CN114613103B - Alarm positioning processing method and system based on big data - Google Patents
Alarm positioning processing method and system based on big data Download PDFInfo
- Publication number
- CN114613103B CN114613103B CN202210504774.2A CN202210504774A CN114613103B CN 114613103 B CN114613103 B CN 114613103B CN 202210504774 A CN202210504774 A CN 202210504774A CN 114613103 B CN114613103 B CN 114613103B
- Authority
- CN
- China
- Prior art keywords
- alarm
- intention
- data
- network
- target
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application provides an alarm positioning processing method and system based on big data, which combine target track data of a target mobile terminal corresponding to a real-time node and recent access activity data before the real-time node to determine at least one historical alarm data associated with the target access activity data from a historical alarm big database which is subjected to reliability authentication in advance when the target access activity data associated with the target track data exists in the recent access activity data, and output an alarm intention object in the historical alarm data as an alarm auxiliary reference basis of alarm request data sent by the target mobile terminal, thereby combining track dimension and recent access activity dimension, outputting the alarm auxiliary reference basis from the historical alarm big database which is subjected to reliability authentication so as to provide more possible detailed alarm characteristics for related personnel to refer, the accurate position of the alarm help seeking personnel in the large or multi-storey building is positioned, and the rescue efficiency is improved.
Description
Technical Field
The application relates to the technical field of big data, in particular to an alarm positioning processing method and system based on big data.
Background
At present, mobile terminal usually can embed SDK or the applet that the warning was sought help, when the user dialed the phone of seeking help, mobile terminal detected this phone and seeks help the phone for the warning, then start embedded SDK's APP or applet at once, report this mobile terminal's real-time positioning data to the central system of seeking help of warning, the central system of seeking help of warning sends real-time positioning data to the succour personnel, the succour personnel just can in time salvage the personnel of seeking help according to the real-time positioning data that should report. The sending positions are divided into two types, one type is an outdoor address, and the outdoor address can be jointly positioned through a satellite and a mobile communication base station; the other is an indoor address, a large number of personnel are needed to carry out on-site surveying and mapping, and various positioning big data (such as wireless clutter signals, geomagnetic signals and the like) are uploaded to a platform after surveying and mapping, so that the mobile terminal can be assisted to finish positioning indoors. However, in an emergency, a user cannot perfectly reflect a specific alarm reason or an alarm reason, so that reference information obtained by a rescuer is less, and a rescue scheme cannot be accurately decided, that is, a scheme of performing alarm reference only according to real-time positioning data in the related art still has a further optimization space.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, the present application aims to provide an alarm positioning processing method and system based on big data.
In a first aspect, the present application provides an alarm positioning processing method based on big data, which is applied to an alarm positioning processing system based on big data, and the method includes:
acquiring alarm request data sent by a target mobile terminal, acquiring real-time positioning data corresponding to the target mobile terminal based on the alarm request data, and calling historical positioning data before a real-time node corresponding to the real-time positioning data and latest access activity data before the real-time node of each online registered account corresponding to the target mobile terminal;
determining target track data of the target mobile terminal corresponding to the real-time node based on real-time positioning data corresponding to the target mobile terminal and historical positioning data before the time node corresponding to the real-time positioning data;
judging whether target access activity data associated with the target track data exists in the recent access activity data or not, if the target access activity data associated with the target track data exists in the recent access activity data, determining at least one historical alarm data associated with the target access activity data from a large historical alarm database subjected to reliability authentication in advance, and outputting an alarm intention object in the historical alarm data as an alarm auxiliary reference basis of alarm request data sent by the target mobile terminal.
In a second aspect, the present application further provides a big data based alarm positioning processing system, which includes a processor and a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions, and the machine-executable instructions are loaded and executed by the processor to implement the aforementioned big data based alarm positioning processing method.
According to any one of the aspects, the target track data of the target mobile terminal corresponding to the real-time node and the latest access activity data before the real-time node are combined, so that when the target access activity data associated with the target track data exists in the latest access activity data, at least one piece of historical alarm data associated with the target access activity data is determined from a historical alarm big database subjected to reliability authentication in advance, and an alarm intention object in the historical alarm data is output as an alarm auxiliary reference of alarm request data sent by the target mobile terminal, so that the track dimension and the latest access activity dimension are combined, and the alarm auxiliary reference is output from the historical alarm big database subjected to reliability authentication, so that more possible detailed alarm characteristics can be provided for reference of related personnel.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a big data-based alarm positioning processing method according to an embodiment of the present application;
fig. 2 is a schematic block diagram of a structure of a big data-based alarm positioning processing system for implementing the big data-based alarm positioning processing method according to an embodiment of the present application.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention and is provided in the context of a particular application and its requirements. It will be apparent to those of ordinary skill in the art that various changes can be made to the disclosed embodiments and that the general principles defined in this application can be applied to other embodiments and applications without departing from the principles and scope of the application. Thus, the present application is not limited to the described embodiments, but should be accorded the widest scope consistent with the claims.
The terminology used in the description presented herein is for the purpose of describing particular example embodiments only and is not intended to limit the scope of the present application. As used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, components, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, and/or groups thereof.
