CN114756660A

CN114756660A - Extraction method, device, equipment and storage medium of natural disaster event

Info

Publication number: CN114756660A
Application number: CN202210651099.6A
Authority: CN
Inventors: 邓迎贵; 谈启龙; 李佳馨; 张金玲
Original assignee: Guangdong Ruziniu Geographic Information Technology Co ltd
Current assignee: Guangdong Ruziniu Geographic Information Technology Co ltd
Priority date: 2022-06-10
Filing date: 2022-06-10
Publication date: 2022-07-15
Anticipated expiration: 2042-06-10
Also published as: CN114756660B

Abstract

According to the natural disaster event extraction method, the natural disaster event extraction device, the natural disaster event extraction equipment and the storage medium, the disaster event identification network matched with the disaster event state description is extracted based on the geological disaster event state description of the target geological natural disaster event to be extracted, so that the target geological natural disaster event extracted based on the disaster event identification network has high disaster environment matching degree and emergency record pertinence. When the natural disaster event emergency records are transmitted to the identification unit in the disaster event identification network, the matching degree of the environmental factors between the natural disaster event emergency records and the identification unit is considered, and the disaster event adaptive description corresponding to the natural disaster event emergency records and the identification unit is also considered, so that the event extraction state of the natural disaster event emergency records corresponding to the disaster event identification network can be effectively determined, and the defect that the natural disaster event is partially lost due to state incompatibility during the extraction of the natural disaster event is effectively overcome.

Description

Extraction method, device, equipment and storage medium of natural disaster event

Technical Field

The application relates to the technical field of big data processing, in particular to a method, a device, equipment and a storage medium for extracting natural disaster events.

Background

Natural disasters (Natural disasters) refer to Natural phenomena that harm human lives or damage human living environments, and bring great threats to the property safety of people to a certain extent.

In order to minimize property damage to people caused by natural disasters, deep analysis and summarization of related disaster events are generally required. Before deep analysis and summary of related disaster events, collection and summarization of disaster events are required, however, the related art has a problem of incomplete extraction when collecting and summarizing/extracting disaster events.

Disclosure of Invention

In view of this, the present application provides a method, an apparatus, a device and a storage medium for extracting a natural disaster event.

The embodiment of the application provides an extraction method of a natural disaster event, which is applied to event extraction equipment and comprises the following steps:

acquiring geological disaster event state description corresponding to a target geological natural disaster event to be extracted;

extracting a disaster event identification network from historical geological natural disaster events based on the geological disaster event state description, wherein the disaster event identification network comprises at least one identification unit, and the identification unit is used for identifying the historical geological natural disaster events;

extracting a natural disaster event emergency record set to be transmitted into the disaster event identification network, wherein the natural disaster event emergency record set comprises at least one natural disaster event emergency record;

matching the natural disaster event emergency record with an identification unit in the disaster event identification network for environmental factors to obtain a pending natural disaster event emergency record transmitted to the identification unit;

selecting a target natural disaster event emergency record from the undetermined natural disaster event emergency records according to the disaster event adaptation description between the undetermined natural disaster event emergency records and the identification unit;

and transmitting the target natural disaster event emergency record to the identification unit so as to transmit the target natural disaster event emergency record to the disaster event identification network and extract the target geological natural disaster event.

In an alternative embodiment, a disaster event identification network is extracted from historical geological natural disaster events based on the geological disaster event status description, wherein the disaster event identification network includes at least one identification unit, and the identification unit is configured to identify the historical geological natural disaster events and includes:

extracting an original identification network from the historical geological natural disaster events based on the geological disaster event state description, wherein the original identification network comprises at least one identification unit to be improved;

improving the identification unit based on the comparison result of the functional conflict of the identification unit in the original identification network to obtain an improved identification unit;

and determining a disaster event identification network in the historical geological natural disaster events according to the improved identification units, wherein the disaster event identification network comprises at least one improved identification unit which is used for identifying the historical geological natural disaster events.

In an alternative embodiment, extracting the original recognition network from the historical geological natural disaster event based on the geological disaster event state description comprises:

determining the distribution condition of network units corresponding to the extracted original identification network;

performing feature optimization on the geological disaster event state description to obtain a key information cluster corresponding to the geological disaster event state description;

extracting an original recognition network from the historical geological natural disaster event based on the network unit distribution condition and the key information cluster;

correspondingly, extracting an original recognition network from the historical geological natural disaster event based on the network unit distribution situation and the key information cluster, including:

extracting an original identification network matched with the distribution condition of the network units from the historical geological natural disaster events, wherein the original identification network comprises at least one identification unit to be updated;

according to the key information cluster, time attention updating is carried out on the identification unit in the original identification network to obtain an updated identification unit;

and determining an original identification network in the historical geological natural disaster event according to the updated identification unit.

In an alternative embodiment, the modifying the identification unit based on the comparison result of the functional conflict of the identification unit in the original identification network to obtain a modified identification unit includes:

matching the function conflict comparison result according to a preset unit prompt condition to determine a target identification unit to be improved;

and improving the target identification unit according to the unit prompting condition to obtain an improved identification unit.

