Business evaluation method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of image processing, is applied to a vehicle claim settlement loss assessment scene, and relates to a business assessment method, device and equipment and a storage medium thereof. Performing segmentation processing on the target image in the image group, and identifying a collision part contained in the target image and collision intensity corresponding to the collision part; the damage conditions of all vehicle parts in the affected area of the vehicle collision part under the collision strength are predicted; a maintenance list is generated, and the maintenance list comprises the component names of all to-be-maintained or to-be-replaced vehicle components; and generating a corresponding expense document according to the maintenance list, reporting the expense document to a target receiver, and completing the business evaluation. When the service evaluation method is applied to a vehicle insurance claim settlement service scene, a vehicle claim settlement worker is helped to identify a collision part and collision intensity, so that a claim settlement service related list is generated.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and is applied to vehicle claim settlement and damage assessment scenarios, and in particular to a business assessment method, device, equipment, and storage medium thereof. Background Art

[0002] In recent years, the number of cars in my country has been growing at an accelerated pace, and the auto insurance industry has also been developing rapidly. In the auto insurance market, vehicle accident damage assessment is a very important link. Generally speaking, when an insured vehicle is involved in a traffic accident, the insurance company will assign front-end surveyors and damage assessors to go to the scene or 4S stores to conduct surveys and damage assessments, and cooperate with back-end damage assessment and price assessment personnel to complete the accident damage assessment and claims work.

[0003] At present, for vehicle damage assessment at this stage, the accident vehicle valuation and damage assessment systems currently used by insurance companies and auto repair companies are mostly operated on PCs, which cannot conveniently implement vehicle damage assessment; there is also a lack of systematic and standardized damage assessment methods, which cannot better assist vehicle claims staff in conducting claims business assessments. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a business assessment method, device, equipment and storage medium thereof to solve the problem that the existing damage assessment method lacks systematic and standardized methods and cannot better assist vehicle claims personnel in conducting claims business assessments.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a service evaluation method, which adopts the following technical solution:

[0006] A business evaluation method comprises the following steps:

[0007] Acquire an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle;

[0008] Inputting the image group into a pre-trained image segmentation model, performing segmentation processing on the target image in the image group, and identifying the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result;

[0009] According to the preset vehicle component position relationship table and vehicle component bearing strength table, predict the damage of all vehicle components in the affected area of ​​the vehicle collision under the intensity of this collision;

[0010] Input the damage conditions of all vehicle components in the affected area of ​​the vehicle collision under the intensity of the collision as evaluation indicators into a preset evaluation model to obtain a maintenance list output by the evaluation model, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced;

[0011] Generate corresponding expense documents based on the maintenance list and report them to the target recipient to complete this business evaluation.

[0012] Furthermore, before executing the step of inputting the image group into the pre-trained image segmentation model, the method further includes:

[0013] Obtain batches of vehicle accident images and construct a training dataset;

[0014] The training data set is input into the image segmentation model to be trained, and the image segmentation model to be trained is trained to obtain a pre-trained image segmentation model.

[0015] Furthermore, before executing the step of inputting the training data set into the image segmentation model to be trained and performing learning training on the image segmentation model to be trained to obtain a pre-trained image segmentation model, the method further includes:

[0016] Classifying the segmentation difficulty of all vehicle accident images in the training data set according to the preset vehicle part segmentation difficulty;

[0017] Based on the segmentation difficulty supported by the image segmentation model, filter out the vehicle accident images that can be processed by the image segmentation model from the segmentation difficulty classification results;

[0018] The vehicle accident images processable by the image segmentation model are updated to the latest training data set.

[0019] Furthermore, before executing the step of segmenting the target image in the image group, the method further includes:

[0020] Identify the segmentation difficulty corresponding to each of the images in the image group;

[0021] According to the segmentation difficulty levels corresponding to all the images, the images that can be segmented and processed by the image segmentation model are selected from the image group as the target images, and the images that cannot be segmented and processed by the image segmentation model are selected from the image group;

[0022] All the images that cannot be processed are packaged and transmitted to the preset manual recognition detection end.

