Vibration sense information fusion special report generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a vibration sense information fusion special report generation method and device, electronic equipment and a storage medium, and relates to the technical field of computers. When an earthquake event is monitored, the earthquake feeling comments are automatically collected, manual intervention is reduced, and the real-time performance of earthquake feeling related data collection is improved. The big language model is used for analyzing the vibration sense data extracted from the vibration sense comments to obtain the vibration sense level and the corresponding geographic position, so that the speed and accuracy of data processing are effectively improved. According to the geographic position, the vibration sense grade and the influence field distribution map, the vibration sense distribution map is automatically generated, then the earthquake information, the vibration sense information, the vibration sense distribution map and the rapid evaluation special report are fused in the special report template, the vibration sense information fusion special report is obtained, the generation efficiency and accuracy of the vibration sense information fusion special report are remarkably improved, and the method is suitable for popularization and application. And solid support is provided for emergency response of earthquake disasters.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for generating a seismic information fusion report. Background Art

[0002] Earthquake disasters pose a huge threat to people's life and property safety. Emergency rescue work after an earthquake is very important. Therefore, quickly generating a fusion report of earthquake information has become the top priority of rescue work.

[0003] Existing technologies mainly rely on manual collection and screening of seismic information, classification of the screened seismic information according to hard-coded rules and scripts, manual evaluation of the accuracy and reliability of the classified data, and finally manual compilation of seismic information fusion reports based on the evaluated data. Since a large amount of work in generating seismic information fusion reports relies on manual operations, there are problems of low work efficiency and low accuracy, which will seriously affect the timeliness and accuracy of the generation of seismic information fusion reports. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, electronic device and storage medium for generating a seismic information fusion special report, which can improve the generation efficiency and accuracy of the seismic information fusion special report.

[0005] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows: In a first aspect, the present invention provides a method for generating a special report of seismic information fusion, the method comprising: If an earthquake event is detected, collecting earthquake sensation comments of the earthquake event, and extracting earthquake sensation data from the earthquake sensation comments; Analyzing the seismic data using a large language model to obtain seismic information corresponding to the seismic data; the seismic information includes a geographic location and a seismic level; Generate a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map; the impact field distribution map is obtained from the rapid assessment special report; A seismic information fusion special report is obtained according to the seismic information of the seismic event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template.

[0006] In an optional implementation manner, before the monitoring of the occurrence of an earthquake event, collecting the earthquake commentary of the earthquake event, and extracting the earthquake data from the earthquake commentary, the method further includes: When the background task obtains earthquake information of an earthquake event from the official earthquake website and the earthquake level exceeds the preset threshold, it is determined that an earthquake event has been monitored.

[0007] In an optional implementation manner, generating a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map includes: Obtaining the longitude and latitude coordinates of the administrative center according to the geographical location; The earthquake distribution map is generated according to the latitude and longitude coordinates, the earthquake feeling level, the layer parameter template, the administrative division map and the impact field distribution map.

[0008] In an optional implementation, generating the earthquake distribution map according to the latitude and longitude coordinates, the earthquake feeling level, a layer parameter template, an administrative division map and an impact field distribution map includes: Marking the corresponding earthquake feeling levels in the administrative division map based on the latitude and longitude coordinates to obtain an earthquake point map; Generate an initial distribution map according to the earthquake point map, the administrative division map and the layer parameter template; The initial distribution map is corrected using the influence field distribution map to obtain a seismic distribution map.

[0009] In an optional implementation manner, generating an initial distribution map according to the earthquake point map, the administrative division map and the layer parameter template includes: Connecting the longitude and latitude coordinates of the same earthquake feeling level in the earthquake point map to obtain multiple earthquake feeling layers; The seismic layers and the administrative division map are integrated based on the layer parameter template to obtain the initial distribution map.

[0010] In an optional implementation, the initial distribution map includes a plurality of seismic perception layers; and the step of correcting the initial distribution map using the influence field distribution map to obtain the seismic perception distribution map includes: For each of the seismic layers, determining a layer in the impact field distribution map having the same seismic level as the seismic layer as the target layer; When the difference between the tilt angle of the earthquake-sensing layer and the tilt angle of the target layer exceeds an angle threshold, rotating the earthquake-sensing layer according to the tilt angle of the target layer; When the length ratio of the seismic layer differs from that of the target layer by more than a ratio threshold, adjusting the minor axis length of the seismic layer according to the length ratio of the target layer; the length ratio is the ratio of the major axis to the minor axis; The corrected initial distribution map is determined as the seismic distribution map.

[0011] In an optional implementation manner, obtaining a seismic information fusion special report based on the seismic information of the seismic event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template includes: Obtain earthquake impact information from the rapid assessment report; Based on the earthquake feeling level, statistics are collected on the geographical location to generate an earthquake feeling description; The earthquake information, the earthquake impact information, the seismic description and the seismic distribution map are filled into the special report template to obtain the seismic information fusion special report.