In an optional embodiment, the selecting a target natural disaster event emergency record from the pending natural disaster event emergency records according to the disaster event adaptation description between the pending natural disaster event emergency record and the identification unit includes:

determining disaster event adaptation description between the undetermined natural disaster event emergency record and the identification unit based on the emergency record environmental characteristics of the undetermined natural disaster event emergency record;

according to the disaster event adaptive description, disturbance influence evaluation is carried out on the undetermined natural disaster event emergency record and the identification unit;

selecting target natural disaster event emergency records transmitted to the identification unit from undetermined natural disaster event emergency records passing the disturbance influence evaluation;

correspondingly, from undetermined natural disaster event emergency records that are passed through in disturbance influence evaluation, the target natural disaster event emergency records that are transmitted to the identification unit are selected, and the method comprises the following steps:

determining an emergency record cluster to which an emergency record of the undetermined natural disaster event passes through the disturbance influence evaluation, wherein the emergency record cluster has corresponding emergency record urgency degree prompt information;

and selecting the emergency records of the natural disaster events to be determined under the emergency record clustering according to the emergency record emergency degree prompt information to obtain the selected target natural disaster event emergency records.

In an alternative embodiment, the transmitting the target natural disaster event emergency record to the identification unit for importing the target natural disaster event emergency record into the disaster event identification network for extracting the target geological natural disaster event comprises:

sequentially adjusting the target natural disaster event emergency records to determine the global influence degree of each target natural disaster event emergency record;

according to the global influence degree, carrying out disturbance influence evaluation on the target natural disaster event emergency record;

transmitting the target natural disaster event emergency record passing the disturbance influence evaluation to the identification unit so as to transmit the target natural disaster event emergency record into the disaster event identification network and extract the target geological natural disaster event;

correspondingly, according to the global influence degree, disturbance influence evaluation is carried out on the target natural disaster event emergency record, and the method comprises the following steps:

disturbance influence evaluation is carried out on the target natural disaster event emergency records belonging to the same emergency record cluster;

selecting the target natural disaster event emergency records corresponding to the emergency record cluster based on the evaluation result to obtain the selected target natural disaster event emergency records;

and determining the target natural disaster event emergency records which pass the evaluation from the selected target natural disaster event emergency records based on the global influence degree of the selected target natural disaster event emergency records.

In an alternative embodiment, a set of natural disaster event emergency records to be introduced into the disaster event identification network is extracted, wherein the set of natural disaster event emergency records includes at least one natural disaster event emergency record, comprising:

acquiring event element information of natural disaster event emergency records to be extracted;

determining a combination strategy corresponding to the event element information; based on the emergency record element information of the event element information and the combination strategy, carrying out emergency record element combination on the event element information to obtain a combined natural disaster event emergency record;

extracting a natural disaster event emergency record set to be transmitted into the disaster event identification network according to the combined natural disaster event emergency records, wherein the natural disaster event emergency record set comprises at least one natural disaster event emergency record;

correspondingly, the natural disaster event emergency record is matched with an identification unit in the disaster event identification network for environmental factors, and an undetermined natural disaster event emergency record transmitted to the identification unit is obtained, including:

determining emergency record environmental factors of the natural disaster event emergency record and unit environmental factors of the identification unit;

matching the environmental factors of the emergency record with the environmental factors of the units;

and determining the matched natural disaster event emergency record as the pending natural disaster event emergency record transmitted to the identification unit.

In an optional embodiment, the method further comprises: detecting a key disaster scene by using the target geological natural disaster event;

correspondingly, the method for detecting the key disaster scene by using the target geological natural disaster event comprises the following steps:

acquiring scene mark list information of scene distribution conditions to be detected and characteristics of each geological scene according to active natural disaster event emergency records in the target geological natural disaster event;

determining feature correlation degrees between each geological scene feature under the real-time scene mark of the scene distribution condition to be detected and each geological scene feature under the time delay scene mark of the scene distribution condition to be detected according to the geological scene features under the time delay scene marks of the scene distribution condition of a plurality of disaster emergency servers and the scene mark contents thereof on the premise of determining that the scene distribution condition to be detected contains the time delay scene marks according to the scene mark list information, and transferring the geological scene features under the real-time scene marks of the scene distribution condition to be detected and the geological scene features under the time delay scene marks to be corresponding to the time delay scene marks;

under the premise that the current real-time scene mark of the scene distribution condition to be detected contains a plurality of geological scene features, determining the feature correlation degree between each geological scene feature under the current real-time scene mark of the scene distribution condition to be detected according to the geological scene features under the time delay scene marks of the scene distribution condition of a plurality of disaster emergency servers and the scene mark content thereof, and grouping each geological scene feature under the current real-time scene mark according to the feature correlation degree between each geological scene feature;

setting delay scene mark content for each group of geological scene features obtained by grouping according to geological scene features under the delay scene marks of the scene distribution conditions of a plurality of disaster emergency servers and scene mark content thereof, and transferring each group of geological scene features to the delay scene marks represented by the delay scene mark content;

