Natural disaster early warning method, device and computer equipment based on multi-source data

Abstract

The present application proposes a natural disaster early warning method, device and computer equipment based on multi-source data, wherein the method comprises: obtaining an identification of a plot to be predicted; according to the identification, obtaining each data source feature of the plot to be predicted from each data source platform, wherein the data source feature is a feature extracted by the data source platform from relevant data of the plot to be predicted; according to each data source feature of the plot to be predicted, predicting natural disasters for the plot to be predicted and obtaining natural disaster prediction results; according to the natural disaster prediction results, performing natural disaster early warning processing on the plot to be predicted, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction results, and in the above scheme, a feature extraction method is used to extract features from multi-source heterogeneous data of each platform to avoid prediction difficulties caused by inconsistent data structures of the data source platform, thereby reducing the warning cost and improving the timeliness of the warning.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a natural disaster early warning method, device and computer equipment based on multi-source data. Background Art

[0002] In related technologies, natural disaster warnings in rural areas mainly rely on data cooperation between agricultural and rural departments and meteorological departments. Due to the storage of data in various departments and the security and confidentiality of data, it takes a long time of communication and discussion between departments to exchange data. In addition, the data structures of various data source platforms are inconsistent, resulting in high warning costs and poor timeliness of warnings. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] The present application proposes a natural disaster warning method, device and computer equipment based on multi-source data to achieve the acquisition of characteristics of each data source for the predicted area and natural disaster prediction, avoiding the prediction difficulties caused by inconsistent data structures of various data source platforms, thereby reducing the warning cost and improving the timeliness of the warning.

[0005] The first embodiment of the present application proposes a natural disaster early warning method based on multi-source data, including:

[0006] Get the identifier of the plot to be predicted;

[0007] According to the identifier, each data source feature of the land parcel to be predicted is obtained from each data source platform, wherein the data source feature is a feature extracted by the data source platform from relevant data of the land parcel to be predicted;

[0008] According to the data source characteristics of the land parcel to be predicted, natural disaster prediction is performed on the land parcel to be predicted to obtain a natural disaster prediction result;

[0009] According to the natural disaster prediction results, natural disaster warning processing is performed on the land to be predicted.

[0010] The natural disaster warning method based on multi-source data in the embodiment of the present application obtains the identification of the land parcel to be predicted; according to the identification, obtains each data source feature of the land parcel to be predicted from each data source platform, wherein the data source feature is the feature extracted by the data source platform from the relevant data of the land parcel to be predicted; according to each data source feature of the land parcel to be predicted, performs natural disaster prediction on the land parcel to be predicted and obtains the natural disaster prediction result; according to the natural disaster prediction result, performs natural disaster warning processing on the land parcel to be predicted, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction result, and in the above scheme, the feature extraction method is used to extract features of the multi-source heterogeneous data of each platform to avoid the prediction difficulties caused by inconsistent data source structure, thereby reducing the warning cost and improving the timeliness of the warning.

[0011] The second embodiment of the present application proposes a natural disaster early warning device based on multi-source data, including:

[0012] A first acquisition module is used to acquire the identifier of the land parcel to be predicted;

[0013] A second acquisition module is used to acquire, according to the identifier, various data source features of the land parcel to be predicted from various data source platforms, wherein the data source features are features extracted by the data source platform from relevant data of the land parcel to be predicted;

[0014] A prediction module, used to predict natural disasters for the land parcel to be predicted according to the data source characteristics of each land parcel to be predicted, and obtain natural disaster prediction results;

[0015] A processing module is used to perform natural disaster warning processing on the land to be predicted according to the natural disaster prediction result.

[0016] The natural disaster warning device based on multi-source data in the embodiment of the present application obtains the identification of the land parcel to be predicted; obtains the data source characteristics of the land parcel to be predicted from each data source platform according to the identification, wherein the data source characteristics are the characteristics extracted by the data source platform from the relevant data of the land parcel to be predicted; performs natural disaster prediction on the land parcel to be predicted and obtains the natural disaster prediction result according to the data source characteristics of the land parcel to be predicted; performs natural disaster warning processing on the land parcel to be predicted according to the natural disaster prediction result, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction result, and in the above scheme, the feature extraction method is used to extract features of the multi-source heterogeneous data of each platform to avoid the prediction difficulties caused by inconsistent data source structures, thereby reducing the warning cost and improving the timeliness of the warning.

