Water disaster early warning data processing method and device, computer device and storage medium

Abstract

The present disclosure provides a water disaster early warning data processing method and device, computer equipment and a storage medium. The method comprises: obtaining water disaster early warning data, wherein the water disaster early warning data comprises dynamic early warning data and static early warning data; determining the space-time coordinates of the dynamic early warning data and the static early warning data, and the target characteristic values corresponding to the space-time coordinates; and optimizing a preset water disaster early warning model according to the space-time coordinates and the target characteristic values to obtain a target water disaster early warning model, wherein the target water disaster early warning model is used to generate water disaster early warning information. Through the implementation of the method of the present disclosure, the dynamic early warning data and the static early warning data can be effectively combined in the water disaster early warning process, thereby greatly improving the early warning accuracy of the obtained target water disaster early warning model.

Description

Technical Field

[0001] This disclosure relates to the field of mine water hazard prevention and control technology, specifically to a water hazard early warning data processing method, device, computer equipment, and storage medium. Background Technology

[0002] Coal mine water hazard early warning is mainly based on hydrological parameter monitoring data combined with water inrush mechanism and relevant regulations and standards. Mathematical statistics and weight analysis methods are used to propose water hazard risk early warning indicators, criteria and standards, and then predict and forecast water inrush risk. Alternatively, based on geophysical data and hydrological parameter data, machine learning is used to train and test the above data to establish an intelligent early warning model and quantitatively calculate borehole water output to determine water inrush risk.

[0003] In related technologies, the processing effect of flood hazard early warning data is not good, which affects the accuracy of flood hazard early warning. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the purpose of this disclosure is to propose a method, device, computer equipment, and storage medium for processing flood hazard early warning data, which can effectively combine dynamic and static early warning data in the process of flood hazard early warning, so as to greatly improve the early warning accuracy of the obtained target flood hazard early warning model.

[0006] The flood hazard early warning data processing method proposed in the first aspect of this disclosure includes: acquiring flood hazard early warning data, wherein the flood hazard early warning data includes: dynamic early warning data and static early warning data; determining the spatiotemporal coordinates of the dynamic early warning data and the static early warning data, and the target feature value corresponding to the spatiotemporal coordinates; optimizing a preset flood hazard early warning model according to the spatiotemporal coordinates and the target feature value to obtain a target flood hazard early warning model, wherein the target flood hazard early warning model is used to generate flood hazard early warning information.

[0007] The flood hazard early warning data processing method proposed in the first aspect of this disclosure acquires flood hazard early warning data, which includes dynamic early warning data and static early warning data. It determines the spatiotemporal coordinates of the dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates. Based on the spatiotemporal coordinates and target feature values, it optimizes a preset flood hazard early warning model to obtain a target flood hazard early warning model. This target flood hazard early warning model is used to generate flood hazard early warning information. Therefore, it can effectively combine dynamic and static early warning data during the flood hazard early warning process, thereby significantly improving the early warning accuracy of the obtained target flood hazard early warning model.

[0008] The flood hazard early warning data processing apparatus proposed in the second aspect of this disclosure includes: an acquisition module for acquiring flood hazard early warning data, wherein the flood hazard early warning data includes dynamic early warning data and static early warning data; a determination module for determining the spatiotemporal coordinates of the dynamic early warning data and the static early warning data, and the target feature value corresponding to the spatiotemporal coordinates; and a processing module for optimizing a preset flood hazard early warning model according to the spatiotemporal coordinates and the target feature value to obtain a target flood hazard early warning model, wherein the target flood hazard early warning model is used to generate flood hazard early warning information.

[0009] The flood hazard early warning data processing device proposed in the second aspect of this disclosure acquires flood hazard early warning data, which includes dynamic early warning data and static early warning data. It determines the spatiotemporal coordinates of the dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates. Based on the spatiotemporal coordinates and target feature values, it optimizes a preset flood hazard early warning model to obtain a target flood hazard early warning model. The target flood hazard early warning model is used to generate flood hazard early warning information. Thus, it can effectively combine dynamic and static early warning data in the flood hazard early warning process to greatly improve the early warning accuracy of the obtained target flood hazard early warning model.

