CN116778412A - Park abnormal event early warning method and system based on model analysis - Google Patents
Park abnormal event early warning method and system based on model analysis Download PDFInfo
- Publication number
- CN116778412A CN116778412A CN202310717973.6A CN202310717973A CN116778412A CN 116778412 A CN116778412 A CN 116778412A CN 202310717973 A CN202310717973 A CN 202310717973A CN 116778412 A CN116778412 A CN 116778412A
- Authority
- CN
- China
- Prior art keywords
- park
- abnormal
- abnormal event
- network
- event decision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 296
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 82
- 238000001931 thermography Methods 0.000 claims abstract description 80
- 230000000694 effects Effects 0.000 claims abstract description 46
- 238000005457 optimization Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 14
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a park abnormal event early warning method and system based on model analysis, which are used for acquiring park infrared thermal imaging monitoring flow data corresponding to a target intelligent park, wherein the park infrared thermal imaging monitoring flow data comprises park infrared thermal imaging monitoring flow data corresponding to a set abnormal knowledge point of the target intelligent park in a set early warning analysis period; the park infrared thermal imaging monitoring stream data is loaded into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, and the park abnormal event decision network conforming to the network deployment conditions is generated by updating network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activities, so that early warning operation is conveniently executed based on the park abnormal event decision data, and reliability of park security monitoring is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a park abnormal event early warning method and system based on model analysis.
Background
The intelligent park is a novel generation information and communication technology, has the advantages of rapid information acquisition, high-speed information transmission, high centralized calculation, intelligent transaction processing and ubiquitous service providing capability, and realizes timely, interactive and integrated information sensing, transmission and processing in the park so as to improve the park industry gathering capability, enterprise economic competitiveness and the advanced park development idea of the park sustainable development as a target. For an intelligent park, how to timely early warn the park abnormal events related to the safety of the park, so as to improve the reliability of park security monitoring is a technical problem to be solved currently.
Disclosure of Invention
Accordingly, the present application is directed to a method and system for early warning of abnormal events in a park based on model analysis.
According to a first aspect of the present application, there is provided a method for early warning of a park abnormal event based on model analysis, applied to a cloud server, the method comprising:
acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park, wherein the park infrared thermal imaging monitoring stream data comprises park infrared thermal imaging monitoring stream data corresponding to a set abnormal knowledge point of the target intelligent park in a set early warning analysis period;
loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, wherein the park abnormal event decision data comprises at least one of real-time abnormal park abnormal events, forward abnormal park abnormal events and backward abnormal park abnormal events corresponding to the target intelligent park;
executing early warning operation based on the park abnormal event decision data;
the park abnormal event decision network meeting the network deployment condition is generated by updating network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity.
In a possible implementation manner of the first aspect, the method further includes:
updating the network weight parameters of the initialized park abnormal event decision network to generate a park abnormal event decision network generated by updating the network weight parameters;
and the method for updating the network weight parameters of the initialized park abnormal event decision network, generating the park abnormal event decision network generated by updating the network weight parameters, comprises the following steps:
acquiring infrared thermal imaging monitoring sample learning data corresponding to a target intelligent park, loading the infrared thermal imaging monitoring sample learning data into an initialization park abnormal event decision network, and generating sample learning results corresponding to a plurality of abnormal knowledge points;
judging whether the initialization park abnormal event decision network meets the sample learning termination requirement or not based on sample learning results corresponding to all the abnormal knowledge points;
and generating a park abnormal event decision network generated by updating the network weight parameters based on sample learning results corresponding to all the abnormal knowledge points when the initialized park abnormal event decision network meets the sample learning termination requirements.