[0017] The third aspect embodiment of the present application proposes a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the natural disaster warning method based on multi-source data proposed in the first aspect embodiment of the present application.

[0018] The fourth aspect of the present application provides a computer program product. When the instruction processor in the computer program product is executed, the natural disaster warning method based on multi-source data proposed in the first aspect of the present application is executed.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A flowchart of a natural disaster early warning method based on multi-source data provided in Example 1 of the present application;

[0022] Figure 2 This is a schematic diagram of natural disaster early warning based on multi-source data;

[0023] Figure 3 A schematic diagram of the structure of a natural disaster warning device based on multi-source data provided in Example 3 of the present application;

[0024] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0026] Traditional natural disaster early warning methods require data cooperation between the agricultural and rural departments and the meteorological departments. Due to the data storage in various departments and the security and confidentiality of the data, it takes a long time for the departments to communicate and discuss to exchange data, which results in high early warning costs and poor timeliness. In addition, the amount of reference data for early warning is small, and the accuracy of early warning is low.

[0027] Therefore, this application mainly aims at the technical problems of high warning cost, poor timeliness and low warning accuracy in the prior art, and proposes a natural disaster warning method based on multi-source data.

[0028] The natural disaster warning method based on multi-source data in the embodiment of the present application obtains the identification of the land parcel to be predicted; according to the identification, obtains each data source feature of the land parcel to be predicted from each data source platform, wherein the data source feature is the feature extracted by the data source platform from the relevant data of the land parcel to be predicted; according to each data source feature of the land parcel to be predicted, performs natural disaster prediction on the land parcel to be predicted and obtains the natural disaster prediction result; according to the natural disaster prediction result, performs natural disaster warning processing on the land parcel to be predicted, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction result, and in the above scheme, the feature extraction method is used to extract features of the multi-source heterogeneous data of each platform to avoid the prediction difficulties caused by inconsistent data source structure, thereby reducing the warning cost and improving the timeliness of the warning.

[0029] The following describes the natural disaster warning method, device and computer equipment based on multi-source data in embodiments of the present application with reference to the accompanying drawings.

[0030] Figure 1 A flowchart of a natural disaster warning method based on multi-source data provided in Example 1 of the present application.

[0031] The embodiment of the present application takes the natural disaster warning method based on multi-source data as an example, in which the natural disaster warning method based on multi-source data is configured in a natural disaster warning device based on multi-source data. The natural disaster warning device based on multi-source data can be applied to any computer device so that the computer device can perform the natural disaster warning function based on multi-source data.

[0032] Among them, the computer device can be a personal computer (PC), a cloud device, a mobile device, etc. The mobile device can be, for example, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a car device, etc., which are hardware devices with various operating systems, touch screens and / or display screens.

[0033] like Figure 1 As shown, the natural disaster early warning method based on multi-source data may include the following steps:

[0034] Step 101, obtaining the identification of the land parcel to be predicted.

[0035] In the embodiments of the present application, a plot may refer to a land area. For example, the ground may be divided according to a fixed area size to obtain multiple plots. For another example, a plot division model may be set, and the plot division model divides the ground according to area, fertility, yield, etc. to obtain multiple plots. Among them, the plot to be predicted may be any plot, for example, a plot located in an area where natural disasters often occur.

[0036] Step 102, according to the identifier, obtain various data source features of the land parcel to be predicted from various data source platforms, wherein the data source features are features extracted by the data source platform from relevant data of the land parcel to be predicted.

[0037] In the embodiment of the present application, the data source platform may be, for example, a production-related platform, an agricultural product platform, etc. The production-related platform may be, for example, an agricultural platform, a meteorological platform, etc. The data stored on the agricultural platform may be, for example, soil data, cultivation data, agricultural product data, soil and fertilizer data, etc. of each plot of land. After the agricultural platform collects these data, it may perform pre-processing such as data cleaning on the data and then store them.

