Car insurance fraud identification method and device, computer equipment and storage medium

Abstract

The invention provides a vehicle insurance fraud identification method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring vehicle accident scene data and vehicle accident scene information; performing analysis processing on the vehicle accident scene data to determine a first fraud risk assessment value; performing matching processing on the vehicle accident scene information based on a preset risk rule base to determine a second fraud risk assessment value; and performing weighted summation on the first fraud risk assessment value and the second fraud risk assessment value based on the first weight distribution information to obtain a comprehensive fraud risk assessment value. By implementing the method disclosed by the invention, the accuracy of the vehicle insurance fraud recognition result can be effectively improved by combining the vehicle accident scene data and the vehicle accident scene information, and the quantitative evaluation of the vehicle insurance fraud risk is realized based on the comprehensive fraud risk evaluation value.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment and storage medium for identifying auto insurance fraud. Background Art

[0002] Insurance fraud often occurs in the insurance field. For example, in car insurance, users may fabricate or forge car accident scenarios to defraud insurance companies of compensation. Therefore, in order to prevent insurance companies from incurring losses due to insurance fraud, it is necessary to identify such insurance fraud.

[0003] When identifying auto insurance fraud in related technologies, the accuracy is low and the fraud risk is immeasurable. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the purpose of the present invention is to propose a method, device, computer equipment and storage medium for identifying auto insurance fraud, which can effectively improve the accuracy of auto insurance fraud identification results by combining vehicle accident scene data and vehicle accident scene information, and realize quantitative assessment of auto insurance fraud risk based on comprehensive fraud risk assessment value.

[0006] To achieve the above-mentioned purpose, the first aspect of the present disclosure provides a method for identifying auto insurance fraud, including:

[0007] Obtain vehicle accident scene data and vehicle accident scene information;

[0008] Analyzing and processing the vehicle accident scene data to determine a first fraud risk assessment value;

[0009] Performing matching processing on the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value;

[0010] The first fraud risk assessment value and the second fraud risk assessment value are weighted and summed based on the first weight allocation information to obtain a comprehensive fraud risk assessment value.

[0011] To achieve the above-mentioned purpose, a second aspect of the present disclosure provides a vehicle insurance fraud identification device, comprising:

[0012] An acquisition module, used to acquire vehicle accident scene data and vehicle accident scene information;

[0013] A first determination module, configured to parse and process the vehicle accident scene data to determine a first fraud risk assessment value;

[0014] A second determination module is used to match the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value;

[0015] A processing module is used to perform weighted summation of the first fraud risk assessment value and the second fraud risk assessment value based on first weight allocation information to obtain a comprehensive fraud risk assessment value.

[0016] The computer device proposed in the third aspect embodiment of the present disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the auto insurance fraud identification method proposed in the first aspect embodiment of the present disclosure is implemented.

[0017] The fourth aspect embodiment of the present disclosure proposes a non-temporary computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for identifying auto insurance fraud proposed in the first aspect embodiment of the present disclosure is implemented.

[0018] The fifth aspect embodiment of the present disclosure proposes a computer program product. When the instructions in the computer program product are executed by a processor, the auto insurance fraud identification method proposed in the first aspect embodiment of the present disclosure is executed.

[0019] The auto insurance fraud identification method, device, computer equipment and storage medium provided by the present disclosure obtain vehicle accident scene data and vehicle accident scene information; parse and process the vehicle accident scene data to determine a first fraud risk assessment value; match and process the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value; and perform weighted summation of the first fraud risk assessment value and the second fraud risk assessment value based on the first weight distribution information to obtain a comprehensive fraud risk assessment value. Thus, the accuracy of the auto insurance fraud identification results can be effectively improved by combining the vehicle accident scene data and the vehicle accident scene information, and a quantitative assessment of the auto insurance fraud risk can be achieved based on the comprehensive fraud risk assessment value.

