CN114186743A

CN114186743A - Method, device and equipment for predicting danger-appearing area and storage medium

Info

Publication number: CN114186743A
Application number: CN202111519161.8A
Authority: CN
Inventors: 曾思敏; 郑越; 任伯阳; 王创; 江一航
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2021-12-13
Filing date: 2021-12-13
Publication date: 2022-03-15

Abstract

The invention relates to an artificial intelligence technology, and discloses a method for predicting an outbreak area, which comprises the following steps: carrying out data matching on the rainfall related data by using the risk related data to obtain standard risk data; constructing a characteristic data set based on the rainfall related data and the standard emergence data; performing region prediction on a standard reference image obtained by performing data fusion on the feature data set and the region reference image by using a region prediction model to obtain a region prediction image; counting the number of pixel points in the regional prediction image, calculating to obtain a loss value based on the number of the pixel points and a loss function, and outputting a standard regional prediction model according to the size between the loss value and a loss threshold value; and inputting the image to be recognized into a standard region prediction model to obtain the danger area. In addition, the invention also relates to a block chain technology, and the characteristic data set can be stored in the node of the block chain. The invention also provides a risk area prediction device, electronic equipment and a storage medium. The method and the device can improve the efficiency of predicting the danger areas.

Description

Method, device and equipment for predicting danger-appearing area and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for predicting an insurance exposure area, electronic equipment and a computer readable storage medium.

Background

In the field of insurance, fine early warning and targeted personnel and material allocation are generally required according to a natural disaster range grasped in advance, so that rescue can be performed as soon as possible in a disaster, and loss caused by the disaster is reduced as much as possible. The existing disaster area range prediction method generally utilizes a hydrological model to model the water accumulation condition under the given precipitation condition. The hydrological model itself needs more parameters, many parameters such as pipe network data are difficult to obtain, the city surface is complex, and great challenges exist for parameter calibration of the hydrological model. In addition, the hydrological model has the problems of poor generalization and difficult wide-range application. Therefore, a more efficient method for predicting the risk emergence area is urgently needed.

Disclosure of Invention

The invention provides a method and a device for predicting an insurance exposure area and a computer readable storage medium, and mainly aims to improve the efficiency of the insurance exposure area prediction.

In order to achieve the above object, the present invention provides a method for predicting an emergence area, comprising:

acquiring rainfall related data and emergence related data, and performing data matching on the rainfall related data by using the emergence related data to obtain standard emergence data;

constructing a feature data set based on the precipitation-related data and the standard emergence data;

acquiring a preset regional reference image, and performing data fusion on the characteristic data set and the regional reference image to obtain a standard reference image;

performing region prediction on the standard reference image by using a preset region prediction model to obtain a region prediction image;

counting the number of pixel points in the regional prediction image, calculating to obtain a loss value based on the number of the pixel points and a preset loss function, and outputting a standard regional prediction model according to the size between the loss value and a preset loss threshold value;

and acquiring an image to be recognized, and inputting the image to be recognized into the standard region prediction model to obtain the danger area of the image to be recognized.

Optionally, the performing region prediction on the standard reference map by using a preset region prediction model to obtain a region prediction image includes:

performing convolution compression on the standard reference image based on a preset compression level to obtain a first compression image, a second compression image, a third compression image and a fourth compression image;

inputting the first compressed graph into a first semantic segmentation module in the region prediction model to obtain a first semantic graph;

inputting the first semantic graph and the second compressed graph into a second semantic segmentation module in the region prediction model to obtain a second semantic graph;

inputting the second semantic graph and the third compressed graph into a third semantic segmentation module in the region prediction model to obtain a third semantic graph;

and inputting the third semantic graph and the fourth compressed graph into a fourth semantic segmentation module in the region prediction model to obtain a region prediction image.

Optionally, the inputting the first semantic graph and the second compressed graph into a second semantic segmentation module in the region prediction model to obtain a second semantic graph includes:

extracting information of the first semantic graph and the second compressed graph respectively by using a residual convolution unit in the second semantic segmentation module to obtain residual information corresponding to the first semantic graph and the second compressed graph;

performing multi-resolution fusion on the residual error information by using the multi-resolution fusion unit to obtain fusion information;

and performing pooling processing on the fusion information based on a chain residual pooling unit in the second semantic segmentation module to obtain a second semantic graph.

