Vehicle insurance risk identification method and device, computer equipment and storage medium

Abstract

The invention discloses a vehicle insurance risk identification method and device, computer equipment and a storage medium, relates to the technical field of artificial intelligence, is applied to a vehicle insurance risk identification scene related to financial services, and comprises the following steps: obtaining case report information of a target vehicle insurance case; inputting the case reporting information into a case reporting factor model for risk assessment, and generating a first risk result of the target car insurance case; when the first risk result exceeds a first preset threshold value, inputting the case report information into a text survey model for risk assessment, and generating a second risk result of the target car insurance case; when the second risk result exceeds a second preset threshold value, inputting the case report information into one or more of a vehicle single-party intentional collision model, a vehicle multi-party intentional collision model and an accident scene forgery model for risk assessment, and generating a third risk result of the target vehicle insurance case; and judging whether the target car insurance case is a car insurance risk case based on the third risk result. According to the invention, the vehicle insurance risk behavior can be automatically, efficiently and accurately identified.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and is applied to auto insurance risk identification scenarios related to financial services, and specifically to an auto insurance risk identification method, device, computer equipment, and non-volatile computer-readable storage medium. Background Art

[0002] Currently, in the auto insurance industry, risky behaviors have always been a major challenge for insurance companies. Among them, intentional collisions by one party, intentional collisions by multiple parties, and forgery of accident scenes are the most common types of risks. These risky behaviors usually involve buying high-end second-hand cars and deliberately creating accidents to defraud insurance companies of high premiums. Such behaviors not only damage the economic interests of insurance companies, but may also damage public facilities and have a negative impact on social order.

[0003] At present, when insurance companies identify this type of auto insurance risk behavior, they mainly rely on investigating the driver's historical accident records to see if there are frequent collisions, or rely on surveyors to inspect the traces on site to determine whether the traces are reasonable. However, these two methods have certain limitations:

[0004] 1. Historical record analysis: This method relies on the driver's historical data, but the historical data may not be comprehensive, resulting in poor accuracy in risk identification and inability to predict future behavior;

[0005] 2. On-site inspection: This method relies on the experience and judgment of the inspector, which may lead to strong subjectivity, low efficiency, and difficulty in forming a standardized assessment process;

[0006] In addition, although some vehicle inspection instruments can detect the condition of the accelerator and brakes before a vehicle collision, these data often cannot be used as recognized evidence, limiting their application in auto insurance risk identification.

[0007] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0008] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a method, apparatus, computer equipment and non-volatile computer-readable storage medium for identifying auto insurance risks that can be used in financial technology or other related fields, aiming to solve the problem of how to automatically, efficiently and accurately identify auto insurance risk behaviors.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions:

[0010] A method for identifying auto insurance risks, comprising:

[0011] Obtain the reporting information of the target auto insurance case;

[0012] Inputting the case reporting information into the case reporting factor model for risk assessment to generate a first risk result of the target auto insurance case;

[0013] When the first risk result exceeds a first preset threshold, the case report information is input into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case;

[0014] When the second risk result exceeds a second preset threshold, the report information is input into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case;

[0015] Based on the third risk result, determine whether the target auto insurance case is an auto insurance risk case.

[0016] In a further technical solution, the method for identifying automobile insurance risks, wherein the step of obtaining the report information of the target automobile insurance case includes:

[0017] Obtain case information uploaded by the target user regarding the target auto insurance case;

[0018] The case information is integrated to generate corresponding case report information.

[0019] In a further technical solution, the method for identifying auto insurance risk, wherein the inputting of the case reporting information into the case reporting factor model for risk assessment to generate the first risk result of the target auto insurance case, comprises:

[0020] Pre-construction of the reporting factor model;

[0021] The case reporting information is input into the case reporting factor model for risk assessment to generate a first risk result for the target vehicle insurance case.