[0010] The computer device proposed in the third aspect of this disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the flood hazard early warning data processing method proposed in the first aspect of this disclosure.

[0011] The fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the flood hazard early warning data processing method as proposed in the first aspect of this disclosure.

[0012] The fifth aspect of this disclosure provides a computer program product that, when executed by a processor, performs the flood hazard early warning data processing method as proposed in the first aspect of this disclosure.

[0013] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0014] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0015] Figure 1 This is a schematic flowchart of a water hazard early warning data processing method proposed in an embodiment of this disclosure;

[0016] Figure 2 This is a flowchart illustrating a water hazard early warning data processing method according to another embodiment of this disclosure;

[0017] Figure 3 This is a schematic diagram of the structure of a flood early warning model proposed in an embodiment of this disclosure;

[0018] Figure 4 This is a schematic diagram of a flood hazard early warning data processing flow proposed in an embodiment of this disclosure;

[0019] Figure 5 This is a schematic diagram of the structure of a flood hazard early warning data processing device according to an embodiment of this disclosure;

[0020] Figure 6 This is a schematic diagram of the structure of a flood hazard early warning data processing device according to another embodiment of this disclosure;

[0021] Figure 7 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0022] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0023] Figure 1 This is a flowchart illustrating a water hazard early warning data processing method proposed in an embodiment of this disclosure.

[0024] It should be noted that the execution subject of the flood hazard early warning data processing method in this embodiment is a flood hazard early warning data processing device. This device can be implemented by software and / or hardware. The device can be configured in a computer device, which may include, but is not limited to, a terminal, a server, etc. For example, the terminal may be a mobile phone, a PDA, etc.

[0025] like Figure 1 As shown, the flood hazard early warning data processing method includes:

[0026] S101: Obtain flood hazard early warning data, which includes dynamic early warning data and static early warning data.

[0027] Among them, flood hazard early warning data refers to data used for flood hazard early warning. For example, it can be hydrological parameter monitoring data, microseismic monitoring data, resistivity monitoring data, etc., without any restrictions.

[0028] Dynamic early warning data refers to flood hazard early warning data that changes over time. Examples include microseismic event data, water temperature, and stress.

[0029] Static early warning data refers to data that does not change over time within the flood warning period. Examples include apparent resistivity and electric field strength.

[0030] In this embodiment of the disclosure, when acquiring flood warning data, it can be based on a pre-configured data table that records corresponding dynamic and static warning data, or it can be based on a third-party data acquisition device, without any limitation.

[0031] In other words, in this embodiment of the disclosure, dynamic early warning data and static early warning data can be obtained together as flood hazard early warning data to achieve effective combination of multi-dimensional early warning data and provide reliable data support for the subsequent generation of target flood hazard early warning models.

[0032] S102: Determine the spatiotemporal coordinates of dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates.

[0033] Spatiotemporal coordinates refer to the coordinates of dynamic and static early warning data in the spatial and temporal dimensions. Target feature values ​​refer to the feature values ​​of dynamic and static early warning data corresponding to their spatiotemporal coordinates.

[0034] It is understandable that there may be a large amount of dynamic and static early warning data. When the spatiotemporal coordinates of the dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates, are determined, the dynamic and static early warning data can be effectively integrated based on the spatiotemporal coordinates. This can effectively improve the systematic nature of the dynamic and static early warning data, so as to facilitate the subsequent optimization of the preset flood hazard early warning model.

[0035] S103: Optimize the preset flood hazard early warning model based on the spatiotemporal coordinates and target feature values ​​to obtain the target flood hazard early warning model, which is used to generate flood hazard early warning information.