[0012] In a second aspect, the present invention provides a device for generating a special report of seismic information fusion, the device comprising: An acquisition module, for collecting the seismic comments of the seismic event and extracting seismic data from the seismic comments if a seismic event is detected; A processing module, used to analyze the seismic data using a large language model to obtain seismic information corresponding to the seismic data; the seismic information includes a geographical location and a seismic level; A generation module is used to generate a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map; the impact field distribution map is obtained from a rapid assessment special report; and a seismic information fusion special report is obtained according to the seismic information of the earthquake event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template.

[0013] In a third aspect, the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for generating a seismic information fusion report as described in any of the aforementioned embodiments.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a seismic information fusion report as described in any one of the aforementioned embodiments is implemented.

[0015] Compared with the prior art, the method, device, electronic device and storage medium for generating a special report of seismic information fusion provided by the embodiment of the present invention automatically collect seismic comments after monitoring the occurrence of an earthquake event, reduce manual intervention, and improve the real-time nature of seismic-related data collection. The seismic data extracted from the seismic comments are analyzed using a large language model to obtain the seismic level and the corresponding geographical location, effectively improving the speed and accuracy of data processing. A seismic distribution map is automatically generated based on the geographical location, seismic level and impact field distribution map, and then the earthquake information, seismic information, seismic distribution map and rapid assessment special report are integrated into the special report template to obtain a seismic information fusion special report, which significantly improves the generation efficiency and accuracy of the seismic information fusion special report and provides solid support for earthquake disaster emergency response.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of a method for generating a special report of seismic information fusion provided by an embodiment of the present invention is shown.

[0019] Figure 2 Another schematic flow chart of the method for generating a special report of seismic information fusion provided by an embodiment of the present invention is shown.

[0020] Figure 3 Another schematic flow chart of the method for generating a special report of seismic information fusion provided by an embodiment of the present invention is shown.

[0021] Figure 4 A schematic diagram of a seismic information fusion report provided by an embodiment of the present invention is shown.

[0022] Figure 5 A block diagram of a device for generating a special report of seismic information fusion provided by an embodiment of the present invention is shown.

[0023] Figure 6 A block diagram of an electronic device provided by an embodiment of the present invention is shown.

[0024] Icons: 100 - electronic device; 110 - memory; 120 - processor; 130 - communication module; 400 - seismic information fusion report generating device; 401 - acquisition module; 402 - processing module; 403 - generating module. DETAILED DESCRIPTION

[0025] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0028] At present, the traditional method of generating special reports on seismic information fusion mainly relies on preset rules and manual intervention. Once these rules are set, it is difficult to flexibly adjust them. Even a small change in the business process may require a lot of reprogramming. The inventors have found that traditional technology generates special reports on seismic information fusion through the following steps. First, manually collect the original seismic information through various channels, manually screen and organize the original seismic information, and remove duplicate and invalid content.

[0029] Secondly, the operations of human users on the computer interface are simulated according to preset rules and scripts to classify the sorted information (such as geographic location, earthquake level, etc.), and the accuracy and reliability of the classified information are evaluated manually by comparing and verifying with multiple sources. However, there are limitations to interface interaction. This technology usually executes the process by simulating interface interactions such as mouse clicks and keyboard input, which makes it extremely sensitive to the interface layout. Once the interface changes, the script automation process may fail.

[0030] At the same time, when faced with abnormal situations or errors during process execution, traditional methods often lack effective error handling mechanisms and recovery strategies, and their error handling and recovery capabilities are weak, which may cause the entire process to be interrupted. For business processes involving complex judgment logic or data processing, traditional methods may not be able to handle them and require manual intervention or additional software development.

[0031] Finally, the seismic information fusion report is manually compiled based on the classified and evaluated information. During the manual compilation process, it may be necessary to communicate with relevant departments or experts multiple times to maximize the accuracy and completeness of the seismic information fusion report. Due to the lack of unified standards and interfaces, traditional methods have difficulties in integrating with other systems or applications, limiting the breadth and depth of their application, and poor integration and scalability.

[0032] It can be seen that the traditional method has problems such as poor automation, insufficient data processing capabilities and lack of intelligent decision-making. Among them, the poor automation is due to the fact that a large amount of work still relies on manual operations, such as data collection, screening, sorting and information coding. Manual intervention not only increases the error rate, but also reduces work efficiency.

[0033] The lack of data processing capabilities is reflected in the fact that traditional methods cannot quickly and accurately process and analyze data when faced with a large amount of earthquake information, which will lead to information delays or legacy, affecting the timeliness and accuracy of earthquake information fusion reports. The lack of intelligent decision-making is reflected in the fact that traditional methods usually make decisions based on preset rules and scripts, which lack flexibility. When faced with complex or uncertain situations, it may not be possible to make the best decision.

[0034] Based on this, the method and device for generating a special report of seismic information fusion provided by the embodiment of the present invention automatically collect seismic comments after monitoring the occurrence of an earthquake event, reduce manual intervention, and improve the real-time nature of the collection of seismic-related data. The seismic data extracted from the seismic comments are analyzed using a large language model to obtain the seismic level and the corresponding geographical location, effectively improving the speed and accuracy of data processing. A seismic distribution map is automatically generated based on the geographical location, seismic level, and impact field distribution map, and then the earthquake information, seismic information, seismic distribution map, and rapid assessment special report are integrated into the special report template to obtain a seismic information fusion special report, which significantly improves the generation efficiency and accuracy of the seismic information fusion special report and provides solid support for earthquake disaster emergency response.