In a possible implementation manner of the first aspect, the determining, based on the sample learning results corresponding to all the abnormal knowledge points, whether the initialization-park abnormal event decision network meets a sample learning termination requirement includes:
determining target sample abnormal learning data corresponding to each abnormal knowledge point, and determining a learning effect value corresponding to each abnormal knowledge point based on the target sample abnormal learning data corresponding to the abnormal knowledge point and a corresponding sample learning result;
judging whether one or more target abnormal knowledge points meeting the learning effect requirements exist in all the abnormal knowledge points or not based on learning effect values corresponding to all the abnormal knowledge points;
when one or more target abnormal knowledge points exist in all the abnormal knowledge points, determining that the initialization park abnormal event decision network meets a sample learning termination requirement;
and when the target abnormal knowledge points do not exist in all the abnormal knowledge points, determining that the initialization park abnormal event decision network does not meet the sample learning termination requirement.
In a possible implementation manner of the first aspect, the generating a campus abnormal event decision network that performs updating generation of a network weight parameter based on sample learning results corresponding to all the abnormal knowledge points includes:
extracting target sample learning results corresponding to the target abnormal knowledge points from sample learning results corresponding to all the abnormal knowledge points;
determining target network weight information based on the target abnormal knowledge points and the target sample learning result;
and generating a park abnormal event decision network for updating and generating network weight parameters based on the target network weight information and the initialized park abnormal event decision network.
In a possible implementation manner of the first aspect, the method further includes:
when the initialization park abnormal event decision network does not meet the sample learning termination requirement, determining weight information to be updated corresponding to the initialization park abnormal event decision network based on sample learning results corresponding to all the abnormal knowledge points and a set network weight information updating requirement;
determining a weight information optimization state corresponding to the weight information to be updated based on the weight information to be updated, sample learning results corresponding to all the abnormal knowledge points and a set network weight information optimization requirement;
and based on the weight information optimization state, executing weight information optimization operation on the initialization park abnormal event decision network, generating the initialization park abnormal event decision network after weight information optimization, and executing the operation of loading the infrared thermal imaging monitoring sample learning data into the initialization park abnormal event decision network according to the initialization park abnormal event decision network after weight information optimization, and generating sample learning results corresponding to a plurality of abnormal knowledge points.
In a possible implementation manner of the first aspect, after the loading the campus infrared thermal imaging monitoring stream data into a campus exception decision network that meets a network deployment condition, generating the campus exception decision data, the method further includes:
acquiring actual abnormal event data corresponding to the target intelligent park, analyzing the actual abnormal event data and the park abnormal event decision data, and generating a loss function value;
judging whether the loss function value is not smaller than a preset set loss function value;
when the loss function value is not smaller than the set loss function value, determining that the abnormal event decision state corresponding to the park abnormal event decision network is inaccurate in abnormal event decision;
determining abnormal event decision distinguishing information based on the loss function value, the actual abnormal event data and the park abnormal event decision data when the loss function value is smaller than the set loss function value;
determining decision distinguishing optimization information corresponding to the park abnormal event decision network based on the abnormal event decision distinguishing information and the set decision distinguishing optimization requirement;
based on the decision distinguishing optimization information, performing weight parameter optimization operation on the park abnormal event decision network, and generating a park abnormal event decision network with optimized weight parameters; and executing the operation of loading the park infrared thermal imaging monitoring stream data into the park abnormal event decision network conforming to the network deployment condition according to the park abnormal event decision network after the weight parameter optimization, and generating park abnormal event decision data.
In a possible implementation manner of the first aspect, the method further includes:
when the abnormal event decision state corresponding to the park abnormal event decision network is an abnormal event decision accuracy, determining an infrared thermal imaging monitoring activity state corresponding to the target intelligent park based on the park abnormal event decision data and the actual abnormal event data, wherein the infrared thermal imaging monitoring activity state comprises an infrared thermal imaging monitoring activity real-time state and/or an infrared thermal imaging monitoring activity trend state;
determining a trigger probability value of the infrared thermal imaging monitoring activity linkage state corresponding to the target intelligent park based on the infrared thermal imaging monitoring activity state and the set linkage state mining requirement;
judging whether the trigger probability value is not smaller than a preset threshold trigger probability value or not;
and when the trigger probability value is not smaller than the threshold trigger probability value, predicting linkage trigger information corresponding to the target intelligent park based on the infrared thermal imaging monitoring activity state, the trigger probability value and the set linkage state estimation requirement, wherein the linkage trigger information is used for indicating abnormal linkage activities with high trigger probability value.