[0036] Among them, a flood hazard early warning model refers to a machine learning model configured for flood hazard early warning data, which can be used to process flood hazard early warning data to issue flood hazard warnings. A preset flood hazard early warning model, on the other hand, refers to a pre-configured, untrained flood hazard early warning model.

[0037] Among them, the target flood warning model refers to the flood warning model obtained after optimizing the preset flood warning model.

[0038] In this embodiment, flood hazard early warning data is acquired, including dynamic and static early warning data. The spatiotemporal coordinates of the dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates, are determined. Based on the spatiotemporal coordinates and target feature values, a preset flood hazard early warning model is optimized to obtain a target flood hazard early warning model. The target flood hazard early warning model is used to generate flood hazard early warning information. Thus, dynamic and static early warning data can be effectively combined during the flood hazard early warning process to greatly improve the early warning accuracy of the obtained target flood hazard early warning model.

[0039] Figure 2 This is a flowchart illustrating a water hazard early warning data processing method proposed in another embodiment of this disclosure.

[0040] like Figure 2 As shown, the flood hazard early warning data processing method includes:

[0041] S201: Determine the information required for flood hazard early warning.

[0042] Among them, the information required for flood warning can refer to the types and quantities of flood warning data that need to be accessed during the flood warning process, and there are no restrictions on this.

[0043] It is understandable that the demand for flood warning data may vary in different application scenarios. Determining the required information for flood warning can provide a reliable basis for subsequent acquisition of flood warning data.

[0044] For example, in this embodiment of the disclosure, the types of water hazard early warning data that need to be accessed at the coal mine working face can be determined, including but not limited to geological data, geophysical exploration data, geophysical monitoring data, and hydrological parameter monitoring data. The data is divided into two categories: dynamic real-time monitoring data containing time coordinates and static exploration data not containing time coordinates.

[0045] S202: Obtain flood warning data based on the flood warning requirements.

[0046] For example, the features extracted from flood warning data are shown in Table 1 below. The features are extracted and stored according to the data format in Table 1. In addition to the extracted features contained in Table 1, the dynamic real-time data also includes the i-th order rate of change of the corresponding extracted features. i is a positive integer from 1 to 3 according to actual needs.

[0047] Table 1

[0048]

[0049]

[0050] It is understood that each element in Table 1 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 1. Therefore, those skilled in the art will understand that the value of each element in Table 1 is an independent embodiment.

[0051] In other words, in this embodiment of the disclosure, the demand information for flood warning can be determined, and flood warning data can be obtained based on the demand information for flood warning. Thus, the adaptability between the obtained flood warning data and personalized application scenarios can be guaranteed, thereby effectively improving the practicality of flood warning data.

[0052] S203: Determine at least one spatial coordinate.

[0053] Spatial coordinates refer to the spatial coordinates of flood hazard early warning data in the application scenario.

[0054] It is understandable that dynamic early warning data and static early warning data describe the same application scenario, and therefore, they can contain the same spatial coordinates.

[0055] S204: Determine at least one time coordinate corresponding to the dynamic early warning data and spatial coordinates.

[0056] The time coordinate refers to the coordinates of the dynamic early warning data in the time dimension.

[0057] It is understandable that dynamic early warning data records early warning data over a period of time. Therefore, dynamic early warning data may correspond to multiple time coordinate thresholds for a single spatial coordinate.

[0058] In this embodiment of the disclosure, when at least one time coordinate corresponding to the dynamic early warning data and the spatial coordinates is determined, reliable reference information can be provided for subsequently obtaining the first normalized value corresponding to the dynamic early warning data.

[0059] S205: Based on the time coordinate, obtain the first normalized value corresponding to the dynamic early warning data.

[0060] Normalization is a dimensionless processing method that transforms the absolute values ​​of physical system values ​​into relative values, such as converting data into decimals between (0,1) and (-1,1). The normalized value refers to the value obtained by normalizing flood warning data. The first normalized value refers to the normalized value obtained by processing dynamic warning data.