These and other features, aspects, and advantages of the present application, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description of the accompanying drawings, all of which form a part of this specification. It is to be understood, however, that the drawings are designed solely for the purposes of illustration and description and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.
Flowcharts are used herein to illustrate the operations performed by systems according to some embodiments of the present application. It should be understood that the operations in the flow diagrams may be performed out of order. Rather, various steps may be processed in reverse order or simultaneously. Further, one or more other operations may be added to the flowchart. One or more operations may also be deleted from the flowchart.
The present application is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the apparatus embodiments or the system embodiments.
Fig. 1 is a schematic flow chart of an alarm positioning processing method based on big data according to an embodiment of the present application, and the alarm positioning processing method based on big data is described in detail below.
Step S100, acquiring alarm request data sent by a target mobile terminal, acquiring real-time positioning data corresponding to the target mobile terminal based on the alarm request data, and calling historical positioning data before a real-time node corresponding to the real-time positioning data and latest access activity data before the real-time node of each online registered account corresponding to the target mobile terminal.
Step S200, determining target track data of the target mobile terminal corresponding to the real-time node based on the real-time positioning data corresponding to the target mobile terminal and historical positioning data before the time node corresponding to the real-time positioning data.
Step S300, judging whether target access activity data associated with the target track data exists in the latest access activity data or not, if the target access activity data associated with the target track data exists in the latest access activity data, determining at least one piece of historical alarm data associated with the target access activity data from a historical alarm big database which is subjected to reliability authentication in advance, and outputting an alarm intention object in the historical alarm data as an alarm auxiliary reference of alarm request data sent by the target mobile terminal.
Based on the above steps, the embodiment of the application combines the target track data of the target mobile terminal corresponding to the real-time node and the latest access activity data before the real-time node, such that when there is target access activity data associated with the target trajectory data in the most recent access activity data, determining at least one historical alarm data associated with the target access activity data from a large historical alarm database which is subjected to reliability authentication in advance, and outputs an alarm intention object in the history alarm data as an alarm auxiliary reference basis of the alarm request data sent by the target mobile terminal, therefore, the trace dimension and the recent access activity dimension are combined, and the alarm auxiliary reference basis is output from the historical alarm big database of reliability authentication, so that more possible detailed alarm characteristics can be provided for the reference of related personnel.
After the step S300, the method provided in the embodiment of the present application may further include the following steps, which are described in detail below.
Step S400, summarizing the target track data, the target access activity data and the alarm intention objects in the historical alarm data of each target mobile terminal to be used as example alarm learning data, and determining the alarm intention label corresponding to each example alarm learning data based on a development instruction so as to obtain an example alarm learning data set formed by the example alarm learning data carrying the corresponding alarm intention label;
step S500, training an initialization alarm intention prediction model based on the example alarm learning data set to obtain a trained target alarm intention prediction model, wherein the target alarm intention prediction model is used for performing alarm intention prediction on candidate alarm data corresponding to any mobile terminal.
The following further describes an embodiment of the target alarm intention prediction model in step S500 for performing alarm intention prediction on candidate alarm data corresponding to any mobile terminal, and refer to the following contents.
Step A101: and performing alarm characteristic field mining on the candidate alarm data to determine a first alarm characteristic field network.
Step A102: and analyzing each forward alarm node and each backward alarm node in the candidate alarm data based on the first alarm characteristic field network.
One forward alarm node corresponds to a node with a pre-triggered alarm behavior corresponding to the alarm intention, and the rest nodes can be used as backward alarm nodes.
Step A103: each forward alarm node and each backward alarm node corresponding to each first alarm feature field sub-network is determined in the first alarm feature field network based on the corresponding trigger node of each forward alarm node and each backward alarm node in the candidate alarm data.
Each alarm feature field in the first network of alarm feature fields may form a knowledge graph, i.e., the first network of alarm feature fields is configured to express a feature segment relationship between each alarm feature field, i.e., each alarm feature field is configured to describe an alarm feature in the candidate alarm data. For each forward alarm node or backward alarm node, the corresponding portion of the alarm feature field in the first alarm feature field network may be determined based on its corresponding trigger node in the candidate alarm data, and may thus be constructed as a corresponding first alarm feature field sub-network since it actually belongs to an alarm feature field sub-network of the first alarm feature field network.
Step A104: and respectively updating the first alarm field weight of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each second alarm characteristic field sub-network after the first alarm field weight is updated.
Step A105: and performing alarm intention characteristic prediction based on each second alarm characteristic field sub-network, and determining each target alarm intention characteristic in the candidate alarm data.
Step A106: and determining each first alarm feature field sub-network corresponding to each target alarm intention feature in the first alarm feature field network based on the corresponding trigger node of each target alarm intention feature in the candidate alarm data, and fusing each first alarm feature field sub-network corresponding to all target alarm intention features to generate a third alarm feature field network.
For each target alarm intent feature, a portion of the alarm feature fields corresponding to the target alarm intent feature, referred to as a first alarm feature field sub-network corresponding to the target alarm intent feature, may be determined in the first alarm feature field network based on the corresponding trigger node of the target alarm intent feature in the candidate alarm data.