[0038] In the embodiment of the present application, the data stored on the meteorological platform may be, for example, meteorological data and hydrological data of each plot of land. After the meteorological platform collects these data, it may perform pre-processing such as data cleaning on these data and then store them. In the embodiment of the present application, the data stored on the agricultural product platform may be, for example, agricultural products related to the plot of land, and consumption data of agricultural products, etc. Among them, agricultural products include various fertilizers, pesticides, herbicides, etc.

[0039] In an embodiment of the present application, the data source characteristics on each data source platform can be processed through data encryption, secure computing, data perturbation, etc. to ensure the security of data interaction between the natural disaster warning device based on multi-source data and each data source platform, and to ensure that the privacy data of each data source platform is not leaked.

[0040] In an embodiment of the present application, the data source platform extracts features from relevant data of the plot to be predicted by, based on an identifier, obtaining relevant data of the plot to be predicted; obtaining a feature extraction model that matches the data of the data source platform; and extracting data source features of the plot to be predicted from the relevant data of the plot to be predicted in combination with the feature extraction model.

[0041] In the embodiment of the present application, taking the production-related platform as an example, the features mentioned in the data of the production-related platform are production features, for example, the agricultural production features of the agricultural platform and the meteorological production features of the meteorological platform. The feature extraction model that matches the data of the data source platform can be, for example, a gated recurrent unit network model or a long short-term memory artificial neural network model. The data collected by the production-related platform changes according to the development of time. Therefore, the feature extraction model needs to extract features based on the data at each time point, and the gated recurrent unit network model and the long short-term memory artificial neural network model can extract features from the sequence data, so as to extract the features of the data of the production-related platform within a period of time. Specifically, when the data source platform is a production-related platform, the data source platform combines the feature extraction model to extract the data source features of the plot to be predicted from the relevant data of the plot to be predicted, and divides the preset time period to obtain multiple time segments; combines multiple gated recurrent units or multiple artificial neural network layers in the feature extraction model to process the production-related data in multiple time segments; and uses the processing result of the last gated recurrent unit or artificial neural network layer as the production feature of the plot to be predicted.

[0042] In the embodiment of the present application, taking the agricultural product platform as an example, the features extracted from the data by the agricultural product platform are consumption features. The data collected by the agricultural product platform are consumption data of agricultural products related to the plot, etc., and the feature extraction model that matches the data of the data source platform can be, for example, a vector representation model. When the data source platform is an agricultural product platform, the data source platform extracts the data source features of the plot to be predicted from the relevant data of the plot to be predicted in combination with the feature extraction model, including: obtaining the consumption data of each agricultural product in the relevant data of the plot to be predicted; establishing an agricultural product network diagram of the plot to be predicted based on the consumption data of each agricultural product; performing random walk processing on the agricultural product network diagram based on the vector representation model to obtain the consumption features of the plot to be predicted.

[0043] In the embodiment of the present application, the process of establishing the agricultural product network diagram may be, for example, obtaining parameters such as price and sales volume in the consumption data of each agricultural product, and determining the distance between each agricultural product in combination with the parameters of each agricultural product, wherein the determination method may be, for example, cosine distance calculation, Euclidean distance calculation, Mahalanobis distance calculation, etc., which may be set according to actual needs. After determining the distance between each agricultural product, the agricultural product network diagram may be constructed in combination with the distance between each agricultural product and the consumption data of each agricultural product.

[0044] Step 103: predict natural disasters for the land parcel to be predicted based on the data source characteristics of the land parcel to be predicted, and obtain natural disaster prediction results.

[0045] In the embodiment of the present application, the process of executing step 103 by the natural disaster warning device based on multi-source data can, for example, be to combine a preset fusion prediction model, fuse and predict the characteristics of each data source of the predicted plot, and obtain the natural disaster prediction result of the predicted plot.