According to a second aspect of the application, there is provided a model analysis-based park abnormal event early warning system; the park abnormal event early warning system based on model analysis comprises a cloud server and a park thermal imaging monitoring system in communication connection with the cloud server, wherein the cloud server is particularly used for:
acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park, wherein the park infrared thermal imaging monitoring stream data comprises park infrared thermal imaging monitoring stream data corresponding to a set abnormal knowledge point of the target intelligent park in a set early warning analysis period;
loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, wherein the park abnormal event decision data comprises at least one of real-time abnormal park abnormal events, forward abnormal park abnormal events and backward abnormal park abnormal events corresponding to the target intelligent park;
executing early warning operation based on the park abnormal event decision data;
the park abnormal event decision network meeting the network deployment condition is generated by updating network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity.
According to any one of the above aspects, in the present application, the campus infrared thermal imaging monitoring stream data corresponding to the target smart campus is obtained, where the campus infrared thermal imaging monitoring stream data includes the campus infrared thermal imaging monitoring stream data corresponding to the target smart campus for the set abnormal knowledge points in the set early warning analysis period; loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, wherein the park abnormal event decision data comprises at least one of real-time abnormal park abnormal events, forward abnormal park abnormal events and backward abnormal park abnormal events corresponding to the target intelligent park; the park abnormal event decision network meeting the network deployment condition is generated by updating the network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity, so that early warning operation is conveniently executed based on park abnormal event decision data, and reliability of park security monitoring is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for early warning of a park abnormal event based on model analysis according to an embodiment of the present application;
fig. 2 is a schematic component structure of a cloud server for implementing the above-mentioned method for early warning of a park abnormal event based on model analysis according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are for the purpose of illustration and description only, and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented based on some embodiments of the application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Furthermore, one or more other operations may be added to the flow chart or one or more operations may be destroyed from the flow chart as directed by those skilled in the art in light of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
Fig. 1 shows a flow chart of a method for early warning of a park abnormal event based on model analysis according to an embodiment of the present application, and it should be understood that in other embodiments, the order of part of the steps in the method for early warning of a park abnormal event based on model analysis according to the present application may be shared with each other according to actual needs, or part of the steps may be omitted or maintained. The park abnormal event early warning method based on model analysis comprises the following steps of:
step S101, acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park.
In one exemplary design concept, the campus infrared thermal imaging monitoring stream data includes the campus infrared thermal imaging monitoring stream data corresponding to a target smart campus for a set abnormal knowledge point in a set early warning analysis period.
In an exemplary design concept, the infrared thermal imaging monitoring flow data of the park may be thermal imaging image acquisition data of a target intelligent park in a certain time, and the thermal imaging technology refers to that an infrared detector and an optical imaging objective lens are utilized to receive infrared radiation energy distribution patterns of a detected target and reflect the infrared radiation energy distribution patterns onto a photosensitive element of the infrared detector, so as to obtain an infrared thermal image, wherein the thermal image corresponds to a thermal distribution field of the surface of an object. Infrared thermographic monitoring systems colloquially convert invisible infrared energy emitted by an object into a visible thermal image. Different colors on the thermal image represent different temperatures of the object under test.
And step S102, loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data.
In an exemplary design concept, the campus exception decision data includes at least one of a real-time exception, a forward exception, and a backward exception for the target smart campus; the park abnormal event decision network meeting the network deployment condition is generated by updating the network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity.
And step 103, executing early warning operation based on the park abnormal event decision data.
Based on the above steps, the park abnormal event decision of the target intelligent park is realized by adopting the priori park infrared thermal imaging monitoring flow data training convergence park abnormal event decision network according to the target intelligent park, and the abnormal trend state of the infrared thermal imaging monitoring activity of the target intelligent park can be decided, so that early warning operation is conveniently executed based on park abnormal event decision data, and the reliability of park security monitoring is improved.