[0035] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0036] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a method for generating a special report of earthquake information fusion provided by an embodiment of the present invention is shown. The method comprises the following steps: Step S10: if an earthquake event is detected, collect the earthquake sensation comments and extract the earthquake sensation data from the earthquake sensation comments.

[0037] In an embodiment of the present invention, when an earthquake event is detected, a data collection instruction is sent to Robotic Process Automation (RPA), and RPA is used to obtain users' comments on the earthquake sensation corresponding to the earthquake event from social platforms. The social platform can be a self-media platform, such as the earthquake network quick report, the earthquake network and the earthquake bureau of a province, and other accounts within two hours after the earthquake. The social platform can also be an instant messaging platform, such as the earthquake sensation comments provided instantly by member units in the disaster work group.

[0038] As a possible implementation, by using a simulated user interface (User Interface, hereinafter referred to as: UI), such as DrissionPage, continuously collect the shaking comments of key accounts on the social platform, and the Application Programming Interface (hereinafter referred to as: API) saves the shaking comments in the data resource pool.

[0039] Use RPA to parse the shaking comments to obtain the shaking data related to the earthquake event, and store the shaking data in the structured shaking data table to ensure the integrity and accuracy of the shaking data, which is convenient for subsequent processing and analysis. Through the data resource pool API, the structured shaking data table and earthquake information are integrated in real time to provide comprehensive data support for rapid assessment.

[0040] The shaking comments of earthquake events need to pay attention to real-time and accuracy. Using RPA to achieve automated collection of shaking comments and reducing manual intervention can ensure that a large number of original shaking comments are quickly collected after the earthquake event, providing strong support for subsequent information processing and the generation of special reports on the integration of shaking information.

[0041] It should be noted that the shaking data includes basic information, propagation and interaction information, and comment information. Among them, the basic information includes the identifier of the shaking comment, the account name of the social platform (such as the earthquake network), the information release time (such as the Weibo release time), and the release content (such as #Earthquake News# The earthquake network automatically determined: aaa). The propagation and interaction information includes the number of forwards (such as the Weibo forward number), the number of comments, and the number of likes. The comment information includes the commenter's name, comment timestamp, the geographical location of the commenter, the comment content, and the comment date.

[0042] Step S20: Use a large language model to analyze the shaking data to obtain the shaking information corresponding to the shaking data; the shaking information includes the geographical location and the shaking level.

[0043] In the embodiment of the present invention, a prompt word is constructed, and each piece of shaking data and the prompt word are input into the large language model in turn. The large language model performs reasoning and analysis on each piece of shaking data according to the prompt word and the internal model to obtain the shaking information corresponding to each piece of shaking data, that is, the geographical location and the shaking level corresponding to each piece of shaking data.

[0044] As a possible implementation, the prompt word can be set as: "You are a data analyst. Your task is to analyze the earthquake level and location from a paragraph. Each paragraph will have two elements: location and level. This paragraph may directly give you these two elements, or it may need to be analyzed. You can only output the five categories I provide for the level, namely: severe, strong, slight, no earthquake, and unknown. There are two types of locations: specific location and unknown. For the two given elements, you can output them directly. For the ungiven elements, I will give you several judgment criteria, and you can learn to analyze according to the judgment criteria I give you. Judgment criteria: 1. For severe: people's reactions will include crying, feeling like they are going to collapse, feeling a very strong earthquake, shaking and bumping, difficulty in movement, panicking and fleeing outdoors, drivers feeling it, cyclists falling, people in an unstable state falling, feeling thrown up, etc.; the reactions of objects will include objects falling, heavy objects on the top turning over, and furniture tipping over and shifting. 2. For strong: people's reactions will include obvious earthquakes, strong earthquakes, unstable standing, sleeping Being shaken awake in a dream, lying in bed shaking without feeling sleepy, being frightened, feeling scared to death, being shaken, dizzy, shaking violently, feeling dizzy, panicking, frightened legs, running to the toilet, objects may shake, some objects may fall over, water may spill, light furniture may move, and buildings may shake. 3. For minor: people may react by high-rise shaking, feeling a tremor but not strong, not knowing whether to run, feeling the bed shaking slightly, feeling the ground shaking slightly, and the water in the cup shaking gently; objects may react by hanging objects shaking slightly, and lights shaking. .For no earthquake: people will not feel it obviously, and objects will not shake obviously. 5.For unknown: you have not analyzed the above four earthquake levels, then fill in unknown. The earthquake is judged by people's reaction first. If people's reaction is not mentioned, refer to the reaction of objects. Please output in strict accordance with the following format: location-seismic level, and do not output other content. You can only output two types of location: only output this location if it is a prefecture-level city, prefecture-level county or prefecture-level district, otherwise output unknown. The output sample is: City A, District B.

[0045] It should be noted that the earthquake information is classified into those with earthquake, those without earthquake, those with geographic location and those without geographic location. The earthquake information with no earthquake but with geographic location is directly recorded in the data resource pool through the API. For earthquake information without geographic location, check whether the earthquake comment contains the location information of the IP Internet Protocol (IP) address. If it contains the location information of the IP address, determine the geographic location corresponding to the earthquake data based on the location information of the IP address.