Optionally, the calculating the loss value based on the number of the pixel points and a preset loss function includes:

wherein L is_diceFor the loss value, X is the number of pixels labeled as positive in the region prediction image, | Y | is the number of pixels predicted as positive, | X |, n |, Y | is the number of pixels labeled as positive and predicted as positive.

Optionally, before the data fusion of the feature data set and the region reference map, the method further includes:

cutting the region reference image into a plurality of region sub-images with preset sizes;

and respectively carrying out denoising treatment on the plurality of regional subgraphs to obtain denoised subgraphs.

Optionally, said constructing a feature data set based on said precipitation-related data and said standard emergence data comprises:

carrying out time correction and discretization treatment on the rainfall related data to obtain a plurality of standard rainfall intervals;

and counting the frequency of the standard emergence data in the plurality of standard precipitation intervals, and summarizing the plurality of standard precipitation intervals and the frequency to obtain a characteristic data set.

Optionally, the performing data matching on the precipitation related data by using the risk related data to obtain standard risk data includes:

extracting the insurance place data in the insurance related data and insurance time data corresponding to the insurance place data, and performing time correction on the insurance time to obtain standard insurance time;

and matching the precipitation related data with the insurance place data based on a preset precipitation mapping table, and marking the insurance time data to obtain standard insurance data.

In order to solve the above problem, the present invention also provides a risk area prediction apparatus, including:

the data processing module is used for acquiring precipitation related data and emergence related data, performing data matching on the precipitation related data by using the emergence related data to obtain standard emergence data, and constructing a characteristic data set based on the precipitation related data and the standard emergence data;

the data fusion module is used for acquiring a preset regional reference image, and performing data fusion on the characteristic data set and the regional reference image to obtain a standard reference image;

the model training module is used for carrying out region prediction on the standard reference image by using a preset region prediction model to obtain a region prediction image, counting the number of pixel points in the region prediction image, calculating to obtain a loss value based on the number of the pixel points and a preset loss function, and outputting the standard region prediction model according to the size between the loss value and a preset loss threshold value;

and the area prediction module is used for acquiring an image to be recognized, inputting the image to be recognized into the standard area prediction model and obtaining the danger area of the image to be recognized.

In order to solve the above problem, the present invention also provides an electronic device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of risk area prediction described above.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the risk area prediction method described above.

According to the embodiment of the invention, the data matching is carried out on the precipitation related data by using the emergence related data, the obtained standard emergence data comprises the relation between the emergence related data and the precipitation related data, the feature data set is constructed on the basis of the precipitation related data and the standard emergence data, the feature data set comprises a plurality of feature data, the feature data set and the regional reference map are subjected to data fusion, and the feature data are visually displayed on the regional reference map. The method comprises the steps of performing region prediction on the standard reference image by using a preset region prediction model to obtain a region prediction image, calculating to obtain a loss value based on the number of pixel points in the region prediction image and a preset loss function, outputting the standard region prediction model according to the loss value and the preset loss threshold value, performing region prediction on an image to be recognized according to the standard region prediction model, and improving the efficiency of region prediction in danger. Therefore, the risk area prediction method, the risk area prediction device, the electronic equipment and the computer readable storage medium can solve the problem that the risk area prediction efficiency is not high enough.

Drawings

Fig. 1 is a schematic flow chart illustrating a method for predicting a risk area according to an embodiment of the present invention;

FIG. 2 is a functional block diagram of a risk area prediction apparatus according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device for implementing the method for predicting an emergency area according to an embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a method for predicting an emergence area. The execution subject of the risk occurrence area prediction method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the risk area prediction method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Fig. 1 is a schematic flow chart of a method for predicting a risk area according to an embodiment of the present invention. In this embodiment, the method for predicting an emergency area includes:

and S1, acquiring precipitation related data and emergence related data, and performing data matching on the precipitation related data by using the emergence related data to obtain standard emergence data.