[0022] In a further technical solution, the method for identifying auto insurance risk, wherein when the first risk result exceeds a first preset threshold, the case report information is input into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case, including:

[0023] Pre-build text exploration models;

[0024] When the first risk result exceeds a first preset threshold, the report information is input into the text investigation model for risk assessment to generate a second risk result for the target auto insurance case.

[0025] In a further technical solution, the vehicle insurance risk identification method, wherein when the second risk result exceeds the second preset threshold, the case report information is input into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case, including:

[0026] Pre-build a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model;

[0027] When the second risk result exceeds a second preset threshold, obtaining surveyor remark information of the target auto insurance case, and determining the risk type of the target auto insurance case according to the surveyor remark information;

[0028] Based on the risk type, the report information is input into one of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case.

[0029] In a further technical solution, the method for identifying auto insurance risk, wherein judging whether the target auto insurance case is an auto insurance risk case based on the third risk result, comprises:

[0030] Comparing the third risk result with a third preset threshold to generate a comparison result;

[0031] Based on the comparison result, determine whether the target auto insurance case is an auto insurance risk case.

[0032] In a further technical solution, the method for identifying auto insurance risk, wherein the step of judging whether the target auto insurance case is an auto insurance risk case based on the third risk result, further comprises:

[0033] When the target auto insurance case is an auto insurance risk case, an alarm is issued;

[0034] The first risk result is returned to the target user as the final risk assessment result of the target auto insurance case.

[0035] A vehicle insurance risk identification device, comprising:

[0036] An acquisition module is used to obtain the report information of the target auto insurance case;

[0037] A first assessment module, used for inputting the case reporting information into a case reporting factor model for risk assessment, and generating a first risk result of the target auto insurance case;

[0038] A second assessment module, configured to input the case report information into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case when the first risk result exceeds a first preset threshold;

[0039] A third assessment module is used for inputting the case report information into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model and an accident scene forgery model for risk assessment when the second risk result exceeds a second preset threshold, so as to generate a third risk result of the target vehicle insurance case;

[0040] A judgment module is used to judge whether the target motor vehicle insurance case is a motor vehicle insurance risk case based on the third risk result.

[0041] A computer device, wherein the computer device comprises at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the vehicle insurance risk identification method as described in any one of the above items can be implemented.

[0044] A non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, it can implement the vehicle insurance risk identification method as described in any one of the above.

[0045] Compared with the prior art, the present invention provides a method, device, computer equipment and non-volatile computer-readable storage medium for identifying auto insurance risks, wherein the method includes: obtaining the report information of the target auto insurance case; inputting the report information into the report factor model for risk assessment to generate the first risk result of the target auto insurance case; when the first risk result exceeds the first preset threshold, inputting the report information into the text investigation model for risk assessment to generate the second risk result of the target auto insurance case; when the second risk result exceeds the second preset threshold, inputting the report information into one or more of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment to generate the third risk result of the target auto insurance case; based on the third risk result, judging whether the target auto insurance case is an auto insurance risk case. In this way, the method of the present invention can realize automatic, efficient and accurate identification of auto insurance risk behaviors. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic flow chart of a method for identifying auto insurance risks provided by an embodiment of the present invention.

[0048] Figure 2 A schematic diagram of functional modules of a vehicle insurance risk identification device provided in an embodiment of the present invention.

[0049] Figure 3 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. 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.

[0051] In the description of the present invention, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.

[0052] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] See also Figure 1 The embodiment of the present invention provides a method for identifying auto insurance risks, wherein the method comprises the following steps:

[0054] S100, obtaining the report information of the target automobile insurance case;

[0055] S200, inputting the case reporting information into a case reporting factor model for risk assessment to generate a first risk result of the target auto insurance case;

[0056] S300: When the first risk result exceeds a first preset threshold, the case report information is input into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case;

[0057] S400: when the second risk result exceeds a second preset threshold, inputting the case report information into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment to generate a third risk result for the target vehicle insurance case;

[0058] S500. Based on the third risk result, determine whether the target motor vehicle insurance case is a motor vehicle insurance risk case.

[0059] Furthermore, in the method for identifying vehicle insurance risks, the step S100 of obtaining the report information of the target vehicle insurance case specifically includes:

[0060] Obtain case information uploaded by the target user regarding the target auto insurance case;

[0061] The case information is integrated to generate corresponding case report information.

[0062] In the specific implementation, in this embodiment, the case information uploaded by the target user about the target auto insurance case is obtained; the case information is integrated to generate corresponding report information; wherein the specific implementation process is roughly as follows:

[0063] 1) User uploads case information

[0064] The target user uploads case information related to the target auto insurance case through the insurance company's online platform or mobile application; such case information may include but is not limited to accident scene photos, vehicle damage photos, accident description, driver information, witness statements, weather and road conditions, etc.;

[0065] 2) Information verification and preprocessing

[0066] After receiving the case information uploaded by the target user, first verify it to ensure that all necessary fields are filled in and the format is correct; for multimedia content such as photos and videos, check whether the file format and size meet the requirements;

[0067] Next, the text information is preprocessed, including text cleaning (removing useless punctuation marks, blank characters, etc.), word segmentation, and removal of stop words, etc., to facilitate subsequent text analysis;

[0068] 3) Information Integration

[0069] Consolidate all information uploaded by the target user into a single case record; this includes associating text descriptions, photos, videos, and other relevant files, and generating a unique case number for each auto insurance case;

[0070] During the information integration process, some information may be automatically filled in, such as weather and road condition data automatically obtained based on the location of the target user;

[0071] 4) Report information generation

[0072] After the information is integrated, a structured report information document will be generated; this document will contain all the key information of the target auto insurance case, such as case number, accident time, location, involved vehicles, driver information, accident description, on-site photos, etc.

[0073] Through the above process, the case information uploaded by the target users can be effectively collected, integrated and processed, laying a solid foundation for subsequent risk assessment and risk identification.

[0074] Furthermore, the method for identifying the risk of automobile insurance, wherein the step S200, inputting the case reporting information into the case reporting factor model for risk assessment to generate the first risk result of the target automobile insurance case, specifically includes:

[0075] Pre-construction of the reporting factor model;

[0076] The case reporting information is input into the case reporting factor model for risk assessment to generate a first risk result for the target vehicle insurance case.

[0077] In the specific implementation, in this embodiment, a case reporting factor model is pre-built; the case reporting information is input into the case reporting factor model for risk assessment to generate the first risk result of the target auto insurance case; wherein the specific implementation process is roughly as follows:

[0078] 1) Construction of the reporting factor model

[0079] Data collection: First, it is necessary to collect historical auto insurance case data, including confirmed auto insurance risk cases and non-auto insurance risk cases; this data will be used to train the model;

[0080] Feature selection: Select features related to risk behavior from historical auto insurance case data, such as reporting time, accident type, vehicle information, driver history, accident location, etc.;

[0081] Model training: Use machine learning algorithms (such as logistic regression, random forest, support vector machine, etc.) to train the selected features and build a reporting factor model. During the training process, the reporting factor model will learn how to predict whether a case is a risk based on the input features.

[0082] Model validation: The reporting factor model is validated through cross-validation and other methods to ensure that the reporting factor model has high accuracy and generalization ability;

[0083] 2) Input of report information

[0084] When the target user uploads the case information of the target auto insurance case and generates the report information, the report information will be used as input data, including text description, photos, videos, etc.;

[0085] Data preprocessing: preprocess the input report information, including text cleaning, feature extraction, data standardization, etc., to ensure that the data format is consistent with the data format used in the training of the report factor model;

[0086] 3) Risk Assessment

[0087] Model reasoning: The pre-processed report information is input into the report factor model, which will perform risk assessment on the target auto insurance case based on the rules learned during training;

[0088] Generate risk results: The reporting factor model will output a risk score, which reflects the possibility that the target auto insurance case is judged as an auto insurance risk case; the higher the risk score, the greater the possibility that the target auto insurance case is judged as an auto insurance risk case;

[0089] Through the above process, the reporting factor model can effectively conduct a preliminary risk assessment of the target auto insurance case and provide insurance companies with preliminary decision support for risk identification.

[0090] Furthermore, the method for identifying the risk of automobile insurance, wherein the step S300, when the first risk result exceeds a first preset threshold, inputs the case report information into a text investigation model for risk assessment to generate a second risk result of the target automobile insurance case, specifically includes:

[0091] Pre-build text exploration models;

[0092] When the first risk result exceeds a first preset threshold, the report information is input into the text investigation model for risk assessment to generate a second risk result for the target auto insurance case.

[0093] In specific implementation, in this embodiment, a text investigation model is pre-built; when the first risk result exceeds a first preset threshold, the case report information is input into the text investigation model for risk assessment to generate a second risk result of the target auto insurance case; wherein the specific implementation process is roughly as follows:

[0094] 1) Construction of text exploration model

[0095] Data preparation: Collect text data of historical auto insurance cases, including accident descriptions, witness statements, on-site investigation records, etc.; these data will be used to train the model;

[0096] Feature engineering: extract useful features from text data, such as keywords, phrases, semantic patterns, sentiment tendencies, etc. These features can reflect the relevance of text content and risky behavior;

[0097] Model selection: Select appropriate natural language processing (NLP) models for text analysis and risk assessment;

[0098] Model training: Use the extracted features and historical case data to train the text investigation model; the text investigation model learns how to predict the risk of a case based on the text content;

[0099] Model validation: The text search model is validated through methods such as cross-validation to ensure that the text search model has high accuracy and generalization ability;

[0100] 2) Evaluation of the first risk outcome

[0101] Application of the case reporting factor model: Input the case reporting information into the case reporting factor model to generate the first risk result of the target auto insurance case;

[0102] Threshold judgment: compare the first risk result with the first preset threshold; if the first risk result exceeds the first preset threshold, it indicates that the case has a high risk and requires further analysis;

[0103] 3) Input of report information

[0104] When the first risk result exceeds a first preset threshold, the report information is input into the text investigation model;

[0105] Data preprocessing: preprocess the input report information to ensure that the data format is consistent with the data format used in text investigation model training;

[0106] 4) Risk Assessment

[0107] Model reasoning: The pre-processed report information is input into the text investigation model, which will conduct risk assessment on the target auto insurance case based on the rules learned during training;

[0108] Generate a second risk result: The text investigation model will output a new risk score, which reflects the possibility of the case being judged as a risk at the text level;

[0109] 5) Interpretation of results

[0110] Based on the second risk result output by the text investigation model, the risk level of the target auto insurance case is explained; for example, different risk thresholds can be set to divide the target auto insurance case into three levels: high risk, medium risk and low risk;

[0111] Through the above process, the text investigation model can effectively conduct in-depth text analysis and risk assessment of target auto insurance cases, providing insurance companies with more accurate risk identification decision support.

[0112] Further, the vehicle insurance risk identification method, wherein the step S400, when the second risk result exceeds the second preset threshold, inputs the case report information into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment, and generates a third risk result of the target vehicle insurance case, specifically including:

[0113] Pre-build a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model;

[0114] When the second risk result exceeds a second preset threshold, obtaining surveyor remark information of the target auto insurance case, and determining the risk type of the target auto insurance case according to the surveyor remark information;

[0115] Based on the risk type, the report information is input into one of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case.

[0116] In specific implementation, in this embodiment, a single-vehicle intentional collision model, a multi-vehicle intentional collision model and an accident scene forgery model are pre-built; when the second risk result exceeds the second preset threshold, the surveyor's remarks information of the target vehicle insurance case is obtained, and the risk type of the target vehicle insurance case is determined according to the surveyor's remarks information; based on the risk type, the report information is input into one of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment, and a third risk result of the target vehicle insurance case is generated; wherein the specific implementation process is roughly as follows:

[0117] 1) Build a specialized risk model

[0118] Data preparation: Collect historical auto insurance case data, especially those confirmed to be intentional single-vehicle collisions, intentional collisions by multiple parties, and cases of accident scene fabrication;

[0119] Feature Engineering: For each risk type, extract features related to the risk behavior; this may include the pattern of vehicle damage, description of the accident scene, surveyor notes, etc.

[0120] Model selection: Choose the appropriate machine learning algorithm, such as decision tree, random forest, gradient boosting machine, etc., to build the model for each risk type;

[0121] Model training: Use the extracted features and historical case data to train a model for each risk type; the model learns how to predict the risk type of a case based on the input features;

[0122] Model validation: Each model is validated through methods such as cross-validation to ensure that the model has high accuracy and generalization ability;

[0123] 2) Evaluation of the Second Risk Outcome

[0124] Application of text investigation model: input the report information into the text investigation model to generate the second risk result;

[0125] Threshold judgment: compare the second risk result with the second preset threshold; if the second risk result exceeds the second preset threshold, it indicates that the case has a higher risk and requires further analysis;

[0126] 3) Obtain surveyor's notes

[0127] When the second risk result exceeds the second preset threshold, the surveyor's remarks information of the target auto insurance case is obtained; such information may include the surveyor's observation of the accident scene, the assessment of the vehicle damage, the description of the driver's behavior, etc.;

[0128] 4) Determine the risk type

[0129] Analyze the surveyor's notes: Analyze and determine the risk type of the target auto insurance case based on the surveyor's notes; for example, if the surveyor mentions that the vehicle damage pattern does not match the accident description, it may be classified as a single-vehicle intentional collision;

[0130] 5) Input the corresponding model for risk assessment

[0131] Select model: Based on the determined risk type, select the corresponding risk model (single-vehicle intentional collision model, multiple-vehicle intentional collision model or accident scene forgery model);

[0132] Data preprocessing: Preprocess the reported information to ensure that the data format is consistent with the data format used in the training of each risk model;

[0133] Model reasoning: The pre-processed report information is input into the selected risk model. Each risk model will conduct risk assessment on the target auto insurance case based on the rules learned during training;

[0134] Generating the third risk result: Each risk model will output a new risk score, which reflects the possibility of the target auto insurance case being judged as an auto insurance risk case under a specific risk type;

[0135] 6) Interpretation of results

[0136] Result interpretation: Based on the third risk results output by each risk model, the risk level of the target auto insurance case is explained;

[0137] Through the above process, insurance companies can more accurately identify different types of risk behaviors and improve the efficiency and accuracy of auto insurance risk identification.

[0138] Furthermore, in the method for identifying the risk of automobile insurance, the step S500 of determining whether the target automobile insurance case is an automobile insurance risk case based on the third risk result specifically includes:

[0139] Comparing the third risk result with a third preset threshold to generate a comparison result;

[0140] Based on the comparison result, determine whether the target auto insurance case is an auto insurance risk case.

[0141] Furthermore, the method for identifying auto insurance risk, wherein the step S500, based on the third risk result, determines whether the target auto insurance case is an auto insurance risk case, specifically further includes:

[0142] When the target auto insurance case is an auto insurance risk case, an alarm is issued;

[0143] The first risk result is returned to the target user as the final risk assessment result of the target auto insurance case.

[0144] In specific implementation, in this embodiment, the third risk result is compared with the third preset threshold to generate a comparison result; based on the comparison result, it is determined whether the target auto insurance case is an auto insurance risk case; when the target auto insurance case is an auto insurance risk case, an alarm is issued; the first risk result is returned to the target user as the final risk assessment result of the target auto insurance case; wherein the specific implementation process is roughly as follows:

[0145] 1) Compare the third risk result with the third preset threshold

[0146] Risk comparison: Compare the generated third risk results with the third preset threshold; this threshold is set based on historical data and business needs to distinguish high-risk and low-risk cases;

[0147] 2) Generate comparison results

[0148] Generate result: Generate a clear comparison result based on the comparison; if the third risk result exceeds the third preset threshold, the comparison result is "high risk", otherwise it is "low risk";

[0149] 3) Determine whether it is a car insurance risk case

[0150] Decision-making judgment: Based on the comparison results, determine whether the target auto insurance case is an auto insurance risk case; for example, if the comparison result is "high risk", it is determined to be an auto insurance risk case; if it is "low risk", it is determined to be a non-auto insurance risk case;

[0151] 4) Alarm prompts

[0152] Alarm mechanism: Once the target auto insurance case is determined to be an auto insurance risk case, an alarm will be automatically triggered; this alarm can be a warning within the system, an email or SMS notification sent to relevant personnel, or a warning message displayed on the user interface;

[0153] Investigation start: After the alarm is triggered, the relevant investigators or risk detection team will intervene to conduct an in-depth investigation of the target auto insurance case to confirm whether there is indeed any risky behavior;

[0154] 5) Return the final risk assessment results

[0155] Result return: Regardless of whether the target auto insurance case is determined to be an auto insurance risk case, the first risk result (score or level) will be returned to the target user as the final risk assessment result of the target auto insurance case; this final risk assessment result can be used as a reference for the target user to understand the risk assessment of the target auto insurance case;

[0156] Through the above process, auto insurance cases can be handled automatically, potential risk behaviors can be identified quickly and accurately, and relevant personnel can be notified in a timely manner for processing, while providing users with the final risk assessment results.

[0157] It can be seen from the above method embodiments that the auto insurance risk identification method provided by the present invention includes: obtaining the report information of the target auto insurance case; inputting the report information into the report factor model for risk assessment to generate the first risk result of the target auto insurance case; when the first risk result exceeds the first preset threshold, inputting the report information into the text investigation model for risk assessment to generate the second risk result of the target auto insurance case; when the second risk result exceeds the second preset threshold, inputting the report information into one or more of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment to generate the third risk result of the target auto insurance case; based on the third risk result, judging whether the target auto insurance case is an auto insurance risk case. In this way, the method of the present invention can realize automatic, efficient and accurate identification of auto insurance risk behaviors.

[0158] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.

[0159] Based on the above method embodiment, please refer to Figure 2 Another embodiment of the present invention further provides a vehicle insurance risk identification device, wherein the device comprises:

[0160] The acquisition module 11 is used to obtain the report information of the target vehicle insurance case;

[0161] A first evaluation module 12, used for inputting the case reporting information into a case reporting factor model for risk evaluation, and generating a first risk result of the target auto insurance case;

[0162] A second evaluation module 13 is used to input the report information into a text investigation model for risk evaluation to generate a second risk result of the target auto insurance case when the first risk result exceeds a first preset threshold;

[0163] A third assessment module 14 is configured to input the case report information into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment when the second risk result exceeds a second preset threshold, and generate a third risk result of the target vehicle insurance case;

[0164] The judgment module 15 is used to judge whether the target motor vehicle insurance case is a motor vehicle insurance risk case based on the third risk result.

[0165] Furthermore, in the method for identifying the risk of automobile insurance, the acquisition module 11 specifically includes:

[0166] A case information acquisition unit, used to acquire case information uploaded by a target user regarding a target auto insurance case;

[0167] The information integration unit is used to integrate the case information and generate corresponding report information.

[0168] Furthermore, in the vehicle insurance risk identification method, the first assessment module 12 specifically includes:

[0169] A first model building unit, used to pre-build a case reporting factor model;

[0170] The first risk assessment unit is used to input the report information into the report factor model for risk assessment to generate a first risk result of the target motor vehicle insurance case.

[0171] Furthermore, in the method for identifying the risk of automobile insurance, the second evaluation module 13 specifically includes:

[0172] A second model building unit is used to pre-build a text exploration model;

[0173] The second risk assessment unit is used to input the report information into the text investigation model for risk assessment when the first risk result exceeds a first preset threshold value, so as to generate a second risk result of the target motor vehicle insurance case.

[0174] Furthermore, in the vehicle insurance risk identification method, the third assessment module 14 specifically includes:

[0175] The third model building unit is used to pre-build a single-vehicle intentional collision model, a multi-vehicle intentional collision model and an accident scene forgery model;

[0176] a risk type determination unit, configured to obtain surveyor remark information of the target auto insurance case when the second risk result exceeds a second preset threshold, and determine the risk type of the target auto insurance case according to the surveyor remark information;

[0177] The third risk assessment unit is used to input the report information into one of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment based on the risk type, and generate a third risk result of the target vehicle insurance case.

[0178] Furthermore, in the method for identifying the risk of automobile insurance, the judgment module 15 specifically includes:

[0179] A comparison unit, used for comparing the third risk result with a third preset threshold value to generate a comparison result;

[0180] A judgment unit is used to judge whether the target motor vehicle insurance case is a motor vehicle insurance risk case based on the comparison result.

[0181] Furthermore, in the method for identifying the risk of automobile insurance, the judgment module 15 specifically further comprises:

[0182] An alarm unit, used for issuing an alarm when the target vehicle insurance case is a vehicle insurance risk case;

[0183] A result returning unit is used to return the first risk result as the final risk assessment result of the target auto insurance case to the target user.

[0184] The specific implementation process and effects of the device embodiment of the present invention can be found in the above method embodiment, which will not be described in detail here.

[0185] It can be seen from the above device embodiments that the vehicle insurance risk identification device provided by the present invention includes: an acquisition module for acquiring the report information of the target vehicle insurance case; a first evaluation module for inputting the report information into the report factor model for risk assessment to generate the first risk result of the target vehicle insurance case; a second evaluation module for inputting the report information into the text investigation model for risk assessment when the first risk result exceeds the first preset threshold value to generate the second risk result of the target vehicle insurance case; a third evaluation module for inputting the report information into one or more of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment when the second risk result exceeds the second preset threshold value to generate the third risk result of the target vehicle insurance case; a judgment module for judging whether the target vehicle insurance case is a vehicle insurance risk case based on the third risk result. In this way, the device of the present invention can realize automatic, efficient and accurate identification of vehicle insurance risk behavior.

[0186] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides a computer device, wherein the computer device 10 includes:

[0187] memory 120 and one or more processors 110, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a communication bus or other means. Figure 3 The example of connection via a communication bus is taken as an example.

[0188] The processor 110 is used to complete various control logics of the computer device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP, or any other such configuration.

[0189] The memory 120 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the computer program corresponding to the auto insurance risk identification method in any of the above method embodiments of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, implements the auto insurance risk identification method in any of the above method embodiments.

[0190] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created according to the use of the computer device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0191] One or more units are stored in the memory 120, and when executed by one or more processors 110, the vehicle insurance risk identification method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S500.

[0192] Those skilled in the art will understand that Figure 3 The hardware structure diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0193] Based on the above method embodiments, another embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the vehicle insurance risk identification method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S500.

[0194] It should be noted that the above-mentioned functions or steps that can be implemented by the non-volatile computer-readable storage medium or computer device, and the technical effects brought about by the functions / steps, can be found in the relevant descriptions in the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0195] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0196] Based on the above method embodiments, another embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the vehicle insurance risk identification method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S500.

[0197] It should be noted that the above-mentioned functions or steps that can be implemented by the computer program product, and the technical effects brought about by the functions / steps, can be found in the relevant descriptions in the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0198] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units 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.

[0199] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0200] Conditional language such as "can," "can," "might," or "may," unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey, among other things, that a particular embodiment can include (while other embodiments do not) a particular feature, element, and / or operation. Thus, such conditional language is also generally intended to imply that a feature, element, and / or operation is required for one or more embodiments anyway or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.

[0201] 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 example and do not represent actual use. The content described herein, in the specification and in the drawings includes examples that can provide a method, device, computer device and non-volatile computer-readable storage medium for identifying auto insurance risks. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure, but all these various modifications should fall within the scope of the claims attached to the present invention. In addition, or in the alternative, other embodiments of the present disclosure may be obvious from consideration of the present specification and the drawings and from the practice of the present disclosure as presented herein. It is intended that the examples set forth in the present specification and the drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are used herein, they are used in a general and descriptive sense and are not used for limiting purposes.

Claims

1. A method for identifying auto insurance risk, characterized in that: include: Obtain the reporting information of the target auto insurance case; Inputting the case reporting information into the case reporting factor model for risk assessment to generate a first risk result of the target auto insurance case; When the first risk result exceeds a first preset threshold, the case report information is input into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case; When the second risk result exceeds a second preset threshold, the report information is input into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case; Based on the third risk result, determine whether the target auto insurance case is an auto insurance risk case.

2. The method for identifying auto insurance risk according to claim 1, characterized in that: The obtaining of the reporting information of the target motor vehicle insurance case includes: Obtain case information uploaded by the target user regarding the target auto insurance case; The case information is integrated to generate corresponding case report information.

3. The method for identifying auto insurance risk according to claim 1, characterized in that: The step of inputting the case reporting information into a case reporting factor model for risk assessment to generate a first risk result of the target auto insurance case includes: Pre-construction of the reporting factor model; The case reporting information is input into the case reporting factor model for risk assessment to generate a first risk result for the target vehicle insurance case.

4. The method for identifying auto insurance risk according to claim 1, characterized in that: When the first risk result exceeds the first preset threshold, the case report information is input into the text investigation model for risk assessment to generate the second risk result of the target auto insurance case, including: Pre-build text exploration models; When the first risk result exceeds a first preset threshold, the report information is input into the text investigation model for risk assessment to generate a second risk result for the target auto insurance case.

5. The method for identifying auto insurance risk according to claim 1, characterized in that: When the second risk result exceeds the second preset threshold, the report information is input into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case, including: Pre-build a single-vehicle intentional collision model, a multi-vehicle intentional collision model, and an accident scene forgery model; When the second risk result exceeds a second preset threshold, obtaining surveyor remark information of the target auto insurance case, and determining the risk type of the target auto insurance case according to the surveyor remark information; Based on the risk type, the report information is input into one of the single-vehicle intentional collision model, the multi-vehicle intentional collision model and the accident scene forgery model for risk assessment to generate a third risk result of the target vehicle insurance case.

6. The method for identifying auto insurance risk according to any one of claims 2 to 5, characterized in that: The determining, based on the third risk result, whether the target auto insurance case is an auto insurance risk case includes: Comparing the third risk result with a third preset threshold to generate a comparison result; Based on the comparison result, determine whether the target auto insurance case is an auto insurance risk case.

7. The method for identifying auto insurance risk according to claim 6, characterized in that: The determining, based on the third risk result, whether the target auto insurance case is an auto insurance risk case further includes: When the target auto insurance case is an auto insurance risk case, an alarm is issued; The first risk result is returned to the target user as the final risk assessment result of the target auto insurance case.

8. A vehicle insurance risk identification device, characterized in that: include: An acquisition module is used to obtain the report information of the target auto insurance case; A first assessment module, used for inputting the case reporting information into a case reporting factor model for risk assessment, and generating a first risk result of the target auto insurance case; A second assessment module, configured to input the case report information into a text investigation model for risk assessment to generate a second risk result of the target auto insurance case when the first risk result exceeds a first preset threshold; A third assessment module is used for inputting the case report information into one or more of a single-vehicle intentional collision model, a multi-vehicle intentional collision model and an accident scene forgery model for risk assessment when the second risk result exceeds a second preset threshold, so as to generate a third risk result of the target vehicle insurance case; A judgment module is used to judge whether the target motor vehicle insurance case is a motor vehicle insurance risk case based on the third risk result.

9. A computer device, characterized in that: The computer device comprises at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the vehicle insurance risk identification method as described in any one of claims 1-7 can be implemented.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the vehicle insurance risk identification method as described in any one of claims 1-7 can be implemented.

Images