[0046] Invalid earthquake information that cannot be supplemented with geographical location will be archived, and earthquake information with geographical location and earthquake level will be saved in the earthquake information classification table. The earthquake information classification table will be saved in the data resource pool using the API interface as the basis for generating earthquake information fusion reports.

[0047] It is worth mentioning that the embodiment of the present invention uses carefully designed prompt words to guide the large language model to classify the seismic level according to the seismic information. The prompt words clearly define the description information of "human feeling" and "object reaction" corresponding to the three seismic levels of "mild", "strong" and "violent" based on business standards. While improving the data processing speed and accuracy, the carefully designed prompt words are used to achieve intelligent decision-making, improving the accuracy and flexibility of seismic level decision-making.

[0048] When designing prompt words, a series of prompt words are pre-written according to business needs and the definition of the vibration level. The prompt words should include detailed descriptions of the five vibration levels: no vibration, slight vibration, strong vibration, severe vibration, and unknown vibration, as well as specific descriptions of human feelings (such as slight vibration, people feel slight shaking) and object reactions (such as strong vibration, causing objects to fall) at each vibration level.

[0049] When using prompt words, the pre-designed prompt words are used as input and input into the large language model together with the seismic data. The large language model parses and classifies the seismic data based on the prompt words and the internally learned language model to obtain the seismic level, such as mild or strong. The geographic location is obtained from the seismic data, and the large language model outputs the seismic level and geographic location as the seismic information corresponding to the seismic data. If the geographic location is not obtained in the seismic data, the geographic location is set to unknown.

[0050] Step S30, generating a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map; the impact field distribution map is obtained from the rapid assessment report.

[0051] Step S40, obtaining a seismic information fusion special report based on the seismic information, seismic information, seismic distribution map, rapid assessment special report and special report template of the seismic event.

[0052] In an embodiment of the present invention, a rapid assessment system is accessed to obtain a rapid assessment report corresponding to an earthquake event and a vector data file corresponding to an impact field distribution map. The vector data file records vector data of earthquake events with an earthquake impact range of five degrees or above. The vector data intuitively displays the possible impact range of earthquake disasters and provides an important basis for generating a seismic distribution map.

[0053] Generate a seismic distribution map based on the seismic level, the geographical location corresponding to the seismic level, and the vector data corresponding to the impact field distribution map. Integrate the earthquake information, seismic information, seismic distribution map, and rapid assessment report of the earthquake event, and fill the integrated data into the report template to obtain a seismic information fusion report.

[0054] In summary, the method for generating a special report of seismic information fusion provided by an embodiment of the present invention automatically collects seismic comments after an earthquake event is monitored, reduces manual intervention, and improves the real-time nature of seismic-related data collection. The seismic data extracted from the seismic comments are analyzed using a large language model to obtain the seismic level and the corresponding geographical location, effectively improving the speed and accuracy of data processing. A seismic distribution map is automatically generated based on the geographical location, seismic level, and impact field distribution map, and then the earthquake information, seismic information, seismic distribution map, and rapid assessment special report are integrated into the special report template to obtain a seismic information fusion special report, which significantly improves the generation efficiency and accuracy of the seismic information fusion special report and provides solid support for earthquake disaster emergency response.

[0055] Optionally, a possible implementation method is provided below for determining whether an earthquake event has occurred. Figure 2 ,exist Figure 1 Before step S10, it also includes: Step S00: When the background task obtains earthquake information of an earthquake event from the official earthquake website and the earthquake level exceeds a preset threshold, it is determined that an earthquake event has been monitored.

[0056] In the embodiment of the present invention, the application scenario of the earthquake information fusion special report includes application level, application time and function. Among them, the application level includes earthquake events of magnitude 5 and above; the application time includes the "black box period" within two hours after the earthquake event; the function includes helping emergency rescue forces to better refer to the earthquake intensity of the people in various regions, and providing data support for rapid response and precise rescue.

[0057] The background task monitors the earthquake officials in real time. When an earthquake event is released on the official earthquake website, the background task obtains the earthquake information of the earthquake event from the official earthquake website. When the earthquake level recorded in the earthquake information exceeds the preset threshold (for example, level five), it is determined that an earthquake event has been monitored and the collection mechanism is triggered immediately to ensure that earthquake comments are continuously and efficiently collected within two hours after the earthquake, thereby improving the timeliness of earthquake information collection.

[0058] Optionally, a possible implementation method for generating a seismic distribution map is provided below. Figure 3 , Figure 2 The sub-steps of step S30 may include: Step S301, obtaining the longitude and latitude coordinates of the administrative center according to the geographical location.

[0059] Step S302, generating a seismic distribution map according to the longitude and latitude coordinates, the seismic level, the layer parameter template, the administrative division map and the impact field distribution map.