carrying out early warning response heat detection on the geological scene characteristics under the real-time scene mark, and obtaining a current key disaster scene according to an early warning detection result;

correspondingly, the determining, according to the geological scene features under the time-delay scene marks of the scene distribution conditions of the disaster emergency servers and the scene mark contents thereof, the feature correlation between each geological scene feature under the real-time scene mark of the scene distribution conditions to be detected and each geological scene feature under the time-delay scene marks of the scene distribution conditions to be detected, and transferring the geological scene features under the real-time scene marks of the scene distribution conditions to be detected and related to the geological scene features under the time-delay scene marks to the corresponding time-delay scene marks includes:

calculating a Pearson correlation coefficient between the environment description vectors of the geological scene features under the real-time scene mark of the scene distribution condition to be detected and the geological scene features under the time delay scene mark of the scene distribution condition to be detected;

respectively judging whether the Pearson correlation coefficients reach a first Pearson correlation coefficient threshold value or not, and transferring the geological scene characteristics under the real-time scene mark with the Pearson correlation coefficients reaching the first Pearson correlation coefficient threshold value to the corresponding time-delay scene mark;

wherein the environment description vector of the geological scene features is as follows: according to the geological scene characteristics under the delay scene marks of the scene distribution conditions of the disaster emergency servers and the statistic results of the contents of the scene marks, the geological scene characteristics belong to the statistic results of the contents of the delay scene marks;

correspondingly, the determining, according to the geological scene features and the scene mark contents under the delayed scene marks of the scene distribution conditions of the disaster emergency servers, the feature correlation degree between the geological scene features under the current real-time scene marks of the scene distribution conditions to be detected, and the grouping, according to the feature correlation degree between the geological scene features, of the geological scene features under the current real-time scene marks comprises:

calculating a Pearson correlation coefficient between environment description vectors of each geological scene feature under the current real-time scene mark of the scene distribution condition to be detected;

for a geological scene feature under the current real-time scene mark of the scene distribution condition to be detected, classifying all geological scene features of which the Pearson correlation coefficient between the geological scene feature and the environment description vector reaches a second Pearson correlation coefficient threshold into one class;

wherein the environment description vector of the geological scene features is: and the geological scene features under the delay scene marks according to the scene distribution conditions of the disaster emergency servers and the geological scene features counted by the scene mark contents belong to the counting result of the delay scene mark contents.

The embodiment of the application also provides an extraction device for natural disaster events, which is applied to event extraction equipment, and the device comprises:

the description acquisition module is used for acquiring the geological disaster event state description corresponding to the target geological natural disaster event to be extracted;

the network extraction module is used for extracting a disaster event identification network from historical geological natural disaster events based on the geological disaster event state description, wherein the disaster event identification network comprises at least one identification unit, and the identification unit is used for identifying the historical geological natural disaster events;

the system comprises a record extraction module, a disaster event identification network and a disaster event identification module, wherein the record extraction module is used for extracting a natural disaster event emergency record set to be transmitted into the disaster event identification network, and the natural disaster event emergency record set comprises at least one natural disaster event emergency record;

the record matching module is used for matching the natural disaster event emergency record with an identification unit in the disaster event identification network for environmental factors to obtain an undetermined natural disaster event emergency record transmitted to the identification unit;

the record selection module is used for selecting a target natural disaster event emergency record from the undetermined natural disaster event emergency records according to the disaster event adaptation description between the undetermined natural disaster event emergency records and the identification unit;

and the event extraction module is used for transmitting the target natural disaster event emergency record to the identification unit so as to transmit the target natural disaster event emergency record to the disaster event identification network and extract the target geological natural disaster event.

The embodiment of the application also provides event extraction equipment, which comprises a processor, a network module and a memory; the processor and the memory communicate through the network module, and the processor reads the computer program from the memory and operates to perform the above-described method.

An embodiment of the present application further provides a computer storage medium, where a computer program is stored, and the computer program implements the method when running.

Compared with the prior art, the extraction method, the extraction device, the extraction equipment and the storage medium for the natural disaster event provided by the embodiment of the application have the following technical effects: the scheme can effectively improve the efficiency of extracting the geological natural disaster event, further, the scheme can extract the disaster event identification network matched with the disaster event state description based on the geological disaster event state description of the target geological natural disaster event to be extracted, and the target geological natural disaster event extracted finally based on the disaster event identification network has higher disaster environment matching degree and emergency record pertinence. In addition, in the process of transmitting the natural disaster event emergency record to the identification unit in the disaster event identification network, the scheme not only considers the matching degree of the environmental factors between the natural disaster event emergency record and the identification unit, but also considers the disaster event adaptation description corresponding to the natural disaster event emergency record and the identification unit, so that the event extraction state of the natural disaster event emergency record corresponding to the disaster event identification network can be effectively determined, and the defect that the natural disaster event is partially lost due to state incompatibility in the natural disaster event extraction process can be effectively overcome. In addition, in this scheme, only need provide the geological disaster event state description of the target geological natural disaster event that the sign is waited to extract to and wait to extract into the event element information of natural disaster event emergency record, just can accurately, completely and intelligently extract complete and high-quality geological natural disaster event through above-mentioned scheme, this efficiency and the intelligent degree that can greatly improve geological natural disaster event extraction.

