M first predicted events associated with the target event are determined based on the fire protection system topology and event similarity of the fire protection system; finally, the target event is monitored, and based on the relationship between the next occurrence event of the target event and the M first predicted events, the event rule mining results of the fire protection system can be obtained. That is, the embodiment of the present application proposes a new rule mining method, which uses the equipment data of N fire protection equipment in the fire protection system to extract the target event, and combines the correlation of the events to make predictions, and uses the prediction results and the actual monitoring situation to perform rule mining. In this way, it can be determined whether there are unknown representations of known events or completely unknown events, thereby improving the comprehensiveness of the analysis of the fire protection system status.

[0044] Optionally, the equipment data detected by each fire-fighting equipment includes at least one of operation data and perception data; the operation data is the data detected on the operation of the fire-fighting equipment itself; the perception data is the data obtained by the fire-fighting equipment through perception of the environment.

[0045] For example, the fire protection system consists of N fire protection equipment, and the operation data of the fire protection equipment can be expressed as ; Among them, the operating data can specifically include: voltage, current, water pressure and other data of the fire-fighting equipment itself.

[0046] The perception data of fire-fighting equipment can be expressed as ; Among them, you can use Indicates the type of sensory data collected by the device. The sensory data collected by a single firefighting device can be a single type or multiple types. Sensory data can specifically include smoke concentration, temperature, humidity, and other data sensed and acquired by the firefighting device.

[0047] Correspondingly, the above-mentioned step 102 extracts target events in the fire protection system based on equipment data, which may specifically include: inputting the operation data and the perception data into the autoencoder, projecting the perception data to the same dimension as the operation data through the autoencoder, and then performing event recognition to extract the target event.

[0048] It should be noted that before inputting the operation data and perception data into the autoencoder, the operation data and perception data need to be aligned according to the timestamp, which can effectively improve the accuracy of subsequent event extraction and the accuracy of event rule mining.

[0049] Specifically, the data will be run and sensory data Aligning by timestamp yields: 、 etc.

[0050] The following describes the network structure of the autoencoder. In the embodiment of the present application, the autoencoder is a two-stage network, which includes a projection network and a visual self-attention network.

[0051] The autoencoder can be expressed by the following formula:

[0052] ;

[0053] Among them, the above formula represents the working principle of the self-encoder, that is, first the perception data Projecting and running data The same dimension is used for joint feature extraction. In this formula, Data representing dimension alignment in perceptual data; Represents dimensionally aligned data in running data; represents the projection network; Represents the visual self-attention network (i.e., ViT network).

[0054] Specifically, the projection network is used to project the perception data into the same dimension as the running data; the visual self-attention network is used to perform event recognition based on the perception data and running data of the same dimension to extract the target event.

[0055] The loss function of the projection network is based on KL divergence; the loss function expression of the projection network includes:

[0056] ;

[0057] in, represents the loss function of the projection network; represents KL divergence; representing the sensory data; Indicates operating data; Data representing dimension alignment in perceptual data; Represents dimensionally aligned data in running data;

[0058] The loss function expression of the visual self-attention network includes:

[0059] ;

[0060] in, Represents the loss function of the visual self-attention network; Indicates the number of fire-fighting equipment; Represents event indicators about operational data; Represents the event indicator about the perception data. When training the above autoencoder, + That's it.

[0061] In summary, in the embodiment of the present application, the sensory data is first converted into Projecting and running data The same dimension is used, and then joint feature extraction is performed to finally output the target event. That is, the present invention uses perception data and operation data to complete joint event extraction by projection. The extraction results can be used not only for rule mining, but also for all downstream tasks involving perception data and operation data, making the analysis of the fire protection system more diverse, and there is no need to build a specific model for a specific task as in the prior art.

[0062] Optionally, M first predicted events associated with the target event are determined based on the fire system topology and event similarity of the fire system, including: obtaining G known events in the fire system; calculating the correlation between each known event and the target event based on the fire system topology of the fire system and the event similarity between each known event and the target event; and extracting M first predicted events from the G known events based on the correlation between each known event and the target event.

[0063] It should be explained that the operation process of the fire protection system is the series of events in time. Assuming that these events are known in advance, the operation process of the fire protection system is transformed into an event allocation task. At each specific moment, a specific event is allocated to the system. A series of allocated behaviors is defined as an activity. Assuming that a specific time period is ~ ,exist The event assigned at time (start) is , The duration of , then the next event that occurs Should be with The highest correlation. ~ The sum of the durations of events initiated within a time period should be greater than - .

