Disaster task processing method based on physical sensors and social media observation capabilities

Abstract

The present invention provides a method for mining the observation capabilities of physical sensors and social media for disaster missions. It addresses the current situation in which traditional disaster perception research ignores the observation needs of social factors, lacks the construction of comprehensive disaster observation tasks, and the observation capabilities of physical sensors and social media. A technical process for mining the observation capabilities of physical sensors and social media for disaster observation tasks is formed to meet comprehensive disaster observation needs. Compared with existing sensor capability mining methods, this method can cover more observation factors of disaster phenomena, can effectively enhance the management of sensor observation capabilities for disaster observation tasks, provide sensor observation capabilities for observation tasks in different fields and at different granularities, and provide a basis for disaster sensor planning and selection and improving disaster observation plans. It has been proven that this method is a practical and reliable method that is conducive to increasing observable factors and enhancing sensor observation capabilities in disaster observation tasks.

Description

Technical Field

[0001] The present invention relates to the field of smart geographic information service technology, and in particular to a disaster task processing method based on physical sensors and social media observation capabilities. Background Art

[0002] Traditional disaster monitoring mainly focuses on physical factors in observation tasks, ignoring the need to observe social factors. When facing disaster observation tasks involving multiple factors, it is necessary to integrate the observation capabilities of physical sensors and social media to observe disasters comprehensively and efficiently.

[0003] Sensor observation capability, as a new geographic phenomenon, aims to characterize and describe the multidimensional spatiotemporal capabilities of sensors to evaluate their observation effectiveness. It is crucial attribute metadata that facilitates user understanding and use of sensors. However, physical sensors differ from social media in terms of their form, observation mechanism, and information representation, significantly hindering their mining. Therefore, to overcome these obstacles, it is necessary to comprehensively extract the observation capabilities of these sensors and represent them in a unified and standardized manner. Previous research has primarily focused on mining the observation capabilities of physical sensors, which has enabled effective management and discovery of physical sensors and achieved standardized representation and association of observation capabilities, providing greater online discovery, management, sharing, and interoperability for sensors. For example, based on SensorML defined by the Open Geospatial Consortium (OGC) Sensor Web Enablement (SWE) and ISO 19130, Fan et al. proposed a sensor capability representation model to describe sensor capabilities for soil moisture detection.

[0004] In recent years, social media has been increasingly used for disaster monitoring, expanding access to disaster information and enabling fine-grained monitoring of the social factors that influence disasters. For example, Zhang et al. proposed a topic analysis model framework for Twitter data that can identify the demand, supply, and distribution of disaster relief supplies. Using social media as social sensors to observe various types of information has garnered widespread attention. However, related research has not explored the observation capabilities of social media from a sensor perspective, leaving their own observation capabilities unclear. This hinders the rapid discovery and management of social sensors in disaster response scenarios. Therefore, a more comprehensive and systematic understanding of social media's observation capabilities is needed. Traditional physical sensors have relatively fixed observation elements and capabilities. In contrast, social media, through mining, can provide detailed observations of various social factors. Once their observation capabilities are determined, social media can complement physical sensors to achieve more comprehensive observation of disaster information. Therefore, an observation method is urgently needed to mine and integrate the observation capabilities of physical sensors and social media in disaster response scenarios.

[0005] Currently, the main problems faced in mining the observation capabilities of physical sensors and social media in disaster observation missions are:

[0006] (1) The current research under the traditional disaster observation task only meets the observation needs of physical factors, ignores the observation needs of social factors, and lacks a comprehensive observation task construction process that can realize the simultaneous observation of physical and social factors of disasters.

[0007] (2) Due to the unclear mechanism of social media observation capability mining, it can only meet the mining of physical sensor observation capabilities. It is necessary to form an overall process that can realize the mining of physical sensors and social media to meet the comprehensive disaster observation task requirements. Summary of the Invention

[0008] The main technical problem to be solved by the present invention is that the research under the traditional disaster observation task only meets the observation needs of physical factors, ignores the observation needs of social factors, and lacks a comprehensive observation task construction process that can realize the simultaneous observation of physical and social factors of disasters.