In an embodiment of the present invention, the precipitation related data may be 1 × 1km mesh reanalysis daily precipitation data up to 2020, the emergence related data may be national vehicle insurance emergence data up to 2020 and national vehicle insurance underwriting data up to 2020, and the precipitation related data and the emergence related data are not limited herein.

Specifically, the performing data matching on the precipitation related data by using the risk related data to obtain standard risk data includes:

In detail, since the emergence date may have a long tail phenomenon, the emergence time needs to be subjected to time correction processing, and the emergence date can be adjusted to the date with the maximum precipitation intensity in the [ T-3, T +1] interval by using the average precipitation amount of the area 3x3km where the emergence point is located as the precipitation intensity. And matching the corresponding precipitation to the insurance point according to the date and the place of the insurance data.

S2, constructing a feature data set based on the precipitation related data and the standard risk data.

In an embodiment of the present invention, the constructing a feature data set based on the precipitation related data and the standard risk data includes:

In detail, the time correction and discretization processing of the standard precipitation data is to discretize the time-corrected precipitation into a plurality of intervals, for example: the frequency of the standard risk occurrence data in the standard precipitation intervals is counted according to the precipitation intervals, and the number of risk occurrences in the intervals (0,10], (10,50], (50,100], (100,200], (200, + ∞) of the area is counted, and the sum of historical risk occurrences is added.

And S3, acquiring a preset area reference image, and performing data fusion on the feature data set and the area reference image to obtain a standard reference image.

In the embodiment of the present invention, the regional reference map may refer to a map in a national range, or a map in a specific province range. And selecting and acquiring the area reference map according to the actual demand of the risk area prediction, wherein the acquisition of the preset area reference map is not limited.

Specifically, before the data fusion of the feature data set and the region reference map, the method further includes:

In detail, the preset size is 90 × 90. The denoising processing mainly comprises the steps of eliminating samples without precipitation or a small amount of precipitation, eliminating samples with the accumulated risk number of 1, and eliminating risks caused by known flood events.

Wherein, no or little precipitation theoretically hardly causes danger and can be directly removed. Even if the samples of the occurrence risk exist, the data of the occurrence risk which is possibly directly caused by non-precipitation or the address deviation of the occurrence risk are all regarded as noise elimination. Daily precipitation <30mm is considered as a small amount of precipitation. The regional historical risk occurrence number is less than 1, the amount of historical information is insufficient, the current risk occurrence amount cannot be predicted through the information of the historical risk occurrence, and therefore the regional historical risk occurrence number is directly eliminated. And eliminating special emergent disaster events, such as Guangzhou 522 Zhujiang backflow event and 818 Leshan flood event. Flood incidents are not simply caused by the precipitation condition at the risk emergence points, the cause is complex, and the risk emergence is difficult to predict directly through precipitation.

Further, the data fusion of the feature data set and the region reference map refers to labeling the feature data in the feature data set at a corresponding position on the region reference map.

And S4, performing area prediction on the standard reference image by using a preset area prediction model to obtain an area prediction image.

In the embodiment of the invention, the preset region prediction model is a refinenet model, wherein the refinenet model applies a large number of net blocks and identification mapping between different refinenet modules, and the operations retain a large number of original details of pictures, so that the accuracy of pixel point level prediction is improved.

Specifically, the performing region prediction on the standard reference map by using a preset region prediction model to obtain a region prediction image includes:

In detail, the compression levels are 1/32, 1/16, 1/8 and 1/4, so that the standard reference map is convolution-compressed based on preset compression levels respectively to obtain a first compression map with the compression level of 1/32, a second compression map with the compression level of 1/16, a third compression map with the compression level of 1/8 and a fourth compression map with the compression level of 1/4. The regional prediction model comprises a plurality of semantic segmentation modules, and the input of the semantic segmentation modules is usually compressed information of an original image and information extracted by a high-order semantic segmentation module.