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those of ordinary skill in the art upon examination of the following and the accompanying drawings or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

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 from the drawings without inventive effort.

Fig. 1 is a schematic block diagram of an event extraction device according to an embodiment of the present disclosure.

Fig. 2 is a flowchart of a method for extracting a natural disaster event according to an embodiment of the present disclosure.

Fig. 3 is a block diagram of an extraction apparatus for a natural disaster event according to an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: related reference numerals and letters indicate similar items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

Fig. 1 shows a block schematic diagram of an event extraction device 10 provided in an embodiment of the present application. The event extraction device 10 in the embodiment of the present application may be a server with data storage, transmission, and processing functions, as shown in fig. 1, the event extraction device 10 includes: memory 11, processor 12, network module 13 and extraction means 20 of natural disaster events.

The memory 11, the processor 12 and the network module 13 are electrically connected in real time or with a delay to realize the transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 11 stores an extraction device 20 for natural disaster events, the extraction device 20 for natural disaster events includes at least one software functional module which can be stored in the memory 11 in the form of software or firmware (firmware), and the processor 12 executes various functional applications and data processing by running software programs and modules stored in the memory 11, such as the extraction device 20 for natural disaster events in the embodiment of the present application, so as to implement the extraction method for natural disaster events in the embodiment of the present application.

The Memory 11 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like. The memory 11 is used for storing a program, and the processor 12 executes the program after receiving an execution instruction.

The processor 12 may be an integrated circuit chip having data processing capabilities. The Processor 12 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like. The various methods, steps and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The network module 13 is used for establishing communication connection between the event extraction device 10 and other communication terminal devices through a network, and implementing transceiving operation of network signals and data. The network signal may include a wireless signal or a wired signal.

It will be appreciated that the configuration shown in fig. 1 is merely illustrative and that the event extraction device 10 may also include more or fewer components than shown in fig. 1 or have a different configuration than shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.

An embodiment of the present application further provides a computer storage medium, where a computer program is stored, and the computer program implements the foregoing method when running.

Fig. 2 shows a flow chart of extraction of a natural disaster event according to an embodiment of the present application. The method steps defined by the flow associated with the method, as applied to the event extraction device 10, may be implemented by the processor 12, and include the following S21-S26.

In S21, the event extraction device obtains a geological disaster event state description corresponding to the target geological natural disaster event to be extracted.

In the embodiment of the present application, the geological natural disaster event may be a comprehensive natural disaster event (for example, a seismic event + an emergency measure event, a debris flow event + an emergency measure event, and the like) configured with a relevant emergency record. Accordingly, the description of the geological disaster event state can be understood as feature information of the natural disaster event, such as, but not limited to, a regional feature, a temporal feature, or a property loss feature of the natural disaster event.

In addition, the event extraction device may obtain the geological disaster event state description corresponding to the target geological natural disaster event to be extracted after receiving the relevant event extraction request.

At S22, the event extraction device extracts a disaster event identification network from historical geological natural disaster events based on the geological disaster event status description.

In an embodiment of the application, the disaster event identification network comprises at least one identification unit for identifying the historical geological natural disaster event.

It will be appreciated that the disaster event identification network may be a machine learning based long and short term memory network, and the network model may include different identification units for identifying historical geological natural disaster events from different perspectives, so as to enable accurate analysis of historical geological natural disaster events (without associated contingency records).

In some possible embodiments, the method described in S22 may be implemented by following S221-S223, extracting a disaster event identification network from historical geological natural disaster events based on the geological disaster event status description, wherein the disaster event identification network includes at least one identification unit for identifying the historical geological natural disaster events.

In S221, based on the geological disaster event state description, extracting an original identification network from the historical geological natural disaster event, wherein the original identification network comprises at least one identification unit to be improved.

For example, an identification unit to be improved may be understood as an identification unit to be adjusted or updated.

Further, the extracting an original recognition network from the historical geological natural disaster event based on the geological disaster event state description described in S221 may include the following technical solutions: determining the distribution condition of network units corresponding to the extracted original identification network; performing feature optimization on the geological disaster event state description to obtain a key information cluster corresponding to the geological disaster event state description; and extracting an original identification network from the historical geological natural disaster event based on the network unit distribution condition and the key information cluster.

For example, the network element distribution situation can be understood as an element distribution mode, the feature optimization can be understood as feature information conversion, and the key information cluster can be understood as integrated feature information. Therefore, the original identification network which is suitable for the actual natural disaster environment can be extracted according to the distribution condition of the network units and the key information cluster.