Further embodiments are described below, specifically, a network weight information update flow for a campus exceptional decision network, comprising the following operations:
step S201, updating the network weight parameters of the initialized park abnormal event decision network to generate a park abnormal event decision network generated by updating the network weight parameters.
Step S202, acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park.
And step 203, loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to the network deployment condition to generate park abnormal event decision data.
The above-mentioned updating of the network weight parameter for initializing the park abnormal event decision network, generating the park abnormal event decision network for updating the network weight parameter, may include:
acquiring infrared thermal imaging monitoring sample learning data corresponding to a target intelligent park, loading the infrared thermal imaging monitoring sample learning data into an initialization park abnormal event decision network, and generating sample learning results corresponding to a plurality of abnormal knowledge points;
judging whether the initialization park abnormal event decision network meets the sample learning termination requirement or not based on sample learning results corresponding to all abnormal knowledge points;
and when the initialized park abnormal event decision network meets the sample learning termination requirement, generating a park abnormal event decision network for updating the network weight parameters based on sample learning results corresponding to all abnormal knowledge points.
In other exemplary design ideas, the determining whether the initialization park abnormal event decision network meets the sample learning termination requirement based on the sample learning results corresponding to all the abnormal knowledge points may include:
determining target sample abnormal learning data corresponding to each abnormal knowledge point, and determining a learning effect value corresponding to each abnormal knowledge point based on the target sample abnormal learning data corresponding to the abnormal knowledge point and a corresponding sample learning result;
judging whether one or more target abnormal knowledge points meeting the learning effect requirements exist in all the abnormal knowledge points based on learning effect values corresponding to all the abnormal knowledge points;
when one or more target abnormal knowledge points exist in all abnormal knowledge points, determining that an initialization park abnormal event decision network meets a sample learning termination requirement;
and when the target abnormal knowledge points do not exist in all the abnormal knowledge points, determining that the initialization park abnormal event decision network does not meet the sample learning termination requirement.
In an exemplary design concept, the learning effect value determination may be performed by partially combining the abnormal knowledge points, for example, the learning effect value determination corresponding to each two abnormal knowledge points may be performed by all the abnormal knowledge points.
In an exemplary design concept, the learning effect requirement is met, and the learning effect value sorting condition is met, the learning effect value threshold comparison condition is met, and the learning effect value comparison condition between abnormal knowledge points is met.
In an exemplary design concept, the generating a campus abnormal event decision network based on the sample learning results corresponding to all abnormal knowledge points, where the generating is performed by updating the network weight parameters, may include:
extracting target sample learning results corresponding to the target abnormal knowledge points from sample learning results corresponding to all the abnormal knowledge points;
determining target network weight information based on the target abnormal knowledge points and the target sample learning result;
and generating a park abnormal event decision network for updating and generating network weight parameters based on the target network weight information and the initialized park abnormal event decision network.
In an exemplary design concept, the method may further include the operations of:
when the initialization park abnormal event decision network does not accord with the sample learning termination requirement, determining weight information to be updated corresponding to the initialization park abnormal event decision network based on sample learning results corresponding to all abnormal knowledge points and set network weight information updating requirements;
determining a weight information optimization state corresponding to the weight information to be updated based on the weight information to be updated, sample learning results corresponding to all abnormal knowledge points and the set network weight information optimization requirement;
based on the weight information optimization state, performing weight information optimization operation on the initialization park abnormal event decision network, generating an initialization park abnormal event decision network after weight information optimization, and performing operation of loading infrared thermal imaging monitoring sample learning data into the initialization park abnormal event decision network according to the initialization park abnormal event decision network after weight information optimization, and generating sample learning results corresponding to a plurality of abnormal knowledge points.
