Disaster loss prediction method, system and readable storage medium
By creating tasks to be predicted on the client and obtaining disaster data from the server for prediction, the risk of data leakage in the existing technology is solved, and data security and memory space optimization are achieved.
Patent Information
- Application Number
- CN202411830768.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-12
- Publication Date
- 2025-04-04
Smart Images
Figure CN119759986A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a disaster loss prediction method, system and readable storage medium. Background Art
[0002] In order to predict the losses caused by possible disasters, one possible implementation method is that users input the target to be predicted on the cloud platform, and the cloud platform predicts the target and returns the prediction result. However, this implementation method will put the data entered by the user on the Internet, which is prone to data leakage. Therefore, how to ensure the security of data has become a technical problem that needs to be solved at present. Summary of the invention
[0003] In view of the above problems, the purpose of the present invention is to provide a disaster loss prediction method, system and readable storage medium to ensure the security of data. The specific scheme is as follows:
[0004] In a first aspect, an embodiment of the present application provides a disaster loss prediction method, which is applied to a client and includes:
[0005] Create tasks to be predicted;
[0006] Obtaining disaster data of the task to be predicted from the server;
[0007] Based on the disaster data, disaster loss prediction is performed on the task to be predicted to obtain the disaster loss prediction result.
[0008] Optionally, the creating a task to be predicted includes:
[0009] A task to be predicted including at least one target to be predicted is created; the task to be predicted includes location information of each target to be predicted.
[0010] Optionally, the obtaining the disaster data of the task to be predicted from the server includes:
[0011] Extract disaster data of the location information from the server.
[0012] Optionally, performing disaster loss prediction on the task to be predicted based on the disaster data to obtain the disaster loss prediction result includes:
[0013] Dividing the task to be predicted into a plurality of subtasks to be predicted;
[0014] Using multiple computing engines to perform disaster loss prediction on the multiple subtasks to be predicted, and obtaining prediction results of the multiple subtasks to be predicted;
[0015] The prediction results of the multiple subtasks to be predicted are summarized to obtain the disaster loss prediction result.
[0016] Optionally, dividing the task to be predicted into a plurality of subtasks to be predicted includes:
[0017] Obtaining the file sources of each target to be predicted contained in the task to be detected;
[0018] The targets to be predicted with the same file source are divided into the same subtask to be predicted.
[0019] Optionally, the method further includes:
[0020] After obtaining the disaster loss prediction result, the disaster data is deleted.
[0021] In a second aspect, an embodiment of the present application provides a disaster loss prediction system, the system comprising:
[0022] Client, used to create tasks to be predicted;
[0023] The server is used to return the disaster data of the task to be predicted to the client;
[0024] The client is also used to perform disaster loss prediction on the task to be predicted based on the disaster data to obtain the disaster loss prediction result.
[0025] Optionally, the client is specifically used for:
[0026] Dividing the task to be predicted into a plurality of subtasks to be predicted;
[0027] Using multiple computing engines to perform disaster loss prediction on the multiple subtasks to be predicted, and obtaining prediction results of the multiple subtasks to be predicted;
[0028] The prediction results of the multiple subtasks to be predicted are summarized to obtain the disaster loss prediction result.
[0029] Optionally, the client is specifically used for:
[0030] Obtaining the file sources of each target to be predicted contained in the task to be detected;
[0031] The targets to be predicted with the same file source are divided into the same subtask to be predicted.
[0032] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any one of the above-mentioned disaster loss prediction methods.
[0033] Compared with the prior art, this application has the following beneficial effects:
[0034] By creating a task to be predicted, the disaster data of the task to be predicted is obtained from the server. Disaster loss prediction is performed on the task to be predicted based on the disaster data to obtain the disaster loss prediction result. Therefore, disaster loss prediction is performed through the client, so that the client only needs to obtain disaster data from the server, and there is no need to upload the task to be predicted and / or the files involved in the task to be predicted to the server, thereby avoiding data leakage and ensuring data security. In addition, since the client only obtains disaster data related to the task to be predicted from the server, there is no need to store all disaster data in the client, thereby reducing the memory space required by the client for easy migration and deployment. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0036] Figure 1 A schematic diagram of a flow chart of a disaster loss prediction method provided in an embodiment of the present application;
[0037] Figure 2 A schematic diagram of the interaction process between the client and the server provided in the embodiment of the present application;
[0038] Figure 3 A schematic diagram of the structure of a disaster loss prediction system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.