Step A107: performing frequent mode field network mining on the first alarm characteristic field network to determine a fourth alarm characteristic field network; and the network format of the fourth alarm characteristic field network is the same as that of the third alarm characteristic field network.
Step A108: and performing feature fusion on the fourth alarm feature field network and the third alarm feature field network to determine a fifth alarm feature field network.
Step A109: and predicting alarm intention based on the fifth alarm characteristic field network, and determining a target alarm intention label corresponding to the candidate alarm data.
By adopting the steps, the alarm intention prediction is carried out after the local characteristic field network (third alarm characteristic field network) corresponding to each target alarm intention characteristic in the candidate alarm data and the global characteristic field network (fourth alarm characteristic field network) characteristic extracted from the candidate alarm data are fused, the alarm intention label range of the alarm intention prediction is refined, and the accuracy of the alarm intention prediction is improved.
For some exemplary design considerations, steps a101, a102, a105, and a109 may be implemented by a target alarm intention prediction model that is mainly composed of an alarm feature field mining unit, an alarm node parsing unit, an alarm intention feature prediction unit, and an alarm intention prediction unit.
Another embodiment of the present application is described below, comprising the steps of:
step A201: and loading the candidate alarm data to an alarm characteristic field mining unit of the target alarm intention prediction model to mine an alarm characteristic field and determine a first alarm characteristic field network.
Step A202: and loading the first alarm characteristic field network into an alarm node analysis unit of the target alarm intention prediction model to analyze each forward alarm node and each backward alarm node in the candidate alarm data.
Step A203: each forward alarm node and each backward alarm node corresponding to each first alarm feature field sub-network is determined in the first alarm feature field network based on the corresponding trigger node of each forward alarm node and each backward alarm node in the candidate alarm data.
Step A204: and respectively updating the first alarm field weight of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each second alarm characteristic field sub-network after the first alarm field weight is updated.
Step A205: and loading each second alarm characteristic field sub-network to an alarm intention characteristic prediction unit of the target alarm intention prediction model to perform alarm intention characteristic prediction, and determining each target alarm intention characteristic in the candidate alarm data.
Step A206: and determining each first alarm feature field sub-network corresponding to each target alarm intention feature in the first alarm feature field network based on the corresponding trigger node of each target alarm intention feature in the candidate alarm data, and fusing each first alarm feature field sub-network corresponding to all target alarm intention features to generate a third alarm feature field network.
Step A207: performing frequent mode field network mining on the first alarm characteristic field network to determine a fourth alarm characteristic field network; and the network format of the fourth alarm characteristic field network is the same as that of the third alarm characteristic field network.
Step A208: and performing feature fusion on the fourth alarm feature field network and the third alarm feature field network to determine a fifth alarm feature field network.
Step A209: and loading the fifth alarm characteristic field network to an alarm intention prediction unit of the target alarm intention prediction model for alarm intention prediction, and determining a target alarm intention label corresponding to the candidate alarm data.
For some exemplary design concepts, after step a106, before step a108, or after step a206, before step a208, further comprising: performing alarm characteristic field derivation processing on the third alarm characteristic field network, determining a derived alarm characteristic field of each alarm characteristic field in the third alarm characteristic field network, performing association fusion on each alarm characteristic field in the third alarm characteristic field network and the derived alarm characteristic field thereof respectively, and determining a derived alarm characteristic field network of the third alarm characteristic field network;
in step a108 or step a208, performing feature fusion on the fourth alarm feature field network and the third alarm feature field network, including: and performing feature fusion on the fourth alarm feature field network and the derivative alarm feature field network of the third alarm feature field network.
In the above embodiment, by calculating the derived alarm feature field of each alarm feature field in the third alarm feature field network, the alarm feature field corresponding to the target alarm intention feature in the candidate alarm data may be derived, thereby improving the accuracy of alarm intention prediction.
Another embodiment of the present application is described below, comprising the steps of:
step A301: and acquiring an example alarm learning data set, and adding each target alarm intention characteristic and a corresponding alarm intention label in each example alarm learning data.
In order to distinguish from the fuzzy alarm intention features in the subsequent step a306, each target alarm intention feature carried in the step a301 is referred to as an example alarm intention feature; in order to distinguish from the ambiguous alarm intention tags in the subsequent steps a306 and a311, the alarm intention tag carried in this step a301 is referred to as an alarm intention tag.
Step A302: and respectively extracting example alarm learning data from the example alarm learning data set, loading the example alarm learning data to an alarm characteristic field mining unit of the target alarm intention prediction model for alarm characteristic field mining, and determining a first alarm characteristic field network of the loaded example alarm learning data.
Step A303: and loading the first alarm characteristic field network to an alarm node analysis unit of the target alarm intention prediction model, and determining each forward alarm node and each backward alarm node in the loaded example alarm learning data.
Step A304: each forward warning node and each backward warning node corresponding to each first warning feature field sub-network are determined in the first warning feature field network based on the corresponding trigger node of each forward warning node and each backward warning node in the loaded example warning learning data.