In an exemplary design concept, after the loading the infrared thermal imaging monitoring stream data of the campus into the campus abnormal event decision network meeting the network deployment condition to generate the campus abnormal event decision data, the following operations may further be included:
acquiring actual abnormal event data corresponding to a target intelligent park, analyzing the actual abnormal event data and park abnormal event decision data, and generating a loss function value;
judging whether the loss function value is not smaller than a preset set loss function value;
when the loss function value is not smaller than the set loss function value, determining that the abnormal event decision state corresponding to the park abnormal event decision network is accurate in abnormal event decision;
determining abnormal event decision distinguishing information based on the loss function value, actual abnormal event data and park abnormal event decision data when the loss function value is smaller than the set loss function value; determining decision distinguishing optimization information corresponding to a park abnormal event decision network based on the abnormal event decision distinguishing information and the set decision distinguishing optimization requirement; based on the decision distinguishing optimization information, performing weight parameter optimization operation on the park abnormal event decision network to generate a park abnormal event decision network with optimized weight parameters; and according to the park abnormal event decision network after the weight parameter optimization, executing the operation of loading the park infrared thermal imaging monitoring stream data into the park abnormal event decision network conforming to the network deployment condition to generate park abnormal event decision data.
In an exemplary design concept, the method may further include the operations of:
when the abnormal event decision state corresponding to the park abnormal event decision network is accurate in abnormal event decision, determining an infrared thermal imaging monitoring activity state corresponding to the target intelligent park based on park abnormal event decision data and actual abnormal event data, wherein the infrared thermal imaging monitoring activity state comprises an infrared thermal imaging monitoring activity real-time state and/or an infrared thermal imaging monitoring activity trend state;
determining a trigger probability value of the infrared thermal imaging monitoring activity linkage state corresponding to the target intelligent park based on the infrared thermal imaging monitoring activity state and the set linkage state mining requirement;
judging whether the trigger probability value is not smaller than a preset threshold trigger probability value or not;
when the trigger probability value is not smaller than the threshold trigger probability value, based on the infrared thermal imaging monitoring activity state, the trigger probability value and the set linkage state estimation requirement, the linkage trigger information corresponding to the target intelligent park is predicted, and the linkage trigger information is used for indicating the linkage abnormal activity with high trigger probability value.
Fig. 2 schematically illustrates a cloud server 100 that may be used to implement various embodiments described in the present disclosure.
For one embodiment, fig. 2 shows a cloud server 100, the cloud server 100 having one or more processors 102, a control module (chipset) 104 coupled to one or more of the processor(s) 102, a memory 106 coupled to the control module 104, a non-volatile memory (NVM)/storage 108 coupled to the control module 104, one or more input/output devices 110 coupled to the control module 104, and a network interface 112 coupled to the control module 106.
The processor 102 may include one or more single-core or multi-core processors, and the processor 102 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some exemplary design considerations, the cloud server 100 can be used as a server device such as a gateway in the embodiments of the present application.
In some example design considerations, cloud server 100 may include one or more computer-readable media (e.g., memory 106 or NVM/storage 108) having instructions 114 and one or more processors 102, in conjunction with the one or more computer-readable media, configured to execute instructions 114 to implement modules to perform actions described in this disclosure.
For one embodiment, the control module 104 may include any suitable interface controller to provide any suitable interface to one or more of the processor(s) 102 and/or any suitable device or component in communication with the control module 104.
The control module 104 may include a memory controller module to provide an interface to the memory 106. The memory controller modules may be hardware modules, software modules, and/or firmware modules.
Memory 106 may be used, for example, to load and store data and/or instructions 114 for cloud server 100. For one embodiment, memory 106 may comprise any suitable volatile memory, such as, for example, a suitable DRAM. In some exemplary design considerations, memory 106 may include a double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).
For one embodiment, control module 104 may include one or more input/output controllers to provide interfaces to NVM/storage 108 and input/output device(s) 110.
For example, NVM/storage 108 may be used to store data and/or instructions 114. NVM/storage 108 may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).
NVM/storage 108 may include storage resources that are physically part of the device on which cloud server 100 is installed, or may be accessible by the device without necessarily being part of the device. For example, NVM/storage 108 may be accessed via input/output device(s) 110 according to a network.
