Vehicle damage determination method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a vehicle damage determination method and device, electronic equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring an original image obtained by shooting a target vehicle; the original image is input into an image recognition model to obtain a recognition result, the image recognition model is obtained by training a first basic model through a plurality of first training samples, the plurality of first training samples comprise a plurality of vehicle images, and each vehicle image comprises a damage area of the vehicle and description information of the damage area; and when the identification result indicates that the original image has the damaged area, acquiring description information of the damaged area of the target vehicle from the identification result. Therefore, the damage determination process of the vehicle is completed by the electronic equipment, the damage determination of the vehicle does not need to be performed manually, the vehicle damage determination efficiency is improved, and the vehicle damage assessment process is accelerated.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a vehicle damage determination method, device, electronic device and medium. Background Art

[0002] Currently, in the insurance industry, there are many business scenarios that require vehicle damage assessment. Damage assessment refers to the assessment of the damage to the damaged vehicle and the determination of the cost of repair or replacement during the insurance claims process.

[0003] In the related technology, the process of damage assessment usually occurs after an accident or incident occurs to the insured party, and the insurance company sends professionals (surveyors or damage assessors) to determine the damage of the damaged vehicle. At present, the manual method of vehicle damage assessment is inefficient. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a vehicle damage determination method, device, electronic device and medium, aiming to improve the efficiency of vehicle damage determination.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a vehicle damage determination method, the method comprising:

[0006] Acquire an original image obtained by photographing the target vehicle;

[0007] Inputting the original image into an image recognition model to obtain a recognition result, wherein the image recognition model is obtained by training a first basic model through a plurality of first training samples, wherein the plurality of first training samples include a plurality of vehicle images, each of the vehicle images includes a damaged area of ​​the vehicle, and description information of the damaged area, wherein the description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree;

[0008] When the recognition result indicates that a damaged area exists in the original image, description information of the damaged area of ​​the target vehicle is obtained from the recognition result.

[0009] In some embodiments, the target vehicle has a plurality of damaged areas;

[0010] After acquiring the description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes:

[0011] Displaying description information of the damaged area of ​​the target vehicle;

[0012] In response to a first user input, correcting the description information of a first damaged area of ​​the target vehicle using the first user input;

[0013] A damage investigation report is generated based on the description information of the first damage area and the description information of the second damage area of ​​the target vehicle, wherein the second damage area is a damage area among the damage areas of the target vehicles except the first damage area.

[0014] In some embodiments, in response to the first user input, correcting the description information of the first damaged area of ​​the target vehicle using the first user input includes:

[0015] In response to a first user input, when the first user input is a voice input, performing voice recognition on the audio input by the voice input to obtain a recognized text;

[0016] Performing semantic analysis on the recognized text to obtain an analysis result;

[0017] If the analysis result includes preset information, obtaining correction information of the first damage area from the analysis result, the correction information of the first damage area including at least one of a damage position, a damage type, and a damage degree of the first damage area;

[0018] The description information of the first damaged area is corrected using the correction information of the first damaged area.

[0019] In some embodiments, after obtaining the description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes:

[0020] Inputting description information of the damaged area of ​​the target vehicle into a repair cost prediction model to obtain a repair cost of the target vehicle output by the repair cost prediction model;

[0021] The repair cost prediction model is obtained by training a second basic model using a plurality of second training samples, wherein the plurality of second training samples include a plurality of repair costs and description information of a damaged area of ​​the vehicle corresponding to each of the plurality of repair costs.

[0022] In some embodiments, after inputting the description information of the damaged area of ​​the target vehicle into a repair cost prediction model to obtain the repair cost of the target vehicle output by the repair cost prediction model, the method further includes:

[0023] The repair cost of the target vehicle is matched with a plurality of repair costs in a repair solution set, and a target repair solution is determined according to the matching result. The repair solution set includes a plurality of repair costs and a repair solution corresponding to each repair cost.

[0024] In some implementations, the acquiring of an original image obtained by photographing the target vehicle includes:

[0025] Acquire a first image obtained by photographing a target vehicle through a photographing device;

[0026] comparing the resolution of the first image with a resolution threshold;

[0027] When the resolution of the first image is less than a resolution threshold, outputting a shooting guidance prompt, wherein the shooting guidance prompt is used to prompt the user to adjust the shooting focal length;

[0028] In response to a second user input, adjusting the shooting focal length of the shooting device, shooting the target vehicle by the shooting device, obtaining a second image, taking the second image as the first image, and performing the step of comparing the resolution of the first image with a resolution threshold until the resolution of the first image is greater than or equal to the resolution threshold;

[0029] The first image is determined as the original image.