Further, the extracting of the original recognition network in the historical geological natural disaster event based on the network unit distribution and the key information cluster described in the above steps may include the following technical solutions: extracting an original identification network matched with the distribution condition of the network units from the historical geological natural disaster events, wherein the original identification network comprises at least one identification unit to be updated; according to the key information cluster, time attention updating is carried out on the identification units in the original identification network to obtain updated identification units; and determining an original identification network in the historical geological natural disaster event according to the updated identification unit.

For example, the temporal attention update may be a unit optimization manner based on a temporal angle, which may ensure that updated recognition units have no mutual influence on temporal features as much as possible, thereby ensuring the model quality of the original recognition network.

In S222, the recognition unit is improved based on the comparison result of the functional conflict of the recognition unit in the original recognition network, so as to obtain an improved recognition unit.

For example, the function conflict comparison result can be understood as unit indication information with overlapping or interference, and the function conflict comparison result is analyzed to realize identification unit improvement, so that mutual independence between improved identification units can be ensured, and occurrence of event identification disorder caused by unit interference is avoided.

In a related embodiment, the modifying the identification unit based on the comparison result of the functional conflict of the identification unit in the original identification network as described in S222 to obtain a modified identification unit may include the following: matching the function conflict comparison result according to a preset unit prompt condition to determine a target identification unit to be improved; and improving the target identification unit according to the unit prompting condition to obtain an improved identification unit. For example, a unit hint condition may be understood as a unit configuration condition.

In S223, a disaster event identification network in the historical geological natural disaster event is determined according to the improved identification unit, wherein the disaster event identification network includes at least one improved identification unit, and the identification unit is configured to identify the historical geological natural disaster event.

It is to be understood that the disaster event identification network in historical geological natural disaster events can be understood as a disaster event identification network corresponding to historical geological natural disaster events.

By the design, based on the above S221-S223, the function conflict comparison results of different identification units can be considered, so that mutual independence between the improved identification units is ensured, and the occurrence of event identification confusion caused by unit interference is avoided, so that the normal operation of a disaster event identification network can be ensured, the subsequent event identification can be smoothly realized, and the occurrence rate of event identification errors is reduced as much as possible.

In S23, the event extraction device extracts a set of natural disaster event emergency records to be passed into the disaster event identification network.

In an embodiment of the application, the set of emergency records of natural disaster events includes at least one emergency record of natural disaster events. The natural disaster event emergency records can be emergency records generated after emergency rescue is carried out on different events or different emergency situations, and include but are not limited to rescue emergency degree, rescue process information, property loss statistics and the like. The set of emergency records of natural disaster events may cluster the emergency records of natural disaster events with a certain correlation, in other words, the set of emergency records of natural disaster events may be understood as a cluster of emergency records of natural disaster events.

In an actual implementation process, the extraction described in S23 is to be performed on a natural disaster event emergency record set to be introduced into the disaster event identification network, where the natural disaster event emergency record set includes at least one natural disaster event emergency record, and may include the technical solutions described in S231-S233.

In S231, event element information of a natural disaster event emergency record to be extracted is acquired.

For example, the event element information may be key content or recording clip information of different emergency records.

In S232, determining a combination policy corresponding to the event element information; and carrying out emergency record element combination on the event element information based on the emergency record element information of the event element information and the combination strategy to obtain a combined natural disaster event emergency record.

For example, a combination policy may be understood as a combination rule or a concatenation rule.

In S233, according to the combined natural disaster event emergency records, a natural disaster event emergency record set to be transmitted to the disaster event identification network is extracted, where the natural disaster event emergency record set includes at least one natural disaster event emergency record.

By designing in this way, based on the above S231-S233, the event element information can be taken into account, and the emergency record elements can be combined with the combination strategy, so that the integrity of the extracted natural disaster event emergency record set can be ensured.

In S24, the event extraction device matches the natural disaster event emergency record with an identification unit in the disaster event identification network for environmental factors, and obtains an undetermined natural disaster event emergency record transmitted to the identification unit.

For example, environmental factors include air temperature, humidity, and altitude, but may also be distinguished by different urgency levels.

In a related embodiment, the matching of the environmental factors between the emergency record of the natural disaster event and the identification unit in the disaster event identification network as described in S24 to obtain the emergency record of the pending natural disaster event transmitted to the identification unit may include the following S241-S243.

In S241, the emergency record environmental factors of the natural disaster event emergency record and the unit environmental factors of the identification unit are determined.

In S242, the environmental factor matching is performed on the emergency record environmental factor and the unit environmental factor.

In S243, the matched natural disaster event emergency record is determined as the pending natural disaster event emergency record transmitted to the identification unit.

By the design, the environmental factor matching can be performed based on the environmental factors of the emergency records and the environmental factors of the units through the S241-S243, so that the emergency records of the undetermined natural disaster events can be accurately determined.

In S25, the event extraction device selects a target natural disaster event emergency record from the pending natural disaster event emergency records according to the disaster event adaptation description between the pending natural disaster event emergency record and the identification unit.