[0023] Furthermore, the step of segmenting the images in the image group and identifying the collision parts contained in the target image and the collision strengths corresponding to the collision parts according to the segmentation results specifically includes:

[0024] Using the image segmentation model to perform image segmentation processing on all target images;

[0025] Identifying actual damage information of the collision part contained in the target image according to the image segmentation processing result, wherein the actual damage information includes the damage size and the damage depression depth;

[0026] The collision intensity corresponding to the collision part in the target image is determined by referring to a preset collision intensity and actual damage information table.

[0027] Furthermore, before executing the step of predicting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of the collision according to the preset vehicle component position relationship table and vehicle component bearing strength table, the method further includes:

[0028] Receiving actual damage information of the collision part contained in all the indivisible processed images fed back by the manual recognition detection end;

[0029] Based on the collision intensity and actual damage information reference table, determining the collision intensity corresponding to the collision parts in all the images that cannot be processed in segments;

[0030] Calculating a comprehensive collision location and a comprehensive collision intensity according to the collision intensity corresponding to the collision location in the target image and the collision intensity corresponding to the collision location in all the indivisible processed images;

[0031] The comprehensive collision part is set as the current vehicle collision part, and the comprehensive collision intensity is set as the current collision intensity.

[0032] Furthermore, the step of predicting the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of the collision according to the preset vehicle component position relationship table and the vehicle component bearing strength table also includes:

[0033] Based on prior knowledge, identify whether there are vehicle parts in the affected area of ​​the vehicle collision whose damage is difficult to predict;

[0034] If there are vehicle parts whose damage is difficult to predict in the area affected by the vehicle collision, the vehicle parts whose damage is difficult to predict are marked, and a request for manual inspection is sent to the target end.

[0035] In order to solve the above technical problems, the embodiment of the present application also provides a service evaluation device, which adopts the following technical solution:

[0036] A service evaluation device, comprising:

[0037] An image group acquisition module, used to acquire an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle;

[0038] An image segmentation processing module, used for inputting the image group into a pre-trained image segmentation model, performing segmentation processing on the target image in the image group, and identifying the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result;

[0039] The damage prediction module is used to predict the damage of all vehicle components in the affected area of ​​the vehicle collision under the intensity of this collision according to the preset vehicle component position relationship table and vehicle component bearing strength table;

[0040] A maintenance evaluation module, used to input the damage conditions of all vehicle components in the affected area of ​​the vehicle collision under the intensity of the collision as evaluation indicators into a preset evaluation model, and obtain a maintenance list output by the evaluation model, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced;

[0041] The expense document generation and reporting module is used to generate corresponding expense documents according to the maintenance list and report them to the target recipient to complete this business evaluation.

[0042] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0043] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned business evaluation method when executing the computer-readable instructions.

[0044] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0045] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business evaluation method described above are implemented.

[0046] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0047] The business evaluation method described in the embodiment of the present application obtains an image group uploaded by a target user; segments the target image in the image group, identifies the collision site contained in the target image and the collision intensity corresponding to the collision site; predicts the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of this collision; generates a maintenance list, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced; generates corresponding expense documents based on the maintenance list, reports them to the target recipient, and completes this business evaluation. Applying the business evaluation method to the auto insurance claims business scenario helps to assist vehicle claims staff in identifying collision sites and collision intensities, thereby generating a list related to the claims business. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0050] Figure 2 is a flow chart of an embodiment of a business evaluation method according to the present application;

[0051] Figure 3 yes Figure 2 A flowchart of a specific embodiment of learning and training the image segmentation model before step 202 is shown;

[0052] Figure 4 yes Figure 3 A flowchart of a specific embodiment of updating the training data set before step 302 is shown;

[0053] Figure 5 yes Figure 2 A flowchart of a specific embodiment of pre-classifying all images in the image group before step 202 is shown;

[0054] Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 202 is shown;

[0055] Figure 7 is a structural diagram of an embodiment of a service evaluation device according to the present application;

[0056] Figure 8 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0058] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0060] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0061] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0062] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0063] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0064] It should be noted that the service evaluation method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the service evaluation device is generally arranged in the terminal device.