[0040] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0041] The disaster prediction platform includes two deployment methods. One deployment method is to privatize the disaster prediction platform and deploy it to the client. The client extracts the corresponding disaster data from its own database or disk for calculation. However, since the privatized deployment requires all disaster data to be stored locally, the disaster prediction platform takes up a lot of space, and there is a risk of data leakage when the disaster data is stored in the client. Another deployment method is cloud platform deployment. Users need to transfer relevant files to the disaster prediction platform via the Internet, and the disaster prediction platform generates the prediction results. However, since the corresponding files need to be uploaded to the Internet, there is a risk of data leakage. In response to the above problems, the present application provides a disaster loss prediction method, system and readable storage medium, and the specific scheme is as follows.
[0042] like Figure 1 As shown, the present application provides a disaster loss prediction method, which is applied to a client and includes:
[0043] S101: Create a task to be predicted.
[0044] The user creates tasks to be predicted in the client. There can be one or more tasks to be predicted. The creation method can be set based on actual needs, such as filling in a preset template and creating tasks to be predicted based on the filled-in preset template, or importing a file to generate tasks to be predicted.
[0045] To facilitate understanding, the following explanation will be given by taking the example of importing a file to generate a task to be predicted. For example, when the file imported by the user is an insurance policy, the client uses the buildings and / or facilities included in the policy as the target file that the user wants to predict, and creates a task to be predicted about the buildings in the policy.
[0046] It should be noted that the files imported into the client at the same time may be one or more. When only one file is imported, a task to be predicted is created for the file separately. When multiple files are imported at the same time, tasks to be predicted are created for disaster loss prediction for the multiple files.
[0047] In an optional embodiment, creating a task to be predicted includes:
[0048] A task to be predicted is created, which includes at least one target to be predicted; the task to be predicted includes location information of each target to be predicted.
[0049] The target to be predicted is the target for which disaster loss prediction is required, such as buildings or infrastructure within a certain range. The task to be predicted contains the location information of each target to be predicted. The location information is information that can indicate a unique location, such as longitude and latitude, a combination of longitude and latitude, address, etc. The file imported by the user can be a file containing the target to be predicted, such as an insurance policy, document, or scanned copy of the insurance policy.
[0050] For ease of understanding, an example is given below. When the target to be predicted is a certain building A, the location information of the target to be predicted is the longitude and latitude or address of the building, such as (120°30′15″E, 40°25′30″N), where E represents east longitude and N represents north latitude. When the target to be predicted is all the buildings in area B, if area B is a regular shape, the longitude and latitude of each corner are obtained, and the longitude and latitude of each corner are combined as the location information to indicate that the location information of the target to be predicted is the location of all buildings in area B. For example, when area B is a triangle and the vertices are vertex 1, vertex 2 and vertex 3, the location information can be expressed as (the longitude and latitude of vertex 1; the longitude and latitude of vertex 2; the longitude and latitude of vertex 3). If area B is an irregular shape, the location information of the target to be predicted may be the address or longitude and latitude of each building contained in area B.
[0051] Furthermore, the task to be predicted may also include a prediction time period, which is used to indicate the time period corresponding to the disaster loss prediction result, so as to indicate that the disaster loss prediction result to be obtained by the user is the disaster loss situation of the target to be predicted within the prediction time period. For example, when the prediction time period is from 2030 to 2031, the task to be predicted is to predict the disaster loss prediction result of the target to be predicted from 2030 to 2031.
[0052] It should be noted that when the prediction time period is not set in the prediction task, the corresponding disaster loss prediction result can be returned based on actual needs. For example, the loss situation when the next prediction target suffers a disaster is used as the disaster loss prediction result.