[0061] For example, according to Table 2, time coordinates and spatial coordinates are matched, normalized, and vectorized. t represents time, m represents the number of dynamic real-time data time series, (X,Y,Z) represents the spatial coordinates of the data acquisition measurement points, M represents the feature extraction dimension (i.e., the number of data acquisition feature types), M' represents the number of static data extracted features, N represents the number of data acquisition measurement points, var represents the normalized feature values ​​extracted by various data acquisition methods, VAR represents the normalized value of the data label, and represents the water outflow event. The normalization method uses Z-score standardization. For microseismic monitoring trigger-type data, referring to the one-hot data encoding method, time points where no microseismic event occurred are encoded as 0. For time points where a microseismic event occurred, Z-score standardization is used for normalization according to the event energy magnitude.

[0062] Table 2

[0063]

[0064]

[0065] It is understood that each element in Table 2 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 2. Therefore, those skilled in the art will understand that the value of each element in Table 2 is an independent embodiment.

[0066] Optionally, in some embodiments, when obtaining the first normalized value corresponding to the dynamic early warning data based on the time coordinate, the normalization value range can be determined, the forward time step corresponding to the time coordinate can be determined, multiple first feature values ​​corresponding to the forward time step can be determined based on the dynamic early warning data, the first feature values ​​can be transformed according to the normalization value range to obtain candidate normalized values, and multiple candidate normalized values ​​can be used together as the first normalized value. In this way, the vectorization processing of the dynamic early warning data can be realized, thereby enriching the indication effect of the obtained first normalized value and effectively improving the practicality of the obtained first normalized value.

[0067] The normalized value range refers to the range of values ​​of the normalized values ​​obtained after normalizing the flood warning data. For example, it can be (0,1) or (-1,1), and there is no restriction on it.

[0068] The forward time step refers to the length of time taken forward from the aforementioned time coordinates.

[0069] Here, the first eigenvalue refers to multiple eigenvalues ​​of the dynamic early warning data within the aforementioned forward time step. The candidate normalized value refers to the normalized value obtained by normalizing the first eigenvalue.

[0070] For example, for the vectorization of any spatial coordinate point in the dynamic real-time data of coal mine water hazard early warning, the original normalized data table can be vectorized as a dataset according to Table 2 for dataset partitioning, or the data features within a certain time series range before any time coordinate can be vectorized and reconstructed to form a new dataset for data partitioning, as shown in Table 3, where k is the forward time step and is a positive integer.

[0071] Table 3

[0072]

[0073] It is understood that each element in Table 3 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 3. Therefore, those skilled in the art will understand that the value of each element in Table 3 is an independent embodiment.

[0074] S206: Obtain the second normalized value corresponding to the static early warning data based on the spatial coordinates.

[0075] The second normalized value refers to the normalized value of the static early warning data at the aforementioned spatial coordinate points.

[0076] Optionally, in some embodiments, when obtaining the second normalized value corresponding to the static early warning data based on the spatial coordinates, the second feature value corresponding to the spatial coordinates can be determined based on the static early warning data, and the second feature value can be transformed according to the normalization value range to obtain the second normalized value. This can effectively improve the reliability of the process of obtaining the second normalized value.

[0077] S207: Use the first normalized value and the second normalized value together as the target feature value.

[0078] In other words, in this embodiment of the present disclosure, after acquiring flood warning data, at least one spatial coordinate can be determined, and at least one time coordinate corresponding to the dynamic warning data and the spatial coordinate can be determined. Based on the time coordinate, a first normalized value corresponding to the dynamic warning data is obtained, and based on the spatial coordinate, a second normalized value corresponding to the static warning data is obtained. The first normalized value and the second normalized value are used together as the target feature value. Thus, the normalized value can be obtained by combining the different characteristics of the dynamic warning data and the static warning data and adopting corresponding data processing methods, so as to effectively improve the rationality of the data processing process.