Step A305: and respectively updating the first alarm field weight of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each second alarm characteristic field sub-network after the first alarm field weight is updated.
Step A306: and loading each second alarm characteristic field sub-network to an alarm intention characteristic prediction unit of the target alarm intention prediction model, and determining each fuzzy alarm intention characteristic and a fuzzy alarm intention label of each fuzzy alarm intention characteristic in the loaded example alarm learning data.
The fuzzy alarm intent features are target alarm intent features detected by the alarm intent feature prediction unit of the target alarm intent prediction model in the loaded example alarm learning data.
Step A307: and performing prediction capability evaluation based on the fuzzy alarm intention characteristics and the fuzzy alarm intention labels of the fuzzy alarm intention characteristics and each example alarm intention characteristic and alarm intention label carried in the loaded example alarm learning data, and determining a first alarm intention prediction capability evaluation value based on a first alarm intention prediction capability function which is previously specified and configured.
Here, since the alarm intention feature prediction unit outputs two parameters: the fuzzy alarm intention characteristics and the fuzzy alarm intention labels are used for evaluating the alarm intention prediction capability of the two parameters respectively, and the alarm intention prediction capability functions based on the two parameters can be the same or different, for example: smoothing the fuzzy alarm intention characteristic base by using an L1 loss function, adding the alarm intention prediction capability evaluation value corresponding to the fuzzy alarm intention characteristic and the alarm intention prediction capability evaluation value corresponding to the fuzzy alarm intention label on the basis of a cross entropy function, and determining a first alarm intention prediction capability evaluation value.
Step A308: and determining each first alarm feature field sub-network corresponding to each fuzzy alarm intention feature in the first alarm feature field network based on the corresponding trigger node of each fuzzy alarm intention feature in the loaded example alarm learning data, and fusing each first alarm feature field sub-network corresponding to all fuzzy alarm intention features to generate a third alarm feature field network.
Step A309: performing frequent mode field network mining on the first alarm characteristic field network to determine a fourth alarm characteristic field network; and the network format of the fourth alarm characteristic field network is the same as that of the third alarm characteristic field network.
Step A310: and performing feature fusion on the fourth alarm feature field network and the third alarm feature field network to determine a fifth alarm feature field network.
Step A311: and loading the fifth alarm characteristic field network to an alarm intention prediction unit of the target alarm intention prediction model, and determining fuzzy alarm intention labels contained in the loaded example alarm learning data.
Step A312: and performing prediction capability evaluation based on a second alarm intention prediction capability function which is previously specified and configured based on the fuzzy alarm intention labels output by the alarm intention prediction unit and each alarm intention label carried in the loaded example alarm learning data, and determining a second alarm intention prediction capability evaluation value.
The second alarm intent prediction capability function may be based on a cross entropy function.
Step A313: and performing weighted fusion calculation on the first alarm intention prediction capability evaluation value and the second alarm intention prediction capability evaluation value, and updating model function weight information of the target alarm intention prediction model based on the weighted fusion evaluation value.
For example: model function weight information of the target alarm intention prediction model may be updated based on a stochastic gradient descent algorithm based on the weighted fusion assessment value.
Step A314: and if the target alarm intention prediction model meets the training termination condition through analysis, taking the target alarm intention prediction model meeting the training termination condition output as a target alarm intention prediction model for development and deployment.
For some exemplary design considerations, after step a308 and before step a310, the method further includes: performing alarm characteristic field derivation processing on the third alarm characteristic field network, determining a derived alarm characteristic field of each alarm characteristic field in the third alarm characteristic field network, performing association fusion on each alarm characteristic field in the third alarm characteristic field network and the derived alarm characteristic field thereof respectively, and determining a derived alarm characteristic field network of the third alarm characteristic field network;
in step a310, performing feature fusion on the fourth alarm feature field network and the third alarm feature field network, including:
and performing feature fusion on the fourth alarm feature field network and the derivative alarm feature field network of the third alarm feature field network.
For some exemplary design considerations, in step a301, the intention data characteristics and categories of the alarm intention objects are further labeled in the example alarm learning data, and after "determining each first alarm characteristic field sub-network corresponding to each fuzzy alarm intention characteristic in the first alarm characteristic field network" in step a308, and before "performing weighted fusion calculation on the first alarm intention prediction capability evaluation value and the second alarm intention prediction capability evaluation value" in step a313, the method further includes:
respectively updating the weights of the second alarm fields of the first alarm characteristic field sub-networks, and determining sixth alarm characteristic field sub-networks after the weights of the second alarm fields are updated; loading each sixth alarm characteristic field sub-network to an intention data characteristic analysis unit of the target alarm intention prediction model, and determining intention data characteristics and alarm intention labels of each alarm intention object in the loaded example alarm learning data; based on the intention data characteristics and the alarm intention labels of all alarm intention objects in the loaded example alarm learning data obtained by the intention data characteristic analysis unit and the intention data characteristics and the alarm intention labels of all alarm intention objects carried in the loaded example alarm learning data, carrying out prediction ability evaluation based on a third alarm intention prediction ability function which is specified and configured in advance, and determining a third alarm intention prediction ability evaluation value; here, the third alarm intention prediction capability function may be a cross entropy function. Wherein the intention data characteristic of the alarm intention object is the real intention data characteristic of the alarm object.