[0009] In order to solve this technical problem, the present invention proposes a disaster task processing method based on the observation capabilities of physical sensors and social media. According to the multi-field and multi-granularity observation task requirements of disasters, it can tap the observation capabilities of physical sensors and social media, and accurately extract and characterize the sensor's observation capability information on physical and social elements in disasters.

[0010] The technical solution adopted by the present invention is as follows: a disaster task processing method based on physical sensors and social media observation capabilities, specifically comprising the following steps:

[0011] Construct disaster observation missions and determine the temporal, spatial and thematic parameters of disaster observations;

[0012] The observation capabilities of physical sensors and social media are extracted based on spatiotemporal and topic parameters to obtain spatiotemporal observation capabilities and topic observation capabilities.

[0013] Standardize the representation of the extracted observation capabilities to form a unified description of observation capability information;

[0014] Build an observation capability library to query available sensors under disaster observation tasks.

[0015] Preferably, RDF triples are used to perform standardized representation on the extracted observation capabilities to form a unified description of the observation capability information.

[0016] Furthermore, the construction of the disaster observation task and determination of the temporal, spatial and thematic parameters of the disaster observation include:

[0017] Conduct observation demand analysis on the physical and social factors of disasters in the observation area;

[0018] Constructing multi-granularity disaster observation indicators with discrete and coupled features;

[0019] Convert observation requirements and observation indicators into observation tasks;

[0020] Determine the spatiotemporal and thematic parameters for hazard observations.

[0021] Furthermore, the observation capabilities of physical sensors and social media are extracted based on the spatiotemporal and topic parameters to obtain spatiotemporal observation capabilities and topic observation capabilities, including:

[0022] The ground coverage model is used to calculate the spatiotemporal coverage of the physical sensor, forming its spatiotemporal observation capability of the observation area;

[0023] The trained deep learning BERT model is used to build an extractor for disaster observation topics on social media, extracting the topic observation capabilities of social media.

[0024] Preferably, the standardized characterization of the extracted observation capabilities to form unified description of observation capability information includes:

[0025] Use the d2rq tool to convert different observation capabilities into RDF triple format structures;

[0026] Associate the RDF triples of observation capability information with the observation task to obtain the observation capability ontology pointing to the observation task;

[0027] Build a knowledge graph of observation capabilities and tasks to form standardized observation capability information of sensors.

[0028] Furthermore, the construction of the observation capability library and querying the available sensors under the disaster observation task include:

[0029] Build a sensor observation capability library for storage and query, and store standardized observation capability information;

[0030] According to the disaster observation task, the observation capability database is queried to obtain available sensors that meet the observation needs.

[0031] Preferably, a multi-dimensional sensor observation capability library is constructed by utilizing the relational database PostgreSQL and the non-relational database Neo4j to access the observation capability information of the sensor and support queries on the sensor observation capability by space, time, and observation subject.

[0032] In addition, the present invention also provides a disaster task processing device for implementing the method, comprising the following modules:

[0033] Observation mission construction module, used to construct disaster observation missions and determine the temporal, spatial and thematic parameters of disaster observations;

[0034] The observation capability extraction module is used to extract the observation capabilities of physical sensors and social media based on spatiotemporal and topic parameters, and obtain spatiotemporal observation capabilities and topic observation capabilities;

[0035] The observation capability characterization module is used to standardize the extracted observation capabilities and form a unified description of the observation capability information;

[0036] The available sensor query module is used to build an observation capability library and query the available sensors under the disaster observation task based on the observation capability library.

[0037] In addition, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the disaster task processing method based on physical sensors and social media observation capabilities are implemented.

[0038] Finally, the present invention also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the disaster task processing method based on physical sensors and social media observation capabilities.

[0039] The technical solution provided by the present invention has the following beneficial effects:

[0040] (1) Covering more observation elements of disaster phenomena. The method proposed in this paper can fully tap the observation capabilities of physical sensors and social media for disaster observation tasks, meet the observation task requirements of complex disasters, and significantly enhance the coverage of observable elements of disaster observation.