[0079] S208: Determine the reference early warning information corresponding to the flood warning data.

[0080] Among them, reference early warning information refers to early warning information obtained in advance based on the aforementioned flood warning data.

[0081] It is understandable that during the model training process, the warning information output by the preset flood warning model may differ from the actual flood situation. In this embodiment of the disclosure, when the reference warning information corresponding to the flood warning data is determined, it can provide reliable reference information for subsequent optimization of the preset flood warning model.

[0082] S209: Based on the preset flood hazard early warning model, process the first normalized value and the second normalized value to obtain simulated early warning information.

[0083] Among them, simulated early warning information refers to the early warning information obtained by processing the first normalized value and the second normalized value using a preset flood hazard early warning model.

[0084] Optionally, in some embodiments, the preset flood warning model includes a dynamic data processing unit and a fusion data processing unit. When processing the first normalized value and the second normalized value based on the preset flood warning model to obtain simulated warning information, the first normalized value can be processed by the dynamic data processing unit to obtain data to be fused. The data to be fused and the second normalized value are then fused to obtain fused data. The fusion data processing unit processes the fused data to obtain simulated warning information. This can effectively improve the rationality of the preset flood warning model in processing the first normalized value and the second normalized value, thereby achieving deep fusion of dynamic warning data and static warning data.

[0085] The dynamic data processing unit refers to the data processing unit in the preset flood hazard early warning model used to process the first normalized value corresponding to the dynamic early warning data. The fusion data processing unit refers to the processing unit used to process the fused data.

[0086] The data to be fused refers to the data obtained by processing the first normalized value through the dynamic data processing unit, which can be fused with the second normalized value to obtain fused data.

[0087] For example, such as Figure 3 As shown, Figure 3This is a schematic diagram of the structure of a flood warning model proposed in this embodiment. In the diagram, x is the dynamic real-time data input, Unit represents the flood warning unit corresponding to time t, specifically an LSTM or GRU computing unit, h is the LSTM or GRU network output, x' is the static data input, h and x' are connected to form a new matrix and fused as the new DNN network input X', D is the fully connected layer computing node, the number of fully connected layers is 1 to 3, p is the number of fully connected layer nodes, H is the prediction warning output, and q is the number of output values ​​or the number of categories.

[0088] S210: Determine the comparison results between the reference warning information and the simulated warning information.

[0089] The comparison result refers to the result obtained by comparing the reference early warning information and the simulated early warning information. For example, it could be the difference between the water discharge indicated by the two.

[0090] S211: Based on the comparison results, optimize the preset flood hazard early warning model to obtain the target flood hazard early warning model.

[0091] In other words, in this embodiment of the present disclosure, after using the first normalized value and the second normalized value together as the target feature value, reference early warning information corresponding to the flood warning data can be determined. The first normalized value and the second normalized value are processed based on the preset flood warning model to obtain simulated early warning information. The comparison result between the reference early warning information and the simulated early warning information is determined. The preset flood warning model is optimized based on the comparison result to obtain the target flood warning model. Thus, reliable reference information can be provided for the optimization process of the preset flood warning model based on the comparison result between the reference early warning information and the simulated early warning information, thereby effectively improving the reliability of the obtained target flood warning model.

[0092] For example, in this embodiment of the disclosure, the training set, test set, and validation set of the multi-source data for flood hazard early warning can be divided in a ratio of 8:1:1. The GRU-DNN model described above is then trained. The Adam optimization algorithm is used to update the weight gradients, and the classification cross-entropy loss function is used to optimize and update the network parameters to obtain the prediction model. The accuracy performance of the trained flood hazard early warning model on the training set and validation set is observed, and a reflection graph of the relationship between accuracy and the number of training samples is generated. The model parameters are then changed, and the model is retrained until the model has similar accuracy on the training set and validation set and has good generalization ability.

