Claim settlement prediction method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of financial science and technology, is applied to a financial business engineering insurance claim settlement prediction scene, and relates to a claim settlement prediction method, device and equipment and a storage medium thereof. According to the method, the target satellite image corresponding to the latest satellite image of the engineering insurance subject is acquired from the target claim library, then the change area of the latest satellite image relative to the target satellite image is identified, and whether claim application is carried out or not is judged according to the size information and the position information of the change area, so that the claim application can be carried out conveniently when the engineering insurance subject is identified. And assisting the target user terminal to apply for claim settlement according to the weak-texture satellite image.

Description

Technical Field

[0001] The present application relates to the field of financial technology and is applied to claims prediction scenarios of engineering insurance in financial business, and in particular to a claims prediction method, device, equipment and storage medium thereof. Background Art

[0002] With the rapid development of the Internet, all walks of life are relying on the Internet to seek breakthroughs in the industry. In recent years, the financial industry has also been expanding its online business around the Internet, such as claims processing for various types of insurance.

[0003] Feature matching is a prerequisite for image registration, geometric correction, change detection, etc. A large number of engineering hazards are located in wilderness and mountainous areas. The optical satellite images of such areas often do not have rich textures, which makes it very difficult to describe feature points and is not conducive to image registration processing.

[0004] Since a large number of engineering insurance targets lack texture information, it is difficult to construct feature vectors to describe feature points. Therefore, the existing technology of constructing feature vectors using feature points is difficult to use for claim prediction of engineering insurance targets, and it is impossible to combine satellite images of engineering insurance targets for claim prediction. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a claim prediction method, device, equipment and storage medium thereof, so as to solve the problem that the prior art uses feature points to construct feature vectors, which is difficult to use for claim prediction of engineering risk targets and cannot be combined with satellite images of engineering risk targets for claim prediction.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a claim prediction method, which adopts the following technical solution:

[0007] A claims prediction method comprises the following steps:

[0008] Acquire the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject;

[0009] Extracting feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image;

[0010] Matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and filtering out the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result;

[0011] By comparison, the changed area of ​​the latest satellite image compared with the target satellite image is identified, and whether the engineering insurance subject meets the preset claim requirements is determined according to the size information and location information of the changed area;

[0012] If the engineering insurance subject meets the claim requirements, a claim application is sent to a preset claim processing terminal;

[0013] If the engineering insurance subject does not meet the claim settlement requirement, feedback indicating that the claim settlement requirement is not met is sent to the target user terminal based on the terminal identification information of the target user terminal.

[0014] Furthermore, the step of extracting feature points from the latest satellite image using the wide baseline based weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image specifically includes:

[0015] Setting the target extraction quantity of the feature points;

[0016] Extracting the target extraction quantity of feature points from the latest satellite image using a weak texture feature point extraction algorithm based on a wide baseline;

[0017] Adding the target extracted number of feature points to a preset first set;

[0018] Randomly select a point from the first set as the coordinate origin;

[0019] Based on the coordinate origin, determining position information of all feature points in the first set;

[0020] The location information of all feature points is added to a preset second set to obtain the feature point set of the latest satellite image.

[0021] Furthermore, before performing the step of matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and screening out the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result, the method further includes:

[0022] Setting the extraction number of feature points of all satellite images pre-stored in the target claims database to be equal to the target extraction number;

[0023] Using a wide baseline based weak texture feature point extraction algorithm, respectively extracting the target extraction quantity of feature points from all satellite images pre-stored in the target claims database;

[0024] Based on the distinguishing identification information of all satellite images pre-stored in the target claims library, the feature points of all the satellite images are stored respectively, the feature point sets corresponding to all the satellite images are obtained, and the distinguishing identification information is set as the set name of the corresponding feature point set.

[0025] Further, after executing the steps of storing the feature points of all satellite images respectively based on the distinguishing identification information of all satellite images pre-stored in the target claim database, obtaining the feature point sets respectively corresponding to all satellite images, and setting the distinguishing identification information as the set names of the corresponding feature point sets respectively, the method further includes:

[0026] Sequentially acquiring different feature point sets from the feature point sets corresponding to all the satellite images as target feature point sets;

[0027] Randomly select a point from the target feature point set as the coordinate origin;

[0028] Based on the coordinate origin, position information of all feature points in the target feature point set is determined.