[0041] (2) Enhanced management of multi-source sensor observation capabilities for disaster mission observation. The process for mining physical sensor and social media observation capabilities constructed in this paper can adapt to different sensor observation capabilities and provide sensor observation tasks that meet observation requirements in different fields and at different granularities. This provides a basis for disaster sensor planning and selection, as well as improving disaster observation plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0043] Figure 1 It is an overall flow chart of a disaster task processing method based on physical sensors and social media observation capabilities of the present invention;

[0044] Figure 2 It is a flow chart of the disaster observation task construction of the present invention;

[0045] Figure 3 It is a flow chart of observation capability extraction of the present invention;

[0046] Figure 4 It is a flow chart of the characterization of the observation capability of the present invention;

[0047] Figure 5 This is a flow chart of the sensor query available in the present invention;

[0048] Figure 6 This is a graph of the spatiotemporal observation capabilities of the Sentinel2B satellite sensor of the present invention;

[0049] Figure 7 This is a graph of the spatiotemporal observation capabilities of the Superview1-02 satellite sensor of the present invention;

[0050] Figure 8 This is the spatiotemporal observation capability diagram of the Station_RWYN4 in-situ site of the present invention;

[0051] Figure 9 This is the spatiotemporal observation capability diagram of the Station_14737 in-situ site of the present invention;

[0052] Figure 10 This is a result graph of constructing the flood disaster observation capability knowledge graph of the present invention;

[0053] Figure 11 is a diagram showing the construction result of the observation capability library of the present invention;

[0054] Figure 12 It is a result diagram of available sensors under the flood disaster task of the present invention;

[0055] Figure 13 It is a schematic structural diagram of a physical sensor and social media observation capability mining device for disaster missions according to the present invention;

[0056] Figure 14 It is a structural schematic diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0057] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0058] Starting on the evening of September 1, 2021, the remnants of Hurricane Ida dumped up to 11 inches of rain across densely populated areas of the New York-Newark-Jersey City (NY-NJ-PA) metropolitan area, including New York and New Jersey. In just one hour, Central Park received over three inches of rain, setting a record for the region. This rainfall caused severe flooding. Compared to traditional physical sensors, densely populated areas offer richer social media resources that can be tapped into, enabling more comprehensive flooding observations. The New York metropolitan area spans latitude and longitude from 39°30′21″N to 42°10′48″N, and 71°51′23″W to 75°59′52″W. Flooding observations were conducted from 2021-09-01T19:00:00Z to 2021-09-02T09:00:00Z.

[0059] Therefore, we selected the New York metropolitan area as the experimental scenario for the scheme, observed flood disasters within the above time and space range, constructed a comprehensive observation task based on the flood observation needs, and explored the observation capabilities of physical sensors and social media. Finally, we obtained usable sensors for the flood observation task, providing scientific guidance for disaster monitoring of rainstorm waterlogging.

[0060] The following describes in detail the disaster observation method proposed by the present invention that couples physical sensors and social media observation capabilities in combination with the above application scenarios and the accompanying drawings. The overall process is shown in FIG. Figure 1 .

[0061] Step S1: Disaster observation mission construction

[0062] Construct disaster observation tasks and determine the time, space and subject parameters of disaster observation. The specific process is as follows: Figure 2 As shown:

[0063] S1-1: Analyze the observation needs of the physical and social factors of disasters in the observation area;

[0064] S1-2: Constructing multi-granularity disaster observation indicators with discrete and coupled features;

[0065] S1-3: Convert observation requirements and observation indicators into observation tasks with time, space and themes;

[0066] Specifically, an analysis of flood disaster needs in the New York metropolitan area was conducted, including the construction of physical and social elements to obtain discrete and coupled observation parameters, which were converted into executable and measurable observation tasks based on spatiotemporal information and observation needs. Three-process observation tasks were proposed, as shown in Table 1.

[0067] Table 1. Observation mission construction results

[0068]

[0069] S2: Observation Capability Extraction

[0070] The observation capabilities of physical sensors and social media are extracted according to the spatiotemporal and topic parameters to obtain spatiotemporal observation capabilities and topic observation capabilities. The specific process is as follows: Figure 3 As shown:

[0071] S2-1: Spatiotemporal Observation Capability Extraction

[0072] Based on the spatiotemporal and thematic information of the observation mission, the spatiotemporal observation capabilities of physical sensors (including satellites and ground stations) are extracted. The extraction results are shown in Table 2. The spatiotemporal observation coverage of a single satellite sensor is determined by simulating satellite orbital parameters and scanning the coverage of the satellite sensor. This process yields the spatiotemporal coverage strips for satellites such as Sentinel 2B and Superview1-02, as shown in the extraction results in Table 2. For in-situ sensors, the Boolean disk coverage model is a typical type of station model. For example, meteorological stations, hydrological stations, and soil and moisture monitoring stations use interpolated circular service ranges to represent the spatiotemporal observation range of a single station, as shown in the extraction results for Station_RWYN4 and Station_14737 in Table 2.