In step a313, the weighted fusion calculation of the first alarm intention prediction ability evaluation value and the second alarm intention prediction ability evaluation value includes: and performing weighted fusion calculation on the first alarm intention prediction capability evaluation value, the second alarm intention prediction capability evaluation value and the third alarm intention prediction capability evaluation value.
For some exemplary design ideas, in this embodiment, a corresponding alarm intention thermal distribution map may also be constructed according to the alarm intention of each candidate alarm data generated by obtaining the target alarm intention prediction model, a corresponding hotspot alarm intention is determined based on the alarm intention thermal distribution map, and corresponding safety knowledge point information is pushed to each target mobile terminal based on the hotspot alarm intention.
For example, an alarm intention with a heat value larger than a preset heat value can be determined from the alarm intention thermodynamic distribution diagram as a hot spot alarm intention, then a security problem mapped by the hot spot alarm intention is obtained, and after a security knowledge point corresponding to the security problem is obtained, source content information of the security knowledge point is pushed to each target mobile terminal.
Fig. 2 illustrates a hardware structure of a big data based alarm positioning processing system 100 for implementing the big data based alarm positioning processing method according to an embodiment of the present application, and as shown in fig. 2, the big data based alarm positioning processing system 100 may include a processor 110, a machine readable storage medium 120, a bus 130, and a communication unit 140.
In some embodiments, big data based alarm location processing system 100 may be a single server or a group of servers. The server set may be centralized or distributed (e.g., big data based alarm location processing system 100 may be a distributed system). In some embodiments, big data based alarm location processing system 100 may be local or remote. For example, big data based alarm location processing system 100 may access information and/or data stored in machine readable storage medium 120 via a network. As another example, big data based alarm location processing system 100 may be directly connected to machine readable storage medium 120 to access stored information and/or data. In some embodiments, big data based alarm location processing system 100 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, the like, or any combination thereof.
Machine-readable storage medium 120 may store data and/or instructions. In some embodiments, the machine-readable storage medium 120 may store the data from an external terminal. In some embodiments, machine-readable storage medium 120 may store data and/or instructions for execution or use by big data based alarm location processing system 100 to perform the exemplary methods described in this application. In some embodiments, the machine-readable storage medium 120 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary RAM may include active random access memory (DRAM), double data rate synchronous active random access memory (DDR SDRAM), passive random access memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), among others. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (perrom), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory, and the like. In some embodiments, the machine-readable storage medium 120 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.
In a specific implementation process, the plurality of processors 110 execute the computer executable instructions stored in the machine readable storage medium 120, so that the processors 110 may execute the alarm positioning processing method based on big data according to the above method embodiment, the processors 110, the machine readable storage medium 120, and the communication unit 140 are connected through the bus 130, and the processors 110 may be configured to control the transceiving action of the communication unit 140.
For a specific implementation process of the processor 110, reference may be made to each method embodiment executed by the alarm positioning processing system 100 based on big data, which has similar implementation principle and technical effect, and this embodiment is not described herein again.
In addition, an embodiment of the present application further provides a readable storage medium, where a computer-executable instruction is preset in the readable storage medium, and when a processor executes the computer-executable instruction, the above alarm positioning processing method based on big data is implemented.
It should be understood that the above description is intended for illustrative purposes only, and is not intended to limit the scope of the present application. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the description of the present application. However, such modifications and variations do not depart from the scope of the present application.
While the basic concepts have been described above, it will be apparent to those of ordinary skill in the art in view of this disclosure that this disclosure is intended to be exemplary only, and is not intended to limit the present application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. For example, "one embodiment," "an embodiment," and/or "some embodiments" means a certain feature, structure, or characteristic described in connection with the embodiments of the application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those of ordinary skill in the art will understand that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, articles, or materials, or any new and useful modification thereof. Accordingly, each aspect of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "unit", "module", or "system". Furthermore, aspects disclosed herein may take the form of a computer program product embodied in one or more computer-readable media, with computer-readable program code embodied therein.
A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electro-magnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination thereof.
Computer program code required for operation of various portions of the present application may be written in any one or more programming languages, including a subject oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, ForOPan 2003, Perl, COBOL 2002, PHP, ABAP, an active programming language such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the embodiments. Similarly, it should be noted that in the preceding description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the embodiments.