[0029] Furthermore, the step of matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and selecting the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result, specifically includes:

[0030] Step 301, obtaining edge lines formed by all the feature points in pairs in the feature point set of the latest satellite image, and generating a first edge line set;

[0031] Step 302, obtaining different feature point sets from the feature point sets corresponding to all the satellite images in sequence according to the distinguishing identification information as the currently selected feature point sets;

[0032] Step 303, obtaining the edge lines formed by all the feature points in pairs in the currently screened feature point set, and generating a second edge line set;

[0033] Step 304, constructing an edge pair matrix according to the first edge set and the second edge set;

[0034] Step 305, based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set, setting the value of each matrix element in the edge pair matrix, wherein the feature information of the edge includes the position information of two feature points constituting the edge and the length information of the edge, if the feature information of the two edges corresponding to the current matrix element meets the preset constraint condition, then the value of the matrix element is set to 1, if the feature information of the two edges corresponding to the current matrix element does not meet the preset constraint condition, then the value of the matrix element is set to 0;

[0035] Step 306, counting the number of matrix elements whose values ​​are 0 in the edge pair matrix by means of statistics;

[0036] Step 307, repeatedly executing steps 302 to 306, obtaining the number of matrix elements that are 0 in the edge pair matrices corresponding to all the satellite images;

[0037] Step 308, sorting the number of matrix elements in the matrix that are 0 in ascending order based on the edge lines corresponding to all satellite images, to obtain a sorting sequence;

[0038] Step 309: Determine the target satellite image corresponding to the latest satellite image in the target claims database according to the set name of the feature point set corresponding to the first quantity value in the sorting sequence.

[0039] Furthermore, the step of setting the value of each matrix element in the edge pair matrix based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set specifically includes:

[0040] Based on the constraints: Set the values ​​of all matrix elements in the edge pair matrix, where A i，j；a，b is the matrix element in the edge pair matrix, i, j represents the edge formed by feature points i and j, a, b represents the edge formed by feature points a and b, d i，j and d a，b is the edge relationship vector of the two edge lines corresponding to the matrix element, and the edge relationship vector is obtained according to the feature information between the edge lines, d i，j and d a，b The smaller the difference, the i，j；a，b The larger the value of , the higher the similarity between the edge line formed by feature points i and j and the edge line formed by feature points a and b. e and σ are constants.

[0041] When A i，j；a，bIf the value of exceeds a preset threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element meets the preset constraint condition, and the value of the matrix element is set to 1;

[0042] When A i，j；a，b If the value of does not exceed the threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element does not meet the preset constraint condition, and the value of the matrix element is set to 0.

[0043] Furthermore, the step of identifying the changed area of ​​the latest satellite image compared with the target satellite image by comparison, and judging whether the engineering insurance subject meets the preset claim requirements according to the size information and location information of the changed area, specifically includes:

[0044] Obtaining edge line pair matrices corresponding to the latest satellite image and the target satellite image;

[0045] Identify edge pairs whose matrix element values ​​in the edge pair matrix are 0 as region constituting edges;

[0046] Generating the change region according to the region forming edge line;

[0047] Determine whether the size information and the position information of the changed area meet the preset claim conditions, wherein the claim conditions include the size information and the position information of the changed area set for claim;

[0048] If the size information and location information of the changed area meet the preset claim conditions, the engineering insurance subject meets the preset claim requirements;

[0049] If any one of the size information and the location information of the changed area does not meet the preset claim conditions, the engineering insurance subject does not meet the preset claim requirements.

[0050] In order to solve the above technical problems, the embodiment of the present application also provides a claim prediction device, which adopts the following technical solution:

[0051] A claims prediction device, comprising:

[0052] A claim application material acquisition module is used to acquire the claim application material uploaded by the target user terminal, wherein the claim application material includes the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject;

[0053] A feature point set extraction module, used to extract feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image;

[0054] A target satellite image screening module is used to match the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim database, and screen out the target satellite image corresponding to the latest satellite image in the target claim database according to the matching result;

[0055] A claim judgment module is used to identify the changed area of ​​the latest satellite image compared with the target satellite image by comparison, and judge whether the engineering insurance subject meets the preset claim requirements according to the size information and location information of the changed area;

[0056] The first branch processing module is used to send a claim application to a preset claim processing terminal if the engineering insurance subject meets the claim requirements;

[0057] The second branch processing module is used to send feedback that the claim settlement requirement has not been met to the target user terminal based on the terminal identification information of the target user terminal if the engineering insurance subject has not met the claim settlement requirement.