[0093] In this embodiment, by determining the flood warning demand information and obtaining flood warning data based on it, the adaptability of the obtained flood warning data to personalized application scenarios can be guaranteed, thereby effectively improving the practicality of the flood warning data. By determining at least one spatial coordinate, at least one time coordinate corresponding to the dynamic warning data and the spatial coordinate is determined. Based on the time coordinate, a first normalized value corresponding to the dynamic warning data is obtained, and based on the spatial coordinate, a second normalized value corresponding to the static warning data is obtained. The first and second normalized values ​​are used together as the target feature value. Therefore, by combining the different characteristics of dynamic and static warning data, corresponding data processing methods can be adopted to obtain normalized values, effectively improving the rationality of the data processing process. By identifying reference early warning information corresponding to flood hazard warning data, and processing the first and second normalized values ​​based on a preset flood hazard warning model, simulated early warning information is obtained. The comparison result between the reference and simulated early warning information is determined, and the preset flood hazard warning model is optimized based on the comparison result to obtain the target flood hazard warning model. Thus, the comparison result between the reference and simulated early warning information provides reliable reference information for the optimization process of the preset flood hazard warning model, effectively improving the reliability of the obtained target flood hazard warning model. By determining the normalization value range and the forward time step corresponding to the time coordinate, multiple first feature values ​​corresponding to the forward time step are determined based on dynamic early warning data. The first feature values ​​are transformed according to the normalization value range to obtain candidate normalized values. Multiple candidate normalized values ​​are used together as the first normalized value. This enables vectorized processing of dynamic early warning data, enriching the indicative effect of the obtained first normalized value and effectively improving its practicality. By determining the second eigenvalue corresponding to spatial coordinates based on static early warning data, and transforming the second eigenvalue according to the normalization range, a second normalized value is obtained. This effectively improves the reliability of obtaining the second normalized value. The first normalized value is processed by a dynamic data processing unit to obtain data to be fused. The data to be fused and the second normalized value are then fused to obtain fused data. The fused data is then processed by a fusion data processing unit to obtain simulated early warning information. This effectively improves the rationality of the preset flood hazard early warning model in processing the first and second normalized values, thereby achieving deep fusion of dynamic and static early warning data.

[0094] For example, such as Figure 4 As shown, Figure 4 This is a schematic diagram of a flood hazard early warning data processing flow proposed in an embodiment of this disclosure, which includes:

[0095] (1) Classify and extract features from water hazard early warning data obtained from designated mining faces;

[0096] (2) Match and normalize the time and spatial coordinates of the multi-source data for flood warning;

[0097] (3) Vectorize the multi-source data for flood disaster early warning;

[0098] (4) Design the network structure of the intelligent early warning model for water hazards based on multi-source data fusion;

[0099] (5) Training, testing and verification of the multi-source data fusion water hazard early warning model;

[0100] (6) Save the training completed model parameters, input new multi-source water hazard data into the early warning model, and output the water hazard accident risk level.

[0101] Figure 5 This is a schematic diagram of the structure of a flood hazard early warning data processing device according to an embodiment of this disclosure.

[0102] like Figure 5 As shown, the flood hazard early warning data processing device 50 includes:

[0103] The acquisition module 501 is used to acquire flood hazard early warning data, which includes dynamic early warning data and static early warning data.

[0104] The determination module 502 is used to determine the spatiotemporal coordinates of dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates;

[0105] The processing module 503 is used to optimize the preset flood hazard early warning model based on the spatiotemporal coordinates and target feature values ​​to obtain the target flood hazard early warning model, wherein the target flood hazard early warning model is used to generate flood hazard early warning information.

[0106] In some embodiments of this disclosure, such as Figure 6 As shown, Figure 6 This is a schematic diagram of the structure of a flood disaster early warning data processing device according to another embodiment of this disclosure. The acquisition module 501 includes:

[0107] The first determining submodule 5011 is used to determine the water hazard early warning demand information;

[0108] The first acquisition submodule 5012 is used to acquire flood warning data based on the flood warning requirement information.