[0064] Optionally, in an embodiment of the present application, the calculation formula for the correlation between the known event and the target event includes:

[0065] ;

[0066] In this formula, Indicates the target event; Indicates any known event; Indicates the correlation between the target event and the known events; Indicates that in the fire protection system topology diagram, the target event and known events The path length between them; it should be noted that here, the target event and known events The path length between the target events Source device to known events The access step length of the source device is determined by the traversal method, which is depth-optimal traversal. Indicates the data-level similarity between the target event and known events. Data-level similarity can be understood as the similarity in data changes, such as the spread of a fire, carbon monoxide concentration, and changes in indoor temperature. This similarity can be measured using the Jcard similarity, but this application does not limit this.

[0067] Optionally, in step 104, obtaining the event rule mining result of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events may further specifically include the following three situations:

[0068] In the first case, if the first event is not one of the M first predicted events, then M second predicted events associated with each first predicted event are determined based on the fire system topology and event similarity of the fire system; where the first event is the next occurrence of the target event; the total number of second predicted events is If the second event is If one of the second predicted events is found, the second event is determined to be a hidden representation of the first event; wherein the second event is the next occurrence event of the first event; and the event rule mining result of the fire protection system includes that the second event is a hidden representation of the first event.

[0069] In other words, the first case can mine hidden representations between events, that is, mine unknown representations.

[0070] For example, when M=5, when acquiring the target event Then, five associated first prediction events are obtained through step 103, including ( , , , , ), then, for the target event Monitor and when an event changes, enter the next event (the first event ), judge the first event Does it belong to ( , , , , ), if not, then based on the above step 103, five second predicted events associated with each first event are determined, for example, The associated 5 second prediction events include ( , , , , ); and the first predicted event The associated 5 second prediction events include ( , , , , ); and the first predicted event The associated 5 second prediction events include ( , , , , ); and the first predicted event The associated 5 second prediction events include ( , , , , ); and the first predicted event The associated 5 second prediction events include ( , , , , ). The total number of the second predicted events is 25. Then, continue to predict the first event The next event (i.e. the second event) ) judgment. If the second event Belong to one of the above 25 second prediction events, then the second event is determined It is the first event hidden representation of .

[0071] Case 2: If the second event is not One of the second predicted events is determined based on the target event, the first event and the second event; wherein the event rule mining result of the fire protection system includes the new event rule.

[0072] That is, continuing with the above example, if the second event If it does not belong to one of the above 25 second prediction events, then based on the target event , First Event And the second event Once a new event rule is determined, the staff can be notified to extract the specific operating status and perception data of the equipment and analyze the specific representation of the rule.

[0073] In the third case, if the first event is one of the M first predicted events, the M third predicted events associated with the first event are determined according to the fire protection system topology and event similarity of the fire protection system; M is a positive integer; the first event is monitored, and based on the relationship between the next occurrence of the first event and the M third predicted events, the event rule mining results of the fire protection system are obtained.

[0074] In other words, when the first event is one of the M first predicted events, it is characterized as a prediction of a known activity, and then the above method can be synchronously executed on the next event to continue monitoring and mining.

[0075] For example, the above M=5, when obtaining the target event Then, five associated first prediction events are obtained through step 103, including ( , , , , ), then, for the target event Monitor and when an event changes, enter the next event (the first event ), judge the first event Does it belong to ( , , , , ), if so, then based on the above step 103, determine M third predicted events associated with the first event, and continue to predict the first event. Monitor and obtain event rule mining results of the fire protection system based on the relationship between the next occurrence event of the first event and the M third predicted events.

[0076] See also Figure 3Based on the same inventive concept, the embodiment of the present application further provides an event rule mining device 300 for a fire protection system, comprising:

[0077] The data acquisition module 301 is used to obtain the equipment data of N fire-fighting equipment detected in real time in the fire-fighting system; N is a positive integer.

[0078] The event extraction module 302 is configured to extract target events in the fire protection system based on the device data.

[0079] The activity model correlation module 303 is configured to determine M first predicted events associated with the target event according to the fire protection system topology and event similarity of the fire protection system; M is a positive integer.

[0080] The rule mining module 304 is configured to monitor the target event and obtain an event rule mining result of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events.