[0073] Table 2. Spatial and temporal observation capabilities of physical sensors (partial)

[0074]

[0075] S2-2: Subject Observation Capability Extraction

[0076] Based on the spatiotemporal and topical parameters of the observation task, we extracted the topical observation capabilities of social media, such as Twitter text and images. The extraction results are shown in Table 3. After labeling these social media tweets according to the parameters of social indicators, we trained a deep learning model on multiple topical parameters (for example, flood reports, negative emotions, and rescue) as a topic observation capability extractor. This allows us to analyze whether a social media post possesses the observation capabilities for that topic parameter.

[0077] Table 3. Thematic observation capabilities of Twitter social media (partial)

[0078]

[0079] S3: Observational Capability Characterization

[0080] The extracted observation capabilities are standardized and characterized to form a unified description of observation capability information. The specific process is as follows: Figure 4 As shown:

[0081] S3-1: RDF triple conversion

[0082] After extracting the temporal, spatial and thematic observation capabilities of the sensors, the d2rq tool is used to convert the observation capabilities stored in the relational database into RDF triple format. Taking the RDF triple structure of the satellite strip as an example, as shown in Table 4, it includes<spatiotemporalset_Geometry> 、<spatiotemporalset_Time> 、<DiscreteThematicset_Theme> 、<IntegratedThematicset_Theme> And other basic nodes.

[0083] Table 4. Satellite RDF triples

[0084]

[0085] S3-2: Relationship between Observation Tasks and Observation Capabilities

[0086] After being converted into an RDF triple structure, the represented observation capability knowledge is mapped to the indicator parameters, and the parameters of the subject observation capability are mapped one by one to the spatiotemporal and subject parameters of the observation task. The observation capability can be mapped to the requirements of the corresponding disaster observation task, realizing the association between flood disaster observation tasks and observation capabilities.

[0087] S3-3: Construction of Observation Capability Knowledge Graph

[0088] like Figure 10 As shown in the figure, this knowledge graph is constructed, where node 1 represents flood disasters, node 2 represents aggregated parameter nodes, and node 3 represents discrete parameter nodes. The aggregated parameter node (node ​​2) points to the disaster node (node ​​1), and the discrete parameter node (node ​​3) points to the aggregated parameter node (node ​​2). Node 4 represents the sensor ID, which points to the available observation parameter nodes. Nodes 5-8 represent the sensor's observation capabilities and point to the corresponding sensor ID (node ​​4). Discrete parameters at different levels can be associated with the sensor's observation capabilities to complete the coupled flood observation task.

[0089] S4: Available sensor query

[0090] Build an observation capability library and query the available sensors under the disaster observation task. The specific process is as follows: Figure 5 As shown:

[0091] S4-1: Construction of Observation Capability Library

[0092] like Figure 11As shown in Figure 1, the observation capability library is a composite database used to store and manage observation capabilities and provide indexed queries for sensor observation capabilities. It contains a rich set of data types, including regular observation capability information and various node relationships associated with observation indicators. By leveraging the relational database PostgreSQL and the non-relational database Neo4j, a multidimensional observation capability library is constructed to access sensor observation capability information and support queries based on space, time, and observation theme.

[0093] S4-2: Observation Capability Query

[0094] The available sensors for flood disaster tasks are queried in the space and time of the New York metropolitan area. Table 5 shows the available sensors for different observation tasks. Figure 12 As shown, Figure 12 This is the result diagram of the available sensors under the flood disaster task. According to the observation capabilities, each sensor has the observation capabilities in time, space and subject, can complete the discrete observation indicators in the test area, and can combine different types of sensors to reflect the corresponding aggregated indicators to meet certain aspects of observation, and finally generate available sensors for flood disaster observation.

[0095] Table 5. Results of available sensors

[0096]

[0097] The following describes a physical sensor and social media observation capability mining device for disaster missions provided by the present invention. The physical sensor and social media observation capability mining device described below and the physical sensor and social media observation capability mining method described above can be referenced to each other.