Further, the inputting the first semantic graph and the second compressed graph into a second semantic segmentation module in the region prediction model to obtain a second semantic graph includes:

In detail, the second semantic segmentation module includes a Residual Convolution Unit (RCU), a multi-resolution fusion unit (multi-resolution fusion), and a chained residual pooling unit (chained residual pooling). The residual convolution unit comprises a ReLU layer and a convolution layer, and in the network structure, two RCU modules which are connected in series are applied under each resolution ratio and used for extracting the residual of the segmentation result under the resolution ratio. The multi-resolution fusion unit processes the input segmentation results under different resolutions through a convolution layer, so as to learn and obtain the adaptive weight under each channel. And then, applying up-sampling to unify the segmentation results under all channels, and summing the results of all channels to obtain a fusion result. The chain type residual pooling unit mainly comprises a residual structure, a pooling layer and a convolution layer. Wherein the pooling layer plus convolutional layer is used to learn the residual error for correction.

S5, counting the number of pixel points in the area prediction image, calculating to obtain a loss value based on the number of the pixel points and a preset loss function, and outputting a standard area prediction model according to the size between the loss value and a preset loss threshold value.

In the embodiment of the present invention, the counting the number of the pixels in the area prediction image refers to summarizing the number of the pixels in different areas in the area prediction image.

Specifically, the calculating based on the number of the pixel points and a preset loss function to obtain a loss value includes:

Further, a standard region prediction model is output according to the size between the loss value and a preset loss threshold value, if the loss value is smaller than the loss threshold value, the region prediction model is output as the standard region prediction model, if the loss value is larger than or equal to the loss threshold value, model parameter adjustment is performed on the region prediction model until the loss value is smaller than the loss threshold value, and the region prediction model with the adjusted model parameters is used as the standard region prediction model.

In detail, since the risk areas are relatively few compared to the non-risk areas, there is a more significant problem of sample imbalance. Therefore, the original cross entropy loss of the refinenet is changed into dice loss to improve the training effect of the sample unbalanced data.

And S6, acquiring an image to be recognized, and inputting the image to be recognized into the standard region prediction model to obtain the risk area of the image to be recognized.

In the embodiment of the invention, the image to be identified is a pre-disaster city map, and the image to be identified is input into the standard area prediction model, so that a plurality of danger areas in the image to be identified can be identified. In an insurance scene, if the general disaster range is mastered before disaster, fine early warning and targeted personnel and material allocation can be performed in advance, so that rescue can be performed as soon as possible in the disaster, and loss caused by the disaster is reduced as much as possible.

In detail, the scheme utilizes a generalized model to predict the general range of the national insurance caused by precipitation, greatly reduces the workload of model parameter adjustment compared with a hydrological model, improves the calculation efficiency of the model, and provides practical guiding significance for pre-disaster targeted early warning and personnel and material allocation of insurance.

According to the embodiment of the invention, the data matching is carried out on the precipitation related data by using the emergence related data, the obtained standard emergence data comprises the relation between the emergence related data and the precipitation related data, the feature data set is constructed on the basis of the precipitation related data and the standard emergence data, the feature data set comprises a plurality of feature data, the feature data set and the regional reference map are subjected to data fusion, and the feature data are visually displayed on the regional reference map. The method comprises the steps of performing region prediction on the standard reference image by using a preset region prediction model to obtain a region prediction image, calculating to obtain a loss value based on the number of pixel points in the region prediction image and a preset loss function, outputting the standard region prediction model according to the loss value and the preset loss threshold value, performing region prediction on an image to be recognized according to the standard region prediction model, and improving the efficiency of region prediction in danger. Therefore, the risk area prediction method provided by the invention can solve the problem that the risk area prediction efficiency is not high enough.

Fig. 2 is a functional block diagram of a risk area prediction apparatus according to an embodiment of the present invention.