In the embodiment of the application, the disaster event adaptation description is used for representing the matching correlation condition between the pending natural disaster event emergency record and the identification unit, and the disaster event adaptation description is used for screening the pending natural disaster event emergency record so as to ensure the matching degree between the natural disaster event emergency record and the identification unit.

In a related embodiment, the step of selecting a target natural disaster event emergency record from the pending natural disaster event emergency records according to the disaster event adaptation description between the pending natural disaster event emergency records and the identification unit, which is described in S25, may include the following steps described in S251 to S253.

In S251, a disaster event adaptation description between the pending natural disaster event emergency record and the identification unit is determined based on the emergency record environmental characteristics of the pending natural disaster event emergency record.

In S252, according to the disaster event adaptation description, the disturbance influence evaluation is performed on the emergency record of the undetermined natural disaster event and the identification unit.

For example, the disturbance impact assessment is used to determine the impact of different natural disaster event emergency records on the use of the identification unit.

In S253, the target natural disaster event emergency records transmitted to the identification unit are selected from the undetermined natural disaster event emergency records that have passed the disturbance impact evaluation.

Further, the step of selecting the target natural disaster event emergency record transmitted to the identification unit from the pending natural disaster event emergency records passed through the disturbance influence evaluation as described in the above step S253 includes: determining an emergency record cluster to which an emergency record of the undetermined natural disaster event passes through the disturbance influence evaluation, wherein the emergency record cluster has corresponding emergency record urgency degree prompt information; and selecting the emergency records of the natural disaster events to be determined under the emergency record clustering according to the emergency record emergency degree prompt information to obtain the selected target natural disaster event emergency records.

It can be understood that when the above-mentioned S251-S253 is implemented, the disturbance influence evaluation can be considered, and accurate screening of the pending natural disaster event emergency records can be realized, so as to ensure the matching degree between the natural disaster event emergency records and the identification unit.

At S26, the event extraction device transmits the target natural disaster event emergency record to the identification unit, so as to transmit the target natural disaster event emergency record to the disaster event identification network, and extract a target geological natural disaster event.

In some embodiments, the transmitting the target natural disaster event emergency record to the identification unit to transmit the target natural disaster event emergency record to the disaster event identification network to extract the target geological natural disaster event as described in the above S26 may include the following technical solutions described in S261-S263.

In S261, the target natural disaster event emergency records are sequentially adjusted to determine a global influence degree of each target natural disaster event emergency record.

For example, the target natural disaster event emergency records may be sorted to determine the urgency of each target natural disaster event emergency record.

And in S262, according to the global influence degree, carrying out disturbance influence evaluation on the target natural disaster event emergency record.

For example, the target natural disaster event emergency records may be evaluated for perturbation impact in descending order of global impact.

For another example, S262 may also be implemented by the following embodiments: disturbance influence evaluation is carried out on the target natural disaster event emergency records belonging to the same emergency record cluster; selecting the target natural disaster event emergency records corresponding to the emergency record cluster based on the evaluation result to obtain the selected target natural disaster event emergency records; and determining the target natural disaster event emergency records which pass the evaluation from the selected target natural disaster event emergency records based on the global influence degree of the selected target natural disaster event emergency records.

In S263, the target natural disaster event emergency record passing the disturbance influence evaluation is transmitted to the identification unit, so as to transmit the target natural disaster event emergency record to the disaster event identification network, and extract the target geological natural disaster event.

It can be understood that the accuracy of the disaster event identification network in the event identification and extraction process can be ensured by transmitting the target natural disaster event emergency record passing the disturbance influence evaluation to the identification unit, so that the integrity and quality of the obtained target geological natural disaster event are ensured.

Based on the above S21-S23, a key disaster scenario detection scheme for the target geological natural disaster event may be further included, and based on this, in some optional embodiments, the method may further include S24: and detecting a key disaster scene by using the target geological natural disaster event.

Further, the detection of the critical disaster scene by using the target geological natural disaster event as described in the above S24 may include the following technical solutions described in S241-S245.

In S241, scene mark list information of the scene distribution condition to be detected and characteristics of each geological scene are obtained according to the emergency record of the active natural disaster event in the target geological natural disaster event.

In S242, on the premise that it is determined that the scene distribution condition to be detected includes the time delay scene marker according to the scene marker list information, the feature correlation between each geological scene feature under the time delay scene marker of the scene distribution condition to be detected and each geological scene feature under the time delay scene marker of the scene distribution condition to be detected is determined according to the geological scene features under the time delay scene marker of the scene distribution condition of the plurality of disaster emergency servers and the scene marker content thereof, and the geological scene features under the real-time scene marker of the scene distribution condition to be detected and the geological scene features under the time delay scene marker are transferred to the corresponding geological scene marker.