[0060] In an embodiment of the present invention, the earthquake distribution map is used to record the distribution of the three earthquake levels of mild, strong and severe. Based on the geographical locations corresponding to the three earthquake levels of mild, strong and severe, the administrative center corresponding to the geographical location is obtained, and the longitude and latitude coordinates corresponding to the administrative center are obtained. For example, if the geographical location is City A, the longitude and latitude coordinates corresponding to the administrative center of City A are obtained. According to the requirements of the parameter template, the earthquake distribution map is generated according to the longitude and latitude coordinates, earthquake level, administrative division map and impact field distribution map.

[0061] Optionally, a possible implementation method is provided below on how to generate a seismic distribution map using latitude and longitude coordinates and seismic levels. Figure 3 The sub-steps of step S302 may include: Based on the longitude and latitude coordinates, the corresponding earthquake feeling levels are marked in the administrative division map to obtain an earthquake point map; an initial distribution map is generated according to the earthquake point map, the administrative division map and the layer parameter template; the initial distribution map is corrected using the impact field distribution map to obtain a earthquake feeling distribution map.

[0062] In an embodiment of the present invention, the longitude and latitude coordinates corresponding to each geographical location are searched in the administrative division map, and the seismic level corresponding to the geographical location is marked in the position corresponding to the longitude and latitude coordinates to obtain an earthquake point map. The earthquake point map includes multiple marked geographical locations and seismic levels. The earthquake point map and the administrative division map are processed according to the layer parameter template to obtain an initial distribution map. Based on the impact field distribution map, the initial distribution map is corrected to obtain a seismic distribution map, which effectively improves the accuracy of seismic distribution in the seismic information fusion report.

[0063] Optionally, a possible implementation method for generating an initial distribution map is provided below, including the following steps: Connect the longitude and latitude coordinates of the same earthquake level in the earthquake point map to obtain multiple earthquake layers; integrate each earthquake layer and the administrative division map based on the layer parameter template to obtain the initial distribution map.

[0064] In the embodiment of the present invention, the longitude and latitude coordinates of the earthquake point map with a slight earthquake feeling level are connected to obtain a slight layer. The longitude and latitude coordinates of the earthquake point map with a strong earthquake feeling level are connected to obtain a strong layer. The longitude and latitude coordinates of the earthquake point map with a severe earthquake feeling level are connected to obtain a severe layer. The earthquake feeling layer includes a slight layer, a strong layer and a severe layer.

[0065] As a possible implementation method, the Quantum Geographic Information System (QGIS) is used to quickly and accurately generate a seismic distribution map, providing intuitive visual support for the seismic information fusion report. QGIS marks the administrative division map according to the longitude and latitude coordinates and the seismic level to obtain an earthquake point map. QGIS connects the longitude and latitude coordinates of the same seismic level to obtain a slight layer, a strong layer, and a severe layer. Among them, the severe layer is the area with severe seismic closest to the epicenter, usually an ellipse. The strong layer is the area with strong seismic slightly farther from the epicenter, usually an elliptical ring. The slight layer is the area with slight seismic farther from the epicenter, usually an elliptical ring.

[0066] Assume that the layer parameter template includes the color of the severe layer as dark red, the color of the strong layer as pink, the color of the mild layer as yellow, the north direction indication, the legend and the epicenter. According to the layer parameter template, the color of the elliptical area corresponding to the severe layer is set to dark red, and the center of the severe layer is the epicenter. The color of the elliptical ring area corresponding to the strong layer is set to pink, and the color of the elliptical ring area corresponding to the mild layer is set to yellow. The mild layer, the strong layer, the severe layer, the north direction indication, the legend and the epicenter are superimposed on the administrative division map to obtain the initial distribution map.

[0067] Optionally, the initial distribution map includes multiple seismic layers. As to how to correct the initial distribution map using the impact field distribution map, a possible implementation method is provided below, including the following steps: For each seismic layer, the layer with the same seismic level as the seismic layer in the impact field distribution map is determined as the target layer; when the difference between the inclination angle of the seismic layer and the inclination angle of the target layer exceeds the angle threshold, the seismic layer is rotated according to the inclination angle of the target layer; when the difference between the length ratio of the seismic layer and the length ratio of the target layer exceeds the ratio threshold, the short axis length of the seismic layer is adjusted according to the length ratio of the target layer; the length ratio is the ratio of the major axis to the minor axis; the corrected initial distribution map is determined as the seismic distribution map.

[0068] In the embodiment of the present invention, each earthquake layer in the initial distribution map is processed, that is, the slight layer, the strong layer and the severe layer are processed. A layer with the same earthquake level as the earthquake layer is obtained from the impact field distribution map as the target layer. The inclination angle, the major axis distance and the minor axis distance of the target layer are obtained from the vector data corresponding to the target layer, and the length ratio of the target layer is determined according to the major axis distance and the minor axis distance of the target layer.

[0069] Find the ellipse corresponding to the epicenter in the initial distribution map, determine the major axis and minor axis corresponding to the epicenter based on the ellipse corresponding to the epicenter, and determine the inclination angle of the major axis corresponding to the epicenter as the inclination angle of the seismic layer. When the difference between the inclination angle of each seismic layer and the inclination angle of the target layer does not exceed the angle threshold (for example, 20%) and the difference between the length ratio of each seismic layer and the length ratio of the target layer does not exceed the ratio threshold (for example, 10%), there is no need to adjust the inclination angle and length ratio of the seismic layer, and the initial distribution map is used as the seismic distribution map.