[0081] Optionally, the equipment data detected by each fire-fighting equipment includes at least one of operation data and perception data; the operation data is data detected on the operation of the fire-fighting equipment itself; and the perception data is data obtained by the fire-fighting equipment sensing the environment.

[0082] Optionally, the event extraction module 302 is further specifically used to input the operation data and the perception data into an autoencoder, project the perception data to the same dimension as the operation data through the autoencoder, and then perform event recognition to extract the target event.

[0083] Optionally, the autoencoder is a two-stage network, comprising a projection network and a visual self-attention network; the projection network is used to project the perception data into the same dimension as the operational data; the visual self-attention network is used to perform event recognition based on the perception data and operational data of the same dimension to extract the target event;

[0084] The loss function of the projection network is based on KL divergence; the loss function expression of the projection network includes:

[0085] ;in, represents the loss function of the projection network; represents the KL divergence; representing the sensory data; indicating the operating data; Data representing dimension alignment in the perception data; Data representing dimension alignment in the operating data; represents the projection network;

[0086] The loss function expression of the visual self-attention network includes:

[0087] ;in, represents the loss function of the visual self-attention network; Indicates the number of fire-fighting equipment; representing event indicators related to the operational data; representing an event indicator regarding the sensory data; Represents the visual self-attention network.

[0088] Optionally, the activity model correlation module 303 is further configured to obtain G known events in the fire protection system; calculate the correlation between each known event and the target event based on the fire protection system topology of the fire protection system and the event similarity between each known event and the target event; and extract the M first predicted events from the G known events according to the correlation between each known event and the target event.

[0089] Optionally, the calculation formula for the correlation between each of the known events and the target event includes: ;in, represents the target event; represents any of the known events; Indicates the correlation between the target event and the known event; represents the path length between the target event and the known event in the fire protection system topology diagram; Indicates the similarity between the target event and the known event at the data level.

[0090] Optionally, the rule mining module 304 is further specifically configured to determine, if the first event is not one of the M first predicted events, M second predicted events associated with each of the first predicted events based on the fire protection system topology and event similarity of the fire protection system; wherein the first event is the next occurrence event of the target event; the total number of the second predicted events is If the second event is If one of the second predicted events is found, it is determined that the second event is a hidden representation of the first event; wherein, the second event is the next occurrence event of the first event; and the event rule mining result of the fire protection system includes that the second event is a hidden representation of the first event.

[0091] Optionally, the rule mining module 304 is further configured to: one of the second predicted events, then determining a new event rule based on the target event, the first event and the second event; wherein the event rule mining result of the fire protection system includes the new event rule.

[0092] Optionally, the rule mining module 304 is further specifically used to determine, if the first event is one of the M first predicted events, M third predicted events associated with the first event based on the fire protection system topology and event similarity of the fire protection system; M is a positive integer; monitor the first event, and obtain the event rule mining results of the fire protection system based on the relationship between the next occurrence event of the first event and the M third predicted events.

[0093] See also Figure 4 Based on the same inventive concept, the embodiment of the present application provides a module frame of an electronic device 400 that applies the above-mentioned event rule mining method for fire protection system. The electronic device 400 includes: at least one processor 401 ( Figure 4 Only one is shown), a memory 402, a computer program 403 stored in the memory 402 and executable on at least one processor 401, wherein the processor 401 executes the computer program 403 to implement the steps of the event rule mining method for the fire protection system in any of the aforementioned embodiments.

[0094] The electronic device 400 may be a personal computer, a notebook computer, etc., or may be a camera device itself. When the electronic device 400 is a personal computer, the personal computer is electrically connected or communicatively connected to the camera device.

[0095] Processor 401, memory 402. Those skilled in the art will understand that Figure 4 This is merely an example of the electronic device 400 and does not constitute a limitation on the electronic device 400 . The electronic device 400 may include more or fewer components than shown in the figure, or may combine certain components, or may include different components.

[0096] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0097] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 400. Furthermore, the memory 402 may include both an internal storage unit of the electronic device 400 and an external storage device.