[0098] like Figure 13 As shown in FIG, a physical sensor and social media observation capability mining device for disaster missions includes the following modules:

[0099] Observation mission construction module 001 is used to construct the disaster observation mission and determine the temporal, spatial and thematic parameters of the disaster observation;

[0100] Observation capability extraction module 002 is used to extract observation capabilities of physical sensors and social media based on spatiotemporal and topic parameters, and obtain spatiotemporal observation capabilities and topic observation capabilities;

[0101] The observation capability characterization module 003 is used to perform standardized characterization on the extracted observation capabilities to form a unified description of the observation capability information;

[0102] The available sensor query module 004 is used to build an observation capability library and query available sensors under the disaster observation task based on the observation capability library.

[0103] Based on but not limited to the above-mentioned device, the observation task construction module 001 is specifically used to:

[0104] Conduct observation demand analysis on the physical and social factors of disasters in the observation area;

[0105] Constructing multi-granularity disaster observation indicators with discrete and coupled features;

[0106] Convert observation requirements and observation indicators into observation tasks;

[0107] Determine the spatiotemporal and thematic parameters for hazard observations.

[0108] Based on but not limited to the above device, the observation capability extraction module 002 is specifically used to:

[0109] The ground coverage model is used to calculate the spatiotemporal coverage of the physical sensor, forming its spatiotemporal observation capability of the observation area;

[0110] The trained deep learning BERT model is used to build an extractor for disaster observation topics on social media, extracting the topic observation capabilities of social media.

[0111] Based on but not limited to the above device, the observation capability characterization module 003 is specifically used to:

[0112] Use the d2rq tool to convert different observation capabilities into RDF triple format structures;

[0113] Associate the RDF triples of observation capability information with the observation task to obtain the observation capability ontology pointing to the observation task;

[0114] Build a knowledge graph of observation capabilities and tasks to form standardized observation capability information of sensors.

[0115] Based on but not limited to the above device, the available sensor query module 004 is specifically used to:

[0116] Build a sensor observation capability library for storage and query, and store standardized observation capability information;

[0117] According to the disaster observation task, the observation capability database is queried to obtain available sensors that meet the observation needs.

[0118] As a preferred implementation, a multidimensional sensor observation capability library is constructed by utilizing the relational database PostgreSQL and the non-relational database Neo4j to access the sensor's observation capability information and support queries on the sensor's observation capability by space, time, and observation theme.

[0119] like Figure 14 As shown, an example of a physical structure diagram of an electronic device may include: a processor (processor) 610, a communication interface (Communications Interface) 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 can call the logic instructions in the memory 630 to execute the steps of the above-mentioned disaster task processing method based on physical sensors and social media observation capabilities, which specifically include: constructing a disaster observation task and determining the spatiotemporal and thematic parameters of the disaster observation; extracting the observation capabilities of the physical sensors and social media respectively according to the spatiotemporal and thematic parameters to obtain spatiotemporal observation capabilities and thematic observation capabilities; standardizing the extracted observation capabilities to form observation capability information with a unified description; and constructing an observation capability library to query the available sensors under the disaster observation task.

[0120] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. 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 and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0121] On the other hand, an embodiment of the present invention also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned disaster task processing method based on physical sensors and social media observation capabilities, specifically including: constructing a disaster observation task, determining the spatiotemporal and thematic parameters of the disaster observation; extracting the observation capabilities of physical sensors and social media respectively according to the spatiotemporal and thematic parameters to obtain spatiotemporal observation capabilities and thematic observation capabilities; standardizing the extracted observation capabilities to form a unified description of observation capability information; constructing an observation capability library to query the available sensors under the disaster observation task.

[0122] 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.

[0123] 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 lists 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 and should be construed as identifiers.