[0046] In the embodiment of the present application, the fusion prediction model may specifically include: a fusion module and a prediction module; wherein the fusion module is used to splice the features of each data source of the predicted plot to obtain the spliced ​​features; the prediction module is used to predict the spliced ​​features to obtain the natural disaster prediction results. The natural disaster prediction results may include, for example, whether there is a natural disaster, and may also include: the specific type of natural disaster, etc. The specific type of natural disaster may be, for example, drought, flood, pests and diseases, soil deterioration, etc.

[0047] In the embodiment of the present application, the schematic diagram of natural disaster warning based on multi-source data can be as follows: Figure 2 As shown, in Figure 2 It includes data layer, model layer and application layer. The data layer includes: agricultural platform, meteorological platform and agricultural products platform. The model layer includes: feature extraction model for feature extraction and fusion prediction model for prediction. The application layer includes: drought warning application, flood warning application, pest warning application, soil deterioration warning application, etc. Each application can correspond to a fusion prediction model, or multiple applications can be implemented using the same fusion prediction model.

[0048] In an embodiment of the present application, when the data source platform uses a matching feature extraction model to extract features from relevant data of the land parcel to be predicted, the method may further include the following steps: obtaining training data, wherein the training data includes: sample data source data of each sample land parcel, and corresponding natural disaster results; for each sample land parcel, sending the sample data source data of each sample land parcel to the corresponding data source platform to obtain the sample data source features extracted by the data source platform using the matching feature extraction model; combining the sample data source features of each sample land parcel and the fusion prediction model to obtain the sample prediction results; combining the sample prediction results and the natural disaster results to determine the value of a preset loss function; combining the value of the loss function to determine the back propagation gradient values ​​of the fusion prediction model and each feature extraction model, so as to adjust the parameters of the fusion prediction model and each feature extraction model in combination with the back propagation gradient values ​​to achieve training.

[0049] In the embodiment of the present application, by back-propagating the gradient value, it is possible to achieve joint training of the fusion prediction model and the feature extraction model located on different data source platforms, thereby improving the training effect of the model and the accuracy of the trained model.

[0050] Step 104: Perform natural disaster warning processing on the predicted area according to the natural disaster prediction results.

[0051] The natural disaster warning method based on multi-source data in the embodiment of the present application obtains the identification of the land parcel to be predicted; according to the identification, obtains each data source feature of the land parcel to be predicted from each data source platform, wherein the data source feature is the feature extracted by the data source platform from the relevant data of the land parcel to be predicted; according to each data source feature of the land parcel to be predicted, performs natural disaster prediction on the land parcel to be predicted and obtains the natural disaster prediction result; according to the natural disaster prediction result, performs natural disaster warning processing on the land parcel to be predicted, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction result, and in the above scheme, the feature extraction method is used to extract features of the multi-source heterogeneous data of each platform to avoid the prediction difficulties caused by inconsistent data source structure, thereby reducing the warning cost and improving the timeliness of the warning.

[0052] Figure 3 This is a schematic diagram of the structure of a natural disaster warning device based on multi-source data provided in Example 2 of the present application.

[0053] like Figure 3 As shown, the natural disaster warning device 300 based on multi-source data may include: a first acquisition module 310 , a second acquisition module 320 , a prediction module 330 and a processing module 340 .

[0054] The first acquisition module 310 is used to acquire the identifier of the land parcel to be predicted;

[0055] A second acquisition module 320 is used to acquire, according to the identifier, various data source features of the land parcel to be predicted from various data source platforms, wherein the data source features are features extracted by the data source platform from relevant data of the land parcel to be predicted;

[0056] A prediction module 330 is used to perform natural disaster prediction on the land parcel to be predicted according to the data source characteristics of each land parcel to be predicted, and obtain a natural disaster prediction result;

[0057] The processing module 340 is used to perform natural disaster warning processing on the to-be-predicted land parcel according to the natural disaster prediction result.

[0058] Furthermore, in a possible implementation of the embodiment of the present application, the data source platform extracts features from the relevant data of the land parcel to be predicted in the following manner:

[0059] According to the identifier, obtaining relevant data of the land parcel to be predicted;

[0060] Obtain a feature extraction model that matches the data on the data source platform;

[0061] In combination with the feature extraction model, data source features of the land parcel to be predicted are extracted from relevant data of the land parcel to be predicted.