In a related embodiment, the determining, by the method described in S242, a feature correlation between each geological scene feature under the real-time scene mark of the scene distribution situation to be detected and each geological scene feature under the delay scene mark of the scene distribution situation to be detected according to the geological scene features under the delay scene marks of the scene distribution situations of the disaster emergency servers and the scene mark contents thereof, and transferring the geological scene features under the real-time scene mark of the scene distribution situation to be detected and the geological scene features under the delay scene marks to corresponding delay scene marks may include the following: calculating a Pearson correlation coefficient between the environment description vectors of the geological scene features under the real-time scene mark of the scene distribution condition to be detected and the geological scene features under the time delay scene mark of the scene distribution condition to be detected; respectively judging whether the Pearson correlation coefficients reach a first Pearson correlation coefficient threshold value or not, and transferring the geological scene characteristics under the real-time scene mark with the Pearson correlation coefficients reaching the first Pearson correlation coefficient threshold value to the corresponding time-delay scene mark; wherein the environment description vector of the geological scene features is as follows: and the geological scene features under the delay scene marks according to the scene distribution conditions of the disaster emergency servers and the geological scene features counted by the scene mark contents belong to the counting result of the delay scene mark contents.

In S243, on the premise that the current real-time scene mark of the scene distribution to be detected includes a plurality of geological scene features, determining a feature correlation between the geological scene features of the scene distribution to be detected under the current real-time scene mark according to the geological scene features of the scene distribution of the disaster emergency servers under the delay scene mark and the scene mark content thereof, and grouping the geological scene features of the current real-time scene mark according to the feature correlation between the geological scene features.

The determining, at S243, the feature correlation degree between the geological scene features under the current real-time scene mark of the scene distribution to be detected according to the geological scene features under the delayed scene marks of the scene distribution of the multiple disaster emergency servers and the scene mark content thereof, and grouping the geological scene features under the current real-time scene mark according to the feature correlation degree between the geological scene features, which may include the following contents: calculating a Pearson correlation coefficient between environment description vectors of each geological scene feature under the current real-time scene mark of the scene distribution condition to be detected; for a geological scene feature under the current real-time scene mark of the scene distribution condition to be detected, classifying all geological scene features of which the Pearson correlation coefficient between the geological scene feature and the environment description vector reaches a second Pearson correlation coefficient threshold into one class; wherein the environment description vector of the geological scene features is as follows: and the geological scene characteristics under the time delay scene marks according to the scene distribution conditions of the disaster emergency servers and the statistical results of the contents of the scene marks belong to the statistical results of the contents of the time delay scene marks.

In S244, delay scene mark content is set for each group of geological scene features obtained by the grouping according to geological scene features under the delay scene marks of the scene distribution of the disaster emergency servers and the scene mark content thereof, and each group of geological scene features is transferred to the delay scene marks represented by the delay scene mark content.

In S245, performing early warning response heat detection on the geological scene features under the real-time scene mark, and obtaining a current critical disaster scene according to an early warning detection result.

In S241-S245, the real-time scene marker and the delayed scene marker are used to represent the complexity and real-time performance of the scene marker, and generally speaking, the early warning response heat detection may be performed through geological scene features under the real-time scene marker to improve the precision of heat analysis, so that the adjustment and optimization of the scene markers of different types may be realized by performing feature correlation (similarity) analysis on texts under the scene markers of different types, thereby ensuring that the early warning response heat detection is performed according to accurate geological scene features under the real-time scene marker, and thus, the current key disaster scene may be accurately obtained through the early warning detection result.

In conclusion, the scheme can effectively improve the efficiency of extracting the geological natural disaster event, and further, the scheme can extract the disaster event identification network matched with the disaster event state description based on the geological disaster event state description of the target geological natural disaster event to be extracted, so that the target geological natural disaster event extracted finally based on the disaster event identification network has higher disaster environment matching degree and higher emergency record pertinence. In addition, in the process of transmitting the natural disaster event emergency record to the identification unit in the disaster event identification network, the scheme not only considers the matching degree of the environmental factors between the natural disaster event emergency record and the identification unit, but also considers the disaster event adaptation description corresponding to the natural disaster event emergency record and the identification unit, so that the event extraction state of the natural disaster event emergency record corresponding to the disaster event identification network can be effectively determined, and the defect that the natural disaster event is partially lost due to state incompatibility in the natural disaster event extraction process can be effectively overcome. In addition, in the scheme, only the geological disaster event state description representing the target geological natural disaster event to be extracted and the event element information to be extracted into the natural disaster event emergency record are provided, the complete and high-quality geological natural disaster event can be accurately, completely and intelligently extracted through the scheme, and the efficiency and the intelligent degree of extraction of the geological natural disaster event can be greatly improved.