[0124] 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 disaster task processing method based on physical sensors and social media observation capabilities, characterized by: The following steps are involved: S1: Construct disaster observation tasks and determine the temporal, spatial and thematic parameters of disaster observations; Specifically include: S1-1: Analyze the observation needs of the physical and social factors of disasters in the observation area; S1-2: Constructing multi-granularity disaster observation indicators with discrete and coupled features; S1-3: Convert observation requirements and observation indicators into observation tasks with time, space and themes; S2: Extract observation capabilities of physical sensors and social media based on spatiotemporal and topic parameters to obtain spatiotemporal observation capabilities and topic observation capabilities; Specifically include: S2-1: Extract the spatiotemporal observation capabilities of physical sensors based on the spatiotemporal and thematic information of the observation task; S2-2: Extract the topic observation capabilities of social media based on the spatiotemporal and topic parameters of the observation task; S3: Standardize the extracted observation capabilities to form a unified description of observation capability information; Specifically include: S3-1: Convert the observation capabilities stored in the relational database into RDF triple format; S3-2: Map the characterized observation capability knowledge to the indicator parameters, and map the parameters of the subject observation capability to the spatiotemporal and subject parameters of the observation task. The observation capability can be mapped to the requirements of the corresponding disaster observation task, thus realizing the association between the flood disaster observation task and the observation capability. S3-3: Constructing the knowledge graph of observation capabilities; S4: Build an observation capability database to query available sensors under disaster observation tasks; Specifically include: S4-1: Use the relational database PostgreSQL and the non-relational database Neo4j to build a multi-dimensional observation capability library to access sensor observation capability information and support queries on sensor observation capabilities by space, time, and observation theme; S4-2: According to the observation capabilities demonstrated, each sensor has the ability to observe in time, space and subject, can complete discrete observation indicators in the test area, and can combine different types of sensors to reflect the corresponding aggregated indicators to meet certain aspects of observation, and finally generate a usable sensor for flood disaster observation.

2. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 is characterized in that: The extracted observation capabilities are standardized and represented using RDF triples to form a unified description of observation capability information.

3. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 is characterized in that: The construction of the disaster observation task and determination of the temporal, spatial and thematic parameters of the disaster observation include: Conduct observation demand analysis on the physical and social factors of disasters in the observation area; Constructing multi-granularity disaster observation indicators with discrete and coupled features; Convert observation requirements and observation indicators into observation tasks; Determine the spatiotemporal and thematic parameters for hazard observations.

4. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 is characterized in that: The observation capabilities of physical sensors and social media are extracted based on spatiotemporal and topic parameters to obtain spatiotemporal observation capabilities and topic observation capabilities, including: The ground coverage model is used to calculate the spatiotemporal coverage of the physical sensor, forming its spatiotemporal observation capability of the observation area; The trained deep learning BERT model is used to build an extractor for disaster observation topics on social media, extracting the topic observation capabilities of social media.

5. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 or 2 is characterized in that: The standardized characterization of the extracted observation capabilities to form unified description of observation capability information includes: Use the d2rq tool to convert different observation capabilities into RDF triple format structures; Associate the RDF triples of observation capability information with the observation task to obtain the observation capability ontology pointing to the observation task; Build a knowledge graph of observation capabilities and tasks to form standardized observation capability information of sensors.

6. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 is characterized in that: The construction of the observation capability library and querying the available sensors under the disaster observation task include: Build a sensor observation capability library for storage and query, and store standard observation capability information; According to the disaster observation task, the observation capability database is queried to obtain available sensors that meet the observation needs.

7. The disaster task processing method based on physical sensors and social media observation capabilities according to claim 1 or 6, characterized in that: By using the relational database PostgreSQL and the non-relational database Neo4j to build a multi-dimensional sensor observation capability library, we can access the sensor's observation capability information and support queries on sensor observation capabilities based on space, time, and observation themes.

8. A disaster task processing device for implementing the method according to any one of claims 1 to 7, characterized in that: Includes the following modules: Observation mission construction module, used to construct disaster observation missions and determine the temporal, spatial and thematic parameters of disaster observations; The observation capability extraction module is used to extract the observation capabilities of physical sensors and social media based on spatiotemporal and topic parameters, and obtain spatiotemporal observation capabilities and topic observation capabilities; The observation capability characterization module is used to standardize the extracted observation capabilities and form a unified description of the observation capability information; The available sensor query module is used to build an observation capability library and query the available sensors under the disaster observation task based on the observation capability library.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the disaster task processing method based on physical sensors and social media observation capabilities as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the disaster task processing method based on physical sensors and social media observation capabilities are implemented as described in any one of claims 1 to 7.

Images