[0065] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0066] Continue to refer Figure 2 , shows a flow chart of an embodiment of a service evaluation method according to the present application. The service evaluation method comprises the following steps:

[0067] Step 201, obtaining an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle;

[0068] In this embodiment, the target users include car owners, vehicle maintenance 4S shop users, claims service users, etc.; the image group includes vehicle accident images taken according to the collision part of the vehicle; by obtaining the image group uploaded by the target user, it is convenient to subsequently identify the vehicle accident images uploaded by the user and identify the collision information related to the vehicle accident. Applying the business evaluation method to the auto insurance claims business scenario is helpful to assist vehicle claims staff in identifying the collision part and collision intensity, thereby generating a list related to the claims business.

[0069] Step 202, inputting the image group into a pre-trained image segmentation model, performing segmentation processing on the target image in the image group, and identifying the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result;

[0070] An image segmentation model is used to segment the target image in the image group so that the damaged parts of the accident can be accurately identified from the uploaded vehicle accident images. The collision parts contained in the target image and the collision intensity corresponding to the collision parts are identified based on the segmentation processing results, which is helpful for evaluating the claims business.

[0071] Step 203, predicting the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of this collision according to the preset vehicle component position relationship table and vehicle component bearing strength table;

[0072] Specifically, the damage conditions of different vehicle parts under different collision intensities may be set, and the damage conditions include whether they are damaged;

[0073] Correspondingly, the step of predicting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision site under the current collision intensity according to the preset vehicle component position relationship form and vehicle component bearing strength form includes: screening out all vehicle components in the affected area of ​​the collision site according to the vehicle component position relationship form; comparing the bearing strength of all vehicle components with the collision intensity; if the collision intensity is greater than the bearing strength of the corresponding vehicle component, the corresponding vehicle component is damaged, otherwise, the corresponding vehicle component is not damaged.

[0074] Since the captured images can only identify the collision site and collision intensity through visual effects, combined with the vehicle component position relationship form and the vehicle component bearing strength form, the damage of all vehicle components in the affected area of ​​the vehicle collision site under the current collision intensity is predicted. The damage inside the vehicle can be predicted, which is convenient for claims personnel to better conduct claims assessment for vehicle accidents.

[0075] Step 204, inputting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of the collision as evaluation indicators into a preset evaluation model to obtain a maintenance list output by the evaluation model, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced;

[0076] Specifically, according to whether all vehicle components in the area affected by the vehicle collision are damaged, a list of damaged components is enumerated, and the list of damaged components is used as a repair list output by the evaluation model.

[0077] By obtaining the maintenance list output by the evaluation model, it is convenient to subsequently generate corresponding expense documents according to the maintenance list.

[0078] Step 205, generate corresponding expense documents according to the maintenance list, report to the target recipient, and complete this business evaluation.

[0079] Specifically, the target receiving end includes a claim verification end, a 4S store receiving end and a car owner end. The specific target receiving end is determined by the actual business scenario.

[0080] In this embodiment, by obtaining an image group uploaded by the target user; segmenting the target image in the image group, identifying the collision part contained in the target image and the collision intensity corresponding to the collision part; predicting the damage of all vehicle parts in the affected area of ​​the vehicle collision part under the collision intensity; generating a maintenance list, wherein the maintenance list includes the names of all vehicle parts to be repaired or replaced; generating corresponding expense documents according to the maintenance list, and reporting them to the target recipient, the business evaluation is completed. Applying the business evaluation method to the auto insurance claims business scenario is helpful to assist vehicle claims staff in identifying collision parts and collision intensity, thereby generating a list related to the claims business.