[0062] Further, in a possible implementation of the embodiment of the present application, the various data source platforms include: production-related platforms, the production-related platforms include: agricultural platforms and meteorological platforms; the various data source features include: production features; the production features include: agricultural production features and meteorological production features;

[0063] The feature extraction model that matches the data of the production-related platform is a gated recurrent unit network model or a long short-term memory artificial neural network model.

[0064] Further, in a possible implementation of the embodiment of the present application, when the data source platform is a production-related platform, the relevant data of the land parcel to be predicted is production-related data within a preset time period;

[0065] The data source platform combines the feature extraction model to extract the data source features of the land parcel to be predicted from the relevant data of the land parcel to be predicted in the following manner:

[0066] Dividing the preset time period to obtain multiple time segments;

[0067] Processing the production-related data in the multiple time segments in combination with the multiple gated recurrent units or multiple artificial neural network layers in the feature extraction model;

[0068] The processing result of the last gated recurrent unit or artificial neural network layer is used as the production feature of the land parcel to be predicted.

[0069] Further, in a possible implementation of the embodiment of the present application, each data source platform further includes: an agricultural product platform; each data source feature further includes: a consumption feature;

[0070] The feature extraction model that matches the data of the agricultural products platform is a vector representation model;

[0071] When the data source platform is an agricultural product platform, the data source platform extracts the data source features of the to-be-predicted plot from the relevant data of the to-be-predicted plot in combination with the feature extraction model, including:

[0072] Obtaining consumption data of various agricultural products in the relevant data of the land parcel to be predicted;

[0073] Based on the consumption data of each agricultural product, establishing an agricultural product network diagram of the land to be predicted;

[0074] The agricultural product network graph is subjected to random walk processing based on a vector representation model to obtain consumption characteristics of the land parcel to be predicted.

[0075] Furthermore, in a possible implementation of the embodiment of the present application, the prediction module 330 is specifically used to:

[0076] Combined with the preset fusion prediction model, the data source features of the to-be-predicted plot are fused and predicted to obtain the natural disaster prediction result of the to-be-predicted plot.

[0077] Furthermore, in a possible implementation of the embodiment of the present application, the device further includes: a training module;

[0078] The training module is used to obtain training data, wherein the training data includes: each sample data source data of the sample plot, and the corresponding natural disaster results; for each sample plot, the each sample data source data of the sample plot is sent to the corresponding data source platform to obtain the sample data source features extracted by the data source platform using a matching feature extraction model; combining the each sample data source features of the sample plot and the fusion prediction model to obtain the sample prediction results; combining the sample prediction results and the natural disaster results to determine the value of a preset loss function; combining the value of the loss function to determine the back propagation gradient values ​​of the fusion prediction model and each feature extraction model, so as to adjust the parameters of the fusion prediction model and each feature extraction model in combination with the back propagation gradient values ​​to achieve training.

[0079] It should be noted that the explanations in the aforementioned first embodiment are also applicable to the natural disaster warning device based on multi-source data in this embodiment, and will not be repeated here.

[0080] The natural disaster warning device based on multi-source data in the embodiment of the present application obtains the identification of the land parcel to be predicted; obtains the data source characteristics of the land parcel to be predicted from each data source platform according to the identification, wherein the data source characteristics are the characteristics extracted by the data source platform from the relevant data of the land parcel to be predicted; performs natural disaster prediction on the land parcel to be predicted and obtains the natural disaster prediction result according to the data source characteristics of the land parcel to be predicted; performs natural disaster warning processing on the land parcel to be predicted according to the natural disaster prediction result, so that subsequent disaster materials can be deployed or evacuated in advance according to the natural disaster prediction result, and in the above scheme, the feature extraction method is used to extract features of the multi-source heterogeneous data of each platform to avoid the prediction difficulties caused by inconsistent data source structures, thereby reducing the warning cost and improving the timeliness of the warning.

[0081] In order to implement the above embodiments, the present application also proposes a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the natural disaster warning method based on multi-source data proposed in the above embodiments of the present application.