Claims (8)
1. The alarm positioning processing method based on big data is characterized by being applied to an alarm positioning processing system based on big data, and comprises the following steps:
acquiring alarm request data sent by a target mobile terminal, acquiring real-time positioning data corresponding to the target mobile terminal based on the alarm request data, and calling historical positioning data before a real-time node corresponding to the real-time positioning data and latest access activity data before the real-time node of each online registered account corresponding to the target mobile terminal;
determining target track data of the target mobile terminal corresponding to the real-time node based on real-time positioning data corresponding to the target mobile terminal and historical positioning data before the time node corresponding to the real-time positioning data;
judging whether target access activity data associated with the target track data exists in the latest access activity data or not, if the target access activity data associated with the target track data exists in the latest access activity data, determining at least one piece of historical alarm data associated with the target access activity data from a large historical alarm database subjected to reliability authentication in advance, and outputting an alarm intention object in the historical alarm data as an alarm auxiliary reference of alarm request data sent by the target mobile terminal;
the method further comprises the following steps:
summarizing the target track data, the target access activity data and the alarm intention object in the historical alarm data of each target mobile terminal to be used as example alarm learning data, and determining an alarm intention label corresponding to each example alarm learning data based on a development instruction to obtain an example alarm learning data set formed by example alarm learning data carrying the corresponding alarm intention label;
training an initialized alarm intention prediction model based on the example alarm learning data set to obtain a trained target alarm intention prediction model, wherein the target alarm intention prediction model is used for predicting alarm intention of candidate alarm data corresponding to any mobile terminal;
the target alarm intention prediction model is used for predicting the alarm intention of candidate alarm data corresponding to any mobile terminal, and comprises the following steps:
performing alarm characteristic field mining on the candidate alarm data, and determining a first alarm characteristic field network;
analyzing each forward alarm node and each backward alarm node in the candidate alarm data based on a first alarm characteristic field network;
determining each first alarm feature field sub-network corresponding to each forward alarm node and each backward alarm node in a first alarm feature field network based on the corresponding trigger node of each forward alarm node and each backward alarm node in the candidate alarm data;
respectively updating the first alarm field weight of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each second alarm characteristic field sub-network after the first alarm field weight is updated;
performing alarm intention characteristic prediction based on each second alarm characteristic field sub-network, and determining each target alarm intention characteristic in the candidate alarm data;
determining each first alarm feature field sub-network corresponding to each target alarm intention feature in a first alarm feature field network based on the corresponding trigger node of each target alarm intention feature in the candidate alarm data, and fusing each first alarm feature field sub-network corresponding to all target alarm intention features to generate a third alarm feature field network;
performing frequent mode field network mining on the first alarm characteristic field network to determine a fourth alarm characteristic field network; the network format of the fourth alarm characteristic field network is the same as that of the third alarm characteristic field network;
performing feature fusion on the fourth alarm feature field network and the third alarm feature field network to determine a fifth alarm feature field network;
and predicting alarm intention based on a fifth alarm characteristic field network, and determining a target alarm intention label corresponding to the candidate alarm data.
2. The big data based alarm positioning processing method of claim 1, wherein the performing alarm characteristic field mining on the candidate alarm data to determine a first alarm characteristic field network comprises:
loading the candidate alarm data to an alarm characteristic field mining unit of a target alarm intention prediction model to mine an alarm characteristic field;
analyzing each forward alarm node and each backward alarm node in the candidate alarm data based on a first alarm characteristic field network, comprising:
loading a first alarm characteristic field network into an alarm node analysis unit of the target alarm intention prediction model to analyze each forward alarm node and each backward alarm node in the candidate alarm data;
the predicting of the alarm intention characteristics based on the second alarm characteristic field sub-networks comprises the following steps:
loading each second alarm characteristic field sub-network to an alarm intention characteristic prediction unit of the target alarm intention prediction model to predict alarm intention characteristics;
the alarm intention prediction based on the fifth alarm characteristic field network comprises the following steps:
and loading a fifth alarm characteristic field network to an alarm intention prediction unit of the target alarm intention prediction model to predict the alarm intention.