Based on the same inventive concept, as shown in fig. 3, an embodiment of the present application further provides an extraction apparatus 20 for a natural disaster event, which is applied to an event extraction device 10, and the apparatus includes:

the description acquisition module 21 is configured to acquire a geological disaster event state description corresponding to a target geological natural disaster event to be extracted;

a network extraction module 22, configured to extract a disaster event identification network from historical geological natural disaster events based on the geological disaster event status description, where the disaster event identification network includes at least one identification unit, and the identification unit is configured to identify the historical geological natural disaster events;

a record extraction module 23, configured to extract a natural disaster event emergency record set to be transmitted to the disaster event identification network, where the natural disaster event emergency record set includes at least one natural disaster event emergency record;

a record matching module 24, configured to perform environmental factor matching on the natural disaster event emergency record and an identification unit in the disaster event identification network, to obtain an undetermined natural disaster event emergency record transmitted to the identification unit;

the record selection module 25 is configured to select a target natural disaster event emergency record from the pending natural disaster event emergency records according to the disaster event adaptation description between the pending natural disaster event emergency record and the identification unit;

and the event extraction module 26 is configured to transmit the target natural disaster event emergency record to the identification unit, so as to transmit the target natural disaster event emergency record to the disaster event identification network, and extract a target geological natural disaster event.

It is understood that, for the description of the above functional modules, reference may be made to the description of the method shown in fig. 2, and details are not described here.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solution of the present application or a part of the technical solution may be essentially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, an event extraction device 10, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An extraction method of natural disaster events, which is applied to an event extraction device, the method comprising:

acquiring a geological disaster event state description corresponding to a target geological natural disaster event to be extracted;

2. A method of natural disaster event extraction as claimed in claim 1, wherein extracting a disaster event identification network from historical geological natural disaster events based on the geological disaster event status description, wherein the disaster event identification network comprises at least one identification unit for identifying the historical geological natural disaster events, comprises:

3. A method of extracting natural disaster events according to claim 2, wherein extracting a primitive recognition network in the historical geological natural disaster events based on the geological disaster event state description comprises:

correspondingly, based on the network unit distribution condition and the key information cluster, extracting an original identification network from the historical geological natural disaster event, including:

extracting an original identification network matched with the distribution condition of the network units from the historical geological natural disaster event, wherein the original identification network comprises at least one identification unit to be updated;

determining an original identification network in the historical geological natural disaster event according to the updated identification unit;

correspondingly, based on the comparison result of the functional conflict of the identification unit in the original identification network, the identification unit is improved to obtain an improved identification unit, which includes:

4. The method for extracting natural disaster events according to claim 1, wherein the step of selecting the target natural disaster event emergency record from the pending natural disaster event emergency records according to the disaster event adaptation description between the pending natural disaster event emergency record and the identification unit comprises:

determining disaster event adaptation description between the to-be-determined natural disaster event emergency record and the identification unit based on the emergency record environmental characteristics of the to-be-determined natural disaster event emergency record;

5. A method of natural disaster event extraction as claimed in claim 1, wherein the step of transmitting the target natural disaster event emergency record to the identification unit for transmission into the disaster event identification network for extraction of target geological natural disaster event comprises:

transmitting the target natural disaster event emergency record passing the disturbance influence evaluation to the identification unit so as to transmit the target natural disaster event emergency record to the disaster event identification network and extract the target geological natural disaster event;

6. An extraction method of natural disaster events according to claim 1, characterized by extracting a set of natural disaster event emergency records to be introduced into the disaster event identification network, wherein the set of natural disaster event emergency records comprises at least one natural disaster event emergency record, comprising:

7. A method of extracting natural disaster events according to claim 1, further comprising: detecting a key disaster scene by using the target geological natural disaster event;

under the premise that the scene distribution condition to be detected contains the delay scene marks according to the scene mark list information, determining the feature correlation degree between each geological scene feature under the real-time scene mark of the scene distribution condition to be detected and each geological scene feature under the delay scene mark of the scene distribution condition to be detected according to the geological scene features under the delay scene marks of the scene distribution condition of the disaster emergency servers and the scene mark content thereof, and transferring the geological scene features under the real-time scene mark of the scene distribution condition to be detected and the geological scene features under the delay scene marks to be detected to the corresponding delay scene marks;

under the premise that the current real-time scene mark of the scene distribution condition to be detected comprises a plurality of geological scene features, determining the feature correlation degree between the geological scene features under the current real-time scene mark of the scene distribution condition to be detected according to the geological scene features under the time delay scene marks of the scene distribution condition of a plurality of disaster emergency servers and the scene mark content thereof, and grouping the geological scene features under the current real-time scene mark according to the feature correlation degree between the geological scene features;

correspondingly, the determining the feature correlation between each geological scene feature under the real-time scene mark of the scene distribution situation to be detected and each geological scene feature under the time delay scene mark of the scene distribution situation to be detected according to the geological scene features under the time delay scene mark of the scene distribution situation of the disaster emergency servers and the scene mark content thereof, and transferring the geological scene features under the real-time scene mark of the scene distribution situation to be detected and the geological scene features related to the geological scene features under the time delay scene mark to be detected to the corresponding time delay scene marks comprises:

8. An extraction device of natural disaster events, which is applied to an event extraction device, and comprises:

9. An event extraction device, comprising a processor, a network module and a memory; the processor and the memory communicate through the network module, the processor reading a computer program from the memory and operating to perform the method of any of claims 1-7.

10. A computer storage medium, characterized in that it stores a computer program which, when executed, implements the method of any one of claims 1-7.