[0109] In some embodiments of this disclosure, the determining module 502 includes:

[0110] The second determining submodule 5021 is used to determine at least one spatial coordinate;

[0111] The third determining submodule 5022 is used to determine at least one time coordinate corresponding to the dynamic early warning data and spatial coordinates;

[0112] The second acquisition submodule 5023 is used to acquire the first normalized value corresponding to the dynamic early warning data based on the time coordinate;

[0113] The third acquisition submodule 5024 is used to acquire the second normalized value corresponding to the static early warning data based on the spatial coordinates;

[0114] The fourth determination submodule 5025 is used to take the first normalized value and the second normalized value together as the target feature value.

[0115] In some embodiments of this disclosure, the second acquisition submodule 5023 is specifically used for:

[0116] Determine the range of normalized values;

[0117] Determine the forward time step corresponding to the time coordinate;

[0118] Based on dynamic early warning data, determine multiple first feature values ​​corresponding to the forward time step;

[0119] The first eigenvalue is transformed according to the normalization range to obtain candidate normalized values;

[0120] Multiple candidate normalized values ​​are used together as the first normalized value.

[0121] In some embodiments of this disclosure, the third acquisition submodule 5024 is specifically used for:

[0122] Based on static early warning data, determine the second characteristic value corresponding to the spatial coordinates;

[0123] The second eigenvalue is transformed according to the normalization range to obtain the second normalized value.

[0124] In some embodiments of this disclosure, the processing module 503 includes:

[0125] The fifth determination submodule 5031 is used to determine the reference early warning information corresponding to the flood warning data;

[0126] The first processing submodule 5032 is used to process the first normalized value and the second normalized value based on the preset flood warning model to obtain simulated warning information;

[0127] The sixth determination submodule 5033 is used to determine the comparison result between the reference early warning information and the simulated early warning information;

[0128] The second processing submodule 5034 is used to optimize the preset flood hazard early warning model based on the comparison results to obtain the target flood hazard early warning model.

[0129] In some embodiments of this disclosure, the preset flood warning model includes: a dynamic data processing unit and a fusion data processing unit;

[0130] The first processing submodule 5032 is specifically used for:

[0131] The first normalized value is processed by the dynamic data processing unit to obtain the data to be fused.

[0132] The data to be fused and the second normalized value are fused to obtain the fused data;

[0133] The fused data is processed by the fused data processing unit to obtain simulated early warning information.

[0134] It should be noted that the foregoing explanation of the flood hazard early warning data processing method also applies to the flood hazard early warning data processing device of this embodiment, and will not be repeated here.

[0135] In this embodiment, flood hazard early warning data is acquired, including dynamic and static early warning data. The spatiotemporal coordinates of the dynamic and static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates, are determined. Based on the spatiotemporal coordinates and target feature values, a preset flood hazard early warning model is optimized to obtain a target flood hazard early warning model. The target flood hazard early warning model is used to generate flood hazard early warning information. Thus, dynamic and static early warning data can be effectively combined during the flood hazard early warning process to greatly improve the early warning accuracy of the obtained target flood hazard early warning model.

[0136] Figure 7 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 7 The computer device 12 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0137] like Figure 7 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0138] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0139] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0140] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 7 Not shown; usually referred to as a "hard drive".

[0141] although Figure 7 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0142] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0143] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable human interaction with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0144] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the flood warning data processing method mentioned in the foregoing embodiments.

[0145] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the flood hazard early warning data processing method proposed in the foregoing embodiments of this disclosure.

[0146] To implement the above embodiments, this disclosure also proposes a computer program product that, when the instruction processor in the computer program product is executed, performs the flood hazard early warning data processing method proposed in the foregoing embodiments of this disclosure.