[0053] S102: Obtain disaster data for the task to be predicted from the server.
[0054] The server stores multiple disaster data, which are disaster data that may occur in the future based on the prediction analysis of historical disaster data. Disaster data can include disaster type, specific disaster situation and other disaster-related information.
[0055] Specifically, different disaster types correspond to different types of disaster specific conditions. For example, when the disaster is a typhoon, the disaster specific conditions may include typhoon-related information such as wind speed, typhoon level, rainfall, water accumulation, typhoon movement speed, etc. When the disaster is an earthquake, the disaster specific conditions may include earthquake source, earthquake level, aftershock level, etc.
[0056] In an optional embodiment, obtaining disaster data of a task to be predicted from a server includes:
[0057] Extract disaster data determined by location information from the server.
[0058] After creating the task to be predicted, the client sends a disaster data acquisition request to the server based on the location information of each target to be predicted contained in the task to be predicted. The disaster data acquisition request includes the location information of each target to be predicted, so that the disaster data acquisition request can indicate the location corresponding to the disaster data that the client needs to obtain.
[0059] After receiving the disaster data acquisition request, the server searches the local database of the server for the disaster data corresponding to the location indicated by the disaster data acquisition request. If the task to be predicted includes a prediction time period, all disaster data of each target to be predicted within the prediction time period are extracted from the database. The server sends the disaster data determined based on the disaster data acquisition request to the client through the network, so that the client only obtains the disaster data used to calculate the task to be predicted from the server, narrowing the scope of disaster data to be obtained. And because the disaster data is provided by the server, there is no need to store all the disaster data in the client, thereby reducing the memory space required by the client for migration and deployment. And compared to storing all disaster data in the client, the risk of disaster data leakage is smaller.
[0060] Furthermore, in addition to storing disaster data in the database, the server may also set up distributed disks and memory servers. The full amount of catastrophic data is stored through distributed disks. The full amount of catastrophic data is the data of major disasters around the world in history. Since the amount of data of the full amount of catastrophic data is large, this application uses distributed disks for storage to improve storage efficiency and reduce storage costs. The memory server is used to store hotspot disaster data. After receiving a disaster data acquisition request, the server can also determine whether the disaster data to be acquired by the disaster data acquisition request is hotspot disaster data. If it is hotspot disaster data, the hotspot disaster data is extracted from the memory server as the disaster data returned to the client to further improve the efficiency of the server returning disaster data.
[0061] It should be noted that hotspot disaster data refers to disaster data that is obtained at a frequency greater than a preset frequency.
[0062] S103: Perform disaster loss prediction on the task to be predicted based on the disaster data to obtain a disaster loss prediction result.
[0063] Based on the disaster data and the tasks to be predicted, the client calls the local computing engine to calculate the disaster loss prediction and obtain the disaster loss prediction results. Therefore, the disaster loss prediction results are calculated through the client, so that users do not need to upload the tasks to be predicted and the files involved in the tasks to be predicted to the server, avoiding data leakage and ensuring the security of user imported files.
[0064] In an optional embodiment, disaster loss prediction is performed on the task to be predicted based on the disaster data to obtain a disaster loss prediction result, including:
[0065] Divide the task to be predicted into multiple subtasks to be predicted;
[0066] Using multiple computing engines to predict disaster losses for multiple subtasks to be predicted, and obtaining prediction results for multiple subtasks to be predicted;
[0067] The prediction results of multiple subtasks to be predicted are summarized to obtain the disaster loss prediction results.
[0068] Since only one computing engine can be used for calculation when predicting the task to be predicted as a whole, the computing resources of the client cannot be fully utilized. Therefore, in order to improve the computing efficiency of the disaster loss prediction results, this application divides the task to be predicted to obtain multiple sub-tasks to be predicted, so that multiple computing engines can be used for calculation at the same time, thereby improving the utilization of computing resources and the computing efficiency of the disaster loss prediction results.