Input/output device(s) 110 may provide an interface for cloud server 100 to communicate with any other suitable device, and input/output device 110 may include a communication component, pinyin component, sensor component, and the like. The network interface 112 may provide an interface for the cloud server 100 to communicate in accordance with one or more networks, and the cloud server 100 may communicate wirelessly with one or more components of a wireless network in accordance with any of one or more wireless network standards and/or protocols, such as accessing a wireless network in accordance with a communication standard, such as WwFw, 2G, 3G, 4G, 5G, etc., or a combination thereof.
For one embodiment, one or more of the processor(s) 102 may be loaded with logic of one or more controllers (e.g., memory controller modules) of the control module 104. For one embodiment, one or more of the processor(s) 102 may be loaded together with logic of one or more controllers of the control module 104 to form a system level load (SwP). For one embodiment, one or more of the processor(s) 102 may be integrated on the same mold as logic of one or more controllers of the control module 104. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with logic of one or more controllers of the control module 104 to form a system on chip (SoC).
In various embodiments, cloud server 100 may be, but is not limited to being: cloud servers, desktop computing devices, or mobile computing devices (e.g., laptop computing devices, handheld computing devices, tablet computers, netbooks, etc.). In various embodiments, cloud server 100 may have more or fewer components and/or different architectures. For example, in some exemplary design considerations, cloud server 100 includes one or more cameras, keyboards, liquid Crystal Display (LCD) screens (including touch screen displays), non-volatile memory ports, multiple antennas, graphics chips, application Specific Integrated Circuits (ASICs), and speakers.
The foregoing has outlined rather broadly the more detailed description of embodiments of the application, wherein the principles and embodiments of the application are explained in detail using specific examples, the above examples being provided solely to facilitate the understanding of the method and core concepts of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (9)
1. The park abnormal event early warning method based on model analysis is characterized by being applied to a cloud server, and comprises the following steps:
acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park, wherein the park infrared thermal imaging monitoring stream data comprises park infrared thermal imaging monitoring stream data corresponding to a set abnormal knowledge point of the target intelligent park in a set early warning analysis period;
loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, wherein the park abnormal event decision data comprises at least one of real-time abnormal park abnormal events, forward abnormal park abnormal events and backward abnormal park abnormal events corresponding to the target intelligent park;
executing early warning operation based on the park abnormal event decision data;
the park abnormal event decision network meeting the network deployment condition is generated by updating network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity.
2. The model analysis based campus anomaly early warning method of claim 1, further comprising:
updating the network weight parameters of the initialized park abnormal event decision network to generate a park abnormal event decision network generated by updating the network weight parameters;
and the method for updating the network weight parameters of the initialized park abnormal event decision network, generating the park abnormal event decision network generated by updating the network weight parameters, comprises the following steps:
acquiring infrared thermal imaging monitoring sample learning data corresponding to a target intelligent park, loading the infrared thermal imaging monitoring sample learning data into an initialization park abnormal event decision network, and generating sample learning results corresponding to a plurality of abnormal knowledge points;
judging whether the initialization park abnormal event decision network meets the sample learning termination requirement or not based on sample learning results corresponding to all the abnormal knowledge points;
and generating a park abnormal event decision network generated by updating the network weight parameters based on sample learning results corresponding to all the abnormal knowledge points when the initialized park abnormal event decision network meets the sample learning termination requirements.
3. The method for early warning of a park abnormal event based on model analysis according to claim 2, wherein the determining whether the initialized park abnormal event decision network meets a sample learning termination requirement based on sample learning results corresponding to all the abnormal knowledge points comprises:
determining target sample abnormal learning data corresponding to each abnormal knowledge point, and determining a learning effect value corresponding to each abnormal knowledge point based on the target sample abnormal learning data corresponding to the abnormal knowledge point and a corresponding sample learning result;
judging whether one or more target abnormal knowledge points meeting the learning effect requirements exist in all the abnormal knowledge points or not based on learning effect values corresponding to all the abnormal knowledge points;
when one or more target abnormal knowledge points exist in all the abnormal knowledge points, determining that the initialization park abnormal event decision network meets a sample learning termination requirement;
and when the target abnormal knowledge points do not exist in all the abnormal knowledge points, determining that the initialization park abnormal event decision network does not meet the sample learning termination requirement.