3. The big-data-based alarm positioning processing method according to claim 2, wherein the step of training an initial alarm intention prediction model based on the example alarm learning data set to obtain a trained target alarm intention prediction model comprises:
respectively extracting example alarm learning data from an example alarm learning data set, loading the example alarm learning data to an alarm characteristic field mining unit of the target alarm intention prediction model for alarm characteristic field mining, and determining a first alarm characteristic field network of the loaded example alarm learning data;
loading a first alarm characteristic field network to an alarm node analysis unit of the target alarm intention prediction model, and determining each forward alarm node and each backward alarm node in the loaded example alarm learning data;
determining each forward alarm node and each backward alarm node corresponding to each first alarm feature field sub-network in the first alarm feature field network based on the corresponding trigger node of each forward alarm node and each backward alarm node in the loaded example alarm learning data;
respectively updating the first alarm field weight of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each second alarm characteristic field sub-network after the first alarm field weight is updated;
loading each second alarm characteristic field sub-network to an alarm intention characteristic prediction unit of the target alarm intention prediction model, and determining each fuzzy alarm intention characteristic and a fuzzy alarm intention label of each fuzzy alarm intention characteristic in loaded example alarm learning data;
based on each fuzzy alarm intention feature and each fuzzy alarm intention label of each fuzzy alarm intention feature output by the alarm intention feature prediction unit and each example alarm intention feature and corresponding alarm intention label carried in the loaded example alarm learning data, performing prediction capability evaluation based on a first alarm intention prediction capability function which is previously specified and configured, and determining a first alarm intention prediction capability evaluation value;
determining each first alarm characteristic field sub-network corresponding to each fuzzy alarm intention characteristic in the first alarm characteristic field network based on the corresponding trigger node of each fuzzy alarm intention characteristic in the loaded example alarm learning data, and fusing each first alarm characteristic field sub-network corresponding to all fuzzy alarm intention characteristics to generate a third alarm characteristic field network;
performing frequent mode field network mining on the first alarm characteristic field network to determine a fourth alarm characteristic field network; the network format of the fourth alarm characteristic field network is the same as that of the third alarm characteristic field network;
performing feature fusion on the fourth alarm feature field network and the third alarm feature field network to determine a fifth alarm feature field network;
loading a fifth alarm characteristic field network to an alarm intention prediction unit of the target alarm intention prediction model, and determining fuzzy alarm intention labels contained in the loaded example alarm learning data;
based on each fuzzy alarm intention label covered in the loaded example alarm learning data output by the alarm intention prediction unit and the alarm intention label of each example alarm intention characteristic carried in the loaded example alarm learning data, performing prediction ability evaluation based on a second alarm intention prediction ability function which is previously assigned and configured, and determining a second alarm intention prediction ability evaluation value;
performing weighted fusion calculation on the first alarm intention prediction capability evaluation value and the second alarm intention prediction capability evaluation value, and updating model function weight information of the target alarm intention prediction model based on the weighted fusion evaluation value;
and if the target alarm intention prediction model meets the training termination condition through analysis, taking the target alarm intention prediction model meeting the training termination condition output as a target alarm intention prediction model for development and deployment.
4. The big-data based alarm positioning processing method according to claim 1, wherein after fusing each of the first alarm feature field subnetworks corresponding to all target alarm intent features to generate a third alarm feature field network, and before the step of feature fusing the fourth alarm feature field network with the third alarm feature field network, the method further comprises:
performing alarm characteristic field derivation processing on the third alarm characteristic field network, determining a derived alarm characteristic field of each alarm characteristic field in the third alarm characteristic field network, performing association fusion on each alarm characteristic field in the third alarm characteristic field network and the derived alarm characteristic field thereof respectively, and determining a derived alarm characteristic field network of the third alarm characteristic field network;
the feature fusion of the fourth alarm feature field network and the third alarm feature field network includes:
and performing feature fusion on the fourth alarm feature field network and the derivative alarm feature field network of the third alarm feature field network.
5. The big data based alarm positioning processing method according to claim 3, further comprising:
adding intention data characteristics of each alarm intention object in each example alarm learning data;
after determining each first alarm feature field sub-network corresponding to each forward alarm node and each backward alarm node in the first alarm feature field network and before performing weighted fusion calculation on the first alarm intention prediction capability evaluation value and the second alarm intention prediction capability evaluation value, the method further comprises:
respectively updating the weight of a second alarm field of each first alarm characteristic field sub-network corresponding to each forward alarm node and each backward alarm node, and determining each sixth alarm characteristic field sub-network after the weight of the second alarm field is updated;
loading each sixth alarm characteristic field sub-network to an intention data characteristic analysis unit of the target alarm intention prediction model, and determining intention data characteristics and fuzzy alarm intention labels of each alarm intention object in the loaded example alarm learning data;
based on the intention data features and fuzzy alarm intention labels of all alarm intention objects in the loaded example alarm learning data obtained by the intention data feature analysis unit and the intention data features and alarm intention labels of all alarm intention objects carried in the loaded example alarm learning data, carrying out prediction capability evaluation based on a third alarm intention prediction capability function which is specified and configured in advance, and determining a third alarm intention prediction capability evaluation value;
the weighted fusion calculation of the first alarm intention prediction capability evaluation value and the second alarm intention prediction capability evaluation value comprises the following steps:
and performing weighted fusion calculation on the first alarm intention prediction capability evaluation value, the second alarm intention prediction capability evaluation value and the third alarm intention prediction capability evaluation value.
6. The big data based alarm positioning processing method according to any of claims 1-5, wherein the method further comprises:
constructing a corresponding alarm intention thermodynamic distribution map according to the alarm intention of each candidate alarm data generated by the target alarm intention prediction model;
and determining corresponding hotspot alarm intents based on the alarm intention thermal distribution diagram, and pushing corresponding safety knowledge point information to each target mobile terminal based on the hotspot alarm intents.
7. The big data-based alarm positioning processing method according to claim 6, wherein the step of determining a corresponding hot spot alarm intention based on the alarm intention thermodynamic distribution map and pushing corresponding safety knowledge point information to each target mobile terminal based on the hot spot alarm intention comprises:
determining an alarm intention of which the heat value is larger than a preset heat value from the alarm intention heat distribution map as a hot spot alarm intention;
and after the security problem mapped by the hotspot alarm intention is obtained, and the security knowledge point corresponding to the security problem is obtained, the source content information of the security knowledge point is pushed to each target mobile terminal.