[0098] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0100] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0101] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0103] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0104] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0105] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0106] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0107] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An event rule mining method for fire protection system, characterized by: include: Obtain the equipment data of N fire-fighting equipment detected in real time in the fire-fighting system; N is a positive integer; extracting target events in the fire protection system based on the device data; Determining M first predicted events associated with the target event based on a fire protection system topology and event similarities of the fire protection system; M is a positive integer; Monitoring the target event, and obtaining an event rule mining result of the fire protection system based on a relationship between a next occurrence event of the target event and the M first predicted events; The determining of the M first predicted events associated with the target event based on the fire protection system topology and event similarity of the fire protection system includes: obtaining G known events in the fire protection system; calculating the correlation between each known event and the target event based on the fire protection system topology of the fire protection system and the event similarity between each known event and the target event; and extracting the M first predicted events from the G known events based on the correlation between each known event and the target event. The calculation formula for the correlation between each known event and the target event includes: ;in, represents the target event; represents any of the known events; Indicates the correlation between the target event and the known event; Indicates the path length between the target event and the known event in the fire protection system topology diagram, which is determined by the access step length from the source device of the target event to the source device of the known event; Indicates the similarity between the target event and the known event at the data level.

2. The method according to claim 1, characterized in that The equipment data detected by each fire-fighting equipment includes at least one of operation data and perception data; the operation data is the data detected on the operation of the fire-fighting equipment itself; the perception data is the data obtained by the fire-fighting equipment through perception of the environment.

3. The method according to claim 2, characterized in that The extracting target events in the fire protection system based on the device data includes: The operating data and the perception data are input into an autoencoder, and after the perception data is projected to the same dimension as the operating data through the autoencoder, event recognition is performed to extract the target event.

4. The method according to claim 3, characterized in that The autoencoder is a two-stage network, comprising a projection network and a visual self-attention network; the projection network is used to project the perception data into the same dimension as the operational data; the visual self-attention network is used to perform event recognition based on the perception data and operational data of the same dimension to extract the target event; The loss function of the projection network is based on KL divergence; The loss function expression of the projection network includes: ;in, represents the loss function of the projection network; represents the KL divergence; representing the sensory data; indicating the operating data; Data representing dimension alignment in the perception data; Data representing dimension alignment in the operating data; represents the projection network; The loss function expression of the visual self-attention network includes: ;in, represents the loss function of the visual self-attention network; Indicates the number of fire-fighting equipment; representing event indicators related to the operational data; representing an event indicator regarding the sensory data; Represents the visual self-attention network.

5. The method according to claim 1, wherein The acquiring of the event rule mining result of the fire protection system based on the relationship between the next occurrence event of the target event and the M first predicted events includes: If the first event is not one of the M first predicted events, then determine M second predicted events associated with each of the first predicted events based on the fire protection system topology and event similarity of the fire protection system; wherein the first event is the next occurrence event of the target event; the total number of the second predicted events is indivual; If the second event is If one of the second predicted events is found, it is determined that the second event is a hidden representation of the first event; wherein, the second event is the next occurrence event of the first event; and the event rule mining result of the fire protection system includes that the second event is a hidden representation of the first event.

6. The method according to claim 5, characterized in that The method further comprises: If the second event is not the one of the second predicted events, then determining a new event rule based on the target event, the first event and the second event; wherein the event rule mining result of the fire protection system includes the new event rule.

7. The method according to claim 5, characterized in that The method further comprises: If the first event is one of the M first predicted events, determining M third predicted events associated with the first event according to the fire protection system topology and event similarity of the fire protection system; M is a positive integer; The first event is monitored, and based on the relationship between the next occurrence event of the first event and the M third predicted events, an event rule mining result of the fire protection system is obtained.

8. An event rule mining device for fire protection system, characterized in that: include: A data acquisition module is used to obtain equipment data of N fire-fighting equipment detected in real time in the fire-fighting system; N is a positive integer; An event extraction module, configured to extract target events in the fire protection system based on the device data; an activity model correlation module, configured to determine M first predicted events associated with the target event based on a fire protection system topology and event similarities of the fire protection system; M is a positive integer; a rule mining module, configured to monitor the target event and obtain an event rule mining result of the fire protection system based on a relationship between a next occurrence event of the target event and the M first predicted events; The activity model correlation module is specifically configured to obtain G known events in the fire protection system; calculate the correlation between each known event and the target event based on the fire protection system topology of the fire protection system and the event similarity between each known event and the target event; and extract the M first predicted events from the G known events based on the correlation between each known event and the target event. The calculation formula for the correlation between each known event and the target event includes: ;in, represents the target event; represents any of the known events; Indicates the correlation between the target event and the known event; Indicates the path length between the target event and the known event in the fire protection system topology diagram, which is determined by the access step length from the source device of the target event to the source device of the known event; Indicates the similarity between the target event and the known event at the data level.

Images