4. The method for early warning of a campus abnormal event based on model analysis according to claim 3, wherein generating a campus abnormal event decision network for updating network weight parameters based on sample learning results corresponding to all the abnormal knowledge points comprises:
extracting target sample learning results corresponding to the target abnormal knowledge points from sample learning results corresponding to all the abnormal knowledge points;
determining target network weight information based on the target abnormal knowledge points and the target sample learning result;
and generating a park abnormal event decision network for updating and generating network weight parameters based on the target network weight information and the initialized park abnormal event decision network.
5. The model analysis based campus anomaly early warning method of claim 4, further comprising:
when the initialization park abnormal event decision network does not meet the sample learning termination requirement, determining weight information to be updated corresponding to the initialization park abnormal event decision network based on sample learning results corresponding to all the abnormal knowledge points and a set network weight information updating requirement;
determining a weight information optimization state corresponding to the weight information to be updated based on the weight information to be updated, sample learning results corresponding to all the abnormal knowledge points and a set network weight information optimization requirement;
and based on the weight information optimization state, executing weight information optimization operation on the initialization park abnormal event decision network, generating the initialization park abnormal event decision network after weight information optimization, and executing the operation of loading the infrared thermal imaging monitoring sample learning data into the initialization park abnormal event decision network according to the initialization park abnormal event decision network after weight information optimization, and generating sample learning results corresponding to a plurality of abnormal knowledge points.
6. The method for model analysis based on campus anomaly event early warning of claim 5, wherein after loading the campus infrared thermal imaging monitoring stream data into a campus anomaly event decision network that meets network deployment conditions, the method further comprises:
acquiring actual abnormal event data corresponding to the target intelligent park, analyzing the actual abnormal event data and the park abnormal event decision data, and generating a loss function value;
judging whether the loss function value is not smaller than a preset set loss function value;
when the loss function value is not smaller than the set loss function value, determining that the abnormal event decision state corresponding to the park abnormal event decision network is inaccurate in abnormal event decision;
determining abnormal event decision distinguishing information based on the loss function value, the actual abnormal event data and the park abnormal event decision data when the loss function value is smaller than the set loss function value;
determining decision distinguishing optimization information corresponding to the park abnormal event decision network based on the abnormal event decision distinguishing information and the set decision distinguishing optimization requirement;
based on the decision distinguishing optimization information, performing weight parameter optimization operation on the park abnormal event decision network, and generating a park abnormal event decision network with optimized weight parameters; and executing the operation of loading the park infrared thermal imaging monitoring stream data into the park abnormal event decision network conforming to the network deployment condition according to the park abnormal event decision network after the weight parameter optimization, and generating park abnormal event decision data.
7. The model analysis based campus anomaly early warning method of claim 6, further comprising:
and when the abnormal event decision state corresponding to the park abnormal event decision network is an abnormal event decision accuracy, determining an infrared thermal imaging monitoring activity state corresponding to the target intelligent park based on the park abnormal event decision data and the actual abnormal event data, wherein the infrared thermal imaging monitoring activity state comprises an infrared thermal imaging monitoring activity real-time state and/or an infrared thermal imaging monitoring activity trend state.
8. The model analysis based campus anomaly early warning method of claim 7, further comprising: determining a trigger probability value of the infrared thermal imaging monitoring activity linkage state corresponding to the target intelligent park based on the infrared thermal imaging monitoring activity state and the set linkage state mining requirement;
judging whether the trigger probability value is not smaller than a preset threshold trigger probability value or not;
and when the trigger probability value is not smaller than the threshold trigger probability value, predicting linkage trigger information corresponding to the target intelligent park based on the infrared thermal imaging monitoring activity state, the trigger probability value and the set linkage state estimation requirement, wherein the linkage trigger information is used for indicating abnormal linkage activities with high trigger probability value.