[0082] In order to implement the above embodiments, the present application also proposes a computer program product. When the instruction processor in the computer program product is executed, it executes the natural disaster warning method based on multi-source data proposed in the above embodiments of the present application.

[0083] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. Figure 4 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0084] like Figure 4 As shown, the computer device 12 is 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, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0085] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0086] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0087] The 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. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0088] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0089] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the 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.

[0090] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the above embodiments.

[0091] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0092] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0093] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0094] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0095] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0096] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0097] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0098] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A natural disaster early warning method based on multi-source data, characterized in that: include: Get the identifier of the plot to be predicted; According to the identifier, each data source feature of the land parcel to be predicted is obtained from each data source platform, wherein the data source feature is a feature extracted by the data source platform from the relevant data of the land parcel to be predicted, and each data source platform includes: a production-related platform, the production-related platform includes: an agricultural platform and a meteorological platform, an agricultural product platform, and the data stored on the agricultural product platform includes: agricultural products related to the land parcel to be predicted, and consumption data of agricultural products; each data source feature includes: production features; the production features include: agricultural production features and meteorological production features; According to the data source characteristics of the land parcel to be predicted, natural disaster prediction is performed on the land parcel to be predicted to obtain a natural disaster prediction result; According to the natural disaster prediction results, a natural disaster early warning process is performed on the land to be predicted; The data source platform extracts features from the relevant data of the land parcel to be predicted in the following manner: According to the identifier, obtaining relevant data of the land parcel to be predicted; Obtain a feature extraction model that matches the data on the data source platform; In combination with the feature extraction model, data source features of the land parcel to be predicted are extracted from relevant data of the land parcel to be predicted.

2. The natural disaster early warning method based on multi-source data according to claim 1, characterized in that: The feature extraction model that matches the data of the production-related platform is a gated recurrent unit network model or a long short-term memory artificial neural network model.

3. The natural disaster early warning method based on multi-source data according to claim 2, characterized in that: When the data source platform is a production-related platform, the relevant data of the land parcel to be predicted is production-related data within a preset time period; The data source platform combines the feature extraction model to extract the data source features of the land parcel to be predicted from the relevant data of the land parcel to be predicted in the following manner: Dividing the preset time period to obtain multiple time segments; Processing the production-related data in the multiple time segments in combination with the multiple gated recurrent units or multiple artificial neural network layers in the feature extraction model; The processing result of the last gated recurrent unit or artificial neural network layer is used as the production feature of the land parcel to be predicted.

4. The natural disaster early warning method based on multi-source data according to claim 1 or 2, characterized in that: The various data source platforms also include: agricultural products platform; the various data source characteristics also include: consumption characteristics; The feature extraction model that matches the data of the agricultural products platform is a vector representation model; When the data source platform is an agricultural product platform, the data source platform combines the feature extraction model to extract the data source features of the to-be-predicted plot from the relevant data of the to-be-predicted plot in the following manner: Obtaining consumption data of various agricultural products in the relevant data of the land parcel to be predicted; Based on the consumption data of each agricultural product, establishing an agricultural product network diagram of the land to be predicted; The agricultural product network graph is subjected to random walk processing based on a vector representation model to obtain consumption characteristics of the land parcel to be predicted.

5. The natural disaster early warning method based on multi-source data according to claim 1, characterized in that: The step of performing natural disaster prediction on the land parcel to be predicted according to the data source characteristics of each land parcel to be predicted and obtaining the natural disaster prediction result includes: Combined with the preset fusion prediction model, the data source features of the to-be-predicted plot are fused and predicted to obtain the natural disaster prediction result of the to-be-predicted plot.

6. The natural disaster early warning method based on multi-source data according to claim 5, characterized in that: The method further comprises: Acquire training data, wherein the training data includes: data of each sample data source of the sample plot, and corresponding natural disaster results; For each sample plot, each sample data source data of the sample plot is sent to a corresponding data source platform to obtain sample data source features extracted by the data source platform using a matching feature extraction model; Combining the characteristics of each sample data source of the sample plot and the fusion prediction model, obtaining a sample prediction result; Determine the value of a preset loss function by combining the sample prediction result and the natural disaster result; In combination with the value of the loss function, the back propagation gradient value of the fusion prediction model and each feature extraction model is determined, so as to adjust the parameters of the fusion prediction model and each feature extraction model in combination with the back propagation gradient value to achieve training.

