Repeated compensation prevention method and device in large livestock claim settlement, equipment and medium

Abstract

The invention relates to a data verification technology, and discloses a method for preventing repeated claim payment in large livestock claim settlement, which comprises the following steps: acquiring a livestock death image in claim payment request data; extracting claim livestock biological characteristics of the livestock according to the livestock death image, acquiring historical claim livestock biological characteristic data from a pre-established biological characteristic database, and performing layered comparison on the claim livestock biological characteristics according to the historical claim livestock biological characteristic data to obtain comparison result data, according to the comparison result data, whether the compensation request has a repeated compensation behavior or not is judged, if the compensation request has the repeated compensation behavior, early warning information is sent out, and if not, the compensation request is passed, and the biological characteristics of the compensation livestock are stored in the biological characteristic database. The invention further provides a repeated compensation prevention device in large livestock claim settlement, electronic equipment and a storage medium. According to the invention, the efficiency of repeated compensation prevention verification of large livestock can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data verification, and in particular to a method, device, equipment and medium for preventing duplicate payment in large livestock claims. Background Art

[0002] In the process of large-scale livestock insurance claims, due to the lack of effective livestock identity verification methods, the same dead livestock is often reused, resulting in multiple insurance payments. This phenomenon not only damages the interests of insurance companies, but also affects the healthy development of the insurance industry. Therefore, there is an urgent need for an effective method to prevent the problem of duplicate payments in large-scale livestock claims. The present invention extracts multiple types of biometric information and combines hierarchical feature retrieval technology to accurately compare and check for duplicate biometric identities.

[0003] Existing methods of livestock identity verification usually rely on manual comparison of photographs of deceased livestock, which is extremely inefficient and costly. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for preventing duplicate payment in large livestock claims, the main purpose of which is to solve the problem of high efficiency and low cost of the existing method for preventing duplicate payment of large livestock.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for preventing duplicate payment in large livestock claims, comprising:

[0006] Access livestock mortality images from claim data;

[0007] extracting livestock biometric features of the livestock for compensation based on the livestock death image;

[0008] Obtaining historical claim livestock biometric data from a pre-established biometric database;

[0009] Performing a hierarchical comparison of the biometric characteristics of the livestock to be compensated according to the biometric characteristic data of the livestock to be compensated historically, to obtain comparison result data;

[0010] Determine whether there is duplicate payment behavior in this compensation request based on the comparison result data;

[0011] If there is duplicate payment in this claim request, a warning message will be issued;

[0012] If there is no duplicate payment in this compensation, the compensation request will be approved and the biometric characteristics of the compensated livestock will be stored in the biometric database.

[0013] Optionally, the step of extracting the livestock biometric features of the livestock for compensation according to the livestock death image includes:

[0014] Extracting appearance features of livestock based on the livestock death image;

[0015] Extracting the body shape features of the livestock according to the livestock death image;

[0016] The posture features of the livestock are extracted based on the livestock death image.

[0017] The appearance features, the body shape features and the posture features are aggregated into the compensation livestock biological features of the livestock.

[0018] Optionally, extracting the appearance features of the livestock according to the livestock death image includes:

[0019] Using an edge detection algorithm to identify the main area of ​​the livestock in the livestock death image to obtain main features;

[0020] Using a gray level co-occurrence matrix to identify the texture features of the livestock in the livestock death image;

[0021] The main features and the texture features are integrated to obtain the appearance features.

[0022] Optionally, the step of extracting the body shape features of the livestock according to the livestock death image includes:

[0023] Removing the non-subject area in the livestock death image to obtain a subject image;

[0024] Extracting convolution features of the subject image;

[0025] Extracting color features of the subject image;

[0026] The convolution feature and the color feature are fused to obtain the body shape feature.

[0027] Optionally, extracting the posture features of the livestock according to the livestock death image includes:

[0028] identifying key points of livestock in the livestock death image;

[0029] Draw connecting lines according to the key points;

[0030] Constructing a topological space according to the key points and the connecting lines;

[0031] Analyzing the topological properties of the topological space;

[0032] The posture features of the livestock are extracted according to the topological properties.