[0069] Specifically, the present application may divide the task to be predicted in a variety of ways to obtain multiple subtasks to be predicted. For example, each target to be predicted included in the task to be predicted is divided equally according to the number of computing engines, and the targets to be predicted that are evenly divided into the computing engines are used as subtasks to be predicted. For example, when the task to be predicted includes n targets to be predicted and there are m computing engines, the n targets to be predicted are divided into m subtasks to be predicted, and each subtask to be predicted includes n / m targets to be predicted. Alternatively, the subtask to be predicted is determined based on the data characteristics of the target to be predicted. The data characteristics may be data source, data size, data format, and the like.
[0070] Further, taking the determination of the subtask to be predicted based on the data source of the target to be predicted as an example, the task to be predicted is divided into multiple subtasks to be predicted, including:
[0071] Obtain the file sources of each target to be predicted contained in the task to be detected;
[0072] The targets to be predicted with the same file source are divided into the same subtask to be predicted.
[0073] If the user generates a task to be predicted by importing a file, when dividing the task to be predicted, the file where each subtask to be predicted in the task to be detected is located before importing, that is, the file source of each target to be predicted. The subtasks to be predicted that are in the same file before importing are divided into the same subtask to be predicted.
[0074] For example, when the task to be predicted includes target x to be predicted, target y to be predicted, and target z to be predicted, if target x to be predicted and target y to be predicted are in the first policy before importing, and target z to be predicted is in the second policy, then target x to be predicted and target y to be predicted are divided into the first subtask to be predicted, and target z to be predicted is divided into the second subtask to be predicted. Thus, the task to be predicted is reasonably divided into multiple subtasks to be predicted based on the data characteristics, so that multiple subtasks to be predicted can be calculated at the same time, thereby improving the calculation speed.
[0075] In an optional embodiment, after obtaining the disaster loss prediction result, the method further includes:
[0076] Delete disaster data.
[0077] After obtaining the disaster loss prediction result of the task to be predicted, the disaster data obtained by calculating the task to be predicted is deleted in the client, further reducing the memory occupied by the client and avoiding the increase of the memory occupied by the client with the increase of tasks to be predicted, so as to facilitate the migration of the client.
[0078] To facilitate understanding of the method described in this application, an example is given below:
[0079] like Figure 2 As shown in the figure, the client and server are located in the disaster data loss prediction system. The client includes a local disk, a database, a computing engine, and a user service system. The user service system is used to create tasks to be predicted and send disaster data acquisition requests to the server. The local disk is used to store disaster data, and the database is used to divide the tasks to be predicted into multiple subtasks to be predicted. The computing engine is used to calculate each subtask to be predicted and write the output results to the local disk. The local disk summarizes the prediction results of each subtask to be predicted to obtain the disaster loss prediction results.
[0080] The server side includes a catastrophe service system, a database, a distributed disk, and a memory server. The distributed disk is used to store the full amount of catastrophe data, the memory server is used to store hotspot disaster data, and the database is used to store disaster data generated based on the full amount of catastrophe data. When the catastrophe service system receives a request to obtain disaster data, it searches for the disaster data requested by the client from the database or memory server and sends it to the client.
[0081] By creating a task to be predicted, the disaster data of the task to be predicted is obtained from the server. Disaster loss prediction is performed on the task to be predicted based on the disaster data to obtain the disaster loss prediction result. Therefore, disaster loss prediction is performed through the client, so that the client only needs to obtain disaster data from the server, and there is no need to upload the task to be predicted and / or the files involved in the task to be predicted to the server, thereby avoiding data leakage and ensuring data security. In addition, since the client only obtains disaster data related to the task to be predicted from the server, there is no need to store all disaster data in the client, thereby reducing the memory space required by the client for easy migration and deployment.
[0082] like Figure 3 As shown, the embodiment of the present application provides a disaster loss prediction system, the system comprising:
[0083] Client 301, used to create a task to be predicted;
[0084] The server 302 is used to return the disaster data of the task to be predicted to the client 301;
[0085] The client 301 is also used to perform disaster loss prediction for the task to be predicted based on the disaster data to obtain a disaster loss prediction result.
[0086] In an optional embodiment, the client 301 is specifically used for:
[0087] A task to be predicted is created, which includes at least one target to be predicted; the task to be predicted includes location information of each target to be predicted.