7. A natural disaster early warning device based on multi-source data, characterized in that: include: A first acquisition module is used to acquire the identifier of the land parcel to be predicted; The second acquisition module is used to acquire various data source features of the land parcel to be predicted from various data source platforms according to the identifier, wherein the data source features are features extracted by the data source platforms from relevant data of the land parcel to be predicted, and the various data source platforms include: production-related platforms, the production-related platforms include: agricultural platforms and meteorological platforms, agricultural product platforms, and the data stored on the agricultural product platforms include: agricultural products related to the land parcel to be predicted, and consumption data of agricultural products; the various data source features include: production features; the production features include: agricultural production features and meteorological production features; A prediction module, used to perform natural disaster prediction on the land parcel to be predicted according to the data source characteristics of each land parcel to be predicted, and obtain a natural disaster prediction result; A processing module, used for performing natural disaster early warning processing on the land to be predicted according to the natural disaster prediction result; The data source platform extracts features from the relevant data of the land parcel to be predicted in the following manner: According to the identifier, obtaining relevant data of the land parcel to be predicted; Obtain a feature extraction model that matches the data on the data source platform; In combination with the feature extraction model, data source features of the land parcel to be predicted are extracted from relevant data of the land parcel to be predicted.

8. The natural disaster early warning device based on multi-source data according to claim 7, characterized in that: The feature extraction model that matches the data of the production-related platform is a gated recurrent unit network model or a long short-term memory artificial neural network model.

9. The natural disaster early warning device based on multi-source data according to claim 8, characterized in that: When the data source platform is a production-related platform, the relevant data of the land parcel to be predicted is production-related data within a preset time period; The data source platform combines the feature extraction model to extract the data source features of the land parcel to be predicted from the relevant data of the land parcel to be predicted in the following manner: Dividing the preset time period to obtain multiple time segments; Processing the production-related data in the multiple time segments in combination with the multiple gated recurrent units or multiple artificial neural network layers in the feature extraction model; The processing result of the last gated recurrent unit or artificial neural network layer is used as the production feature of the land parcel to be predicted.

10. The natural disaster early warning device based on multi-source data according to claim 7 or 8, characterized in that: The various data source platforms also include: agricultural products platform; the various data source characteristics also include: consumption characteristics; The feature extraction model that matches the data of the agricultural products platform is a vector representation model; When the data source platform is an agricultural product platform, the data source platform extracts the data source features of the to-be-predicted plot from the relevant data of the to-be-predicted plot in combination with the feature extraction model, including: Obtaining consumption data of various agricultural products in the relevant data of the land parcel to be predicted; Based on the consumption data of each agricultural product, establishing an agricultural product network diagram of the land to be predicted; The agricultural product network graph is subjected to random walk processing based on a vector representation model to obtain consumption characteristics of the land parcel to be predicted.

11. The natural disaster early warning device based on multi-source data according to claim 7, characterized in that: The prediction module is specifically used for: Combined with the preset fusion prediction model, the data source features of the to-be-predicted plot are fused and predicted to obtain the natural disaster prediction result of the to-be-predicted plot.

12. The natural disaster early warning device based on multi-source data according to claim 11, characterized in that: Also includes: Training modules; The training module is used to: Acquire training data, wherein the training data includes: data of each sample data source of the sample plot, and corresponding natural disaster results; For each sample plot, each sample data source data of the sample plot is sent to a corresponding data source platform to obtain sample data source features extracted by the data source platform using a matching feature extraction model; Combining the characteristics of each sample data source of the sample plot and the fusion prediction model, obtaining a sample prediction result; Determine the value of a preset loss function by combining the sample prediction result and the natural disaster result; In combination with the value of the loss function, the back propagation gradient value of the fusion prediction model and each feature extraction model is determined, so as to adjust the parameters of the fusion prediction model and each feature extraction model in combination with the back propagation gradient value to achieve training.

13. An electronic 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

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

Images