[0070] When the difference between the tilt angle of the seismic layer and the tilt angle of the target layer exceeds the angle threshold, the seismic layer is rotated according to the tilt angle of the target layer until the difference between the tilt angle of the seismic layer and the tilt angle of the target layer does not exceed the angle threshold. When the difference between the aspect ratio of the seismic layer and the aspect ratio of the target layer exceeds the ratio threshold, the minor axis length of the seismic layer is adjusted according to the aspect ratio of the target layer until the difference between the aspect ratio of the seismic layer and the aspect ratio of the target layer does not exceed the ratio threshold.

[0071] Taking the slight layer as an example, when the length ratio of the earthquake layer differs from that of the target layer by more than the ratio threshold, a straight line is drawn through the center coordinates of the epicenter according to the inclination angle of the target layer, and the longitude and latitude coordinates farthest from the straight line in the slight layer are determined as the long axis reference point of the slight layer. The long axis of the slight layer is determined according to the long axis reference point and the center coordinates of the epicenter. The maximum vertical distance from the longitude and latitude coordinates in the slight layer to the long axis is determined as the short axis length. If the short axis length is greater than the long axis length, the second farthest point is found until the long axis length is greater than the short axis length. The ellipse of the slight layer is determined according to the long axis and short axis. Similarly, the strong layer and the severe layer can be processed with reference to the slight layer to obtain the earthquake distribution map. The earthquake distribution map intuitively shows the distribution of earthquake sensations and provides important reference information for decision makers and the public.

[0072] Optionally, a possible implementation method is provided below for how to generate a special report on the fusion of seismic information. Figure 3 , Figure 2 The sub-steps of step S40 may include: Step S401, obtaining earthquake impact information from the rapid assessment report.

[0073] In an embodiment of the present invention, after obtaining the rapid assessment report, key information, namely earthquake impact information, is obtained from the rapid assessment report. Earthquake impact information may include the earthquake impact range (e.g., kilometers from the epicenter), maximum intensity, disaster-affected areas (including directly affected areas and indirectly affected areas), casualties (preliminary estimates of the number of deaths, injuries, and missing persons), building damage (e.g., damage to houses and infrastructure), and secondary disasters (e.g., areas affected by landslides, mudslides, and secondary disasters, and potential risks).

[0074] Step S402, collecting statistics on geographical locations based on the earthquake feeling levels and generating earthquake feeling descriptions.

[0075] In the embodiment of the present invention, the geographical location of each seismic level is statistically analyzed to obtain the geographical location distribution corresponding to each seismic level, and then the geographical location distribution corresponding to each seismic level is integrated to obtain the seismic description, so that the originally complex seismic comment becomes intuitive and easy to understand. The text description in the seismic information fusion report is concise and clear, allowing readers to quickly grasp the seismic situation of the earthquake and provide strong support for decision-making.

[0076] For example, the description of the earthquake feeling may include that according to the disaster information reported by the earthquake disaster reporter of Province A, some areas such as City A (A1 County, A2 County, A3 County) and City B (District B1, District B2) felt strong earthquakes; some areas such as City C of Province C and City D felt slight earthquakes.

[0077] Step S403, filling the earthquake information, earthquake impact information, seismic description and seismic distribution map into the special report template to obtain a seismic information fusion special report.

[0078] In the embodiment of the present invention, a special report template with clear structure and rich information is prepared in advance, and the earthquake information, earthquake impact information, seismic description and seismic distribution map corresponding to the earthquake event are filled in according to the special report template to obtain a special report fused with seismic information, such as Figure 4 shown.

[0079] Assume that the earthquake information obtained from the official earthquake website is: According to the measurement of the seismic network, a magnitude CC earthquake occurred at 12:12:12 on December 12, 20xx in A41 Town, A4 County, A City (aa degrees north latitude, bb degrees east longitude), with a focal depth of 16 kilometers. The town is located in A41 Town, A4 County, A City, 39 kilometers away from A4 County, 53 kilometers away from A City, and 221 kilometers away from B City.

[0080] It should be noted that earthquake information, earthquake impact information, seismic description, seismic distribution map and special report templates can be stored and managed through the data resource pool. When generating a special report on seismic information fusion, the earthquake information obtained from the official website of the earthquake, the earthquake impact information in the rapid assessment special report, the seismic description and seismic distribution map corresponding to the seismic commentary are integrated into the special report on seismic information fusion, providing detailed information related to the earthquake event to ensure the comprehensiveness and accuracy of the assessment and assist decision makers in making a quick response.

[0081] It is worth mentioning that in order to further improve the real-time performance of the earthquake information fusion report, data can be transmitted in real time through Kafka. Once an earthquake event occurs, earthquake comments, earthquake information and rapid assessment reports can be quickly captured and transmitted to electronic devices, reducing the delay in data transmission and ensuring that the earthquake information fusion report can be generated in the first time and the content is comprehensive and accurate. This immediacy and accuracy are crucial for earthquake emergency response.

[0082] In order to more clearly illustrate the method for generating a special report of seismic information fusion provided by an embodiment of the present invention, an exemplary description is given in combination with a specific implementation method.

[0083] As an implementation method, RPA is used to perform steps S00 to S40 and sub-steps of each step in the above embodiment. RPA can simulate human operations and automatically perform repetitive and standardized tasks, thereby reducing manual burden and improving work efficiency. In the process of generating a special report on seismic information fusion, RPA automatically collects seismic comments of earthquake events, and strictly follows preset rules to parse seismic comments, extract seismic data, and effectively avoid human errors and omissions. RPA can efficiently process large-scale data sets, quickly integrate earthquake information, seismic information, seismic distribution maps and rapid assessment reports from multiple data sources, and generate comprehensive and comprehensive seismic information fusion reports. The content of each seismic information fusion report remains highly accurate and consistent in format, which greatly reduces the pressure on staff and significantly improves the professionalism, timeliness and credibility of the seismic information fusion report, which can meet the needs of complex business scenarios.

[0084] Based on the same inventive concept, the basic principle and technical effect of the device for generating a special report of seismic information fusion provided in the embodiment of the present invention are the same as those in the above embodiment. For the sake of brief description, for parts not mentioned in this embodiment, reference may be made to the corresponding contents in the above embodiment.

[0085] Please refer to Figure 5 , Figure 5 A block diagram of a seismic information fusion report generating device 400 provided in an embodiment of the present invention includes an acquisition module 401 , a processing module 402 and a generation module 403 .

[0086] The acquisition module 401 is used to collect the earthquake sensation comments of the earthquake event and extract the earthquake sensation data from the earthquake sensation comments if an earthquake event is detected; Processing module 402, used to analyze the seismic data using a large language model to obtain seismic information corresponding to the seismic data; the seismic information includes geographic location and seismic level; The generation module 403 is used to generate a seismic distribution map according to the geographical location, seismic level and impact field distribution map; the impact field distribution map is obtained from the rapid assessment special report; based on the earthquake information, seismic information, seismic distribution map, rapid assessment special report and special report template of the earthquake event, a seismic information fusion special report is obtained.

[0087] In summary, the device for generating a special report of seismic information fusion provided by an embodiment of the present invention automatically collects seismic comments after monitoring the occurrence of an earthquake event, reduces manual intervention, and improves the real-time nature of the collection of seismic-related data. The seismic data extracted from the seismic comments are analyzed using a large language model to obtain the seismic level and the corresponding geographical location, effectively improving the speed and accuracy of data processing. A seismic distribution map is automatically generated based on the geographical location, seismic level, and impact field distribution map, and then the earthquake information, seismic information, seismic distribution map, and rapid assessment special report are integrated into the special report template to obtain a seismic information fusion special report, which significantly improves the generation efficiency and accuracy of the seismic information fusion special report and provides solid support for earthquake disaster emergency response.

[0088] Optionally, the acquisition module 401 is also used to determine that an earthquake event has been monitored when the background task obtains earthquake information of the earthquake event from the official earthquake website and the earthquake level exceeds a preset threshold.

[0089] Optionally, the generation module 403 is specifically used to obtain the longitude and latitude coordinates of the administrative center according to the geographical location; and generate a seismic distribution map according to the longitude and latitude coordinates, the seismic level, the layer parameter template, the administrative division map and the impact field distribution map.

[0090] Optionally, generation module 403 is specifically used to mark the corresponding seismic feeling levels in the administrative division map based on the longitude and latitude coordinates to obtain an earthquake point map; generate an initial distribution map based on the earthquake point map, the administrative division map and the layer parameter template; and use the influence field distribution map to correct the initial distribution map to obtain a seismic feeling distribution map.

[0091] Optionally, the generation module 403 is specifically used to connect the longitude and latitude coordinates of the same seismic level in the earthquake point map to obtain multiple seismic layers; and integrate each seismic layer and the administrative division map based on the layer parameter template to obtain an initial distribution map.

[0092] Optionally, the initial distribution map includes multiple seismic layers; the generation module 403 is specifically used to determine, for each seismic layer, a layer with the same seismic level as the seismic layer in the impact field distribution map as a target layer; when the difference between the inclination angle of the seismic layer and the inclination angle of the target layer exceeds an angle threshold, the seismic layer is rotated according to the inclination angle of the target layer; when the difference between the length ratio of the seismic layer and the length ratio of the target layer exceeds a ratio threshold, the short axis length of the seismic layer is adjusted according to the length ratio of the target layer; the length ratio is the ratio of the major axis to the minor axis; and the corrected initial distribution map is determined as the seismic distribution map.

[0093] Optionally, generation module 403 is specifically used to obtain earthquake impact information from the rapid assessment special report; to perform statistics on geographical locations based on the seismic level and generate a seismic description; to fill the earthquake information, earthquake impact information, seismic description and seismic distribution map into the special report template to obtain a seismic information fusion special report.

[0094] Please refer to Figure 6 , is a block diagram of an electronic device 100 provided in an embodiment of the present invention. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, the processor 120, and the communication module 130 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0095] The memory 110 is used to store programs or data. The memory 110 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 programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0096] The processor 120 is used to read / write data or programs stored in the memory 110 and execute corresponding functions. For example, when the computer program stored in the memory 110 is executed by the processor 120, the method for generating a special report of seismic information fusion disclosed in the above embodiments can be implemented.

[0097] The communication module 130 is used to establish a communication connection between the electronic device 100 and other communication terminals through a network, and to send and receive data through the network.

[0098] It should be understood that Figure 6 The structure shown is only a schematic diagram of the structure of the electronic device 100. The electronic device 100 may also include Figure 6 More or fewer components as shown, or with Figure 6 Different configurations are shown. Figure 6 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0099] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 120, the method for generating a special report by fusion of seismic information disclosed in the above embodiments is implemented.

[0100] The embodiment of the present invention further provides a program product. When the program product is executed by the processor 120, the method for generating a special report of seismic information fusion disclosed in the above embodiments is implemented.

[0101] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0103] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating a special report of earthquake information fusion, characterized in that: The method comprises: If an earthquake event is detected, collecting earthquake sensation comments of the earthquake event, and extracting earthquake sensation data from the earthquake sensation comments; Analyzing the seismic data using a large language model to obtain seismic information corresponding to the seismic data; the seismic information includes a geographical location and a seismic level; Generate a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map; the impact field distribution map is obtained from the rapid assessment special report; A seismic information fusion special report is obtained according to the seismic information of the seismic event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template.

2. The method for generating a special report of earthquake information fusion according to claim 1, characterized in that: Before the process of collecting the earthquake sensation comments of the earthquake event and extracting the earthquake sensation data from the earthquake sensation comments if an earthquake event is detected, the process further includes: When the background task obtains earthquake information of an earthquake event from the official earthquake website and the earthquake level exceeds the preset threshold, it is determined that an earthquake event has been monitored.

3. The method for generating a special report of earthquake information fusion according to claim 1, characterized in that: The generating of the earthquake distribution map according to the geographical location, the earthquake level and the impact field distribution map comprises: Obtaining the longitude and latitude coordinates of the administrative center according to the geographical location; The earthquake distribution map is generated according to the latitude and longitude coordinates, the earthquake feeling level, the layer parameter template, the administrative division map and the impact field distribution map.

4. The method for generating a special report of earthquake information fusion according to claim 3, characterized in that: The generating the earthquake distribution map according to the latitude and longitude coordinates, the earthquake feeling level, the layer parameter template, the administrative division map and the impact field distribution map includes: Marking the corresponding earthquake feeling levels in the administrative division map based on the latitude and longitude coordinates to obtain an earthquake point map; Generate an initial distribution map according to the earthquake point map, the administrative division map and the layer parameter template; The initial distribution map is corrected using the influence field distribution map to obtain a seismic distribution map.

5. The method for generating a special report of earthquake information fusion according to claim 4, characterized in that: The generating of the initial distribution map according to the earthquake point map, the administrative division map and the layer parameter template comprises: Connecting the longitude and latitude coordinates of the same earthquake feeling level in the earthquake point map to obtain multiple earthquake feeling layers; The seismic layers and the administrative division map are integrated based on the layer parameter template to obtain the initial distribution map.

6. The method for generating a special report of earthquake information fusion according to claim 4, characterized in that: The initial distribution map includes a plurality of seismic perception layers; the method of using the influence field distribution map to correct the initial distribution map to obtain a seismic perception distribution map includes: For each of the seismic layers, determining a layer in the impact field distribution map having the same seismic level as the seismic layer as the target layer; When the difference between the tilt angle of the earthquake-sensing layer and the tilt angle of the target layer exceeds an angle threshold, rotating the earthquake-sensing layer according to the tilt angle of the target layer; When the length ratio of the seismic layer differs from that of the target layer by more than a ratio threshold, adjusting the minor axis length of the seismic layer according to the length ratio of the target layer; the length ratio is the ratio of the major axis to the minor axis; The corrected initial distribution map is determined as the seismic distribution map.

7. The method for generating a special report of earthquake information fusion according to claim 1, characterized in that: The step of obtaining a seismic information fusion special report based on the seismic information of the seismic event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template includes: Obtain earthquake impact information from the rapid assessment report; Based on the earthquake feeling level, statistics are collected on the geographical location to generate an earthquake feeling description; The earthquake information, the earthquake impact information, the seismic description and the seismic distribution map are filled into the special report template to obtain the seismic information fusion special report.

8. A device for generating a special report of earthquake information fusion, characterized in that: The device comprises: An acquisition module, for collecting the seismic comments of the seismic event and extracting seismic data from the seismic comments if a seismic event is detected; A processing module, used to analyze the seismic data using a large language model to obtain seismic information corresponding to the seismic data; the seismic information includes a geographical location and a seismic level; A generation module is used to generate a seismic distribution map according to the geographical location, the seismic level and the impact field distribution map; the impact field distribution map is obtained from a rapid assessment special report; and a seismic information fusion special report is obtained according to the seismic information of the earthquake event, the seismic information, the seismic distribution map, the rapid assessment special report and the special report template.

9. An electronic device, characterized in that: It includes a processor and a memory, the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for generating a seismic information fusion report as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating a special report of seismic information fusion according to any one of claims 1 to 7 is implemented.

Images