[0088] In an optional embodiment, the server 302 is specifically used for:
[0089] The disaster data including the location information is returned to the client 301 .
[0090] In an optional embodiment, the client 301 is specifically used for:
[0091] Divide the task to be predicted into multiple subtasks to be predicted;
[0092] Using multiple computing engines to predict disaster losses for multiple subtasks to be predicted, and obtaining prediction results for multiple subtasks to be predicted;
[0093] The prediction results of multiple subtasks to be predicted are summarized to obtain the disaster loss prediction results.
[0094] In an optional embodiment, the client 301 is specifically used for:
[0095] Obtain the file sources of each target to be predicted contained in the task to be detected;
[0096] The targets to be predicted with the same file source are divided into the same subtask to be predicted.
[0097] In an optional embodiment, the client 301 is further used for:
[0098] After obtaining the disaster loss prediction results, delete the disaster data.
[0099] By creating a task to be predicted, the disaster data of the task to be predicted is obtained from the server. Disaster loss prediction is performed on the task to be predicted based on the disaster data to obtain the disaster loss prediction result. Therefore, disaster loss prediction is performed through the client, so that the client only needs to obtain disaster data from the server, and there is no need to upload the task to be predicted and / or the files involved in the task to be predicted to the server, thereby avoiding data leakage and ensuring data security. In addition, since the client only obtains disaster data related to the task to be predicted from the server, there is no need to store all disaster data in the client, thereby reducing the memory space required by the client for easy migration and deployment.
[0100] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any one of the above-mentioned disaster loss prediction methods.
[0101] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0102] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0103] The technical content provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for general technical personnel in the field, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A disaster loss prediction method, characterized in that: The method is applied to a client, and the method comprises: Create tasks to be predicted; Obtaining disaster data of the task to be predicted from the server; Based on the disaster data, disaster loss prediction is performed on the task to be predicted to obtain the disaster loss prediction result.
2. The method according to claim 1, characterized in that The step of creating a task to be predicted includes: A task to be predicted including at least one target to be predicted is created; the task to be predicted includes location information of each target to be predicted.
3. The method according to claim 2, characterized in that The obtaining of the disaster data of the task to be predicted from the server includes: Extract disaster data of the location information from the server.
4. The method according to claim 1, characterized in that The performing disaster loss prediction on the task to be predicted based on the disaster data to obtain the disaster loss prediction result includes: Dividing the task to be predicted into a plurality of subtasks to be predicted; Using multiple computing engines to perform disaster loss prediction on the multiple subtasks to be predicted, and obtaining prediction results of the multiple subtasks to be predicted; The prediction results of the multiple subtasks to be predicted are summarized to obtain the disaster loss prediction result.
5. The method according to claim 4, characterized in that The step of dividing the task to be predicted into a plurality of subtasks to be predicted includes: Obtaining the file sources of each target to be predicted contained in the task to be detected; The targets to be predicted with the same file source are divided into the same subtask to be predicted.
6. The method according to claim 1, characterized in that The method further comprises: After obtaining the disaster loss prediction result, the disaster data is deleted.
7. A disaster loss prediction system, characterized in that: The system comprises: Client, used to create tasks to be predicted; The server is used to return the disaster data of the task to be predicted to the client; The client is also used to perform disaster loss prediction on the task to be predicted based on the disaster data to obtain the disaster loss prediction result.
8. The system according to claim 7, characterized in that The client is specifically used for: Dividing the task to be predicted into a plurality of subtasks to be predicted; Using multiple computing engines to perform disaster loss prediction on the multiple subtasks to be predicted, and obtaining prediction results of the multiple subtasks to be predicted; The prediction results of the multiple subtasks to be predicted are summarized to obtain the disaster loss prediction result.
9. The system according to claim 8, characterized in that The client is specifically used for: Obtaining the file sources of each target to be predicted contained in the task to be detected; The targets to be predicted with the same file source are divided into the same subtask to be predicted.
10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the disaster loss prediction method according to any one of claims 1 to 6 is implemented.