[0081] Continue to refer Figure 3 In some optional implementations, before step 202, a step of learning and training the image segmentation model is also included. Figure 3 yes Figure 2 The flowchart of a specific embodiment of learning and training the image segmentation model before step 202 includes the following steps:

[0082] Step 301, obtaining a batch of vehicle accident images and constructing a training data set;

[0083] Step 302: input the training data set into the image segmentation model to be trained, and perform learning training on the image segmentation model to be trained to obtain a pre-trained image segmentation model.

[0084] Specifically, the step of inputting the training data set into the image segmentation model to be trained, and performing learning and training on the image segmentation model to be trained to obtain a pre-trained image segmentation model specifically includes: learning the sizes of damaged positions corresponding to different collision intensities of different vehicle parts according to the vehicle accident images in the training data set, as well as the depth of depression or degree of fragmentation of the damaged positions corresponding to different collision intensities.

[0085] By learning and training the image segmentation model, after the image segmentation model segments the vehicle accident image and identifies the collision site, it can directly identify the collision intensity of the corresponding vehicle site based on the corresponding damaged site size, the depression depth or the degree of fragmentation of the damaged site.

[0086] In this embodiment, during the learning and training of the image segmentation model, a corresponding collision intensity recognition compensation mechanism can be introduced. For example, if the size of the segmented image after being processed by the image segmentation model is smaller than the size of the actual vehicle, it means that the corresponding collision intensity is lower, and the identified collision intensity can be appropriately adjusted by reducing the collision intensity; if the size of the segmented image after being processed by the image segmentation model is larger than the size of the actual vehicle, it means that the corresponding collision intensity is stronger, and the identified collision intensity can be appropriately adjusted by increasing the collision intensity.

[0087] Continue to refer Figure 4 In some optional implementations, a step of updating the training data set is also included before step 302. Figure 4 yes Figure 3 The flowchart of a specific embodiment of updating the training data set before step 302 shown includes the following steps:

[0088] Step 401, classifying the segmentation difficulty of all vehicle accident images in the training data set according to the preset vehicle part segmentation difficulty;

[0089] Step 402, based on the segmentation difficulty supported by the image segmentation model, filter out vehicle accident images that can be processed by the image segmentation model from the segmentation difficulty classification results;

[0090] Step 403: updating the vehicle accident images processable by the image segmentation model to the latest training data set.

[0091] Specifically, due to the collision results after the actual collision, for example, a certain part of the vehicle is completely shattered or severely dented and convoluted together, there is a high difficulty in segmenting such vehicle accident images, and the segmentation process does not play a great role in reference. In this embodiment, the image segmentation model corresponds to the appropriate segmentation scenario for training and segmenting accident images with dents caused by vehicle accidents. Therefore, it is considered to first update the training data set and select vehicle accident images suitable for segmentation, so as to ensure the targeted training effect of the image segmentation model.

[0092] Continue to refer Figure 5 In some optional implementations, before step 202, a step of pre-classifying all images in the image group is also included. Figure 5 yes Figure 2 The flowchart of a specific embodiment of pre-classifying all images in the image group before step 202 includes the following steps:

[0093] Step 501, identifying the segmentation difficulty corresponding to all images in the image group;

[0094] Step 502, according to the segmentation difficulty levels corresponding to all the images, select from the image group the images that can be segmented by the image segmentation model as the target images, and select from the image group the images that cannot be segmented by the image segmentation model;

[0095] Step 503: Pack and transmit all the images that cannot be split to a preset manual recognition detection terminal.

[0096] By pre-classifying all images in the image group, it is convenient to filter out images that can be segmented and processed by the image segmentation model from the image group as the target images, and to filter out images that cannot be segmented and processed by the image segmentation model from the image group, so as to facilitate subsequent separate processing.

[0097] Continue to refer Figure 6 , Figure 6 yes Figure 2 The flowchart of a specific embodiment of step 202 shown includes the following steps:

[0098] Step 601, using the image segmentation model to perform image segmentation processing on all target images;

[0099] Step 602, identifying actual damage information of the collision part contained in the target image according to the image segmentation processing result, wherein the actual damage information includes the damage size and the damage depression depth;

[0100] Step 603: Determine the collision intensity corresponding to the collision part in the target image through a reference table of preset collision intensity and actual damage information.