9. The utility model provides a park abnormal event early warning system based on model analysis, its characterized in that, park abnormal event early warning system based on model analysis includes cloud ware and with cloud ware communication connection's park thermal imaging monitored control system, cloud ware specifically is used for:
acquiring park infrared thermal imaging monitoring stream data corresponding to a target intelligent park, wherein the park infrared thermal imaging monitoring stream data comprises park infrared thermal imaging monitoring stream data corresponding to a set abnormal knowledge point of the target intelligent park in a set early warning analysis period;
loading the park infrared thermal imaging monitoring stream data into a park abnormal event decision network conforming to network deployment conditions to generate park abnormal event decision data, wherein the park abnormal event decision data comprises at least one of real-time abnormal park abnormal events, forward abnormal park abnormal events and backward abnormal park abnormal events corresponding to the target intelligent park;
executing early warning operation based on the park abnormal event decision data;
the park abnormal event decision network meeting the network deployment condition is generated by updating network weight parameters according to the target intelligent park and the target infrared thermal imaging monitoring activity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310717973.6A CN116778412A (en) | 2023-06-16 | 2023-06-16 | Park abnormal event early warning method and system based on model analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310717973.6A CN116778412A (en) | 2023-06-16 | 2023-06-16 | Park abnormal event early warning method and system based on model analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116778412A true CN116778412A (en) | 2023-09-19 |
Family
ID=87995831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310717973.6A Pending CN116778412A (en) | 2023-06-16 | 2023-06-16 | Park abnormal event early warning method and system based on model analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778412A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746338A (en) * | 2024-01-16 | 2024-03-22 | 柏森智慧空间科技集团有限公司 | Property park safety management method and system based on artificial intelligence |
-
2023
- 2023-06-16 CN CN202310717973.6A patent/CN116778412A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746338A (en) * | 2024-01-16 | 2024-03-22 | 柏森智慧空间科技集团有限公司 | Property park safety management method and system based on artificial intelligence |
| CN117746338B (en) * | 2024-01-16 | 2024-05-28 | 柏森智慧空间科技集团有限公司 | Property park safety management method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107408062B (en) | Techniques for offloading and loading data for a processor/coprocessor arrangement | |
| US20190228212A1 (en) | Wakeup method, apparatus and device based on lip reading, and computer readable medium | |
| KR20170050461A (en) | Apparatus and method for storing event signal and image and operating method of vision sensor for transmitting event signal to the apparatus | |
| US20190213069A1 (en) | Dynamically restoring disks based on array properties | |
| CN116778412A (en) | Park abnormal event early warning method and system based on model analysis | |
| US11436188B2 (en) | Resource optimization and update method, server, and device | |
| EP3869404A2 (en) | Vehicle loss assessment method executed by mobile terminal, device, mobile terminal and medium | |
| KR20210036319A (en) | Method, apparatus and electronic device for identifying text content | |
| CN115905450A (en) | Unmanned aerial vehicle monitoring-based water quality abnormity tracing method and system | |
| US10452134B2 (en) | Automated peripheral device handoff based on eye tracking | |
| CN116303100A (en) | File integration test method and system based on big data platform | |
| US20220156086A1 (en) | Processing computing jobs via an acceleration device | |
| US11561801B2 (en) | Predicting execution duration for user-defined functions on function-as-a-service (FaaS) cloud computing platforms | |
| CN116542673B (en) | Fraud identification method and system applied to machine learning | |
| US20230342274A1 (en) | Modular test system | |
| US11669429B2 (en) | Configuration cluster-based performance optimization of applications in an information handling system (IHS) | |
| CN115617411A (en) | Electronic equipment data processing method and device, electronic equipment and storage medium | |
| CN115951344A (en) | Data fusion method and device for radar and camera, electronic equipment and storage medium | |
| CN114912582A (en) | Model production method, model production device, electronic device, and storage medium | |
| US20170192485A1 (en) | Providing a power optimized design for a device | |
| US11221656B2 (en) | Method and apparatus for selective fan control in an information handling system | |
| CN103502948A (en) | Timeframe based data analysis | |
| CN210166772U (en) | Computing system | |
| US11830105B2 (en) | Service request processing utilizing modified versions of images of computing devices | |
| CN117609881B (en) | Metal overlap detection method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |