Disaster risk entity data storage method, equipment, storage medium and device

Abstract

The present invention discloses a disaster risk entity data storage method, equipment, storage medium and device. The present invention obtains an integrated target data set by integrating multi-source heterogeneous disaster data sets; stores the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules and preset semantic relationships through a preset spatiotemporal object model, and queries and extracts disaster emergency information based on the disaster risk entity database. Compared with the existing technology, disaster data is too discrete and cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, which in turn affects the efficiency of disaster emergency management. The present invention solves the integrated and chain-complex characteristics of natural disaster risk monitoring and early warning, and the multi-source heterogeneity of disaster data and the problems of expression being out of context, so as to facilitate the flexible application of disaster entity data to various emergency scenarios.

Description

Technical Field

[0001] The present invention relates to the field of natural disaster emergency management technology, and in particular to a disaster risk entity data storage method, equipment, storage medium and device. Background Art

[0002] Since the beginning of the 21st century, a series of major natural disasters have occurred worldwide, causing enormous casualties and socioeconomic losses, raising important warnings for strengthening natural disaster risk monitoring and early warning. Continuously improving emergency management capabilities, including risk monitoring and early warning, emergency command and support, intelligent decision-making support, government services, and public opinion guidance and response, is a challenge that the current emergency management system must address. Therefore, multi-hazard natural disaster risk monitoring and early warning has become a critical and pressing issue in the field of disaster prevention and mitigation research and work within the emergency management system.

[0003] The existing technical support system for natural disaster risk monitoring and early warning is mainly reflected in the construction of natural disaster monitoring and early warning networks and the implementation of monitoring and early warning information projects. With the rapid development of remote sensing technology and the improvement of ground feature observation capabilities, multimodal remote sensing results such as visible light images, InSAR, infrared images, microwave images, etc. in the form of satellite remote sensing, aerial remote sensing, and ground remote sensing are widely used in the field of natural disaster risk monitoring and early warning.

[0004] Furthermore, the rapid development of multi-source information acquisition technologies, including the Internet of Things (IoT), 5G, and ubiquitous internet information, has enhanced the ability to acquire critical disaster information elements. However, the acquisition processes for various data are independent and based on different standards, resulting in heterogeneous data sources, simple representation methods, and poor traceability. Therefore, existing technologies are still weak in organically combining multi-source data to establish and express key natural disaster elements and the spatiotemporal semantic relationships between them. Furthermore, existing disaster data is too discrete to effectively support disaster prediction and emergency response, resulting in low data utilization and, in turn, hindering the efficiency of disaster emergency management.

[0005] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of the present invention is to provide a disaster risk entity data storage method, equipment, storage medium and device, aiming to solve the technical problem in the prior art that the existing disaster data is too discrete, cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, and thus affecting the efficiency of disaster emergency management.

[0007] To achieve the above object, the present invention provides a method for storing disaster risk entity data, the method comprising the following steps:

[0008] Acquire a multi-source heterogeneous disaster dataset, and integrate the multi-source heterogeneous disaster dataset to obtain an integrated target data set;

[0009] The target data set is stored in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed through a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules;

[0010] Disaster emergency information is queried and extracted based on the disaster risk entity database.

[0011] Optionally, before the step of storing the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, the method further includes:

[0012] Acquire a historical multi-source heterogeneous disaster dataset, perform data preprocessing on the historical multi-source heterogeneous disaster dataset, and obtain a preprocessed data set;

[0013] Determine the preset disaster risk entity system based on the disaster system element theory and the evolution law of disaster chains;

[0014] A disaster risk entity storage model is constructed based on the preset disaster risk entity system and the data set.

[0015] Optionally, after the step of constructing a disaster risk entity storage model based on the preset disaster risk entity system and the data set, the method further includes:

[0016] Identifying potential disaster risk spatiotemporal objects within a preset disaster unit, and extracting the disaster risk spatiotemporal objects to obtain extracted disaster risk spatiotemporal objects;

[0017] Determining a disaster risk entity construction rule based on the structure of the disaster risk spatiotemporal object, wherein the disaster risk entity construction rule includes a single-element rule and a multi-element rule;

[0018] Determining a spatial operation model according to the disaster risk entity construction rule, and performing disaster risk entity matching on the disaster risk spatiotemporal object according to the spatial operation model to obtain a target disaster risk entity;

[0019] The spatial graph corresponding to the target disaster risk entity and its attribute information are stored in the disaster risk entity storage model.

[0020] Optionally, after the step of storing the spatial graph and attribute information corresponding to the target disaster risk entity in the disaster risk entity storage model, the method further includes:

[0021] Determine a coding domain according to different disaster application scenarios, and determine a coding rule according to the coding domain;

[0022] Perform attribute comparison on the coded disaster risk entity objects according to spatial primitive rules and key attributes to obtain comparison results;

[0023] spatially aggregating the disaster risk entity objects according to the comparison results, and calculating the spatial positions of the aggregated entity objects;

[0024] The identity code of the entity object is determined according to the coding rule and the spatial position.

[0025] Optionally, after the step of determining the identity code of the physical object according to the coding rule and the spatial position, the method further includes:

[0026] Constructing an entity relationship storage model based on a preset relationship model, the disaster risk entity system, and the identity code;

[0027] Extracting semantic relationship rules from a preset semantic relationship rule library based on the association scenarios between natural disaster risk entities;

[0028] A target relationship storage model is generated based on the semantic relationship rules and the entity relationship storage model.

[0029] Optionally, after the step of generating a target relationship storage model based on the semantic relationship rules and the entity relationship storage model, the method further includes:

[0030] Constructing an initial spatiotemporal object model based on the target relationship storage model and the disaster risk entity storage model;

[0031] The multi-source heterogeneous spatiotemporal datasets are input into the initial spatiotemporal object model for training to obtain the preset spatiotemporal object model.

[0032] Optionally, the step of acquiring a multi-source heterogeneous disaster dataset, integrating the multi-source heterogeneous disaster dataset, and obtaining an integrated target data set includes:

[0033] Acquire a multi-source heterogeneous spatiotemporal data set, classify the multi-source heterogeneous disaster data set according to a preset disaster risk entity system, and obtain a classified data set;

[0034] Perform data analysis on each data set, eliminate redundant data, and store the eliminated data according to the preset disaster risk entity system to obtain the integrated target data set.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also proposes a disaster risk entity data storage device, which includes a memory, a processor, and a disaster risk entity data storage program stored on the memory and runnable on the processor, and the disaster risk entity data storage program is configured to implement the steps of disaster risk entity data storage as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a disaster risk entity data storage program is stored. When the disaster risk entity data storage program is executed by a processor, the steps of the disaster risk entity data storage method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present invention further proposes a disaster risk entity data storage device, the disaster risk entity data storage device comprising:

[0038] A data acquisition module is used to acquire a multi-source heterogeneous disaster data set, perform data integration on the multi-source heterogeneous disaster data set, and obtain an integrated target data set;

[0039] a model processing module for storing the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed using a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules;

[0040] The data query module is also used to query and extract disaster emergency information based on the disaster risk entity database.

[0041] The present invention obtains a multi-source heterogeneous disaster data set, integrates the multi-source heterogeneous disaster data set, and obtains an integrated target data set; stores the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed through a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules; queries and extracts disaster emergency information based on the disaster risk entity database, and classifies and identifies multi-source heterogeneous disaster data and data that are expressed out of context through the constructed entity data model. Compared with the existing technology, disaster data is too discrete and cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, which in turn affects the efficiency of disaster emergency management. The present invention solves the integrated and chain-complex characteristics of natural disaster risk monitoring and early warning, and the problems of multi-source heterogeneity and expression out of context of disaster data, so as to facilitate the flexible application of disaster entity data to various emergency scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic structural diagram of a disaster risk entity data storage device in a hardware operating environment involved in an embodiment of the present invention;

[0043] Figure 2 This is a flow chart of a first embodiment of a method for storing disaster risk entity data according to the present invention;

[0044] Figure 3 This is a schematic diagram of integrating multi-source heterogeneous disaster data in the first embodiment of the disaster risk entity data storage method of the present invention;

[0045] FIG4( a ) is a schematic diagram of a risk entity object modeling framework according to a second embodiment of a method for storing disaster risk entity data according to the present invention;

[0046] FIG4( b ) is a schematic diagram of a natural disaster risk entity relationship modeling framework according to a second embodiment of the disaster risk entity data storage method of the present invention;

[0047] Figure 5 This is a schematic diagram of the risk entity construction process of the second embodiment of the disaster risk entity data storage method of the present invention;

[0048] Figure 6 This is a schematic diagram of the natural disaster risk entity spatial identity coding process of the second embodiment of the disaster risk entity data storage method of the present invention;

[0049] Figure 7 This is a flowchart of the natural disaster risk entity association technology of the second embodiment of the disaster risk entity data storage method of the present invention;

[0050] Figure 8 This is a technical flow chart of natural disaster risk entity construction in the second embodiment of the disaster risk entity data storage method of the present invention;

[0051] Figure 9 This is a structural block diagram of the first embodiment of the disaster risk entity data storage device of the present invention.

[0052] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a disaster risk entity data storage device in the hardware operating environment involved in an embodiment of the present invention.

[0055] like Figure 1 As shown, the disaster risk entity data storage device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement communication between these components. The user interface 1003 may include a display screen. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. In the present invention, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0056] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the disaster risk entity data storage device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0057] like Figure 1 As shown, the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a disaster risk entity data storage program.

[0058] exist Figure 1 In the disaster risk entity data storage device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the user device; the disaster risk entity data storage device calls the disaster risk entity data storage program stored in the memory 1005 through the processor 1001, and executes the disaster risk entity data storage method provided by the embodiment of the present invention.

[0059] Based on the above hardware structure, an embodiment of the disaster risk entity data storage method of the present invention is proposed.

[0060] Reference Figure 2 , Figure 2 This is a flow chart of the first embodiment of the disaster risk entity data storage method of the present invention, which provides the first embodiment of the disaster risk entity data storage method of the present invention.

[0061] In this embodiment, the disaster risk entity data storage method includes the following steps:

[0062] Step S10: Acquire a multi-source heterogeneous disaster dataset, perform data integration on the multi-source heterogeneous disaster dataset, and obtain an integrated target data set.

[0063] It should be noted that the execution entity in this embodiment can be a device that includes a disaster risk entity data storage system, such as a computer, or other devices that can perform the same or similar functions. This embodiment does not limit this. The disaster risk entity data storage system can be used to achieve real-time monitoring and collection and classification of disaster data in scenarios such as intelligent disaster emergency defense, and can also be applied to disaster warning data analysis. In this embodiment and the following embodiments, the disaster risk entity data storage method of the present invention is described using the disaster risk entity data storage system as an example.

[0064] It is understandable that a multi-source heterogeneous disaster data set can refer to a data set to be stored consisting of multi-source disaster data and spatiotemporal disaster data. The data set contains disaster data in various scenarios. Since the acquisition process of various data is independent of each other and based on different standards, it reflects the characteristics of multi-source heterogeneity, simple expression, and poor traceability. Therefore, it is necessary to integrate this multi-source heterogeneous disaster data to facilitate later data queries and improve processing efficiency when conducting early warning analysis. The integrated target data set can be a data set classified according to preset entity types, wherein the set includes data information corresponding to each entity type.

[0065] Furthermore, the S10 also includes: obtaining a multi-source heterogeneous spatiotemporal data set, classifying the multi-source heterogeneous disaster data set according to a preset disaster risk entity system, and obtaining a classified data set; performing data analysis on each data set, eliminating redundant data, and storing the eliminated data according to the preset disaster risk entity system to obtain an integrated target data set.

[0066] It should be understood that due to the fact that the monitoring vector data comes from many sources, has large differences in data structure, different data granularity, non-uniform spatial reference, and uneven data quality, it is necessary to integrate the data. Data integration includes analysis and evaluation, unified spatial benchmark, effective information extraction, data redundancy and invalid information cleaning, etc. To further illustrate the data integration process, you can refer to Figure 3 As shown in the schematic diagram of multi-source heterogeneous disaster data integration, the acquired multi-source heterogeneous disaster data are analyzed according to the preset disaster risk entity system, redundant data are eliminated, and the eliminated data are stored according to the preset disaster risk entity system to obtain the integrated target data set.

[0067] In specific implementation, the preset disaster risk entity system can be divided into risk entity classification systems such as disaster-prone environment, disaster-causing factors, disaster-bearing bodies, historical disasters, and disaster units, which can be specifically set according to the application scenario.

[0068] Step S20: The target data set is stored in a preset disaster risk entity database according to the preset disaster risk spatiotemporal objects, preset coding rules and preset semantic relationships through the preset spatiotemporal object model. The preset spatiotemporal object model is an entity data storage model constructed in advance through the preset disaster risk entity system, disaster risk entity construction rules and spatiotemporal semantic relationship rules.

[0069] It should be noted that the preset spatiotemporal object model is an entity data storage model constructed in advance through a preset disaster risk entity system, disaster risk entity construction rules and spatiotemporal semantic relationship rules. The entity data storage model is used to aggregate and store discrete features to achieve the purpose of constructing multi-hazard comprehensive disaster risk knowledge of multi-source heterogeneous and multi-hazard natural disaster risk elements.

[0070] It is understandable that the preset disaster risk spatiotemporal object can refer to the spatiotemporal object corresponding to the natural disaster risk entity. The spatiotemporal object can be data of multiple data types, wherein the disaster risk entity construction rule can be the construction rule that should be used when constructing the risk entity by using the geometric composition characteristics of the risk spatiotemporal object to establish the mapping correspondence between entities and primitives, and entities and entities. The preset coding rule can be a coding scheme determined according to different disaster application scenarios. The preset semantic relationship can be based on the association scenario between natural disaster risk entities, and the semantic relationship rule items are flexibly extracted from the semantic relationship rule library to form semantic relationship rule items, which have embedded spatial relationship calculation rules, including spatial topological relationships, spatial distance relationships, and spatial orientation relationships. Spatial topological relationships are subdivided into subcategories such as spanning, intersection, adjacent, connected, spatial inclusion, and spatial inclusion; spatial distance relationships are subdivided into spatial quantitative distance and spatial definition distance; spatial orientation relationships are subdivided into eight directions, sixteen directions, and up and down directions. The preset disaster risk entity database is used to store integrated disaster risk entity data.

[0071] In practice, natural disasters' predisposing environments, hazard-causing factors, and subsequent events typically occur within specific spatial and temporal domains, carrying specific spatiotemporal semantic information. Disaster information elements are inextricably linked, exhibiting spatiotemporal correlations and temporal variations, which underlie the fundamental laws governing the spatiotemporal evolution of disaster chains. To address the problems of traditional disaster risk factor data being multi-source, heterogeneous, and out-of-context, as well as the need to interpret the spatiotemporal evolution of multiple disaster types, this solution studies natural disaster risk spatiotemporal object modeling technology. This technology uses natural disaster risk spatiotemporal semantic representations of hazard-causing factors, disaster-prone environments, disaster-bearing bodies, historical disasters, and disaster risk units, centered on natural disaster risk entities. This technology explores the inherent relationships between multi-hazard natural disaster risk entity objects, constructs a spatiotemporal, multi-hazard comprehensive relationship map, and explores and deeply characterizes the spatiotemporal evolution of multi-hazard disaster risks at multiple levels. This approach is suitable for large-scale modeling and representation of both predictive disaster probability factors and actual disaster-affected objects or scopes. Therefore, this embodiment addresses the integrated, chain-like complexity of natural disaster risk monitoring and early warning, as well as the multi-source, heterogeneous, and out-of-context representation of disaster data. Therefore, this solution uses a preset spatiotemporal object model to store the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships.

[0072] Step S30: querying and extracting disaster emergency information based on the disaster risk entity database.

[0073] In specific implementation, disaster emergency information can be queried and extracted through the disaster risk entity database to support data provision services for disaster emergency and other scenarios.

[0074] This embodiment obtains a multi-source heterogeneous disaster data set, integrates the multi-source heterogeneous disaster data set, and obtains an integrated target data set; stores the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model. The preset spatiotemporal object model is an entity data storage model pre-constructed through a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules; and queries and extracts disaster emergency information based on the disaster risk entity database. This embodiment uses the constructed entity data model to classify, identify, and store multi-source heterogeneous disaster data and data that are expressed out of context. Compared with the existing technology, disaster data is too discrete and cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, which in turn affects the efficiency of disaster emergency management. This embodiment solves the integrated and chain-complex characteristics of natural disaster risk monitoring and early warning, as well as the multi-source heterogeneity and expression-out-of-context problems of disaster data, so as to facilitate the flexible application of disaster entity data to various emergency scenarios.

[0075] Based on the above Figure 2 The first embodiment shown here provides a second embodiment of the disaster risk entity data storage method of the present invention.

[0076] In this embodiment, further, before step S20, it also includes: obtaining a historical multi-source heterogeneous disaster data set, performing data preprocessing on the historical multi-source heterogeneous disaster data set, and obtaining a preprocessed data set; determining a preset disaster risk entity system based on the disaster system element theory and the disaster chain evolution law; and constructing a disaster risk entity storage model based on the preset disaster risk entity system and the data set.

[0077] It should be understood that before data conversion and storage, a model must be trained for later data storage. Therefore, the modeling design step requires obtaining a historical multi-source heterogeneous disaster dataset and performing data preprocessing on it to obtain a preprocessed data set for use as a later training set. Preprocessing refers to data integration, which includes steps such as analysis and evaluation, unified spatial benchmarks, effective information extraction, and data redundancy and invalid information cleaning.

[0078] It is understandable that the preset disaster risk entity system is established based on the theory of disaster system elements and the evolution law of disaster chains, and includes disaster-prone environments, disaster-causing factors, disaster-bearing bodies, historical disasters, disaster units, etc.

[0079] It should be understood that this solution establishes a risk entity graphic storage table, an entity storage table, and an entity relationship table, adds risk entity classification into the entity storage table, sets a unified spatial storage benchmark, and establishes a risk entity classification system such as disaster-prone environment, disaster-causing factors, disaster-bearing bodies, historical disasters, and disaster units, and constructs a risk entity storage model. The newly constructed risk entities will be stored in accordance with the risk entity storage model.

[0080] In practice, existing data resources and models for natural disaster monitoring are multi-source, multi-modal, and multi-temporal, designed to meet specific business needs. They lack a unified object model architecture and design for describing the spatiotemporal structure, inherent relationships, and spatiotemporal characteristics of risk objects in natural disaster monitoring and early warning. Data storage methods do not abstract the real world and its operating laws in an object-oriented or business-oriented manner. Therefore, a unified risk spatiotemporal object model and spatiotemporal object relationship model are necessary. The model design process can be referenced by the schematic diagrams of the risk entity object modeling framework shown in Figure 4 (a) and the natural disaster risk entity relationship modeling framework shown in Figure 4 (b). As can be seen from the figures, the required model structure and corresponding data types for the object spatiotemporal model are determined by establishing the entity object framework and relationship framework. Preprocessing historical multi-source heterogeneous disaster datasets yields a preprocessed data set. A predefined disaster risk entity system is determined based on the theory of disaster system elements and the evolution of disaster chains. A disaster risk entity storage model is constructed based on the predefined disaster risk entity system and data set, and the required spatiotemporal object model is constructed based on the disaster risk entity storage model.

[0081] Furthermore, after the step of constructing a disaster risk entity storage model based on the preset disaster risk entity system and the data set, it also includes: identifying potential disaster risk spatiotemporal objects within the preset disaster unit range, and extracting the disaster risk spatiotemporal objects to obtain extracted disaster risk spatiotemporal objects; determining disaster risk entity construction rules based on the structure of the disaster risk spatiotemporal objects, and the disaster risk entity construction rules include single-element rules and multi-element rules; determining a spatial operation model according to the disaster risk entity construction rules, and performing disaster risk entity matching on the disaster risk spatiotemporal objects according to the spatial operation model to obtain a target disaster risk entity; storing the spatial graphics and attribute information corresponding to the target disaster risk entity in the disaster risk entity storage model.

[0082] It should be noted that in the process of constructing natural disaster risk entities, you can refer to Figure 5The risk entity construction process diagram shown in the figure can be divided into the following specific steps: 1) Establishing an entity object storage model: Establishing a risk entity classification system such as disaster-prone environment, disaster-causing factors, disaster-bearing bodies, historical disasters, and disaster units, and constructing a risk entity storage model. The newly constructed risk entity will be stored according to the risk entity storage model. (2) Identifying potential risk spatiotemporal objects: ① Using spatial indexes to quickly locate risk spatiotemporal objects within the scope of the disaster unit, constructing spatial indexes (such as grid indexes, R-tree indexes, etc.) for objects within the scope of the disaster unit, and using the scope of the disaster unit to quickly obtain potential spatiotemporal objects, narrowing the search scope and improving efficiency. ② When constructing entities according to a certain risk spatiotemporal object category, the search can be combined with the feature coding of this type of entity on the basis of ① to further narrow the search scope and improve efficiency. (3) Determining risk entity construction rules: Using the geometric composition characteristics of risk spatiotemporal objects, determine the construction rules that should be used when constructing risk entities, and establish mapping correspondences between entities and primitives, and entities and entities. ① Point primitive object: When the risk spatiotemporal object has and only has point primitives as the only geometric figure, the point single primitive construction rule is adopted. ② Line primitive objects: When risk spatiotemporal objects are represented by linear primitives as geometric graphics, it is necessary to distinguish between line representation types, such as structural lines, edge lines, range lines, or simultaneous representation. When only structural lines are used for unique representation, the centerline single primitive rule should be adopted; when multiple structural lines are used to continuously represent the object, the centerline multi-prime rule should be adopted; when only edge lines or range lines are used for unique or continuous representation, the edge line or range line single primitive or multi-prime rule should be adopted; when a certain type of object is represented by both structural lines and edge lines, such as roads and bridges, both single primitive and multi-prime rules should be adopted. ③ Surface primitive objects: When a risk spatiotemporal object has only surface primitives as its unique geometric graphics, the surface single primitive construction rule should be adopted; when the object is composed of multiple surface primitives, the surface multi-prime rule should be adopted; when an object has important locational significance and is represented by both point primitives and surface primitives, and the point is located inside the surface primitive, the multi-prime rule should be adopted. ④ Volumetric primitive objects: When risk spatiotemporal objects are expressed in three-dimensional spatial form, it is necessary to distinguish whether they are represented as a whole three-dimensional model or as a three-dimensional patch. The former adopts the single primitive rule, while the latter adopts the multi-primitive rule. (4) Determine the spatial operation model: Use the determined construction rules, single primitive rules or multi-primitive rules, to determine the spatial calculation model required for construction. ① Single primitive batch construction model: Select potential single primitive risk spatiotemporal objects, input risk entity classification, and perform mapping. ② Line batch construction model: For continuously expressed structural lines, edge lines or range lines, the line batch construction model also needs to combine the key attributes of risk spatiotemporal objects, such as geographic unique codes, feature codes, key names, etc., search in the selected potential risk spatiotemporal objects, and output the structural line, edge line or range line primitive object set.③ Object consistency model. This model is usually used in scenarios where a risk entity object is represented by multiple geometric figures at the same time, or the same risk entity is expressed in multiple spatiotemporal scales. This model uses the spatial positional relationship and spatial topological relationship of multiple geometric figures, combined with key attributes, to determine whether two sets of geometric figures are the same risk entity object. ④ Combined entity extraction model. This model should be used when a group of risk entities with spatial clustering or location continuity or certain management characteristics needs to be extracted. This model uses the spatial positional relationship, spatial topological relationship, and category relationship of a group of risk entities, combined with key attributes, to determine whether the group of risk entities has spatial clustering. For example, a courtyard and its houses, internal roads, green facilities, parking facilities, etc. have a spatial containment and inclusion relationship, as well as a spatial whole-part relationship. Spatial connection relationships, key names, and landform professional codes can be used to determine whether a group of risk entities with location continuity, such as a road, is composed of multiple first-connected road sections. (5) Risk entity construction: Select the risk spatiotemporal object to be constructed, set the calculation model, extract the risk entity through spatial calculation, and store its spatial graphics and attribute information in the risk entity storage model.

[0083] In the specific implementation, based on the unified spatiotemporal object model of natural disaster risk, an object storage model is established to identify potential spatiotemporal risk objects within the disaster unit, and an extraction scheme adapted to the modeling of risk entity objects is formulated. This allows the construction of risk spatiotemporal risk objects with geographic spatial locations, as well as the extraction of various risk spatiotemporal risk objects representing abstract concepts such as disaster dynamic processes and socio-economics. Based on the extracted spatiotemporal risk object structure, the risk entity construction rules are determined, and a spatial operation model is selected to construct the risk entity. Entity matching is performed on risk entity objects with the same name or synonyms that cause multiple semantic ambiguities, and these objects are identified as globally unique entities. The definition of the natural disaster risk entity construction rules mainly includes single-element rules and multi-element rules: Single-element rules: Disaster risk elements with only one unique graphic element in any of the geometric expressions of points, lines, surfaces, or volumes are used to construct risk entities using their own single spatial element as the unique spatiotemporal object that occupies geographic space. Multi-element rule: Disaster risk factors, expressed in a composite or multi-scale manner using one or more geometric representations such as points, lines, surfaces, or volumes, must be constructed based on the spatial location and attribute information of multiple elements. This includes determining whether spatial topological features such as inclusion, overlap, and crossing exist, and whether the attribute information is consistent across risk entity classification codes and names. When the spatial location and attribute information can be confirmed as multiple spatiotemporal geometric representations of the same object, the multi-element rule can be used to construct the same risk entity as its spatiotemporal object representation.

[0084] Furthermore, after the step of storing the spatial graphics and attribute information corresponding to the target disaster risk entity in the disaster risk entity storage model, it also includes: determining the coding domain according to different disaster application scenarios, and determining the coding rules according to the coding domain; performing attribute comparison on the disaster risk entity object to be coded according to the spatial graphic element rules and key attributes to obtain a comparison result; spatially aggregating the disaster risk entity object according to the comparison result, and calculating the spatial position of the aggregated entity object; determining the identity code of the entity object according to the coding rules and the spatial position.

[0085] It should be noted that the natural disaster risk entity space identity coding process diagram can be referred to Figure 6 Through identity coding, disaster risk spatiotemporal objects are labeled with unique identities to facilitate their later search. Spatiotemporal geographic location is a basic element in the spatiotemporal data of disaster risk factors, including static semantic attributes and implicit semantic attributes of spatiotemporal geographic location. The geographic spatial location occupied by various entities during the life cycle of a risk entity is unique. This spatiotemporal uniqueness allows us to assign a unique two-dimensional or three-dimensional spatial code to each entity based on a globally unified spatial reference foundation, as a carrier for describing the semantic feature relationship of the spatiotemporal location of the entity object. Therefore, the entity spatial identity code is like the identity card of the entity object, which can provide a spatial basis for association and graph-data linkage analysis for multi-hazard natural disaster risk entities, facilitate the unified management of natural disaster risk entities, and establish semantic associations.

[0086] It is understandable that the comparison results include two results: consistent and inconsistent. If consistent, it can be determined as a unique feature; if inconsistent, it can be determined as a non-unique feature, and spatial aggregation is performed based on the comparison results.

[0087] In specific implementation, the identity coding process of this scheme can be divided into the following steps: (1) Determine the coding rules: formulate a coding scheme and set the coding domain. The coding domain may include multiple domains such as the identification domain, standard domain, and extension domain. Among them, the identification domain and standard domain are relatively fixed, and the extension domain can be a variable-length code that can be determined according to different disaster application scenarios. ① The "identification domain" consists of a 2-bit root identifier code and a 4-bit risk entity dedicated code; ② The "standard domain" consists of a 26-bit (two-dimensional) or 44-bit (three-dimensional) location code, an 8-bit classification code, and a 4-bit sequence code to achieve unique identification of the risk entity; ③ The "extension domain" can be a variable-length code used for interactive association or recording risk entity related information. (2) Spatial aggregation of entity objects: For the entity objects to be coded, attribute comparison is performed according to spatial primitive rules and key attributes, such as single primitive rules, multi-primitive rules, geographic unique coding, feature coding, key names, etc. If they are consistent and can be determined as unique features, the primitives identified as the same entity will be spatially aggregated to achieve the uniqueness and attribute integrity of the entity object in the spatiotemporal dimension. (3) Calculation of entity spatial location: The entity spatial location code is divided into a two-dimensional grid location code and a three-dimensional grid location code. The spatial grid subdivision algorithm is used to calculate the two-dimensional spatial grid location code and the three-dimensional grid location code respectively. The three-dimensional grid location code also requires the addition of a high-level grid subdivision algorithm. Due to the layer-by-layer subdivision characteristics of the grid subdivision algorithm, entity units of various scales can be calculated as adaptive grid units under the grid subdivision algorithm, so that they can be accurately encoded. The spatial location code is a 26-bit mixed code of numbers and letters. (4) Acquisition of entity random sequence code: Combined with the processing power of the coding management engine, it ensures that all geographic entities within each grid unit have a unique sequence code, thereby achieving multi-granularity and global uniqueness in space. (5) Code segment combination: The results of obtaining the contents of each code segment specified in the coding rules are combined according to the coding order.

[0088] Furthermore, after the step of determining the identity code of the entity object according to the coding rules and the spatial position, it also includes: constructing an entity relationship storage model based on a preset relationship model, the disaster risk entity system and the identity code; extracting semantic relationship rules from a preset semantic relationship rule library based on the association scenarios between natural disaster risk entities; and generating a target relationship storage model based on the semantic relationship rules and the entity relationship storage model.

[0089] It should be noted that the technical process diagram of natural disaster risk entity association can be referred to Figure 7Calculation of natural disaster risk entity association relationships: Based on the theories and progress of disaster system theory and spatiotemporal semantics, we can analyze the semantic relationship algorithm model of multiple disaster types, form semantic relationship rule items, and build a semantic relationship rule base for multiple disaster types of natural disaster risks. Based on the association scenarios between natural disaster risk entities, semantic relationship rule items can be flexibly extracted from the semantic relationship rule base, thereby achieving rapid construction of entity semantic relationships based on the semantic rule base.

[0090] In the specific implementation, (1) an entity relationship storage model is established. Based on the pre-designed relationship model, a relationship storage model is established to store risk entities such as disaster-prone environment, disaster-causing factors, disaster-bearing bodies, historical disasters, and disaster units. A semantic relationship table is used to store the relationship content. For example, the "triplet" of the General Resource Description Framework (RDF) is used to describe the entity relationship and important attribute values ​​of natural disaster risk entities. The description rule is: "<entity ID, entity relationship, entity ID>", <entity ID, attribute name, attribute value> (Note: ID is the unique spatial identity code of the entity). (2) Calculation of semantic relationships of risk entities: Based on the association scenarios between natural disaster risk entities, semantic relationship rule items are flexibly extracted from the semantic relationship rule library, and spatial relationship calculation rules are embedded, including spatial topological relationships, spatial distance relationships, and spatial orientation relationships. Spatial topological relationships are subdivided into subcategories such as spanning, intersection, adjacent, connected, spatial inclusion, and spatial inclusion; spatial distance relationships are subdivided into spatial quantitative distance and spatial definition distance; spatial orientation relationships are subdivided into eight directions, sixteen directions, and upper and lower directions. (3) Storage of semantic relationships of risk entities: For example, the Neo4j graph database is used to store and manage the graph structure storage model of natural disaster risk entities. Natural disaster risk entities are stored using a node storage file and a relationship storage file of Neo4j. The node storage file is used to store two types of node information of natural disaster risk entities: object nodes are used to store object information such as disaster-prone environment, disaster-causing factors, disaster-bearing bodies, and disaster units, including object ID, spatial identity code, occurrence time, subject attributes, etc. Event nodes are used to store basic information of historical natural disaster events, including disaster event ID, disaster spatial coverage, disaster occurrence time, disaster type, basic information of attributes, etc.; relationship storage files are used to store edge information of natural disaster risk entities: spatial relationship edges, temporal relationship edges, state relationship edges, etc. Each type of edge has an edge storage ID, edge type, previous node ID, and next node ID. The node storage file and the relationship storage file are connected using a bidirectional linked list.

[0091] Furthermore, after the step of generating a target relationship storage model based on the semantic relationship rules and the entity relationship storage model, it also includes: constructing an initial spatiotemporal object model based on the target relationship storage model and the disaster risk entity storage model; inputting multi-source heterogeneous spatiotemporal datasets into the initial spatiotemporal object model for training to obtain a preset spatiotemporal object model.

[0092] It should be noted that the technical flow chart for constructing natural disaster risk entities can be found in Figure 8 Through entity modeling (model system design, object model design and relationship model design), multi-source heterogeneous data are integrated (reliability evaluation, spatiotemporal processing, information extraction and data cleaning, etc.), and entity construction is completed through object construction and entity matching. The constructed entities are entity coded and identified, and entity association (entity selection, relationship selection and relationship calculation, etc.) and relationship storage (risk entity quality evaluation and graph database relationship storage) are performed. Finally, the constructed data model is obtained to generate a natural disaster risk entity library for storing entity data. This solution completes the construction of the preset spatiotemporal object model through five parts: natural disaster risk spatiotemporal object modeling, multi-source heterogeneous data integration, natural disaster risk entity construction, natural disaster risk entity spatiotemporal identity coding and natural disaster risk entity association relationship calculation.

[0093] In the specific implementation, by studying the spatiotemporal object modeling technology of natural disaster risk, the spatiotemporal semantic expression of disaster-causing factors, disaster-prone environment, disaster-bearing body, historical disasters, disaster risk units, etc. is carried out with natural disaster risk entities as the center, the connotation correlation relationship of multi-hazard natural disaster risk entity objects is explored, and a spatiotemporal comprehensive relationship map of multiple disasters is constructed. The spatiotemporal evolution law of multi-hazard disaster risks is explored and deeply portrayed at multiple levels. It is suitable for both predictive disaster probability elements and large-scale modeling and representation of factual disaster-affected objects or scopes.

[0094] This embodiment completes the construction of a preset spatiotemporal object model in advance through five parts, namely, natural disaster risk spatiotemporal object modeling, multi-source heterogeneous data integration, natural disaster risk entity construction, natural disaster risk entity spatiotemporal identity coding, and natural disaster risk entity association relationship calculation, so as to obtain a multi-source heterogeneous disaster data set, perform data integration on the multi-source heterogeneous disaster data set, and obtain an integrated target data set; the target data set is stored in a preset disaster risk entity database according to the preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through the preset spatiotemporal object model, and the preset spatiotemporal object model is pre-set through the preset disaster risk entity system, disaster risk An entity data storage model is constructed based on the disaster risk entity construction rules and the spatiotemporal semantic relationship rules; disaster emergency information is queried and extracted based on the disaster risk entity database. The present invention classifies and identifies the multi-source heterogeneous disaster data and the data expressed out of the scene through the constructed entity data model. Compared with the existing technology, the disaster data is too discrete and cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, which in turn affects the efficiency of disaster emergency management. The present invention solves the integrated and chain-complex characteristics of natural disaster risk monitoring and early warning, and the multi-source heterogeneity and expression of disaster data out of the scene, so as to flexibly apply disaster entity data to various emergency scenarios.

[0095] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a disaster risk entity data storage program is stored. When the disaster risk entity data storage program is executed by a processor, the steps of the disaster risk entity data storage method described above are implemented.

[0096] Reference Figure 9 , Figure 9 This is a structural block diagram of the first embodiment of the disaster risk entity data storage device of the present invention.

[0097] like Figure 9 As shown, the disaster risk entity data storage device proposed in the embodiment of the present invention includes:

[0098] The data acquisition module 10 is used to acquire a multi-source heterogeneous disaster dataset, perform data integration on the multi-source heterogeneous disaster dataset, and obtain an integrated target data set;

[0099] A model processing module 20 is configured to store the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed using a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules;

[0100] The data query module 30 is further configured to query and extract disaster emergency information based on the disaster risk entity database.

[0101] This embodiment obtains a multi-source heterogeneous disaster data set, integrates the multi-source heterogeneous disaster data set, and obtains an integrated target data set; stores the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed through a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules; queries and extracts disaster emergency information based on the disaster risk entity database. The present invention classifies, identifies, and stores multi-source heterogeneous disaster data and data that are expressed out of context through the constructed entity data model. Compared with the prior art, disaster data is too discrete and cannot effectively support disaster prediction and emergency response services, resulting in low data utilization, which in turn affects the efficiency of disaster emergency management. The present invention solves the integrated and chain-complex characteristics of natural disaster risk monitoring and early warning, and the problems of multi-source heterogeneity and expression out of context of disaster data, so as to facilitate the flexible application of disaster entity data to various emergency scenarios.

[0102] Furthermore, the disaster risk entity data storage device also includes a model construction module, which is used to obtain historical multi-source heterogeneous disaster data sets, perform data preprocessing on the historical multi-source heterogeneous disaster data sets, and obtain a preprocessed data set; determine a preset disaster risk entity system based on the disaster system element theory and the disaster chain evolution law; and construct a disaster risk entity storage model based on the preset disaster risk entity system and the data set.

[0103] Furthermore, the model construction module is also used to identify potential disaster risk spatiotemporal objects within the preset disaster unit, and extract the disaster risk spatiotemporal objects to obtain extracted disaster risk spatiotemporal objects; determine disaster risk entity construction rules based on the structure of the disaster risk spatiotemporal objects, and the disaster risk entity construction rules include single-element rules and multi-element rules; determine a spatial operation model according to the disaster risk entity construction rules, and perform disaster risk entity matching on the disaster risk spatiotemporal objects according to the spatial operation model to obtain a target disaster risk entity; store the spatial graphics corresponding to the target disaster risk entity and its attribute information in the disaster risk entity storage model.

[0104] Furthermore, the model construction module is also used to determine the coding domain according to different disaster application scenarios, and determine the coding rules according to the coding domain; perform attribute comparison on the disaster risk entity objects to be coded according to spatial graphic element rules and key attributes to obtain comparison results; perform spatial aggregation on the disaster risk entity objects according to the comparison results, and calculate the spatial position of the aggregated entity objects; determine the identity code of the entity object according to the coding rules and the spatial position.

[0105] Furthermore, the model construction module is also used to construct an entity relationship storage model based on a preset relationship model, the disaster risk entity system and the identity code; extract semantic relationship rules from a preset semantic relationship rule library based on the association scenarios between natural disaster risk entities; and generate a target relationship storage model based on the semantic relationship rules and the entity relationship storage model.

[0106] Furthermore, the model construction module is also used to construct an initial spatiotemporal object model based on the target relationship storage model and the disaster risk entity storage model; input multi-source heterogeneous spatiotemporal data sets into the initial spatiotemporal object model for training to obtain a preset spatiotemporal object model.

[0107] Furthermore, the data acquisition module 10 is also used to obtain a multi-source heterogeneous spatiotemporal data set, classify the multi-source heterogeneous disaster data set according to a preset disaster risk entity system, and obtain a classified data set; perform data analysis on each data set, eliminate redundant data, and store the eliminated data according to the preset disaster risk entity system to obtain an integrated target data set.

[0108] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0109] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0110] In addition, for technical details not fully described in this embodiment, reference can be made to the disaster risk entity data storage method provided in any embodiment of the present invention, and will not be repeated here.

[0111] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0112] The serial numbers of the embodiments of the present invention are for descriptive purposes only and do not represent superiority or inferiority of the embodiments. In a unit claim that enumerates several means, several of these means may be embodied by the same item of hardware. The use of the terms first, second, and third, etc., does not denote any order; these terms should be interpreted as designations.

[0113] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0114] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for storing disaster risk entity data, characterized in that: The disaster risk entity data storage method comprises the following steps: Acquire a multi-source heterogeneous disaster dataset, and integrate the multi-source heterogeneous disaster dataset to obtain an integrated target data set; The target data set is stored in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed through a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules; querying and extracting disaster emergency information based on the disaster risk entity database; Before the step of storing the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, the method further includes: Acquire a historical multi-source heterogeneous disaster dataset, perform data preprocessing on the historical multi-source heterogeneous disaster dataset, and obtain a preprocessed data set; Determine the preset disaster risk entity system based on the disaster system element theory and the evolution law of disaster chains; Constructing a disaster risk entity storage model based on the preset disaster risk entity system and the data set; Identifying potential disaster risk spatiotemporal objects within a preset disaster unit, and extracting the disaster risk spatiotemporal objects to obtain extracted disaster risk spatiotemporal objects; Determining a disaster risk entity construction rule based on the structure of the disaster risk spatiotemporal object, wherein the disaster risk entity construction rule includes a single-element rule and a multi-element rule; Determining a spatial operation model according to the disaster risk entity construction rule, and performing disaster risk entity matching on the disaster risk spatiotemporal object according to the spatial operation model to obtain a target disaster risk entity; Storing the spatial graph and attribute information corresponding to the target disaster risk entity in the disaster risk entity storage model; Determine a coding domain according to different disaster application scenarios, and determine a coding rule according to the coding domain; Perform attribute comparison on the coded disaster risk entity objects according to spatial primitive rules and key attributes to obtain comparison results; spatially aggregating the disaster risk entity objects according to the comparison results, and calculating the spatial positions of the aggregated entity objects; The identity code of the entity object is determined according to the coding rule and the spatial position.

2. The disaster risk entity data storage method according to claim 1, characterized in that: After the step of determining the identity code of the entity object according to the coding rule and the spatial position, the method further includes: Constructing an entity relationship storage model based on a preset relationship model, the disaster risk entity system, and the identity code; Extracting semantic relationship rules from a preset semantic relationship rule library based on the association scenarios between natural disaster risk entities; A target relationship storage model is generated based on the semantic relationship rules and the entity relationship storage model.

3. The disaster risk entity data storage method according to claim 2, characterized in that: After the step of generating a target relationship storage model based on the semantic relationship rules and the entity relationship storage model, the method further includes: Constructing an initial spatiotemporal object model based on the target relationship storage model and the disaster risk entity storage model; The multi-source heterogeneous spatiotemporal datasets are input into the initial spatiotemporal object model for training to obtain the preset spatiotemporal object model.

4. The disaster risk entity data storage method according to any one of claims 1 to 3, characterized in that: The step of acquiring a multi-source heterogeneous disaster dataset, integrating the multi-source heterogeneous disaster dataset, and obtaining an integrated target data set includes: Acquire a multi-source heterogeneous spatiotemporal data set, classify the multi-source heterogeneous disaster data set according to a preset disaster risk entity system, and obtain a classified data set; Perform data analysis on each data set, eliminate redundant data, and store the eliminated data according to the preset disaster risk entity system to obtain the integrated target data set.

5. A disaster risk entity data storage device, characterized in that: The disaster risk entity data storage device includes: a memory, a processor, and a disaster risk entity data storage program stored in the memory and executable on the processor. When the disaster risk entity data storage program is executed by the processor, the disaster risk entity data storage method according to any one of claims 1 to 4 is implemented.

6. A storage medium, characterized in that The storage medium stores a disaster risk entity data storage program, which, when executed by a processor, implements the disaster risk entity data storage method according to any one of claims 1 to 4.

7. A disaster risk entity data storage device, characterized in that: The disaster risk entity data storage device includes: A data acquisition module is used to acquire a multi-source heterogeneous disaster data set, perform data integration on the multi-source heterogeneous disaster data set, and obtain an integrated target data set; a model processing module for storing the target data set in a preset disaster risk entity database according to preset disaster risk spatiotemporal objects, preset coding rules, and preset semantic relationships through a preset spatiotemporal object model, wherein the preset spatiotemporal object model is an entity data storage model pre-constructed using a preset disaster risk entity system, disaster risk entity construction rules, and spatiotemporal semantic relationship rules; The data query module is further used to query and extract disaster emergency information based on the disaster risk entity database; A model building module is used to obtain a historical multi-source heterogeneous disaster data set, perform data preprocessing on the historical multi-source heterogeneous disaster data set to obtain a preprocessed data set; determine a preset disaster risk entity system based on the disaster system element theory and the evolution law of the disaster chain; and construct a disaster risk entity storage model based on the preset disaster risk entity system and the data set; The model construction module is further used to identify potential disaster risk spatiotemporal objects within a preset disaster unit, and extract the disaster risk spatiotemporal objects to obtain the extracted disaster risk spatiotemporal objects; determine disaster risk entity construction rules based on the structure of the disaster risk spatiotemporal objects, and the disaster risk entity construction rules include single-element rules and multi-element rules; determine a spatial operation model according to the disaster risk entity construction rules, and perform disaster risk entity matching on the disaster risk spatiotemporal objects according to the spatial operation model to obtain a target disaster risk entity; and store the spatial graphics corresponding to the target disaster risk entity and its attribute information in the disaster risk entity storage model; The model construction module is also used to determine the coding domain according to different disaster application scenarios, and determine the coding rules according to the coding domain; perform attribute comparison on the disaster risk entity object to be coded according to the spatial graphic element rules and key attributes to obtain a comparison result; perform spatial aggregation on the disaster risk entity object according to the comparison result, and calculate the spatial position of the aggregated entity object; determine the identity code of the entity object according to the coding rules and the spatial position.

Images