[0101] In this embodiment, before executing the step of predicting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision part under the current collision intensity according to the preset vehicle component position relationship form and the vehicle component bearing strength form, the method also includes: receiving actual damage information of the collision part contained in all the indivisible processed images fed back by the manual recognition detection end; determining the collision intensity corresponding to the collision part in all the indivisible processed images based on the collision intensity and actual damage information reference table; calculating the comprehensive collision part and the comprehensive collision intensity according to the collision intensity corresponding to the collision part in the target image and the collision intensity corresponding to the collision part in all the indivisible processed images; setting the comprehensive collision part as the current vehicle collision part, and setting the comprehensive collision intensity as the current collision intensity.

[0102] The comprehensive collision position and comprehensive collision intensity are calculated by combining the actual damage information of the collision position contained in the separable image identified by the model with the actual damage information of the collision position contained in all the inseparable images fed back by the manual recognition and detection end. The specific calculation method is to set calculation weights for the actual damage information of the collision position contained in the separable image and the actual damage information of the collision position contained in all the inseparable images fed back by the manual recognition and detection end, and then calculate the comprehensive collision position and comprehensive collision intensity.

[0103] In this embodiment, the step of predicting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision site under the current collision intensity based on the preset vehicle component position relationship form and the vehicle component bearing strength form, also includes: identifying, based on prior knowledge, whether there are vehicle components in the affected area of ​​the vehicle collision site whose damage conditions are difficult to predict, wherein the prior knowledge includes vehicle components whose damage conditions are difficult to predict; if there are vehicle components in the affected area of ​​the vehicle collision site whose damage conditions are difficult to predict, marking the vehicle components whose damage conditions are difficult to predict, and sending a request for manual inspection to the target end.

[0104] This application obtains the image group uploaded by the target user; segments the target image in the image group, identifies the collision part contained in the target image and the collision intensity corresponding to the collision part; predicts the damage of all vehicle parts in the affected area of ​​the vehicle collision part under the collision intensity; generates a maintenance list, wherein the maintenance list includes the names of all vehicle parts to be repaired or replaced; generates corresponding expense documents according to the maintenance list, reports them to the target recipient, and completes this business evaluation. Applying the business evaluation method to the auto insurance claims business scenario will help assist vehicle claims staff in identifying collision parts and collision intensity, thereby generating a list related to the claims business.

[0105] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0106] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0107] In the embodiment of the present application, by obtaining an image group uploaded by a target user; segmenting the target image in the image group, identifying the collision part contained in the target image and the collision intensity corresponding to the collision part; predicting the damage of all vehicle parts in the affected area of ​​the vehicle collision part under the current collision intensity; generating a maintenance list, wherein the maintenance list includes the names of all vehicle parts to be repaired or replaced; generating corresponding expense documents according to the maintenance list, and reporting them to the target recipient, the business evaluation is completed. Applying the business evaluation method to the auto insurance claims business scenario is helpful to assist vehicle claims staff in identifying collision parts and collision intensity, thereby generating a list related to the claims business.

[0108] Further references Figure 7 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a service evaluation device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0109] like Figure 7 As shown, the service evaluation device 700 described in this embodiment includes: an image group acquisition module 701, an image segmentation processing module 702, a damage prediction module 703, a maintenance evaluation module 704 and an expense document generation and reporting module 705. Among them:

[0110] An image group acquisition module 701 is used to acquire an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle;

[0111] An image segmentation processing module 702 is used to input the image group into a pre-trained image segmentation model, perform segmentation processing on the target image in the image group, and identify the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result;

[0112] The damage prediction module 703 is used to predict the damage of all vehicle components in the affected area of ​​the vehicle collision site under the current collision intensity according to the preset vehicle component position relationship table and vehicle component bearing strength table;

[0113] The repair evaluation module 704 is used to input the damage conditions of all vehicle components in the affected area of ​​the vehicle collision under the intensity of the collision as evaluation indicators into a preset evaluation model to obtain a repair list output by the evaluation model, wherein the repair list includes the names of all vehicle components to be repaired or replaced;

[0114] The expense document generation and reporting module 705 is used to generate a corresponding expense document according to the maintenance list and report it to the target recipient to complete this business evaluation.

[0115] This application obtains the image group uploaded by the target user; segments the target image in the image group, identifies the collision part contained in the target image and the collision intensity corresponding to the collision part; predicts the damage of all vehicle parts in the affected area of ​​the vehicle collision part under the collision intensity; generates a maintenance list, wherein the maintenance list includes the names of all vehicle parts to be repaired or replaced; generates corresponding expense documents according to the maintenance list, reports them to the target recipient, and completes this business evaluation. Applying the business evaluation method to the auto insurance claims business scenario will help assist vehicle claims staff in identifying collision parts and collision intensity, thereby generating a list related to the claims business.

[0116] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0117] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0118] To solve the above technical problems, the present application also provides a computer device. Figure 8, Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0119] The computer device 8 includes a memory 8a, a processor 8b, and a network interface 8c which are interconnected through a system bus. It should be noted that: Figure 8 Only a computer device 8 having a component memory 8a, a processor 8b, and a network interface 8c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0120] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0121] The memory 8a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 8a can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 8a can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 8a can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 8a is generally used to store the operating system and various application software installed on the computer device 8, such as a computer-readable instruction of a business evaluation method, etc. In addition, the memory 8a can also be used to temporarily store various types of data that have been output or are to be output.

[0122] The processor 8b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 8b is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 8b is used to run the computer-readable instructions or process data stored in the memory 8a, such as the computer-readable instructions for running the business evaluation method.

[0123] The network interface 8c may include a wireless network interface or a wired network interface. The network interface 8c is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0124] The computer device proposed in this embodiment belongs to the field of image processing technology and is applied to vehicle claims and damage assessment scenarios. This application obtains an image group uploaded by a target user; segments the target image in the image group to identify the collision site contained in the target image and the collision intensity corresponding to the collision site; predicts the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of this collision; generates a maintenance list, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced; generates corresponding expense documents based on the maintenance list, reports them to the target recipient, and completes this business evaluation. Applying the business evaluation method to the auto insurance claims business scenario helps to assist vehicle claims staff in identifying collision sites and collision intensities, thereby generating a list related to the claims business.

[0125] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the business evaluation method as described above.

[0126] The computer-readable storage medium proposed in this embodiment belongs to the field of image processing technology and is applied to vehicle claims and damage assessment scenarios. This application obtains an image group uploaded by a target user; segments the target image in the image group to identify the collision site contained in the target image and the collision intensity corresponding to the collision site; predicts the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of this collision; generates a maintenance list, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced; generates corresponding expense documents based on the maintenance list, reports them to the target recipient, and completes this business evaluation. Applying the business evaluation method to the auto insurance claims business scenario can help assist vehicle claims staff in identifying collision sites and collision intensities, thereby generating a list related to the claims business.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0128] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A business evaluation method, characterized in that: The steps include: Acquire an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle; Inputting the image group into a pre-trained image segmentation model, performing segmentation processing on the target image in the image group, and identifying the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result; According to the preset vehicle component position relationship table and vehicle component bearing strength table, predict the damage of all vehicle components in the affected area of ​​the vehicle collision under the intensity of this collision; Input the damage conditions of all vehicle components in the affected area of ​​the vehicle collision under the intensity of the collision as evaluation indicators into a preset evaluation model to obtain a maintenance list output by the evaluation model, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced; Generate corresponding expense documents based on the maintenance list and report them to the target recipient to complete this business evaluation.

2. The business evaluation method according to claim 1, characterized in that: Before executing the step of inputting the image group into the pre-trained image segmentation model, the method further includes: Obtain batches of vehicle accident images and construct a training dataset; The training data set is input into the image segmentation model to be trained, and the image segmentation model to be trained is trained to obtain a pre-trained image segmentation model.

3. The business evaluation method according to claim 2, characterized in that: Before executing the step of inputting the training data set into the image segmentation model to be trained and performing learning training on the image segmentation model to be trained to obtain a pre-trained image segmentation model, the method further includes: Classifying the segmentation difficulty of all vehicle accident images in the training data set according to the preset vehicle part segmentation difficulty; Based on the segmentation difficulty supported by the image segmentation model, filter out the vehicle accident images that can be processed by the image segmentation model from the segmentation difficulty classification results; The vehicle accident images processable by the image segmentation model are updated to the latest training data set.

4. The business evaluation method according to claim 1, characterized in that: Before executing the step of segmenting the target image in the image group, the method further includes: Identify the segmentation difficulty corresponding to each of the images in the image group; According to the segmentation difficulty levels corresponding to all the images, the images that can be segmented and processed by the image segmentation model are selected from the image group as the target images, and the images that cannot be segmented and processed by the image segmentation model are selected from the image group; All the images that cannot be processed are packaged and transmitted to the preset manual recognition detection end.

5. The business evaluation method according to claim 4, characterized in that: The step of segmenting the images in the image group and identifying the collision parts contained in the target image and the collision strengths corresponding to the collision parts according to the segmentation results specifically includes: Using the image segmentation model to perform image segmentation processing on all target images; Identifying actual damage information of the collision part contained in the target image according to the image segmentation processing result, wherein the actual damage information includes the damage size and the damage depression depth; The collision intensity corresponding to the collision part in the target image is determined by referring to a preset collision intensity and actual damage information table.

6. The service evaluation method according to claim 5, characterized in that: Before executing the step of predicting the damage conditions of all vehicle components in the affected area of ​​the vehicle collision site under the current collision intensity according to the preset vehicle component position relationship table and vehicle component bearing strength table, the method further includes: Receiving actual damage information of the collision part contained in all the indivisible processed images fed back by the manual recognition detection end; Based on the collision intensity and actual damage information reference table, determining the collision intensity corresponding to the collision parts in all the images that cannot be processed in segments; Calculating a comprehensive collision location and a comprehensive collision intensity according to the collision intensity corresponding to the collision location in the target image and the collision intensity corresponding to the collision location in all the indivisible processed images; The comprehensive collision part is set as the current vehicle collision part, and the comprehensive collision intensity is set as the current collision intensity.

7. The service evaluation method according to claim 1 or 6, characterized in that: The step of predicting the damage of all vehicle components in the affected area of ​​the vehicle collision site under the intensity of the collision according to the preset vehicle component position relationship table and vehicle component bearing strength table also includes: Based on prior knowledge, identify whether there are vehicle parts in the affected area of ​​the vehicle collision whose damage is difficult to predict; If there are vehicle parts whose damage is difficult to predict in the area affected by the vehicle collision, the vehicle parts whose damage is difficult to predict are marked, and a request for manual inspection is sent to the target end.

8. A service evaluation device, characterized in that: include: An image group acquisition module, used to acquire an image group uploaded by a target user, wherein the image group includes at least one vehicle image taken based on a collision site of the vehicle; An image segmentation processing module, used for inputting the image group into a pre-trained image segmentation model, performing segmentation processing on the target image in the image group, and identifying the collision part contained in the target image and the collision intensity corresponding to the collision part according to the segmentation processing result; The damage prediction module is used to predict the damage of all vehicle components in the affected area of ​​the vehicle collision under the intensity of this collision according to the preset vehicle component position relationship table and vehicle component bearing strength table; A maintenance evaluation module, used to input the damage conditions of all vehicle components in the affected area of ​​the vehicle collision under the intensity of the collision as evaluation indicators into a preset evaluation model, and obtain a maintenance list output by the evaluation model, wherein the maintenance list includes the names of all vehicle components to be repaired or replaced; The expense document generation and reporting module is used to generate corresponding expense documents according to the maintenance list and report them to the target recipient to complete this business evaluation.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business evaluation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service evaluation method according to any one of claims 1 to 7 are implemented.

Images