8. A big-data based alarm location processing system, comprising a processor and a machine-readable storage medium having stored thereon machine-executable instructions that are loaded and executed by the processor to implement the big-data based alarm location processing method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210504774.2A CN114613103B (en) | 2022-05-10 | 2022-05-10 | Alarm positioning processing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210504774.2A CN114613103B (en) | 2022-05-10 | 2022-05-10 | Alarm positioning processing method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114613103A CN114613103A (en) | 2022-06-10 |
| CN114613103B true CN114613103B (en) | 2022-08-23 |
Family
ID=81869842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210504774.2A Active CN114613103B (en) | 2022-05-10 | 2022-05-10 | Alarm positioning processing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114613103B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307644B (en) * | 2023-05-22 | 2023-08-11 | 中感(安徽)矿山技术有限公司 | Mining intrinsic safety type data analysis display alarm terminal and use method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909687A (en) * | 2017-03-06 | 2017-06-30 | 江苏工程职业技术学院 | A kind of high-altitude working safety warning system |
| CN109859437A (en) * | 2019-01-03 | 2019-06-07 | 中国联合网络通信集团有限公司 | A kind of alarm method and equipment, system |
| CN111258854A (en) * | 2020-01-21 | 2020-06-09 | 北京奇艺世纪科技有限公司 | Model training method, alarm method based on prediction model and related device |
| CN111382779A (en) * | 2019-12-31 | 2020-07-07 | 清华大学 | Alarm condition similarity recognition method, device and equipment |
| CN113903420A (en) * | 2021-09-29 | 2022-01-07 | 清华大学 | Semantic label determination model construction method and medical record analysis method |
| CN114238402A (en) * | 2021-11-30 | 2022-03-25 | 中国工商银行股份有限公司 | Alarm data processing method and device, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090077623A1 (en) * | 2005-03-16 | 2009-03-19 | Marc Baum | Security Network Integrating Security System and Network Devices |
-
2022
- 2022-05-10 CN CN202210504774.2A patent/CN114613103B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909687A (en) * | 2017-03-06 | 2017-06-30 | 江苏工程职业技术学院 | A kind of high-altitude working safety warning system |
| CN109859437A (en) * | 2019-01-03 | 2019-06-07 | 中国联合网络通信集团有限公司 | A kind of alarm method and equipment, system |
| CN111382779A (en) * | 2019-12-31 | 2020-07-07 | 清华大学 | Alarm condition similarity recognition method, device and equipment |
| CN111258854A (en) * | 2020-01-21 | 2020-06-09 | 北京奇艺世纪科技有限公司 | Model training method, alarm method based on prediction model and related device |
| CN113903420A (en) * | 2021-09-29 | 2022-01-07 | 清华大学 | Semantic label determination model construction method and medical record analysis method |
| CN114238402A (en) * | 2021-11-30 | 2022-03-25 | 中国工商银行股份有限公司 | Alarm data processing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114613103A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114613103B (en) | Alarm positioning processing method and system based on big data | |
| CN113868010B (en) | Abnormal data processing method and system applied to business system | |
| CN113869778B (en) | Unmanned aerial vehicle river course inspection method and system based on city management | |
| CN112163446B (en) | Obstacle detection method and device, electronic equipment and storage medium | |
| CN111199346A (en) | Comprehensive management gallery supervision method and device, computer equipment and storage medium | |
| CN113859264B (en) | Vehicle control method, device, electronic equipment and storage medium | |
| CN111626519A (en) | Flight arrival time prediction method and device and electronic equipment | |
| CN112241442B (en) | Map updating method, map updating device, computer equipment and storage medium | |
| CN113392330A (en) | Big data processing method and system based on internet behaviors | |
| CN116778292B (en) | Method, device, equipment and storage medium for fusing space-time trajectories of multi-mode vehicles | |
| CN112697134A (en) | Environment sensing method, system and equipment of indoor inspection robot and computer readable storage medium thereof | |
| CN113189989A (en) | Vehicle intention prediction method, device, equipment and storage medium | |
| CN113689291B (en) | Anti-fraud identification method and system based on abnormal movement | |
| CN113486345A (en) | Supervision early warning method and system with risk identification function | |
| CN110749325B (en) | Flight path planning method and device | |
| Korobkin et al. | Diagnosis in SEMS Based on Cognitive Models | |
| CN111695820A (en) | Engineering vehicle electronic coupon management method and device, terminal and storage medium | |
| CN116820121A (en) | Unmanned aerial vehicle group joint investigation strategy generation method and terminal | |
| CN114202126B (en) | Intelligent safety control method and system for electric power operation | |
| US20220312149A1 (en) | Method and apparatus for map query and electronic device | |
| KR20200115716A (en) | Method and apparatus for predicting disater based on big data | |
| EP3672206B1 (en) | A method for determining a geofence parameter of a geofence area related to a point of interest and related electronic device | |
| CN107657474A (en) | The determination method and service end on a kind of commercial circle border | |
| KR102676806B1 (en) | Ttp based automated playbook generation method and system performing the same | |
| Huang | Application of the artificial fish school algorithm and particle filter algorithm in the industrial process control particle filtering algorithm for industrial process control |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |