Vehicle insurance assessment method, system and equipment based on vehicle external damage image and medium

Abstract

The invention provides a vehicle insurance assessment method, system and device based on vehicle external damage images and a medium, and the method comprises the steps: obtaining the accident information of an accident vehicle, and the accident information comprises accident responsibility information and a plurality of external damage images; reading an information text of the accident liability determining information, and determining an accident type according to the information text, the accident type including a collision type, an overturning type and a non-collision type; according to the accident type, calling a preset neural network to identify the external damage image, and obtaining an accident damage area; and evaluating the corresponding claim settlement car insurance based on the accident type, the accident damage area and the accident liability determination information. According to the method, the actual condition of the accident can be accurately determined by combining the accident responsibility determination information and the multiple external damage images so as to fit the full view of the accident, and then comprehensive evaluation is performed according to the full view of the accident and the vehicle fault, so that the evaluation precision is improved, and the evaluation deviation is reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle insurance assessment, and in particular to a vehicle insurance assessment method, system, device and medium based on vehicle external damage images. Background Art

[0002] Motor vehicle insurance, also known as automobile insurance (abbreviated as auto insurance), refers to a commercial insurance that is responsible for compensation for personal injury or property damage caused by natural disasters or accidents involving motor vehicles. In motor vehicle insurance, vehicle loss insurance and third-party liability insurance constitute its main insurance types, and with the cooperation of several additional insurances, they jointly provide insurance customers with a variety of risk protection services.

[0003] Since users purchase multiple types of auto insurance and the terms of each auto insurance are superimposed or used in conjunction with each other, when an accident occurs, it is necessary to evaluate the auto insurance that matches the current accident from multiple auto insurances for subsequent claims processing. The commonly used evaluation method at present is to obtain the damaged image of the vehicle surface uploaded by the user, and then call the image processing method (such as edge detection, color analysis, etc.) to identify the damaged image to determine the type and degree of damage to the vehicle, and then determine the corresponding auto insurance category according to the type and degree of damage to the vehicle, so as to extract the suitable auto insurance terms from multiple auto insurances according to the vehicle category for subsequent services.

[0004] However, the commonly used methods currently have the following technical problems: an accident may involve multiple vehicles or users, and only the damage images on the surface of the accident vehicle are judged, which makes it difficult to reflect the actual picture of the accident and the internal faults of the vehicle, resulting in a large deviation between the subsequent assessed auto insurance category and the actual situation, and the assessment accuracy is low. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a method, system, device and medium for assessing vehicle insurance based on vehicle external damage images, which overcomes the above problems or at least partially solves the above problems, including:

[0006] A method for assessing vehicle insurance based on an image of vehicle external damage, the method comprising:

[0007] Acquiring accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images;

[0008] Reading the information text of the accident responsibility determination information, and determining the accident type according to the information text, the accident type including: collision type, rollover type and non-collision type;

[0009] Calling a preset neural network according to the accident type to identify the external damage image to obtain the accident damage area;

[0010] The corresponding car insurance claim is evaluated based on the accident type, the accident damage area and the accident liability information.

[0011] In a possible implementation, calling a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area includes:

[0012] If the accident type is a collision type or an overturning type, a real-time profile and a historical profile of the vehicle are obtained through a panoramic image of the vehicle;

[0013] Calculating contour line similarities between the real-time contour and the historical contour to obtain multiple contour line similarities;

[0014] Selecting target contour lines whose values ​​are less than a preset similarity from the plurality of contour line similarities, and determining the position coordinates of the target contour lines on the vehicle to obtain first position coordinates;

[0015] Selecting a plurality of first target images at positions corresponding to the first position coordinates from the plurality of external damage images;

[0016] The preset neural network is called to identify the first target image according to the contour of the image to obtain the accident damage area.

[0017] In a possible implementation, calling a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area includes:

[0018] If the accident type is a non-collision type, obtaining a faulty device of the vehicle;

[0019] Determine the position of the faulty device on the vehicle to obtain a second position coordinate;

[0020] Selecting a plurality of second target images at positions corresponding to the second position coordinates from the plurality of external damage images;

[0021] The preset neural network is called to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

[0022] In a possible implementation, the evaluating corresponding claim settlement of the automobile insurance based on the accident type, the accident damage area, and the accident liability information includes:

[0023] Splitting the accident type, the accident damage area and the accident responsibility information into multiple fields and forming a feature field set;

[0024] Calculating the matching degree between the feature field set and the preset auto insurance field set to obtain a plurality of field matching degrees, wherein each of the preset auto insurance field sets is a set of claim service fields of the auto insurance purchased by the user;

[0025] A target matching degree greater than a preset matching degree is screened from the multiple field matching degrees, and the auto insurance corresponding to the target matching degree is determined as the claim settlement auto insurance.

[0026] In a possible implementation, after the step of evaluating the corresponding claim settlement vehicle insurance based on the accident type, the accident damage area, and the accident liability information, the method further includes:

[0027] Determine the process information of the motor insurance claim, and determine the process steps of each claim process according to the process information;

[0028] After assigning a corresponding communication interface to each of the process steps, a user interface for process processing is constructed using the interface components corresponding to the communication interface, and the user interface is transmitted to the user terminal for the user to perform claims processing according to the user interface.

[0029] In a possible implementation, after the step of evaluating the corresponding claim settlement vehicle insurance based on the accident type, the accident damage area, and the accident liability information, the method further includes:

[0030] Obtaining the area value of the accident damage area;

[0031] If the area value of the region is greater than the preset area value, obtaining the operating parameters of the vehicle according to the accident damage area;

[0032] A fault repair solution is provided to the user according to the operating parameters.

[0033] In a possible implementation, providing a fault repair solution to a user according to the operating parameters includes:

[0034] If the operating parameter is not within the preset parameter range, searching for a number of vehicle maintenance coordinates with the current location of the accident vehicle as the center;

[0035] A plurality of maintenance routes are generated using the plurality of vehicle maintenance coordinates, and a fault repair plan is generated using the plurality of maintenance routes and transmitted to a user terminal for user reference.

[0036] A vehicle insurance assessment system based on vehicle external damage images, the system comprising:

[0037] An acquisition module, used to acquire accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images;

[0038] A determination module, used to read the information text of the accident responsibility determination information, and determine the accident type according to the information text, wherein the accident type includes: collision type, overturning type and non-collision type;

[0039] An identification module, used to call a preset neural network to identify the external damage image according to the accident type to obtain the accident damage area;

[0040] An evaluation module is used to evaluate the corresponding car insurance claim based on the accident type, the accident damage area and the accident liability information.

[0041] In a possible implementation, the identification module is further used to:

[0042] If the accident type is a collision type or an overturning type, a real-time profile and a historical profile of the vehicle are obtained through a panoramic image of the vehicle;

[0043] Calculating contour line similarities between the real-time contour and the historical contour to obtain multiple contour line similarities;

[0044] Selecting target contour lines whose values ​​are less than a preset similarity from the plurality of contour line similarities, and determining the position coordinates of the target contour lines on the vehicle to obtain first position coordinates;

[0045] Selecting a plurality of first target images at positions corresponding to the first position coordinates from the plurality of external damage images;

[0046] The preset neural network is called to identify the first target image according to the contour of the image to obtain the accident damage area.

[0047] In a possible implementation, the identification module is further used to:

[0048] If the accident type is a non-collision type, obtaining a faulty device of the vehicle;

[0049] Determine the position of the faulty device on the vehicle to obtain a second position coordinate;

[0050] Selecting a plurality of second target images at positions corresponding to the second position coordinates from the plurality of external damage images;

[0051] The preset neural network is called to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

[0052] In a possible implementation, the evaluation module is further used to:

[0053] Splitting the accident type, the accident damage area and the accident responsibility information into multiple fields and forming a feature field set;

[0054] Calculating the matching degree between the feature field set and the preset auto insurance field set to obtain a plurality of field matching degrees, wherein each of the preset auto insurance field sets is a set of claim service fields of the auto insurance purchased by the user;

[0055] A target matching degree greater than a preset matching degree is screened from the multiple field matching degrees, and the auto insurance corresponding to the target matching degree is determined as the claim settlement auto insurance.

[0056] In a possible implementation, the system further includes:

[0057] A process determination module, configured to determine process information of the claim settlement of the auto insurance after evaluating the corresponding claim settlement of the auto insurance based on the accident type, the accident damage area and the accident liability determination information, and determine the process steps of each claim settlement process according to the process information;

[0058] Generate an interface module, which is used to assign a corresponding communication interface to each process step, use the interface components corresponding to the communication interface to build a process processing user interface, and transmit the user interface to the user terminal for the user to process claims according to the user interface.

[0059] In a possible implementation, the system further includes:

[0060] An area acquisition module, used for acquiring the area value of the accident damage area after the step of evaluating the corresponding claim settlement of the motor vehicle insurance based on the accident type, the accident damage area and the accident liability determination information;

[0061] A parameter acquisition module, configured to acquire the operating parameters of the vehicle according to the accident damage area if the area value of the area is greater than a preset area value;

[0062] The solution module is used to provide the user with a fault repair solution according to the operating parameters.

[0063] In a possible implementation, the solution module is used to:

[0064] If the operating parameter is not within the preset parameter range, searching for a number of vehicle maintenance coordinates with the current location of the accident vehicle as the center;

[0065] A plurality of maintenance routes are generated using the plurality of vehicle maintenance coordinates, and a fault repair plan is generated using the plurality of maintenance routes and transmitted to a user terminal for user reference.

[0066] A device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of vehicle insurance assessment based on vehicle external damage images as described above are implemented.

[0067] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of vehicle insurance assessment based on vehicle external damage images as described above are implemented.

[0068] This application has the following advantages:

[0069] In the embodiments of the present application, the present application can obtain the accident liability information and multiple external damage images of the accident vehicle; read the information text of the accident liability information, and determine the type of accident based on the information text; call the preset neural network to identify the external damage image according to the accident type to obtain the accident damage area; evaluate the corresponding claim auto insurance based on the accident type, accident damage area and accident liability information. By combining the accident liability information and multiple external damage images, the actual situation of the accident can be accurately determined to fit the overall picture of the accident, and then a comprehensive evaluation can be performed based on the overall picture of the accident and the vehicle's fault to improve the accuracy of the evaluation and reduce the deviation of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0071] Figure 1 This is a flowchart of a method for evaluating vehicle insurance based on vehicle external damage images provided by an embodiment of the present application;

[0072] Figure 2 This is a structural block diagram of a vehicle insurance assessment system based on vehicle external damage images provided by an embodiment of the present application;

[0073] Figure 3 It is a structural diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0075] Motor vehicle insurance, also known as automobile insurance (abbreviated as auto insurance), refers to a commercial insurance that is responsible for compensation for personal injury or property damage caused by natural disasters or accidents involving motor vehicles. In motor vehicle insurance, vehicle loss insurance and third-party liability insurance constitute its main insurance types, and with the cooperation of several additional insurances, they jointly provide insurance customers with a variety of risk protection services.

[0076] Since users purchase multiple types of auto insurance and the terms of each auto insurance are superimposed or used in conjunction with each other, when an accident occurs, it is necessary to evaluate the auto insurance that matches the current accident from multiple auto insurances for subsequent claims processing. The commonly used evaluation method at present is to obtain the damaged image of the vehicle surface uploaded by the user, and then call the image processing method (such as edge detection, color analysis, etc.) to identify the damaged image to determine the type and degree of damage to the vehicle, and then determine the corresponding auto insurance category according to the type and degree of damage to the vehicle, so as to extract the suitable auto insurance terms from multiple auto insurances according to the vehicle category for subsequent services.

[0077] However, the commonly used methods currently have the following technical problems: an accident may involve multiple vehicles or users, and only the damage images on the surface of the accident vehicle are judged, which makes it difficult to reflect the actual picture of the accident and the internal faults of the vehicle, resulting in a large deviation between the subsequent assessed auto insurance category and the actual situation, and the assessment accuracy is low.

[0078] Reference Figure 1 , showing a flowchart of a method for assessing vehicle insurance based on vehicle external damage images provided by an embodiment of the present application;

[0079] In one embodiment, the vehicle insurance assessment method based on vehicle external damage images is applicable to the management system or business processing system of an insurance company, which can be the management system or business processing system of the company that provides the vehicle insurance service purchased by the user. The database of the system stores relevant data and information of the vehicle insurance service purchased by the user, so that when an accident occurs to the user's vehicle, the claim vehicle insurance that meets the current accident scenario can be screened from a number of vehicle insurance services to improve the accuracy of the vehicle insurance assessment.

[0080] Wherein, as an example, the vehicle insurance assessment method based on the vehicle external damage image may include:

[0081] S11. Obtain accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images.

[0082] In one embodiment, the business processing system can be connected to the user's smart terminal for communication. The user may be a user who has purchased auto insurance. The user can communicate with the business processing system through his smart terminal to facilitate his inquiry and claim processing.

[0083] In one operation mode, when a user has an accident, the user can upload the accident information to the business processing system through his smart terminal, wherein the accident information includes: accident responsibility determination information and multiple external damage images.

[0084] Specifically, the accident responsibility determination information may be relevant information of the accident identification document of the accident. The user may take an image of the accident identification document and transmit the image of the accident identification document to the business processing system.

[0085] Specifically, the external damage image may be an image of the appearance of the accident vehicle taken by the user. The external damage image may include images of the front, side, back, etc. of the accident vehicle; the external damage image may also include images of the collision area or collision position at different angles.

[0086] Through a comprehensive assessment of the relevant information in the accident report and images of external damage, the actual condition of the accident vehicle and the responsibility for the accident are determined. Then, based on the actual condition of the accident vehicle and the responsibility for the accident, the auto insurance and claim items that are in line with the user's actual status are evaluated, and claims services are provided to the user based on the evaluation results.

[0087] S12. Read the information text of the accident responsibility determination information, and determine the accident type according to the information text, wherein the accident type includes: collision type, overturning type and non-collision type.

[0088] In one embodiment, the accident responsibility information may be an image of an accident identification document, and the image content of the accident identification document may be converted into text, and then the text content of the accident identification document may be read to obtain the information text. Next, the content of the accident may be extracted from the information text, including the time of the accident, the object of the accident collision, the number of people or objects collided, the object of the accident responsibility, the cause of the accident, and the like.

[0089] If the cause of the accident is a human collision, then the accident type can be determined to be a collision type; if the cause of the accident is a vehicle failure, then the accident type is a rollover type; if the cause of the accident is neither a human collision nor a vehicle failure, then the accident type can be determined to be a non-collision type.

[0090] In one operation mode, the business processing system may be provided with a text reading and recognition model, and the preset text reading and recognition model may be called to read the field content of the cause of the accident to determine the type of accident.

[0091] To avoid errors, after the accident type is determined, the text of the accident type and cause can be transmitted to the auditor's smart terminal for the auditor to review. If the auditor does not modify it, the accident type is determined; if the auditor modifies it, the assessment type entered by the auditor can be obtained to determine the accident type.

[0092] S13. Calling a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area.

[0093] Different types of accidents may cause different damages, and the location of vehicle damage is also different. After determining the type of accident, the preset neural network can be called according to the different accident types to identify the external damage image. Specifically, the color, outline, shape, etc. of the external damage image can be identified, and then the area of ​​the vehicle damaged after the accident can be determined based on the color, outline, and shape of the image. Subsequently, the claim items can be determined based on the location, size, and severity of the accident damage area, and then the auto insurance that meets the user's current needs can be determined based on the claim items for the user's reference.

[0094] If the accident type is a collision type or an overturning type, the vehicle generally collides or overturns. After the collision or overturning, the shape or structure of the vehicle will change. For example, if the vehicle rear-ends, the front of the vehicle collides with the parking space of the vehicle in front, and the front of the vehicle will be dented. In order to determine the specific damage area of ​​the vehicle according to the structural contour of the vehicle, as an example, calling a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area may include the following sub-steps:

[0095] S21. If the accident type is a collision type or an overturning type, a real-time profile and a historical profile of the vehicle are acquired through a panoramic image of the vehicle.

[0096] S22, calculating the contour line similarity between the real-time contour and the historical contour to obtain a plurality of contour line similarities.

[0097] S23, selecting target contour lines whose similarity values ​​are less than a preset similarity from the plurality of contour lines, and determining position coordinates of the target contour lines on the vehicle to obtain first position coordinates.

[0098] S24, selecting a plurality of first target images at positions corresponding to the first position coordinates from the plurality of external damage images.

[0099] S25. Calling a preset neural network to identify the first target image according to the contour of the image to obtain the accident damage area.

[0100] In one embodiment, if the accident type is a collision type or an overturning type, the business processing system communicates with the vehicle-mounted terminal of the accident vehicle. After the communication is established, a panoramic image of the vehicle can be obtained through the vehicle's radar. The panoramic image may include a real-time panoramic image and a historical panoramic image. The historical panoramic image may be a panoramic image of the vehicle before the accident. The outline of the vehicle can be viewed in the panoramic image.

[0101] In a preferred operation mode, a panoramic image of a bird's-eye view can be obtained. After obtaining the panoramic image, the outline of the vehicle can be obtained in the real-time panoramic image to obtain the real-time outline of the vehicle; at the same time, the outline of the vehicle can be obtained in the historical panoramic image to obtain the historical outline of the vehicle.

[0102] Since the panoramic image is a bird's-eye view, when a collision occurs anywhere on the vehicle, there will be a dent at the collision site. For example, if the vehicle rear-ends, the front of the vehicle will be dented and the outline of the vehicle will also change. The specific accident and damage area can then be identified based on the outline of the vehicle.

[0103] Since there are many contour lines, in order to accurately identify the specific damage area, the contour lines of the real-time contour and the historical contour at the same position can be extracted simultaneously, and then the similarity between the two contour lines is calculated to obtain multiple contour line similarities.

[0104] For example, the contour lines of the real-time contour and the historical contour at the left front side of the vehicle body can be extracted at the same time, and then the similarity between the contour lines can be calculated. Then, the contour lines of the real-time contour and the historical contour at the left side of the vehicle body can be extracted, and then the similarity between the contour lines can be calculated. And so on, until the similarity between the contour lines at each position is calculated, and multiple contour line similarities are obtained.

[0105] If a vehicle collides at a certain location, the real-time contour and historical contour at that location will deviate greatly, and the corresponding contour lines will also have a small similarity.

[0106] Specifically, contour line similarities with values ​​less than a preset similarity may be screened from a plurality of contour line similarities, and the contour line similarities with values ​​less than the preset similarity may be taken as the target contour line.

[0107] If the similarity between the contour lines at a certain position is small, it means that the contour structure has changed greatly, and this may be the location where the collision occurred. The position coordinates of the target contour line on the vehicle can be determined to obtain the first position coordinates. Specifically, the position of the target contour line on the vehicle and the coordinates of the position in the panoramic image can be obtained.

[0108] After determining the position coordinates of the place where the collision is sent, the images at the position corresponding to the first position coordinates can be screened from the plurality of external damage images to obtain a plurality of first target images. The first target image is an image corresponding to the first position coordinates.

[0109] To facilitate screening, when users upload images, the smart terminal can set multiple upload interfaces, each of which corresponds to a location. Users can take pictures of different locations and then transmit the images of the corresponding locations to the business processing system through the upload interface. The business processing system can then search for the corresponding image based on the first location coordinates.

[0110] Next, a preset neural network may be called to identify the first target image according to the contour of the image to obtain the accident damage area.

[0111] The preset neural network may be a CNN neural network pre-trained by the user. Because the surface of the vehicle is smooth and flat before the collision, and the surface is uneven or fragmented or damaged after the collision. The preset neural network can identify the uneven contour of the image, the uneven part of the image, or the broken part of the image, and obtain the accident damage area.

[0112] By identifying the outline of the vehicle, the location where the vehicle collided can be determined, and then the corresponding image can be determined and identified based on the location. The collision and damaged area can be identified quickly and accurately, and damage assessment and claims can be processed based on the size, area and specific location of the accident damage area to determine the appropriate claim car insurance.

[0113] In another optional embodiment, the accident type may be a non-collision type. Non-collision type accidents can be divided into the following categories: First, various natural disasters listed in the insurance policy, such as floods, storms, lightning strikes, mudslides, earthquakes, etc. Second, various accidents listed in the insurance policy, such as fires, explosions, and falling objects in the air. Third, other accidents, such as capsizing, ice sinking, and accidents on the ferry carrying the insured vehicle.

[0114] Various accidents may also cause damage to the vehicle. In order to accurately detect the fault and damage location of the vehicle, image recognition is performed according to the fault and damage location of the vehicle. As an example, calling a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area may include the following sub-steps:

[0115] S31. If the accident type is a non-collision type, obtain the faulty equipment of the vehicle.

[0116] S32: Determine the position of the faulty device in the vehicle to obtain a second position coordinate.

[0117] S33, selecting a plurality of second target images at positions corresponding to the second position coordinates from the plurality of external damage images.

[0118] S34, calling a preset neural network to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

[0119] In one embodiment, a plurality of sensors and radars may be provided on the outside and inside of the vehicle, and each device and apparatus is used to detect the status and parameters of the vehicle so as to perform control according to the parameters.

[0120] In one operation mode, the business processing system can communicate with the vehicle's onboard terminal, and then communicate with various devices or sensors of the vehicle through the onboard terminal. If the communication is successful, the parameters collected by the device or device can be obtained. If the parameters collected by the device or device are not within the normal parameter range, it is determined that the device or device is a faulty device. If the device or device fails to communicate, it can also be determined that the device or device is a faulty device.

[0121] Next, the position coordinates of the faulty device on the vehicle can also be obtained to obtain the second position coordinates. Then, according to the second position coordinates, the images at the position corresponding to the second position coordinates are selected from the plurality of external damage images to obtain a plurality of second target images.

[0122] Finally, the preset neural network is called to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

[0123] Because after an accident, the structural outline of the vehicle will also change. For example, when a vehicle is parked on the side of the road, a battery car next to it catches fire, which may affect the vehicle and burn it. At this time, the appearance of the vehicle will be blackened, and its color will deviate from the actual color. On this basis, the preset neural network can be called to identify the second target image according to the chromaticity value of the image, determine the second target image and the historical image of the same location with different colors, so as to obtain the accident damage area.

[0124] In order to improve the recognition accuracy, the image contrast of the second target image can be enhanced first, and then a preset color recognition model is called to locate and recognize the adjusted second target image to obtain the accident damage area.

[0125] Specifically, the preset neural network may be a CMYK (Cyan Magenta Yellow Key) color model, an HSB model or an RGB model.

[0126] In an actual operation mode, a plurality of vehicle appearance images may be used in advance for model training, and the user may mark the colors corresponding to the vehicle appearance and the colors corresponding to the non-vehicle appearance in a plurality of preset neural networks in advance.

[0127] During recognition, if the vehicle's appearance is defective or damaged (, its color will deviate from the color corresponding to the actual appearance. The model can identify the area of ​​the image corresponding to the color of the vehicle's appearance and the area of ​​the non-vehicle's appearance corresponding to the color based on the color, and then determine the accident damage area in the image.

[0128] S14. Evaluate the corresponding auto insurance claim based on the accident type, the accident damage area and the accident liability information.

[0129] In one embodiment, the accident type, accident damage area and accident liability information are compared one by one with the contents of the auto insurance purchased by the user, so that the claim auto insurance that meets the current actual situation can be evaluated from the multiple auto insurance services purchased by the user, so that the claim calculation can be provided to the user based on the evaluated claim auto insurance.

[0130] In an optional embodiment, since each auto insurance service has multiple clauses, in order to compare the multiple clauses of each auto insurance service one by one, as an example, the corresponding claim auto insurance based on the accident type, the accident damage area and the accident liability information may include the following steps:

[0131] S141. Split the accident type, the accident damage area and the accident responsibility information into multiple fields and form a characteristic field set.

[0132] S142. Calculate the matching degree between the characteristic field set and the preset auto insurance field set to obtain multiple field matching degrees, wherein each of the preset auto insurance field sets is a set of claim service fields of the auto insurance purchased by the user.

[0133] S143. Filter a target matching degree that is greater than a preset matching degree from the multiple field matching degrees, and determine that the auto insurance corresponding to the target matching degree is a claim settlement auto insurance.

[0134] Specifically, the text of the accident type can be split into multiple fields, the text of the accident damage area can be split into multiple fields, and the text of the accident responsibility information can be split into multiple fields. Then, the multiple fields can be combined into a set of fields to obtain a feature field set.

[0135] Next, the auto insurance purchased by the user of the current accident vehicle can be determined, and then the clause text of the claim conditions of each auto insurance can be split to obtain multiple fields, and then the multiple fields can be combined into a field set to obtain a preset auto insurance field set for the auto insurance.

[0136] Then, the matching degree between the feature field set and each preset auto insurance field set can be calculated to obtain multiple field matching degrees. Finally, a target matching degree greater than the preset matching degree can be screened from the multiple field matching degrees, and the auto insurance corresponding to the target matching degree can be determined, and the auto insurance corresponding to the target matching degree can be used as the claim auto insurance.

[0137] In one operation mode, the fields of the feature field set can be abstracted into vectors. If the feature field set contains fields or entries in the preset auto insurance field set, the corresponding position vector of the field of the feature field set is set to 1, otherwise, the vector is set to 0.

[0138] Then count the frequency of the vector taking 1, and construct the weight vector according to the frequency. Finally, calculate the cosine similarity between the feature field set and each preset auto insurance field set based on the vector and the weight vector, so as to obtain the target matching degree.

[0139] In an optional embodiment, the user of the accident vehicle may not have purchased auto insurance. In this case, in order to provide claim services to the user, optionally, a preset auto insurance field set corresponding to each auto insurance of the enterprise can be determined, and then the matching degree of the feature field set and each preset auto insurance field set can be calculated to obtain multiple field matching degrees, and finally the auto insurance corresponding to the field matching degree with the largest value is the claim auto insurance, which is pushed to the user for reference whether to purchase it.

[0140] After determining the claim settlement auto insurance, the user needs to process the claim settlement. In order to facilitate the user to quickly complete the claim settlement process, as an example, after the step of evaluating the corresponding claim settlement auto insurance based on the accident type, the accident damage area and the accident liability information, the method may further include the following sub-steps:

[0141] S41, determining the process information of the motor insurance claim, and determining the process steps of each claim process according to the process information.

[0142] S42. After assigning a corresponding communication interface to each of the process steps, a user interface for process processing is constructed using the interface components corresponding to the communication interface, and the user interface is transmitted to the user terminal for the user to process claims according to the user interface.

[0143] In one operation mode, process information for claiming motor insurance may be determined. The process information may be the relevant steps of the claim process and the information required for each step. Then, the process steps of each claim process may be determined according to the process information.

[0144] In order to facilitate operations on its intelligent terminal, the allocation operation nodes of each process step of the claims process are determined, and the allocation operation nodes are connected according to the order of operations. A communication interface can be allocated to the allocation operation node corresponding to each process step. Each communication interface corresponds to a component, and each component performs a business process.

[0145] The interface components corresponding to the communication interface can be used to build a user interface for process processing, and the user interface can be transmitted to the user's smart terminal. The user can click, upload information and process claims on the user interface of their smart terminal, thereby simplifying the process and improving the user's processing efficiency.

[0146] When the vehicle is damaged, the damaged area may be the speed door panel, the front air intake or the engine, etc. The damage in different areas may affect the driving of the vehicle or may not affect the driving of the vehicle. In order to prompt the user to perform repairs in time, as an example, after the step of evaluating the corresponding claim auto insurance based on the accident type, the accident damage area and the accident liability information, the method may also include the following sub-steps:

[0147] S51. Obtain the area value of the accident damage area.

[0148] S52: If the area value of the region is greater than a preset area value, obtaining the operating parameters of the vehicle according to the accident damage area.

[0149] S53: providing a fault repair solution to the user according to the operating parameters.

[0150] Specifically, the area value of the accident damage area can be obtained. Specifically, the recognized neural network can be called to calculate the area of ​​the accident damage area to obtain the area value. It is determined whether the area value is greater than the preset area value.

[0151] If the area value is greater than the preset area value, it means that the damaged area is large, and the vehicle's operating parameters can be obtained based on the accident damage area. Specifically, the location coordinates of the accident damage area can be determined, and then communication with the vehicle equipment in the area can be performed to obtain its operating parameters. Subsequently, a fault repair plan can be provided to the user based on the operating parameters.

[0152] Optionally, if there is a problem with the operating parameters, the devices whose parameters are not within the preset parameter range can be determined, and a fault repair solution can be provided to the user based on the type of device.

[0153] In actual operation, the user may be at the accident scene or not at the accident scene when processing the claim. In order to provide the user with the address of a shop that repairs the vehicle nearby according to the user's real-time location, as an example, providing the user with a fault repair plan according to the operating parameters may include the following sub-steps:

[0154] S531. If the operating parameter is not within the preset parameter range, searching for a number of vehicle maintenance coordinates with the current location of the accident vehicle as the center.

[0155] S532: Generate a plurality of maintenance routes using the plurality of vehicle maintenance coordinates, generate a fault repair plan using the plurality of maintenance routes, and transmit the plan to a user terminal for user reference.

[0156] Specifically, there may be multiple operating parameters obtained, and each operating parameter may be compared with its corresponding parameter range value one by one to determine whether the value of the operating parameter is within the preset parameter range value.

[0157] If the operating parameters are not within the preset parameter range, it means that the device may be faulty. At this time, you can obtain the current location of the vehicle, and then search for several vehicle maintenance coordinates in the preset map with the current location as the center. Specifically, it can be the address coordinates of the 4S store.

[0158] A driving route is generated using the current positioning and the maintenance coordinates of each vehicle to obtain several maintenance routes. Finally, several maintenance routes and the layers of the preset map can be combined to generate a fault repair plan and transmitted to the user terminal for reference.

[0159] In this embodiment, the embodiment of the present application provides a method for evaluating auto insurance based on vehicle external damage images, and its beneficial effects are: the present application can obtain the accident liability information and multiple external damage images of the accident vehicle; read the information text of the accident liability information, and determine the type of accident based on the information text; call the preset neural network to identify the external damage image according to the accident type, and obtain the accident damage area; evaluate the corresponding claim auto insurance based on the accident type, accident damage area and accident liability information. By combining the accident liability information and multiple external damage images, the actual situation of the accident can be accurately determined to fit the overall picture of the accident, and then a comprehensive evaluation can be performed based on the overall picture of the accident and the vehicle's fault to improve the accuracy of the evaluation and reduce the deviation of the evaluation.

[0160] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0161] Reference Figure 2, showing a structural block diagram of a vehicle insurance assessment system based on vehicle external damage images provided by an embodiment of the present application;

[0162] Specifically include:

[0163] The acquisition module 201 is used to acquire the accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images;

[0164] The determination module 202 is used to read the information text of the accident responsibility determination information and determine the accident type according to the information text, and the accident type includes: collision type, rollover type and non-collision type;

[0165] The recognition module 203 is used to call a preset neural network to recognize the external damage image according to the accident type to obtain the accident damage area;

[0166] The evaluation module 204 is used to evaluate the corresponding automobile insurance claim based on the accident type, the accident damage area and the accident liability information.

[0167] In an optional embodiment, the identification module is further used to:

[0168] If the accident type is a collision type or an overturning type, a real-time profile and a historical profile of the vehicle are obtained through a panoramic image of the vehicle;

[0169] Calculating contour line similarities between the real-time contour and the historical contour to obtain multiple contour line similarities;

[0170] Selecting target contour lines whose values ​​are less than a preset similarity from the plurality of contour line similarities, and determining the position coordinates of the target contour lines on the vehicle to obtain first position coordinates;

[0171] Selecting a plurality of first target images at positions corresponding to the first position coordinates from the plurality of external damage images;

[0172] The preset neural network is called to identify the first target image according to the contour of the image to obtain the accident damage area.

[0173] In an optional embodiment, the identification module is further used to:

[0174] If the accident type is a non-collision type, obtaining a faulty device of the vehicle;

[0175] Determine the position of the faulty device on the vehicle to obtain a second position coordinate;

[0176] Selecting a plurality of second target images at positions corresponding to the second position coordinates from the plurality of external damage images;

[0177] The preset neural network is called to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

[0178] In an optional embodiment, the evaluation module is further used for:

[0179] Splitting the accident type, the accident damage area and the accident responsibility information into multiple fields and forming a feature field set;

[0180] Calculating the matching degree between the feature field set and the preset auto insurance field set to obtain a plurality of field matching degrees, wherein each of the preset auto insurance field sets is a set of claim service fields of the auto insurance purchased by the user;

[0181] A target matching degree greater than a preset matching degree is screened from the multiple field matching degrees, and the auto insurance corresponding to the target matching degree is determined as the claim settlement auto insurance.

[0182] In an optional embodiment, the system further includes:

[0183] A process determination module, configured to determine process information of the claim settlement of the auto insurance after evaluating the corresponding claim settlement of the auto insurance based on the accident type, the accident damage area and the accident liability determination information, and determine the process steps of each claim settlement process according to the process information;

[0184] Generate an interface module, which is used to assign a corresponding communication interface to each process step, use the interface components corresponding to the communication interface to build a process processing user interface, and transmit the user interface to the user terminal for the user to process claims according to the user interface.

[0185] In an optional embodiment, the system further includes:

[0186] An area acquisition module, used for acquiring the area value of the accident damage area after the step of evaluating the corresponding claim settlement of the motor vehicle insurance based on the accident type, the accident damage area and the accident liability determination information;

[0187] A parameter acquisition module, configured to acquire the operating parameters of the vehicle according to the accident damage area if the area value of the area is greater than a preset area value;

[0188] The solution module is used to provide the user with a fault repair solution according to the operating parameters.

[0189] In an optional embodiment, the solution module is used to:

[0190] If the operating parameter is not within the preset parameter range, searching for a number of vehicle maintenance coordinates with the current location of the accident vehicle as the center;

[0191] A plurality of maintenance routes are generated using the plurality of vehicle maintenance coordinates, and a fault repair plan is generated using the plurality of maintenance routes and transmitted to a user terminal for user reference.

[0192] Reference Figure 3 , showing a computer device of a vehicle insurance assessment method based on vehicle external damage images of the present application, which may specifically include the following:

[0193] The computer device 12 is in the form of a general-purpose computing device, and 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 connecting different system components (including the system memory 28 and the processing unit 16).

[0194] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0195] 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.

[0196] System 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. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of the various embodiments of the present application.

[0197] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, 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 herein.

[0198] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable a user 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 cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 3 Not shown, 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 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0199] 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 vehicle insurance assessment method based on the vehicle external damage image provided in the embodiment of the present application.

[0200] That is, when the processing unit 16 executes the above program, the following is achieved:

[0201] Acquiring accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images;

[0202] Reading the information text of the accident responsibility determination information, and determining the accident type according to the information text, the accident type including: collision type, rollover type and non-collision type;

[0203] Calling a preset neural network according to the accident type to identify the external damage image to obtain the accident damage area;

[0204] The corresponding car insurance claim is evaluated based on the accident type, the accident damage area and the accident liability information.

[0205] In an embodiment of the present application, the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle insurance assessment method based on vehicle external damage images as provided in all embodiments of the present application is implemented.

[0206] That is, when the program is executed by the processor:

[0207] Acquiring accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images;

[0208] Reading the information text of the accident responsibility determination information, and determining the accident type according to the information text, the accident type including: collision type, rollover type and non-collision type;

[0209] Calling a preset neural network according to the accident type to identify the external damage image to obtain the accident damage area;

[0210] The corresponding car insurance claim is evaluated based on the accident type, the accident damage area and the accident liability information.

[0211] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device.

[0212] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0213] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0214] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0215] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0216] The above is a detailed introduction to the vehicle insurance assessment method, system, device and medium based on vehicle external damage images provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle insurance assessment method based on vehicle external damage images, characterized in that: The method comprises: Acquiring accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images; Reading the information text of the accident responsibility determination information, and determining the accident type according to the information text, the accident type including: collision type, rollover type and non-collision type; Calling a preset neural network according to the accident type to identify the external damage image to obtain the accident damage area; The corresponding car insurance claim is evaluated based on the accident type, the accident damage area and the accident liability information.

2. The vehicle insurance assessment method based on vehicle external damage images according to claim 1 is characterized in that: The calling of a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area includes: If the accident type is a collision type or an overturning type, a real-time profile and a historical profile of the vehicle are obtained through a panoramic image of the vehicle; Calculating contour line similarities between the real-time contour and the historical contour to obtain multiple contour line similarities; Selecting target contour lines whose values ​​are less than a preset similarity from the plurality of contour line similarities, and determining the position coordinates of the target contour lines on the vehicle to obtain first position coordinates; Selecting a plurality of first target images at positions corresponding to the first position coordinates from the plurality of external damage images; The preset neural network is called to identify the first target image according to the contour of the image to obtain the accident damage area.

3. The vehicle insurance assessment method based on vehicle external damage images according to claim 1 is characterized in that: The calling of a preset neural network according to the accident type to identify the external damage image and obtain the accident damage area includes: If the accident type is a non-collision type, obtaining a faulty device of the vehicle; Determine the position of the faulty device on the vehicle to obtain a second position coordinate; Selecting a plurality of second target images at positions corresponding to the second position coordinates from the plurality of external damage images; The preset neural network is called to identify the second target image according to the chromaticity value of the image to obtain the accident damage area.

4. The vehicle insurance assessment method based on vehicle external damage images according to claim 1 is characterized in that: The corresponding claim settlement of the automobile insurance based on the accident type, the accident damage area and the accident liability information includes: Splitting the accident type, the accident damage area and the accident responsibility information into multiple fields and forming a feature field set; Calculating the matching degree between the feature field set and the preset auto insurance field set to obtain a plurality of field matching degrees, wherein each of the preset auto insurance field sets is a set of claim service fields of the auto insurance purchased by the user; A target matching degree greater than a preset matching degree is screened from the multiple field matching degrees, and the auto insurance corresponding to the target matching degree is determined as the claim settlement auto insurance.

5. The vehicle insurance assessment method based on vehicle external damage images according to any one of claims 1 to 4, characterized in that: After the step of evaluating the corresponding claim settlement of the motor vehicle insurance based on the accident type, the accident damage area and the accident liability information, the method further includes: Determine the process information of the motor insurance claim, and determine the process steps of each claim process according to the process information; After assigning a corresponding communication interface to each of the process steps, a user interface for process processing is constructed using the interface components corresponding to the communication interface, and the user interface is transmitted to the user terminal for the user to perform claims processing according to the user interface.

6. The vehicle insurance assessment method based on vehicle external damage images according to any one of claims 1 to 4, characterized in that: After the step of evaluating the corresponding claim settlement of the motor vehicle insurance based on the accident type, the accident damage area and the accident liability information, the method further includes: Obtaining the area value of the accident damage area; If the area value of the region is greater than the preset area value, obtaining the operating parameters of the vehicle according to the accident damage area; A fault repair solution is provided to the user according to the operating parameters.

7. The vehicle insurance assessment method based on vehicle external damage images according to claim 6 is characterized in that: The providing a fault repair solution to the user according to the operating parameters comprises: If the operating parameter is not within the preset parameter range, searching for a number of vehicle maintenance coordinates with the current location of the accident vehicle as the center; A plurality of maintenance routes are generated using the plurality of vehicle maintenance coordinates, and a fault repair plan is generated using the plurality of maintenance routes and transmitted to a user terminal for user reference.

8. A vehicle insurance assessment system based on vehicle external damage images, characterized in that: The system comprises: An acquisition module, used to acquire accident information of the accident vehicle, wherein the accident information includes: accident responsibility determination information and multiple external damage images; A determination module, used to read the information text of the accident responsibility determination information, and determine the accident type according to the information text, wherein the accident type includes: collision type, overturning type and non-collision type; An identification module, used to call a preset neural network to identify the external damage image according to the accident type to obtain the accident damage area; An evaluation module is used to evaluate the corresponding car insurance claim based on the accident type, the accident damage area and the accident liability information.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle insurance assessment method based on vehicle external damage images as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the vehicle insurance assessment method based on vehicle external damage images as described in any one of claims 1-7.

Images