[0147] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0148] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0149] It should be noted that in the description of this disclosure, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0150] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0151] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0152] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0153] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0154] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0155] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0156] Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for processing flood hazard early warning data, characterized in that, include: Acquire flood hazard early warning data, wherein the flood hazard early warning data includes: dynamic early warning data and static early warning data; Determine at least one spatial coordinate; Determine at least one time coordinate corresponding to the dynamic early warning data and the spatial coordinates; Based on the time coordinates, obtain the first normalized value corresponding to the dynamic early warning data; Based on the spatial coordinates, obtain the second normalized value corresponding to the static early warning data; The first normalized value and the second normalized value are used together as the target feature value; The preset flood hazard early warning model is optimized based on the spatiotemporal coordinates and the target feature values ​​to obtain the target flood hazard early warning model, wherein the target flood hazard early warning model is used to generate flood hazard early warning information.

2. The method as described in claim 1, characterized in that, The acquisition of flood hazard early warning data includes: Determine the information required for flood warning; Based on the aforementioned flood hazard early warning requirements, flood hazard early warning data is obtained.

3. The method as described in claim 1, characterized in that, The step of obtaining the first normalized value corresponding to the dynamic early warning data based on the time coordinate includes: Determine the range of normalized values; Determine the forward time step corresponding to the time coordinate; Based on the dynamic early warning data, determine a plurality of first feature values ​​corresponding to the forward time step; The first feature value is transformed according to the normalization range to obtain candidate normalized values; The multiple candidate normalized values ​​are used together as the first normalized value.

4. The method as described in claim 3, characterized in that, The step of obtaining the second normalized value corresponding to the static early warning data based on the spatial coordinates includes: Based on the static early warning data, determine the second feature value corresponding to the spatial coordinates; The second feature value is transformed according to the normalized value range to obtain the second normalized value.

5. The method as described in claim 1, characterized in that, The step of optimizing the preset flood hazard early warning model based on the spatiotemporal coordinates and the target feature values ​​to obtain the target flood hazard early warning model includes: Determine the reference early warning information corresponding to the aforementioned flood hazard early warning data; Based on the preset flood hazard early warning model, the first normalized value and the second normalized value are processed to obtain simulated early warning information; Determine the comparison result between the reference early warning information and the simulated early warning information; The preset flood hazard early warning model is optimized based on the comparison results to obtain the target flood hazard early warning model.

6. The method as described in claim 5, characterized in that, The preset flood warning model includes: a dynamic data processing unit and a fusion data processing unit; The step of processing the first normalized value and the second normalized value based on the preset flood hazard early warning model to obtain simulated early warning information includes: The dynamic data processing unit processes the first normalized value to obtain the data to be fused. The data to be fused and the second normalized value are fused to obtain fused data; The fused data is processed by the fused data processing unit to obtain the simulated early warning information.

7. A flood hazard early warning data processing device, characterized in that, include: The acquisition module is used to acquire flood warning data, wherein the flood warning data includes dynamic warning data and static warning data; The determination module is used to determine the spatiotemporal coordinates of the dynamic early warning data and the static early warning data, as well as the target feature values ​​corresponding to the spatiotemporal coordinates; The processing module is used to optimize the preset flood hazard early warning model according to the spatiotemporal coordinates and the target feature value to obtain the target flood hazard early warning model, wherein the target flood hazard early warning model is used to generate flood hazard early warning information. The determining module includes: The second determining submodule is used to determine at least one spatial coordinate; The third determining submodule is used to determine at least one time coordinate corresponding to the dynamic early warning data and the spatial coordinates; The second acquisition submodule is used to acquire a first normalized value corresponding to the dynamic early warning data based on the time coordinate; The third acquisition submodule is used to acquire the second normalized value corresponding to the static early warning data based on the spatial coordinates; The fourth determining submodule is used to take the first normalized value and the second normalized value together as the target feature value.

8. A computer device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

Images