[0058] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0059] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned claim prediction method when executing the computer-readable instructions.

[0060] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of the claim prediction method as described above.

[0062] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0063] The claim prediction method described in the embodiment of the present application obtains the claim declaration materials uploaded by the target user terminal, wherein the claim declaration materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk target; extracts the feature points in the latest satellite image based on the wide baseline weak texture feature point extraction algorithm to obtain the feature point set of the latest satellite image; matches the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and selects the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifies the change area of ​​the latest satellite image compared with the target satellite image by comparison, and judges whether the engineering risk target meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk target meets the claim requirements, sends the claim application to the preset claim processing terminal; if the engineering risk target does not meet the claim requirements, sends feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0066] Figure 2 is a flow chart of an embodiment of a method for claim prediction according to the present application;

[0067] Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0068] Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 204 is shown;

[0069] Figure 5is a schematic structural diagram of an embodiment of a claim prediction device according to the present application;

[0070] Figure 6 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0072] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0073] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0074] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0075] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0076] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0077] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0078] It should be noted that the claim prediction method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the claim prediction device is generally set in the server / terminal device.

[0079] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0080] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for claim prediction according to the present application. The method for claim prediction comprises the following steps:

[0081] Step 201, obtaining the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject.

[0082] In this embodiment, the target user terminal is a terminal operated by a user applying for a claim, the claim declaration materials refer to the materials required for a claim, and the weak-texture geographical area indicates that there are no obvious landmarks in the geographical area, such as a large area of ​​barren mountain slopes.

[0083] Step 202: extract feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image.

[0084] In this embodiment, the step of extracting feature points from the latest satellite image using the wide baseline weak texture feature point extraction algorithm to obtain the feature point set of the latest satellite image specifically includes: setting a target extraction number of feature points; extracting the target extraction number of feature points from the latest satellite image using the wide baseline weak texture feature point extraction algorithm; adding the target extraction number of feature points to a preset first set; arbitrarily selecting a point from the first set as a coordinate origin; based on the coordinate origin, determining the position information of all feature points in the first set; adding the position information of all feature points to a preset second set to obtain the feature point set of the latest satellite image.

[0085] By setting the target extraction number of the feature points, a weak texture feature point extraction algorithm based on a wide baseline is used to extract the target extraction number of feature points from the latest satellite image, so as to ensure that the number of extracted feature points is the same.

[0086] Step 203, matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and filtering out the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result.

[0087] In this embodiment, before executing the step of matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and screening out the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result, the method also includes: setting the number of extracted feature points of all satellite images pre-stored in the target claim library to be equal to the target extraction number; using a weak texture feature point extraction algorithm based on a wide baseline to extract the target extraction number of feature points from all satellite images pre-stored in the target claim library; based on the distinguishing identification information of all satellite images pre-stored in the target claim library, storing the feature points of all satellite images respectively, obtaining the feature point sets corresponding to all satellite images respectively, and setting the distinguishing identification information as the set name of the corresponding feature point set respectively.

[0088] By setting the extraction number of feature points of all satellite images pre-stored in the target claim library to be equal to the target extraction number, it is convenient for the edge line formed by the latest satellite image and the edge line formed by all satellite images pre-stored in the target claim library to have the same number of lines when constructing edge line pairs. The distinguishing identification information is respectively set as the set name of the corresponding feature point set, so as to facilitate the identification of the satellite image corresponding to each feature point set.

[0089] In this embodiment, after executing the steps of storing the feature points of all satellite images respectively based on the distinguishing identification information of all satellite images pre-stored in the target claims database, obtaining the feature point sets corresponding to all the satellite images respectively, and setting the distinguishing identification information as the set names of the corresponding feature point sets respectively, the method also includes: sequentially acquiring different feature point sets from the feature point sets corresponding to all the satellite images as target feature point sets; arbitrarily selecting a point from the target feature point set as a coordinate origin; and determining the position information of all feature points in the target feature point set based on the coordinate origin.

[0090] Continue to refer Figure 3 , Figure 3 yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes:

[0091] Step 301, obtaining edge lines formed by all the feature points in pairs in the feature point set of the latest satellite image, and generating a first edge line set;

[0092] Step 302, obtaining different feature point sets from the feature point sets corresponding to all the satellite images in sequence according to the distinguishing identification information as the currently selected feature point sets;

[0093] Step 303, obtaining the edge lines formed by all the feature points in pairs in the currently screened feature point set, and generating a second edge line set;

[0094] Step 304, constructing an edge pair matrix according to the first edge set and the second edge set;

[0095] Step 305, based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set, setting the value of each matrix element in the edge pair matrix, wherein the feature information of the edge includes the position information of two feature points constituting the edge and the length information of the edge, if the feature information of the two edges corresponding to the current matrix element meets the preset constraint condition, then the value of the matrix element is set to 1, if the feature information of the two edges corresponding to the current matrix element does not meet the preset constraint condition, then the value of the matrix element is set to 0;

[0096] In this embodiment, the step of setting the value of each matrix element in the edge pair matrix based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set specifically includes: based on the constraint condition: Set the values ​​of all matrix elements in the edge pair matrix, where A i，j；a，bis the matrix element in the edge pair matrix, i, j represents the edge formed by feature points i and j, a, b represents the edge formed by feature points a and b, d i，j and d a，b is the edge relationship vector of the two edge lines corresponding to the matrix element, and the edge relationship vector is obtained according to the feature information between the edge lines, d i，j and d a，b The smaller the difference, the i，j；a，b The larger the value of is, the higher the similarity between the edge line formed by feature points i and j and the edge line formed by feature points a and b is, and e and σ are constants; when A i，j；a，b If the value of exceeds the preset threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element meets the preset constraint condition, and the value of the matrix element is set to 1; when A i，j；a，b If the value of does not exceed the threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element does not meet the preset constraint condition, and the value of the matrix element is set to 0.

[0097] By constructing an edge pair matrix and setting constraints, it is convenient to quickly identify the similarity between each pair of edge feature information, and set matrix element values ​​for matrix elements in the edge pair matrix according to the similarity between each pair of edge feature information.

[0098] Specifically, for example: the feature point set of the latest satellite image contains 5 feature points, and the currently screened feature point set also contains 5 feature points. Then, there are 10 edge lines formed by all the feature points in the feature point set of the latest satellite image that are combined in pairs, which are assumed to be the edge lines of the detection image. Similarly, there are also 10 edge lines formed by all the feature points in the currently screened feature point set that are combined in pairs, which are assumed to be the edge lines of the comparison image. The edge line pair matrix is ​​a 10*10 matrix, and each edge line pair is composed of an edge line of the detection image and an edge line of the comparison image.

[0099] Step 306, counting the number of matrix elements whose values ​​are 0 in the edge pair matrix by means of statistics;

[0100] Step 307, repeatedly executing steps 302 to 306, obtaining the number of matrix elements that are 0 in the edge pair matrices corresponding to all the satellite images;

[0101] Step 308, sorting the number of matrix elements in the matrix that are 0 in ascending order based on the edge lines corresponding to all satellite images, to obtain a sorting sequence;

[0102] Step 309: Determine the target satellite image corresponding to the latest satellite image in the target claims database according to the set name of the feature point set corresponding to the first quantity value in the sorting sequence.

[0103] By using edge pairs instead of point pairs, the target satellite image corresponding to the latest satellite image in the target claims database is screened out, avoiding the disadvantage that point pairs cannot compare weak textures. The edge pairs are directly used to compare weak textures, thereby identifying the target satellite image corresponding to the latest satellite image in the target claims database.

[0104] Step 204, by comparing, identifying the changed area of ​​the latest satellite image compared to the target satellite image, and judging whether the engineering insurance subject meets the preset claim requirements according to the size information and location information of the changed area.

[0105] Continue to refer Figure 4 , Figure 4 yes Figure 2 The flowchart of a specific embodiment of step 204 shown includes:

[0106] Step 401, obtaining edge line pair matrices corresponding to the latest satellite image and the target satellite image;

[0107] Step 402, identifying edge pairs whose matrix element values ​​in the edge pair matrix are 0 as region constituting edges;

[0108] Step 403, generating the change region according to the region forming edge line;

[0109] Step 404, determining whether the size information and the position information of the changed area meet the preset claim conditions, wherein the claim conditions include the size information and the position information of the changed area set for claim;

[0110] Step 405: If the size information and the location information of the changed area both meet the preset claim settlement conditions, the engineering insurance subject meets the preset claim settlement requirements;

[0111] Step 406: If any one of the size information and the location information of the changed area does not meet the preset claim conditions, the engineering insurance subject does not meet the preset claim requirements.

[0112] Step 205: If the engineering insurance subject meets the claim requirements, a claim application is sent to a preset claim processing terminal.

[0113] Step 206: If the engineering insurance subject does not meet the claim settlement requirement, a feedback indicating that the claim settlement requirement has not been met is sent to the target user terminal based on the terminal identification information of the target user terminal.

[0114] The present application obtains the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk subject; extracts the feature points in the latest satellite image based on the weak texture feature point extraction algorithm with a wide baseline to obtain the feature point set of the latest satellite image; matches the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and selects the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifies the change area of ​​the latest satellite image compared with the target satellite image by comparison, and determines whether the engineering risk subject meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk subject meets the claim requirements, sends the claim application to the preset claim processing terminal; if the engineering risk subject does not meet the claim requirements, sends feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images.

[0115] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0116] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, large claims prediction technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0117] In an embodiment of the present application, by acquiring the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk subject; extracting the feature points in the latest satellite image based on the wide baseline weak texture feature point extraction algorithm to obtain the feature point set of the latest satellite image; matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and screening out the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifying the change area of ​​the latest satellite image compared with the target satellite image by comparison, and judging whether the engineering risk subject meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk subject meets the claim requirements, sending the claim application to the preset claim processing terminal; if the engineering risk subject does not meet the claim requirements, sending feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images.

[0118] Further references Figure 5 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a claim prediction device, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0119] like Figure 5 As shown, the claim prediction device 500 described in this embodiment includes: a claim declaration material acquisition module 501, a feature point set extraction module 502, a target satellite image screening module 503, a claim judgment module 504, a first branch processing module 505 and a second branch processing module 506. Among them:

[0120] The claim application material acquisition module 501 is used to acquire the claim application material uploaded by the target user terminal, wherein the claim application material includes the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject;

[0121] A feature point set extraction module 502 is used to extract feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image;

[0122] The target satellite image screening module 503 is used to match the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim database, and screen out the target satellite image corresponding to the latest satellite image in the target claim database according to the matching result;

[0123] The claim judgment module 504 is used to identify the changed area of ​​the latest satellite image compared with the target satellite image by comparison, and judge whether the engineering insurance subject meets the preset claim requirements according to the size information and location information of the changed area;

[0124] The first branch processing module 505 is used to send a claim application to a preset claim processing terminal if the engineering insurance subject meets the claim requirements;

[0125] The second branch processing module 506 is used to send feedback that the claim settlement requirement has not been met to the target user terminal based on the terminal identification information of the target user terminal if the engineering insurance subject has not met the claim settlement requirement.

[0126] The present application obtains the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk subject; extracts the feature points in the latest satellite image based on the weak texture feature point extraction algorithm with a wide baseline to obtain the feature point set of the latest satellite image; matches the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and selects the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifies the change area of ​​the latest satellite image compared with the target satellite image by comparison, and determines whether the engineering risk subject meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk subject meets the claim requirements, sends the claim application to the preset claim processing terminal; if the engineering risk subject does not meet the claim requirements, sends feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images.

[0127] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0128] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0129] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0130] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 6a-6c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0131] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0132] The memory 6a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 6a can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 6a can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 6a can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 6a is generally used to store the operating system and various application software installed on the computer device 6, such as a computer-readable instruction of a claim prediction method, etc. In addition, the memory 6a can also be used to temporarily store various types of data that have been output or are to be output.

[0133] The processor 6b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other claims prediction chips in some embodiments. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to run computer-readable instructions or process data stored in the memory 6a, such as computer-readable instructions for running the claims prediction method.

[0134] The network interface 6c may include a wireless network interface or a wired network interface. The network interface 6c is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0135] The computer device proposed in this embodiment belongs to the field of financial technology and is applied in the claim prediction scenario of engineering insurance in financial business. The present application obtains the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk subject; extracts the feature points in the latest satellite image based on the weak texture feature point extraction algorithm with a wide baseline to obtain the feature point set of the latest satellite image; matches the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and selects the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifies the change area of ​​the latest satellite image compared with the target satellite image by comparison, and determines whether the engineering risk subject meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk subject meets the claim requirements, sends the claim application to the preset claim processing terminal; if the engineering risk subject does not meet the claim requirements, sends feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images.

[0136] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the claim prediction method as described above.

[0137] The computer-readable storage medium proposed in this embodiment belongs to the field of financial technology and is applied in the claim prediction scenario of engineering insurance in financial business. The present application obtains the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering risk subject; extracts the feature points in the latest satellite image based on the weak texture feature point extraction algorithm with a wide baseline to obtain the feature point set of the latest satellite image; matches the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim library, and selects the target satellite image corresponding to the latest satellite image in the target claim library according to the matching result; identifies the change area of ​​the latest satellite image compared with the target satellite image by comparison, and determines whether the engineering risk subject meets the preset claim requirements according to the size information and position information of the change area; if the engineering risk subject meets the claim requirements, sends the claim application to the preset claim processing terminal; if the engineering risk subject does not meet the claim requirements, sends feedback that the claim requirements are not met to the target user terminal based on the terminal identification information of the target user terminal. By comparing feature points, the target satellite image corresponding to the latest satellite image is first obtained from the target claim database, and then the changed area of ​​the latest satellite image compared to the target satellite image is identified, and whether to apply for a claim is determined based on the size information and position information of the changed area. This facilitates the identification of engineering insurance targets and assists the target user terminal in applying for a claim based on weak-textured satellite images.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0139] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for claim prediction, characterized in that: The steps include: Acquire the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject; Extracting feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image; Matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and filtering out the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result; By comparison, the changed area of ​​the latest satellite image compared with the target satellite image is identified, and whether the engineering insurance subject meets the preset claim requirements is determined according to the size information and location information of the changed area; If the engineering insurance subject meets the claim requirements, a claim application is sent to a preset claim processing terminal; If the engineering insurance subject does not meet the claim settlement requirement, feedback indicating that the claim settlement requirement is not met is sent to the target user terminal based on the terminal identification information of the target user terminal.

2. The claim prediction method according to claim 1, characterized in that: The step of extracting feature points from the latest satellite image using the wide baseline based weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image specifically includes: Setting the target extraction quantity of the feature points; Extracting the target extraction quantity of feature points from the latest satellite image using a weak texture feature point extraction algorithm based on a wide baseline; Adding the target extracted number of feature points to a preset first set; Randomly select a point from the first set as the coordinate origin; Based on the coordinate origin, determining position information of all feature points in the first set; The location information of all feature points is added to a preset second set to obtain the feature point set of the latest satellite image.

3. The claim prediction method according to claim 2, characterized in that: Before performing the step of matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and screening out the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result, the method further includes: Setting the extraction number of feature points of all satellite images pre-stored in the target claims database to be equal to the target extraction number; Using a wide baseline based weak texture feature point extraction algorithm, respectively extracting the target extraction quantity of feature points from all satellite images pre-stored in the target claims database; Based on the distinguishing identification information of all satellite images pre-stored in the target claims library, the feature points of all the satellite images are stored respectively, the feature point sets corresponding to all the satellite images are obtained, and the distinguishing identification information is set as the set name of the corresponding feature point set.

4. The claim prediction method according to claim 3, characterized in that: After executing the steps of storing the feature points of all satellite images respectively based on the distinguishing identification information of all satellite images pre-stored in the target claim database, obtaining the feature point sets respectively corresponding to all satellite images, and setting the distinguishing identification information as the set names of the corresponding feature point sets respectively, the method further includes: Sequentially acquiring different feature point sets from the feature point sets corresponding to all the satellite images as target feature point sets; Randomly select a point from the target feature point set as the coordinate origin; Based on the coordinate origin, position information of all feature points in the target feature point set is determined.

5. The claim prediction method according to claim 3, characterized in that: The step of matching the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claims database, and selecting the target satellite image corresponding to the latest satellite image in the target claims database according to the matching result, specifically includes: Step 301, obtaining edge lines formed by all the feature points in pairs in the feature point set of the latest satellite image, and generating a first edge line set; Step 302, obtaining different feature point sets from the feature point sets corresponding to all the satellite images in sequence according to the distinguishing identification information as the currently selected feature point sets; Step 303, obtaining the edge lines formed by all the feature points in pairs in the currently screened feature point set, and generating a second edge line set; Step 304, constructing an edge pair matrix according to the first edge set and the second edge set; Step 305, based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set, setting the value of each matrix element in the edge pair matrix, wherein the feature information of the edge includes the position information of two feature points constituting the edge and the length information of the edge, if the feature information of the two edges corresponding to the current matrix element meets the preset constraint condition, then the value of the matrix element is set to 1, if the feature information of the two edges corresponding to the current matrix element does not meet the preset constraint condition, then the value of the matrix element is set to 0; Step 306, counting the number of matrix elements whose values ​​are 0 in the edge pair matrix by means of statistics; Step 307, repeatedly executing steps 302 to 306, obtaining the number of matrix elements that are 0 in the edge pair matrices corresponding to all the satellite images; Step 308, sorting the number of matrix elements in the matrix that are 0 in ascending order based on the edge lines corresponding to all satellite images, to obtain a sorting sequence; Step 309: Determine the target satellite image corresponding to the latest satellite image in the target claims database according to the set name of the feature point set corresponding to the first quantity value in the sorting sequence.

6. The claim prediction method according to claim 5, characterized in that: The step of setting the value of each matrix element in the edge pair matrix based on the feature information of each edge in the first edge set and the feature information of each edge in the second edge set specifically includes: Based on the constraints: Set the values ​​of all matrix elements in the edge pair matrix, where A i,；, is the matrix element in the edge pair matrix, i,j represents the edge formed by feature points i and j, a,b represents the edge formed by feature points a and b, d i,j and d a,b is the edge relationship vector of the two edge lines corresponding to the matrix element, and the edge relationship vector is obtained according to the feature information between the edge lines, d i,j and d a,b The smaller the difference, the i,；, The larger the value of , the higher the similarity between the edge line formed by feature points i and j and the edge line formed by feature points a and b. e and σ are constants. When A i,；, If the value of exceeds a preset threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element meets the preset constraint condition, and the value of the matrix element is set to 1; When A i,；, If the value of does not exceed the threshold, it is determined that the feature information of the two edge lines corresponding to the current matrix element does not meet the preset constraint condition, and the value of the matrix element is set to 0.

7. The claim prediction method according to claim 5, characterized in that: The step of identifying the changed area of ​​the latest satellite image compared with the target satellite image by comparison, and judging whether the engineering insurance subject meets the preset claim requirements according to the size information and position information of the changed area, specifically includes: Obtaining edge line pair matrices corresponding to the latest satellite image and the target satellite image; Identify edge pairs whose matrix element values ​​in the edge pair matrix are 0 as region constituting edges; Generating the change region according to the region forming edge line; Determine whether the size information and the position information of the changed area meet the preset claim conditions, wherein the claim conditions include the size information and the position information of the changed area set for claim; If the size information and location information of the changed area meet the preset claim conditions, the engineering insurance subject meets the preset claim requirements; If any one of the size information and the location information of the changed area does not meet the preset claim conditions, the engineering insurance subject does not meet the preset claim requirements.

8. A claim prediction device, characterized in that: include: A claim application material acquisition module is used to acquire the claim application materials uploaded by the target user terminal, wherein the claim application materials include the latest satellite image of the target geographical area and the terminal identification information of the target user terminal, wherein the target geographical area is the weak texture geographical area corresponding to the engineering insurance subject; A feature point set extraction module, used to extract feature points in the latest satellite image based on a wide baseline weak texture feature point extraction algorithm to obtain a feature point set of the latest satellite image; A target satellite image screening module is used to match the feature point set of the latest satellite image with the feature point sets of all satellite images pre-stored in the target claim database, and screen out the target satellite image corresponding to the latest satellite image in the target claim database according to the matching result; A claim judgment module is used to identify the changed area of ​​the latest satellite image compared with the target satellite image by comparison, and judge whether the engineering insurance subject meets the preset claim requirements according to the size information and location information of the changed area; The first branch processing module is used to send a claim application to a preset claim processing terminal if the engineering insurance subject meets the claim requirements; The second branch processing module is used to send feedback that the claim settlement requirement has not been met to the target user terminal based on the terminal identification information of the target user terminal if the engineering insurance subject has not met the claim settlement requirement.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the claim prediction method as described in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the claim prediction method according to any one of claims 1 to 7.

Images