[0020] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 It is a flowchart of a method for identifying auto insurance fraud proposed in an embodiment of the present disclosure;

[0023] Figure 2is a flow chart of a method for identifying auto insurance fraud proposed in another embodiment of the present disclosure;

[0024] Figure 3 It is a structural schematic diagram of a vehicle insurance fraud identification device proposed in an embodiment of the present disclosure;

[0025] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0026] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and are not to be construed as limitations of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications, and equivalents that fall within the spirit and connotation of the appended claims.

[0027] Figure 1 It is a flowchart of a method for identifying auto insurance fraud proposed in an embodiment of the present disclosure.

[0028] Among them, it should be noted that the executor of the car insurance fraud identification method of this embodiment is a car insurance fraud identification device, which can be implemented by software and / or hardware. The device can be configured in a computer device, and the computer device can include but is not limited to a terminal, a server, etc. For example, the terminal can be a mobile phone, a handheld computer, etc.

[0029] like Figure 1 As shown, the method for identifying auto insurance fraud includes:

[0030] S101: Acquire vehicle accident scene data and vehicle accident scene information.

[0031] The vehicle accident scene data refers to the data collected at the vehicle accident scene. The vehicle accident scene data may include image data, radar point cloud data, voice data, etc., without limitation.

[0032] Among them, vehicle accident scene information refers to relevant information used to describe the vehicle accident scene, for example, it may include the type of accident, time of the accident, location of the accident, etc., without any restriction.

[0033] In the disclosed embodiment, when the vehicle accident scene data and vehicle accident scenario information are obtained, reliable data support can be provided for the subsequent identification of vehicle insurance fraud behavior.

[0034] S102: Analyze and process the vehicle accident scene data to determine a first fraud risk assessment value.

[0035] Among them, the first fraud risk assessment value refers to the value obtained by conducting a risk assessment on auto insurance fraud based on the vehicle accident scene data, which can be used to indicate the probability that the vehicle accident is an insurance fraud.

[0036] In the disclosed embodiment, when analyzing and processing the vehicle accident scene data to determine the first fraud risk assessment value, the vehicle accident scene data can be input into a pre-trained machine learning model to obtain the corresponding first fraud risk assessment value. Alternatively, the vehicle accident scene data can be analyzed and processed based on a third-party risk assessment device to determine the first fraud risk assessment value, and there is no limitation on this.

[0037] Optionally, in some embodiments, the vehicle accident scene data includes scene image data and vehicle inspection data; wherein, when the vehicle accident scene data is parsed and processed to determine the first fraud risk assessment value, it can be: determining the vehicle collision position according to the scene image data; determining the vehicle risk part according to the vehicle collision position; determining the vehicle damage part according to the vehicle inspection data; determining the first fraud risk assessment value according to the vehicle risk part and the vehicle damage part. Thus, an accurate assessment of the fraud risk can be achieved based on the comparison results of the vehicle risk part and the vehicle damage part, so as to effectively improve the practicality of the obtained first fraud risk assessment value.

[0038] The on-site image data refers to the image data collected at the scene of the vehicle accident.

[0039] The vehicle inspection data refers to the data obtained after inspecting the vehicle involved in the accident, which can be used to indicate the status of the vehicle.

[0040] Among them, the vehicle collision position refers to the part where the accident vehicle collides with other objects.

[0041] Among them, the risk parts of the vehicle refer to the parts of the vehicle that may be damaged due to an accident.

[0042] Among them, the damaged part of the vehicle refers to the part of the vehicle where the damage actually occurs.

[0043] For example, in the embodiment of the present disclosure, multiple vehicle risk parts and the risk value corresponding to each vehicle risk part can be determined according to the vehicle collision position, and then when the first fraud risk assessment value is determined according to the vehicle risk part and the vehicle damage part, the risk value of the vehicle risk part that is the same as the vehicle damage part can be determined as the above-mentioned first fraud risk assessment value.

[0044] S103: Matching the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value.

[0045] Among them, the preset risk rule library may include fraud risk values ​​pre-configured for various scenario characteristics of vehicle accident scenarios.

[0046] Among them, the second fraud risk assessment value refers to the fraud risk assessment value determined by matching the vehicle accident scene information based on a preset risk rule library.

[0047] Optionally, in some embodiments, the preset risk rule library contains multiple candidate risk rules; wherein, when matching the vehicle accident scene information based on the preset risk rule library to determine the second fraud risk assessment value, it can be: matching the vehicle accident scene information with the candidate risk rules to determine the target risk rule from the multiple candidate risk rules, wherein each target risk rule has a corresponding target fraud risk assessment value; and weighted summing the multiple target fraud risk assessment values ​​based on the second weight allocation information to obtain the second fraud risk assessment value. Thus, the indication accuracy of the obtained second fraud risk assessment value can be effectively improved.

[0048] Among them, the candidate risk rule refers to the rule for determining the fraud risk which is pre-stored in the preset risk rule library. The candidate risk rule can be used to determine the fraud risk value corresponding to the characteristics of the vehicle accident scene.

[0049] Among them, target risk rules refer to risk rules applicable to vehicle accident scenario information.

[0050] Among them, the target fraud risk assessment value refers to the assessment value obtained by conducting a fraud risk assessment on vehicle accident scenario information based on the target risk rules.

[0051] That is to say, in the embodiment of the present disclosure, risk assessment rules can be customized in advance to form a preset risk rule library, and then in the actual application process, the vehicle accident scene information is matched and processed based on the preset risk rule library to determine the second fraud risk assessment value, thereby effectively improving the practicality of the obtained second fraud risk assessment value.

[0052] S104: Performing a weighted summation of the first fraud risk assessment value and the second fraud risk assessment value based on the first weight allocation information to obtain a comprehensive fraud risk assessment value.

[0053] The first weight distribution information can be used to indicate the weight distribution of the first fraud risk assessment value and the second fraud risk assessment value when performing weighted summation. The first weight distribution information can be flexibly adjusted according to the application scenario, and there is no limitation on this.

[0054] Among them, the comprehensive fraud risk assessment value refers to the fraud risk assessment value obtained by weighted summing the first fraud risk assessment value and the second fraud risk assessment value based on the first weight allocation information.

[0055] That is to say, in the embodiment of the present disclosure, after obtaining the first fraud risk assessment value and the second fraud risk assessment value, the first fraud risk assessment value and the second fraud risk assessment value can be weightedly summed based on the first weight distribution information to obtain a comprehensive fraud risk assessment value, so as to achieve the fusion processing of the fraud risk assessment values ​​obtained from different dimensions.

[0056] In this embodiment, the vehicle accident scene data and the vehicle accident scene information are obtained; the vehicle accident scene data is parsed and processed to determine the first fraud risk assessment value; the vehicle accident scene information is matched and processed based on the preset risk rule library to determine the second fraud risk assessment value; the first fraud risk assessment value and the second fraud risk assessment value are weighted and summed based on the first weight distribution information to obtain a comprehensive fraud risk assessment value. In this way, the accuracy of the auto insurance fraud identification results can be effectively improved by combining the vehicle accident scene data and the vehicle accident scene information, and the quantitative assessment of the auto insurance fraud risk can be achieved based on the comprehensive fraud risk assessment value.

[0057] Figure 2 It is a flow chart of a method for identifying auto insurance fraud proposed in another embodiment of the present disclosure.

[0058] like Figure 2 As shown, the method for identifying auto insurance fraud includes:

[0059] S201: Acquire vehicle accident scene data and vehicle accident scene information.

[0060] S202: Analyze and process the vehicle accident scene data to determine a first fraud risk assessment value.

[0061] S203: Matching the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value.

[0062] S204: Performing a weighted summation of the first fraud risk assessment value and the second fraud risk assessment value based on the first weight allocation information to obtain a comprehensive fraud risk assessment value.

[0063] The description of S201 - S204 can be specifically referred to the above embodiment, which will not be repeated here.

[0064] S205: Perform feature analysis based on the vehicle accident scene data to identify target scene features related to the risk assessment of auto insurance fraud.

[0065] Among them, the target scene characteristics may refer to data characteristics in the vehicle accident scene data that may be related to the risk assessment of auto insurance fraud.

[0066] In the disclosed embodiments, when performing feature analysis based on vehicle accident scene data to identify target scene features related to auto insurance fraud risk assessment, the vehicle accident scene data can be input into a pre-trained machine learning model to obtain corresponding target scene features. Alternatively, feature analysis can be performed on different vehicle accident scene data to obtain multiple corresponding reference scene features, and then the overlapping reference scene features of different vehicle accident scene data can be used as target scene features. There is no limitation to this.

[0067] S206: Constructing a basic unit of a data model based on target site characteristics.

[0068] The basic unit of the data model may refer to the basic unit of M-Cube, and each unit represents a specific risk or accident scenario.

[0069] That is to say, in the embodiment of the present disclosure, after performing feature analysis based on the vehicle accident scene data to identify target scene features related to the risk assessment of auto insurance fraud, a basic unit of the data model can be constructed based on the target scene features, thereby providing reliable data support for the subsequent construction of a multidimensional data model.

[0070] S207: Construct a multidimensional data model based on the basic units of the data model.

[0071] The multidimensional data model refers to a model constructed based on the basic units of the data model and used to indicate the characteristics of data in multiple dimensions.

[0072] Optionally, in some embodiments, when constructing a multidimensional data model based on the basic unit of the data model, feature supplementation processing can be performed based on the feature dimensions of the vehicle accident scene data; the processed data is aggregated and summarized according to different dimensions to construct a multidimensional data model. Thus, the comprehensiveness and practicality of the indication of the obtained multidimensional data model can be effectively improved by supplementing the features of different feature dimensions.

[0073] S208: Perform visual display based on comprehensive fraud risk assessment value and multidimensional data model.

[0074] Optionally, in some embodiments, when performing visualization based on the comprehensive fraud risk assessment value and the multidimensional data model, the multidimensional data model may be visualized based on the specified assessment value information; and / or the comprehensive fraud risk assessment value may be visualized based on the specified data model information. Thus, the flexibility of visualization can be effectively improved to meet personalized user needs.

[0075] That is, in the disclosed embodiment, feature analysis can be performed based on vehicle accident scene data to identify target scene features related to auto insurance fraud risk assessment; based on target scene features, basic units of data models can be constructed; based on basic units of data models, multidimensional data models can be constructed; and visualization can be performed based on comprehensive fraud risk assessment values ​​and multidimensional data models. Thus, visualization of auto insurance fraud identification results can be achieved, effectively improving the practicality of the auto insurance fraud identification method.

[0076] In this embodiment, feature analysis is performed based on vehicle accident scene data to identify target scene features related to auto insurance fraud risk assessment; based on the target scene features, a data model basic unit is constructed; based on the data model basic unit, a multidimensional data model is constructed; and based on the comprehensive fraud risk assessment value and the multidimensional data model, a visual display is performed. In this way, a visual display of auto insurance fraud identification results can be achieved, thereby effectively improving the practicality of the auto insurance fraud identification method.

[0077] Based on the above embodiments, the present disclosure may be based on the following steps when identifying auto insurance fraud:

[0078] Step 1: Obtain vehicle accident scene data (image data and basic vehicle data); identify the vehicle collision location based on the vehicle accident scene data, and then determine the risk part of the vehicle; determine the first fraud risk assessment value based on the risk part of the vehicle and the actual repair part of the vehicle;

[0079] Step 2: matching the vehicle accident scene according to multiple risk rules in the preset risk rule library to determine multiple target risk rules and the risk assessment value corresponding to each target risk rule; performing weighted summation according to the weight values ​​corresponding to the multiple target risk rules to obtain a second fraud risk assessment value;

[0080] Step 3: Perform weighted summation on the first fraud risk assessment value and the second fraud risk assessment value based on the preset weight distribution information to obtain a comprehensive fraud risk assessment value, thereby enhancing the accuracy of risk identification.

[0081] Step 4: Perform feature analysis based on the vehicle accident scene data to identify key features related to risk assessment, such as accident type, collision intensity, damaged parts, etc., and build the basic units of M-Cube based on these features. Each unit represents a specific risk or accident scenario. The feature dimensions of the vehicle accident scene data are supplemented with more dimensional information, such as institutions, insurance types, time series, etc., to enrich the data structure of M-Cube. According to the structure of the multidimensional data model, the processed data is aggregated and summarized according to different dimensions to form a multidimensional M-Cube to solve the problem of over-generalization of traditional portraits.

[0082] Step 5. Based on the preset weight distribution information, the first fraud risk assessment value and the second fraud risk assessment value are weighted and summed. This process aims to comprehensively and objectively consider the fraud risks of the two dimensions, so as to obtain a comprehensive fraud risk assessment value. This comprehensive assessment value will serve as the final basis for judging the fraud risk in vehicle accidents to ensure the accuracy and reliability of the assessment results. The comprehensive fraud risk assessment value and the multi-dimensional analysis results of M-Cube are visualized to provide decision support. The multi-dimensional analysis results include the distribution of accident types, showing the proportion of different types of accidents (such as rear-end collisions, side collisions, rollovers, etc.) in the total accidents, and the distribution of fraud risk levels corresponding to each accident type, as well as time trend distribution, damaged parts and repair cost distribution, etc. According to the assessment results and the analysis results of M-Cube, formulate corresponding anti-fraud risk prevention and control measures and audit response strategies.

[0083] Step 6. During the visualization process, there is a close linkage between the comprehensive fraud risk assessment value and the multi-dimensional analysis results of M-Cube. Users can select a specific comprehensive fraud risk assessment value range to automatically highlight the data points or areas related to the range in the multi-dimensional analysis results of M-Cube. When the user filters or adjusts a certain dimension of M-Cube (such as time or location), the chart of the comprehensive fraud risk assessment value will be updated accordingly to reflect the risk assessment results under the current screening conditions, and realize data drilling and in-depth analysis. A risk warning mechanism is set in the visualization interface. When the comprehensive fraud risk assessment value exceeds the preset threshold, an early warning prompt is automatically triggered, and the relevant risk factors are highlighted in the multi-dimensional analysis results of M-Cube, so that users can take anti-fraud risk prevention and control measures and audit response strategies in a timely manner, and truly solve the situation where risks cannot be measured and visualization effects are poor.

[0084] Figure 3 It is a structural schematic diagram of a vehicle insurance fraud identification device proposed in an embodiment of the present disclosure.

[0085] like Figure 3 As shown, the vehicle insurance fraud identification device 30 includes:

[0086] An acquisition module 301 is used to acquire vehicle accident scene data and vehicle accident scene information;

[0087] A first determination module 302 is used to parse and process the vehicle accident scene data to determine a first fraud risk assessment value;

[0088] A second determination module 303 is used to match the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value;

[0089] The processing module 304 is used to perform weighted summation on the first fraud risk assessment value and the second fraud risk assessment value based on the first weight allocation information to obtain a comprehensive fraud risk assessment value.

[0090] It should be noted that the aforementioned explanation of the auto insurance fraud identification method is also applicable to the auto insurance fraud identification device of this embodiment and will not be repeated here.

[0091] In this embodiment, the vehicle accident scene data and the vehicle accident scene information are obtained; the vehicle accident scene data is parsed and processed to determine the first fraud risk assessment value; the vehicle accident scene information is matched and processed based on the preset risk rule library to determine the second fraud risk assessment value; the first fraud risk assessment value and the second fraud risk assessment value are weighted and summed based on the first weight distribution information to obtain a comprehensive fraud risk assessment value. In this way, the accuracy of the auto insurance fraud identification results can be effectively improved by combining the vehicle accident scene data and the vehicle accident scene information, and the quantitative assessment of the auto insurance fraud risk can be achieved based on the comprehensive fraud risk assessment value.

[0092] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 4 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0093] like Figure 4 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0094] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0095] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0096] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 Not shown, often called a "hard drive").

[0097] although Figure 4 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (Compact Disc Read Only Memory; hereinafter referred to as: CD-ROM), a digital versatile disc read only memory (Digital Video Disc Read Only Memory; hereinafter referred to as: DVD-ROM) or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0098] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0099] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a human body to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0100] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the auto insurance fraud identification method mentioned in the above embodiment.

[0101] In order to implement the above embodiments, the present disclosure also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for identifying auto insurance fraud proposed in the above embodiments of the present disclosure is implemented.

[0102] In order to implement the above embodiments, the present disclosure also proposes a computer program product. When the instruction processor in the computer program product is executed, the auto insurance fraud identification method proposed in the above embodiments of the present disclosure is executed.

[0103] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0104] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0105] It should be noted that, in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present disclosure, unless otherwise specified, the meaning of "plurality" is two or more.

[0106] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0107] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0108] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0109] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0110] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0111] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0112] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A method for identifying auto insurance fraud, characterized in that: include: Obtain vehicle accident scene data and vehicle accident scene information; Analyzing and processing the vehicle accident scene data to determine a first fraud risk assessment value; Performing matching processing on the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value; The first fraud risk assessment value and the second fraud risk assessment value are weighted and summed based on the first weight allocation information to obtain a comprehensive fraud risk assessment value.

2. The method according to claim 1, characterized in that The vehicle accident scene data includes scene image data and vehicle inspection data; The step of analyzing and processing the vehicle accident scene data to determine a first fraud risk assessment value includes: Determining a vehicle collision position according to the on-site image data; Determining a risky part of the vehicle according to the collision position of the vehicle; Determining the damaged part of the vehicle according to the vehicle inspection data; The first fraud risk assessment value is determined based on the risk parts of the vehicle and the damaged parts of the vehicle.

3. The method according to claim 1, characterized in that The preset risk rule library includes multiple candidate risk rules; The matching process of the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value includes: Matching the vehicle accident scene information with the candidate risk rules to determine a target risk rule from the multiple candidate risk rules, wherein each target risk rule has a corresponding target fraud risk assessment value; A weighted sum is performed on the plurality of target fraud risk assessment values ​​based on the second weight distribution information to obtain the second fraud risk assessment value.

4. The method according to claim 1, characterized in that The method further comprises: Performing feature analysis based on the vehicle accident scene data to identify target scene features related to the risk assessment of auto insurance fraud; Based on the target site characteristics, construct a data model basic unit; Based on the basic units of the data model, construct a multidimensional data model; A visual display is performed based on the comprehensive fraud risk assessment value and the multidimensional data model.

5. The method according to claim 4, characterized in that The step of constructing a multidimensional data model based on the basic unit of the data model includes: Performing feature supplementation processing based on the feature dimensions of the vehicle accident scene data; The processed data is aggregated and summarized according to different dimensions to construct the multidimensional data model.

6. The method according to claim 4, characterized in that The visual display based on the comprehensive fraud risk assessment value and the multidimensional data model includes at least one of the following: Visually display the multidimensional data model based on the specified evaluation value information; The comprehensive fraud risk assessment value is visualized based on the specified data model information.

7. A vehicle insurance fraud identification device, characterized in that: include: An acquisition module, used to acquire vehicle accident scene data and vehicle accident scene information; A first determination module, configured to parse and process the vehicle accident scene data to determine a first fraud risk assessment value; A second determination module is used to match the vehicle accident scene information based on a preset risk rule library to determine a second fraud risk assessment value; A processing module is used to perform weighted summation of the first fraud risk assessment value and the second fraud risk assessment value based on first weight allocation information to obtain a comprehensive fraud risk assessment value.

8. A computer device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

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

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images