[0033] Optionally, the biometric characteristics of the livestock to be compensated are compared in layers according to the biometric characteristics data of the livestock to be compensated in history to obtain comparison result data, including:

[0034] Performing a first-level comparison based on the appearance features in the biometric features of the compensated livestock and the biometric feature data of the historical compensated livestock to obtain first-level comparison result data;

[0035] Screening the biometric characteristic data of the historically compensated livestock according to the first layer comparison result data to obtain screening biometric characteristics;

[0036] Calculate the cosine similarity between the body shape feature and the posture feature in the biological features of the compensation livestock and each corresponding feature of the screening biological features to obtain a body shape feature similarity set and a posture feature similarity set;

[0037] Adding the body shape feature similarity set and the posture feature similarity set according to a preset weight to obtain a cosine similarity set;

[0038] The comparison result data is confirmed according to whether there is a cosine similarity value greater than a preset similarity threshold in the cosine similarity set.

[0039] Optionally, judging whether there is repeated payment behavior in the current payment request according to the comparison result data includes:

[0040] Determine whether the comparison result data is a null value;

[0041] If the comparison result data is a null value, it is determined that there is no duplicate payment behavior in this compensation request;

[0042] If the comparison result data is not a null value, it is determined that there is duplicate payment behavior in this compensation request.

[0043] In order to solve the above problems, the present invention also provides a device for preventing duplicate payment in large livestock claims, the device comprising:

[0044] A feature extraction module, used to obtain a livestock death image in the compensation request data, and extract the compensation livestock biological features of the livestock according to the livestock death image;

[0045] A hierarchical comparison module is used to obtain biometric data of historically compensated livestock from a pre-established biometric database, and to perform hierarchical comparison on the biometrics of the compensated livestock according to the biometric data of the historically compensated livestock to obtain comparison result data;

[0046] A duplicate payment warning module is used to determine whether there is a duplicate payment behavior in the current payment request based on the comparison result data, and if there is a duplicate payment behavior in the current payment request, a warning message is issued;

[0047] The data updating module is used to determine whether there is any duplicate payment behavior in this compensation request based on the comparison result data. If there is no duplicate payment behavior in this compensation request, the compensation request is approved and the biometric characteristics of the compensated livestock are stored in the biometric characteristic database.

[0048] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0049] at least one processor;

[0050] and, a memory communicatively coupled to the at least one processor;

[0051] Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method for preventing duplicate payment in large livestock claims.

[0052] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned method for preventing duplicate payments in large livestock claims.

[0053] The embodiment of the present invention obtains the livestock death image in the compensation request data; extracts the compensation livestock biometrics of the livestock according to the livestock death image, obtains the historical compensation livestock biometrics data from the pre-established biometrics database, and performs a hierarchical comparison on the compensation livestock biometrics according to the historical compensation livestock biometrics data to obtain the comparison result data, and determines whether there is a duplicate compensation behavior in the current compensation request according to the comparison result data. If there is a duplicate compensation behavior in the current compensation request, an early warning message is issued; if there is no duplicate compensation behavior in the current compensation, the current compensation request is approved, and the compensation livestock biometrics are stored in the biometrics database. Therefore, the anti-duplicate compensation method, device, electronic device and computer-readable storage medium in large livestock claims proposed by the present invention can solve the problem of high efficiency and low cost of the existing large livestock anti-duplicate compensation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a flow chart of a method for preventing duplicate payment in large livestock claims provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a process for extracting biological characteristics of livestock for compensation provided by an embodiment of the present invention;

[0056] Figure 3A schematic diagram of a process for extracting posture features of livestock provided by an embodiment of the present invention;

[0057] Figure 4 A functional module diagram of a device for preventing duplicate payment in large livestock claims provided by an embodiment of the present invention;

[0058] Figure 5 A schematic diagram of the structure of an electronic device for implementing the method for preventing duplicate payment in large livestock claims provided by one embodiment of the present invention.

[0059] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0061] The embodiment of the present application provides a method for preventing duplicate payments in large livestock claims. The execution subject of the method for preventing duplicate payments in large livestock claims includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for preventing duplicate payments in large livestock claims can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0062] Reference Figure 1 FIG. 1 is a flow chart of a method for preventing duplicate payments in large livestock claims provided by an embodiment of the present invention. In this embodiment, the method for preventing duplicate payments in large livestock claims includes:

[0063] S1. Obtain livestock death images in the claim request data.

[0064] In the embodiment of the present invention, the claim request data is a request sent by a user through a pre-established claim settlement system, and the claim request data is obtained from a service end of the claim settlement system.

[0065] In detail, the claim request data generally includes personal information of the user applying for claim settlement and voucher data (livestock death image, etc.) for applying for claim settlement.

[0066] In detail, the claims system is designed to improve the efficiency and accuracy of insurance claims for large livestock (such as horses, mules, donkeys, cattle, pigs, etc.). This system usually combines modern scientific and technological means, such as the Internet of Things, artificial intelligence, big data, etc., to achieve full process automation and intelligence from reporting, investigation, damage assessment to payment. It is a comprehensive management platform that aims to simplify the claims process, improve claims efficiency, reduce claims costs, and enhance the fairness and transparency of claims. The system realizes comprehensive recording, real-time monitoring and intelligent analysis of livestock insurance information through digital means.

[0067] In detail, livestock breeders or related personnel can access the claims system through mobile phones to report cases and upload report information, which usually includes livestock types, causes of livestock death, loss conditions and other information.

[0068] In the embodiment of the present invention, the livestock death image is an image uploaded to the claim system server when the user sends a claim request. The livestock death image generally includes an overall photo, a single photo, a photo before and after ear cutting, and a photo before and after harmlessness.

[0069] In the embodiment of the present invention, by acquiring the livestock death image in the compensation request data, the efficiency of extracting the compensation livestock biometric features of the livestock death image is improved.

[0070] S2. Extracting the compensation livestock biological characteristics of the livestock according to the livestock death image.

[0071] In the embodiment of the present invention, the extraction of livestock compensation livestock biological features based on the livestock death image is based on an image recognition algorithm to extract livestock appearance features, body shape features and posture features.

[0072] In detail, the biometric characteristic of the livestock to be compensated is a characteristic data used to identify the identity information of the dead livestock.

[0073] In the embodiment of the present invention, refer to Figure 2 As shown, a schematic diagram of a process of extracting livestock compensation livestock biometric features according to an embodiment of the present invention is provided, wherein the process of extracting livestock compensation livestock biometric features according to the livestock death image includes:

[0074] S21, extracting appearance features of livestock according to the livestock death image;

[0075] S22, extracting the body shape features of the livestock according to the livestock death image;

[0076] S23, extracting posture features of the livestock according to the livestock death image.

[0077] S24, summarizing the appearance features, the body shape features and the posture features as the compensation livestock biological features of the livestock.

[0078] In detail, the appearance feature is obtained by identifying the main body area of ​​the livestock in the livestock death image and extracting the shallow features of the main body area. The body shape feature is obtained by identifying the deep features of the main body area. The posture feature is a feature obtained by identifying the key points of the livestock in the livestock death image.

[0079] In detail, the posture feature is a deep feature that pays more attention to the death posture of live pigs. Since the death posture of livestock is usually difficult to change after death, it is possible to determine whether it is a duplicate claim by comparing the death posture.

[0080] In the embodiment of the present invention, the step of extracting the appearance features of the livestock according to the livestock death image includes:

[0081] Using an edge detection algorithm to identify the main area of ​​the livestock in the livestock death image to obtain main features;

[0082] Using a gray level co-occurrence matrix to identify the texture features of the livestock in the livestock death image;

[0083] The main features and the texture features are integrated to obtain the appearance features.

[0084] In detail, the edge detection algorithm is an important technology in image processing, which is mainly used to extract the outline of objects or boundaries in images for further analysis and processing. These algorithms detect edges by calculating the change in the grayscale value of pixels in the image. When there is an edge in the image, the grayscale values ​​of adjacent pixels will change suddenly.

[0085] In detail, the grayscale co-occurrence matrix is ​​a statistical tool for image processing, which reflects the texture characteristics of an image by calculating the joint probability distribution of pixel pairs in the image. Specifically, the grayscale co-occurrence matrix defines the probability of a grayscale value j at a point leaving a fixed position starting from a pixel with a grayscale of i, that is, all estimated values ​​can be expressed in the form of a matrix. The grayscale co-occurrence matrix can reflect information such as the direction, interval, and amplitude of change of the image texture. For example, an image with a slowly changing texture will have a larger value on the diagonal of the grayscale co-occurrence matrix; while an image with a fast changing texture will have a smaller value on the diagonal, and larger values ​​on both sides of the diagonal. Due to the large amount of data in the grayscale co-occurrence matrix, it is usually not used directly as a feature for texture distinction, but some statistics constructed based on it are used as texture classification features.

[0086] In the embodiment of the present invention, the step of extracting the body shape features of the livestock according to the livestock death image includes:

[0087] Removing the non-subject area in the livestock death image to obtain a subject image;

[0088] Extracting convolution features of the subject image;

[0089] Extracting color features of the subject image;

[0090] The convolution feature and the color feature are fused to obtain the body shape feature.

[0091] In the embodiment of the present invention, the convolution feature slides on the input image according to a certain step length through the convolution kernel in the convolution layer of the convolutional neural network, and each slide covers a local area of ​​the input image. At each sliding position, the convolution kernel performs element-wise multiplication with the corresponding local area of ​​the input image, and then all products are summed to obtain an element of the output feature map. The convolution kernel is a small matrix whose elements are weights, which is used to extract specific features of the image.

[0092] In detail, the convolutional feature extraction process is a key step in image processing and analysis in the field of deep learning, and it is implemented using the convolutional layer, a core component of the convolutional neural network (CNN). The convolutional layer performs a sliding window operation on the input image using a convolution kernel (also called a filter) to identify and extract local features in the image. The convolution kernel is a small matrix whose internal elements are learnable weights, which are adjusted by the back-propagation algorithm during the training process to maximize the performance of the network for a specific task. The convolution kernel acts like an adjustable template in image processing, which can find and emphasize specific patterns or features in the local area of ​​the image, such as edges, textures, color changes, etc. During the convolution operation, the convolution kernel is first placed in the upper left corner of the input image and aligned with the corresponding local area of ​​the image. Then, each weight in the convolution kernel is element-wise multiplied with the image pixel value below it. After the multiplication operation is completed, all products are added together, and the single value obtained is the element value of the output feature map (also called feature map or activation map) at the current position. The convolution kernel then slides to the right on the input image at a predetermined stride, repeating the above multiplication and summation operations until the entire width of the image is covered. When the convolution kernel reaches the right edge of the image, it moves down one row and continues the sliding operation until the entire height of the image is covered. In this way, each position where the convolution kernel slides on the image generates an element of the output feature map. In this way, the convolution layer is able to generate a feature map, which is a feature representation of the input image under the convolution kernel weights. This feature map captures the characteristics of the input image in the local area covered by the convolution kernel, and through the use of multiple convolution kernels, different features of the image can be extracted, providing rich information for subsequent image analysis tasks (such as classification, detection or segmentation).

[0093] In the embodiment of the present invention, refer to Figure 3 As shown, a schematic diagram of a process of extracting posture features of livestock is provided in an embodiment of the present invention. The process of extracting posture features of livestock according to the livestock death image includes:

[0094] S31, identifying key points of livestock in the livestock death image;

[0095] S32, drawing connecting lines according to the key points;

[0096] S33, constructing a topological space according to the key points and the connecting lines;

[0097] S34, analyzing the topological properties of the topological space;

[0098] S35. Extracting posture features of the livestock according to the topological properties.

[0099] In detail, the key points for identifying the livestock in the livestock death image may be eyes, ears, nose, joints and other parts of the livestock.

[0100] In detail, the topological space is a basic concept in topology, which is an algebraic structure that describes the properties of space through topology, especially the continuity property and the proximity property.

[0101] In detail, the topological space is a tuple consisting of a set X and a topological structure defined on it. The topological structure here covers a series of concepts such as open sets, closed sets, neighborhoods, etc., which together describe the relationship between elements in the set X. Specifically, the family of open sets in the topological space needs to satisfy certain axioms, such as the empty set and the universal set both belong to the family of open sets, the union of any number of open sets is still an open set, and the intersection of a finite number of open sets is also an open set.

[0102] In detail, the analyzing the topological properties of the topological space refers to studying the primitive properties of the topological space, such as the separability, compactness, connectivity, etc. between the key points and the connecting lines.

[0103] In detail, the connectivity means that in a topological space, if any two points can be connected to each other through continuous transformation, the space is called connected. Connectivity is an important property of a topological space, which describes the overall structural characteristics of the space.

[0104] Specifically, compactness means that in a topological space, any open cover has a finite number of subcovers. This property is related to the "size" or "compactness" of a space and is one of the important topics studied in topology.

[0105] Specifically, the separability property means that in a topological space, any two open sets can be contained in two different open covers, respectively. This property is related to the separation property of the space.

[0106] In the embodiment of the present invention, by extracting the biological characteristics of the livestock to be compensated according to the livestock death image, the efficiency of subsequent stratified comparison is improved.

[0107] S3. Obtain historical compensation livestock biometric data from a pre-established biometric database.

[0108] In the embodiment of the present invention, the pre-established biometric database is a database storing a large amount of biometric data of dead livestock.

[0109] Specifically, the biometric database is a system specifically used to store, manage and analyze biometric information of dead livestock. This database has important application value in the fields of animal husbandry, animal disease prevention and control, food safety and insurance claims.

[0110] In detail, the biometric database generally includes a basic information module, a biometric module, a pathological information module, and an image and video data module.

[0111] In detail, the basic information module is used to record the basic information of the dead livestock, such as type, age, sex, weight, time of death, place and other information.

[0112] In detail, the biometric module is used to store biometric information of dead livestock, including but not limited to DNA sequence, fingerprint, facial recognition information, etc. This information is of great significance for determining livestock identity, tracing sources, and conducting disease detection.

[0113] In detail, the pathological information module is used to record the pathological changes, diagnosis results, causes of death, etc. of dead livestock. This helps to analyze the epidemic pattern of the disease, formulate prevention and control measures, and assess the epidemic risk.

[0114] In detail, the image and video data module is used to store on-site photos, video data, etc. of dead livestock to facilitate remote investigation, evidence preservation and case analysis.

[0115] In the embodiment of the present invention, the historical livestock biometric data for compensation refers to a set of biometric data of dead livestock for which compensation has been made.

[0116] In the embodiment of the present invention, by acquiring the biometric data of historically compensated livestock from a pre-established biometric database, the efficiency of subsequent stratified comparison is improved.

[0117] S4. Performing a hierarchical comparison on the biometric characteristics of the livestock to be compensated according to the biometric characteristic data of the livestock to be compensated historically, to obtain comparison result data.

[0118] In the embodiment of the present invention, the biometric data in the historical livestock compensation biometric data also includes three features: appearance features, body shape features and posture features.

[0119] In the embodiment of the present invention, the biometric characteristics of the livestock to be compensated are compared in layers according to the biometric characteristic data of the livestock to be compensated in history to obtain the comparison result data, including:

[0120] Performing a first-level comparison based on the appearance features in the biometric features of the compensated livestock and the biometric feature data of the historical compensated livestock to obtain first-level comparison result data;

[0121] Screening the biometric characteristic data of the historically compensated livestock according to the first layer comparison result data to obtain screening biometric characteristics;

[0122] Calculate the cosine similarity between the body shape feature and the posture feature in the biological features of the compensation livestock and each corresponding feature of the screening biological features to obtain a body shape feature similarity set and a posture feature similarity set;

[0123] Adding the body shape feature similarity set and the posture feature similarity set according to a preset weight to obtain a cosine similarity set;

[0124] The comparison result data is confirmed according to whether there is a cosine similarity value greater than a preset similarity threshold in the cosine similarity set.

[0125] In detail, the first level comparison based on the appearance features in the biometric features of the compensated livestock and the biometric feature data of the historical compensated livestock is performed by calculating the cosine similarity between the appearance features in the biometric features of the compensated livestock and each appearance feature in the biometric feature data of the historical compensated livestock.

[0126] In detail, the biometric feature data of the historically compensated livestock are screened according to the first layer comparison result data to obtain the screened biometric features, which means that feature data with a pre-similarity of appearance features less than a reference threshold are screened out, and the reference threshold may be 0.5.

[0127] In the embodiment of the present invention, the cosine similarity is a similarity measurement method for measuring the angle between two non-zero vectors.

[0128] In detail, the cosine similarity, also known as cosine similarity, is a metric used to measure the similarity between two vectors. Mathematically, it is defined as the dot product of two vectors divided by the product of their Euclidean norms. The cosine similarity evaluates the similarity of two vectors by calculating the cosine of the angle between them.

[0129] Furthermore, the value range of the cosine similarity is [-1,1]. When the directions of the two vectors are exactly the same (the angle is 0°), the cosine similarity is 1; when the directions of the two vectors are completely opposite (the angle is 180°), the cosine similarity is -1; when the two vectors are orthogonal (the angle is 90° or 270°), the cosine similarity is 0. Therefore, the closer the value of the cosine similarity is to 1, the more consistent the directions of the two vectors are, and the more similar they are; conversely, the closer the value is to -1, the more opposite the directions of the two vectors are, and the less similar they are.

[0130] In the embodiment of the present invention, the preset weights may be 0.5 and 0.5.

[0131] In the embodiment of the present invention, confirming the comparison result data according to whether there is a cosine similarity value greater than a preset similarity threshold in the cosine similarity set refers to obtaining biometric data whose cosine similarity is greater than the preset similarity threshold as the final comparison result data.

[0132] S5. Determine whether there is any duplicate payment behavior in this compensation request based on the comparison result data.

[0133] In the embodiment of the present invention, judging whether there is repeated payment behavior in the current compensation request according to the comparison result data includes:

[0134] Determine whether the comparison result data is a null value;

[0135] If the comparison result data is a null value, it is determined that there is no duplicate payment behavior in this compensation request;

[0136] If the comparison result data is not a null value, it is determined that there is duplicate payment behavior in this compensation request.

[0137] In the embodiment of the present invention, by judging whether there is duplicate payment behavior in the current compensation request according to the comparison result data, the efficiency of anti-duplicate payment detection for large livestock is improved.

[0138] If there is duplicate payment in this compensation request, execute S6 and issue a warning message.

[0139] In the embodiment of the present invention, when it is determined that there is duplicate payment behavior in this compensation request, an early warning message is sent to the relevant departments, and the livestock death image uploaded in this compensation request is sent to the relevant parts to facilitate further confirmation by the relevant departments.

[0140] In detail, when it is determined that there is duplicate payment behavior in this claim, the system will automatically send an early warning message to the risk control department or other relevant departments of the insurance company. This early warning message is a clear signal that this claim may involve improper duplicate payment behavior and requires additional review and processing. The early warning message can be sent through email, SMS, system notification or other instant messaging methods to ensure that the relevant departments can receive this important information in a timely manner. At the same time, the system will also send the livestock death images uploaded in this claim to the relevant departments. These images are key evidence for determining the authenticity of the claim and provide intuitive reference materials for the relevant departments. Through these images, the relevant departments can further analyze and confirm the death situation and injury characteristics of the livestock to verify the rationality and authenticity of the claim. In addition, the system may also provide other relevant documents and data, such as insurance documents, historical claim records, livestock registration information, etc., to assist the relevant departments in conducting a comprehensive review. This additional information helps the relevant departments build a complete background for the claim and make more accurate judgments.

[0141] In the embodiment of the present invention, when it is determined that there is duplicate payment behavior in the current claim request, a warning message is issued to effectively prevent duplicate claims.

[0142] If there is no duplicate compensation behavior in this compensation, execute S7, approve this compensation request, and store the biometric characteristics of the compensated livestock in the biometric database.

[0143] In the embodiment of the present invention, storing the biometric characteristics of the compensated livestock in the biometric database is to generate a unique identity ID for the biometric characteristics of the compensated livestock, and storing the biometric characteristics of the compensated livestock in the biometric database in combination with the unique identity ID to facilitate subsequent comparison with other compensation requests.

[0144] In the embodiment of the present invention, by judging whether there is duplicate payment behavior in the current compensation request based on the similarity between the biological characteristics of the dead livestock and all the biological characteristics in the biometric database, duplicate payment is effectively prevented, and the efficiency of anti-duplicate payment verification for large livestock is improved.

[0145] like Figure 4 1 is a functional module diagram of an anti-duplicate payment device for large livestock claims provided by an embodiment of the present invention.

[0146] The anti-duplicate payment device 100 in the large livestock claims of the present invention can be installed in an electronic device. According to the functions to be implemented, the anti-duplicate payment device 100 in the large livestock claims can include a feature extraction module 101, a layered comparison module 102, a duplicate payment warning module 103 and a data update module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0147] In this embodiment, the functions of each module / unit are as follows:

[0148] The feature extraction module 101 is used to obtain the livestock death image in the compensation request data, and extract the compensation livestock biological features of the livestock according to the livestock death image;

[0149] The hierarchical comparison module 102 is used to obtain biometric data of historically compensated livestock from a pre-established biometric database, and perform hierarchical comparison on the biometrics of the compensated livestock according to the biometric data of the historically compensated livestock to obtain comparison result data;

[0150] The duplicate payment warning module 103 is used to determine whether there is a duplicate payment behavior in the current payment request based on the comparison result data, and if there is a duplicate payment behavior in the current payment request, issue a warning message;

[0151] The data updating module 104 is used to determine whether there is a duplicate payment behavior in this compensation request based on the comparison result data. If there is no duplicate payment behavior in this compensation, the compensation request is approved and the biometric characteristics of the compensated livestock are stored in the biometric database.

[0152] The feature extraction module 101 is used to obtain the livestock death image in the compensation request data, and extract the compensation livestock biological features of the livestock according to the livestock death image.

[0153] In the embodiment of the present invention, the claim request data is a request sent by a user through a pre-established claim settlement system, and the claim request data is obtained from a service end of the claim settlement system.

[0154] In detail, the claim request data generally includes personal information of the user applying for claim settlement and voucher data (livestock death image, etc.) for applying for claim settlement.

[0155] In the embodiment of the present invention, the livestock death image is an image uploaded to the claim system server when the user sends a claim request. The livestock death image generally includes an overall photo, a single photo, a photo before and after ear cutting, and a photo before and after harmlessness.

[0156] In the embodiment of the present invention, by acquiring the livestock death image in the compensation request data, the efficiency of extracting the compensation livestock biometric features of the livestock death image is improved.

[0157] In the embodiment of the present invention, the extraction of livestock compensation livestock biological features based on the livestock death image is based on an image recognition algorithm to extract livestock appearance features, body shape features and posture features.

[0158] In the embodiment of the present invention, the feature extraction module 101 is specifically used to extract the compensation livestock biological features of the livestock according to the livestock death image, including:

[0159] Extracting appearance features of livestock based on the livestock death image;

[0160] Extracting the body shape features of the livestock according to the livestock death image;

[0161] The posture features of the livestock are extracted based on the livestock death image.

[0162] The appearance features, the body shape features and the posture features are aggregated into the compensation livestock biological features of the livestock.

[0163] In detail, the appearance feature is obtained by identifying the main body area of ​​the livestock in the livestock death image and extracting the shallow features of the main body area. The body shape feature is obtained by identifying the deep features of the main body area. The posture feature is a feature obtained by identifying the key points of the livestock in the livestock death image.

[0164] In detail, the posture feature is a deep feature that pays more attention to the death posture of live pigs. Since the death posture of livestock is usually difficult to change after death, it is possible to determine whether it is a duplicate claim by comparing the death posture.

[0165] In the embodiment of the present invention, the feature extraction module 101 is specifically used to extract the appearance features of the livestock according to the livestock death image, including:

[0166] Using an edge detection algorithm to identify the main area of ​​the livestock in the livestock death image to obtain main features;

[0167] Using a gray level co-occurrence matrix to identify the texture features of the livestock in the livestock death image;

[0168] The main features and the texture features are integrated to obtain the appearance features.

[0169] In detail, the edge detection algorithm is an important technology in image processing, which is mainly used to extract the outline of objects or boundaries in images for further analysis and processing. These algorithms detect edges by calculating the change in the grayscale value of pixels in the image. When there is an edge in the image, the grayscale values ​​of adjacent pixels will change suddenly.

[0170] In detail, the grayscale co-occurrence matrix is ​​a statistical tool for image processing, which reflects the texture characteristics of an image by calculating the joint probability distribution of pixel pairs in the image. Specifically, the grayscale co-occurrence matrix defines the probability of a grayscale value j at a point leaving a fixed position starting from a pixel with a grayscale of i, that is, all estimated values ​​can be expressed in the form of a matrix. The grayscale co-occurrence matrix can reflect information such as the direction, interval, and amplitude of change of the image texture. For example, an image with a slowly changing texture will have a larger value on the diagonal of the grayscale co-occurrence matrix; while an image with a fast changing texture will have a smaller value on the diagonal, and larger values ​​on both sides of the diagonal. Due to the large amount of data in the grayscale co-occurrence matrix, it is usually not used directly as a feature for texture distinction, but some statistics constructed based on it are used as texture classification features.

[0171] like Figure 5 , which is a schematic diagram of the structure of an electronic device of a method for preventing duplicate payment in large livestock claims provided by an embodiment of the present invention.

[0172] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an anti-duplicate payment program in large livestock claims.

[0173] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as anti-duplicate payment programs in large livestock claims, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0174] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 can also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of the anti-duplicate payment program in the large livestock claim, but also can be used to temporarily store data that has been output or is to be output.

[0175] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0176] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in this embodiment, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0177] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0178] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0179] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0180] The anti-duplicate payment program in large livestock claims stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, the steps of the anti-duplicate payment method in large livestock claims can be implemented. Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0181] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0182] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor of an electronic device, it can implement the steps of the method for preventing duplicate payment in large livestock claims.

[0183] It should be noted that if software tools or components other than those of the Company appear in the embodiments of the present application, they are only used for illustration and do not represent actual use. In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0184] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0186] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0187] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0188] 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.

[0189] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0190] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for preventing duplicate payment in large livestock claims, characterized in that: The method comprises: Access livestock mortality images from claim data; extracting livestock biometric features of the livestock for compensation based on the livestock death image; Obtaining historical claim livestock biometric data from a pre-established biometric database; Performing a hierarchical comparison of the biometric characteristics of the livestock to be compensated according to the biometric characteristic data of the livestock to be compensated historically, to obtain comparison result data; Determine whether there is duplicate payment behavior in this compensation request based on the comparison result data; If there is duplicate payment in this claim request, a warning message will be issued; If there is no duplicate payment in this compensation, the compensation request will be approved and the biometric characteristics of the compensated livestock will be stored in the biometric database.

2. The method for preventing duplicate payment in large livestock claims according to claim 1, characterized in that: The step of extracting the livestock biometric features of the livestock for compensation according to the livestock death image comprises: Extracting appearance features of livestock based on the livestock death image; Extracting the body shape features of the livestock according to the livestock death image; extracting posture features of livestock according to the livestock death image; The appearance features, the body shape features and the posture features are aggregated into the compensation livestock biological features of the livestock.

3. The method for preventing duplicate payment in large livestock claims as claimed in claim 2, characterized in that: The step of extracting the appearance features of the livestock according to the livestock death image comprises: Using an edge detection algorithm to identify the main area of ​​the livestock in the livestock death image to obtain main features; Using a gray level co-occurrence matrix to identify the texture features of the livestock in the livestock death image; The main features and the texture features are integrated to obtain the appearance features.

4. The method for preventing duplicate payment in large livestock claims as claimed in claim 3, characterized in that: The step of extracting the body shape features of the livestock according to the livestock death image comprises: Removing the non-subject area in the livestock death image to obtain a subject image; Extracting convolution features of the subject image; Extracting color features of the subject image; The convolution feature and the color feature are fused to obtain the body shape feature.

5. The method for preventing duplicate payment in large livestock claims according to claim 4, characterized in that: The step of extracting the posture features of the livestock according to the livestock death image comprises: identifying key points of livestock in the livestock death image; Draw connecting lines according to the key points; Constructing a topological space according to the key points and the connecting lines; Analyzing the topological properties of the topological space; The posture features of the livestock are extracted according to the topological properties.

6. The method for preventing duplicate payment in large livestock claims according to claim 1, characterized in that: The biometric characteristics of the livestock to be compensated are compared in layers according to the biometric characteristics data of the livestock to be compensated in history to obtain comparison result data, including: Performing a first-level comparison based on the appearance features in the biometric features of the compensated livestock and the biometric feature data of the historical compensated livestock to obtain first-level comparison result data; Screening the biometric characteristic data of the historically compensated livestock according to the first layer comparison result data to obtain screening biometric characteristics; Calculate the cosine similarity between the body shape feature and the posture feature in the biological features of the compensation livestock and each corresponding feature of the screening biological features to obtain a body shape feature similarity set and a posture feature similarity set; Adding the body shape feature similarity set and the posture feature similarity set according to a preset weight to obtain a cosine similarity set; The comparison result data is confirmed according to whether there is a cosine similarity value greater than a preset similarity threshold in the cosine similarity set.

7. The method for preventing duplicate payment in large livestock claims according to claim 6, characterized in that: The determining whether there is a duplicate payment behavior in the current compensation request according to the comparison result data includes: Determine whether the comparison result data is a null value; If the comparison result data is a null value, it is determined that there is no duplicate payment behavior in this compensation request; If the comparison result data is not a null value, it is determined that there is duplicate payment behavior in this compensation request.

8. A device for preventing duplicate payment in large livestock claims, characterized in that: The device comprises: A feature extraction module, used to obtain a livestock death image in the compensation request data, and extract the compensation livestock biological features of the livestock according to the livestock death image; A hierarchical comparison module is used to obtain biometric data of historically compensated livestock from a pre-established biometric database, and to perform hierarchical comparison on the biometrics of the compensated livestock according to the biometric data of the historically compensated livestock to obtain comparison result data; A duplicate payment warning module is used to determine whether there is a duplicate payment behavior in the current payment request based on the comparison result data, and if there is a duplicate payment behavior in the current payment request, a warning message is issued; The data updating module is used to determine whether there is any duplicate payment behavior in this compensation request based on the comparison result data. If there is no duplicate payment behavior in this compensation request, the compensation request is approved and the biometric characteristics of the compensated livestock are stored in the biometric characteristic database.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the anti-duplicate payment method in large livestock claims as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for preventing duplicate payment in large livestock claims as described in any one of claims 1 to 7 is implemented.

Images