The risk area prediction apparatus 100 according to the present invention may be installed in an electronic device. According to the realized functions, the risk area prediction device 100 may include a data processing module 101, a data fusion module 102, a model training module 103, and an area prediction module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the data processing module 101 is configured to obtain precipitation related data and emergence related data, perform data matching on the precipitation related data by using the emergence related data to obtain standard emergence data, and construct a feature data set based on the precipitation related data and the standard emergence data;

the data fusion module 102 is configured to obtain a preset regional reference map, and perform data fusion on the feature data set and the regional reference map to obtain a standard reference map;

the model training module 103 is configured to perform region prediction on the standard reference map by using a preset region prediction model to obtain a region prediction image, count the number of pixel points in the region prediction image, calculate a loss value based on the number of pixel points and a preset loss function, and output the standard region prediction model according to a magnitude between the loss value and a preset loss threshold;

the region prediction module 104 is configured to obtain an image to be recognized, and input the image to be recognized into the standard region prediction model to obtain an emergency region of the image to be recognized.

In detail, the embodiments of the modules of the risk area prediction apparatus 100 are as follows:

acquiring relevant data of precipitation and relevant data of risk occurrence, and performing data matching on the relevant data of precipitation by using the relevant data of risk occurrence to obtain standard risk occurrence data.

And secondly, constructing a characteristic data set based on the precipitation related data and the standard emergence data.

And step three, acquiring a preset regional reference image, and performing data fusion on the characteristic data set and the regional reference image to obtain a standard reference image.

Specifically, before the data fusion of the feature data set and the region reference map, further performing:

And fourthly, performing area prediction on the standard reference image by using a preset area prediction model to obtain an area prediction image.

And fifthly, counting the number of pixel points in the regional prediction image, calculating to obtain a loss value based on the number of the pixel points and a preset loss function, and outputting a standard regional prediction model according to the size between the loss value and a preset loss threshold value.

And step six, acquiring an image to be recognized, and inputting the image to be recognized into the standard region prediction model to obtain the risk-leaving region of the image to be recognized.

According to the embodiment of the invention, the data matching is carried out on the precipitation related data by using the emergence related data, the obtained standard emergence data comprises the relation between the emergence related data and the precipitation related data, the feature data set is constructed on the basis of the precipitation related data and the standard emergence data, the feature data set comprises a plurality of feature data, the feature data set and the regional reference map are subjected to data fusion, and the feature data are visually displayed on the regional reference map. The method comprises the steps of performing region prediction on the standard reference image by using a preset region prediction model to obtain a region prediction image, calculating to obtain a loss value based on the number of pixel points in the region prediction image and a preset loss function, outputting the standard region prediction model according to the loss value and the preset loss threshold value, performing region prediction on an image to be recognized according to the standard region prediction model, and improving the efficiency of region prediction in danger. Therefore, the danger area prediction device provided by the invention can solve the problem that the efficiency of the danger area prediction is not high enough.

Fig. 3 is a schematic structural diagram of an electronic device implementing a method for predicting a risk area according to an embodiment of the present invention.

The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a risk area prediction program, stored in the memory 11 and executable on the processor 10.

In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., executing a risk area prediction program, etc.) stored in the memory 11 and calling data stored in the memory 11.

The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of the emergency area prediction program, but also to temporarily store data that has been output or will be output.

The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The risk area prediction program stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, which when executed in the processor 10, can implement:

Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.

Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting an area at risk, the method comprising:

2. The method for predicting the risky area according to claim 1, wherein the performing area prediction on the standard reference map by using a preset area prediction model to obtain an area prediction image comprises:

3. The method for predicting a risky area according to claim 2, wherein the step of inputting the first semantic map and the second compressed map into a second semantic segmentation module in the area prediction model to obtain a second semantic map comprises:

4. The method for predicting the danger area according to claim 1, wherein the calculating the loss value based on the number of the pixel points and a preset loss function comprises:

5. The method for predicting a risky area according to claim 1, wherein before the data fusion of the feature data set and the area reference map, the method further comprises:

6. The method of claim 1, wherein the constructing a feature data set based on the precipitation-related data and the standard venture data comprises:

7. The method for predicting the risk area according to any one of claims 1 to 6, wherein the step of performing data matching on the precipitation-related data by using the risk-related data to obtain standard risk data comprises the following steps:

8. An emergence region prediction apparatus, comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of risk area prediction as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the risk area prediction method according to any one of claims 1 to 7.