[0030] In some implementations, the acquiring of an original image obtained by photographing the target vehicle includes:

[0031] Acquire a first image obtained by photographing a target vehicle through a photographing device;

[0032] comparing the brightness of the first image with a brightness threshold;

[0033] When the brightness of the first image is less than the brightness threshold, outputting a shooting guidance prompt, wherein the shooting guidance prompt is used to prompt the user to adjust the shooting fill light intensity;

[0034] In response to a second user input, the fill light intensity of the shooting device is adjusted, and the target vehicle is photographed by the shooting device to obtain a second image, and the second image is used as the first image, and the step of comparing the brightness of the first image with the brightness threshold is performed until the brightness of the first image is greater than or equal to the brightness threshold;

[0035] The first image is determined as the original image.

[0036] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a vehicle damage determination device, the device comprising:

[0037] An image acquisition module is used to acquire an original image obtained by photographing a target vehicle;

[0038] an image recognition module, configured to input the original image into an image recognition model to obtain a recognition result, wherein the image recognition model is obtained by training a first basic model through a plurality of first training samples, wherein the plurality of first training samples include a plurality of vehicle images, each of the vehicle images includes a damaged area of ​​the vehicle, and description information of the damaged area, wherein the description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree;

[0039] The information acquisition module is used to acquire description information of the damaged area of ​​the target vehicle from the recognition result when the recognition result indicates that the original image has a damaged area.

[0040] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the vehicle damage determination method described in the first aspect when executing the computer program.

[0041] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the vehicle damage determination method described in the first aspect above.

[0042] Vehicle damage determination method provided by the present application 、 The device, electronic device and medium first obtain the original image of the captured target vehicle and input the original image into a pre-trained image recognition model. After learning from multiple training samples, the image recognition model can accurately identify the damaged area in the vehicle image and accurately extract descriptive information related to the damaged area, such as the damage location, damage type and damage degree. When the damaged area is identified in the original image, the electronic device extracts the descriptive information of the damaged area of ​​the target vehicle from the recognition result. In this way, the vehicle damage determination process is completed by the electronic device, and there is no need to manually determine the damage of the vehicle, which improves the efficiency of vehicle damage determination and speeds up the vehicle damage assessment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a vehicle damage determination method provided in an embodiment of the present application;

[0044] Figure 2 is a flowchart of a description information correction process provided by an embodiment of the present application;

[0045] Figure 3 It is a flowchart of the damage assessment process provided by the embodiment of the present application;

[0046] Figure 4is a flowchart of a shooting guidance process provided by an embodiment of the present application;

[0047] Figure 5 is a schematic diagram of the structure of a vehicle damage determination device provided in an embodiment of the present application;

[0048] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0052] First, some nouns involved in this application are analyzed:

[0053] Damage assessment: Damage assessment refers to the process of assessing the damage to damaged property (such as vehicles, houses, etc.) and determining the cost of repair or replacement during the insurance claim process. In the field of auto insurance, damage assessment usually occurs after the insured's vehicle is involved in an accident or is damaged, and professionals (adjusters or surveyors) sent by the insurance company inspect and assess the damage to the vehicle and calculate the cost of repairs. The purpose of damage assessment is to determine the amount of compensation that the insurance company needs to pay through an objective judgment of the degree of damage, thereby providing a basis for subsequent claims. The traditional damage assessment method mainly relies on manual inspection, and the insurance company sends professionals (surveyors or adjusters) to determine the damage to the damaged vehicle, which is inefficient.

[0054] Based on this, the embodiments of the present application provide a vehicle damage determination method, device, electronic device and medium, aiming to improve the efficiency of the vehicle damage determination process.

[0055] The vehicle damage determination method, device, electronic device and medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the vehicle damage determination method in the embodiments of the present application is described.

[0056] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0057] 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.

[0058] The vehicle damage determination method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The vehicle damage determination method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the vehicle damage determination method, etc., but is not limited to the above forms.

[0059] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0060] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0061] See also Figure 1 , Figure 1 : is a flow chart of a vehicle damage determination method provided in an embodiment of the present application. The present application embodiment provides a vehicle damage determination method, including the following steps S110 to S130:

[0062] Step S110: Acquire an original image obtained by photographing the target vehicle.

[0063] The electronic device that executes the vehicle damage determination method provided in the embodiment of the present application first obtains the original image obtained by photographing the target vehicle. The original image can be a number of photos or a video. The electronic device can be operated by the surveyor responsible for determining the vehicle damage, and the electronic device can obtain the original image by remote acquisition. Exemplarily, the electronic device obtains the original image captured by the surveillance camera through the surveillance camera at the scene where the target vehicle is located, or the original image taken by the on-site personnel and sent to the electronic device, so that the surveyor can remotely determine the vehicle damage, reduce the time for damage assessment and claims settlement, and improve the efficiency of damage assessment.

[0064] Surveyors can also use the camera integrated in the electronic device to take real-time photos. For example, surveyors use the electronic device to take multiple images of the target vehicle as original images at the accident scene of the target vehicle, ensuring that the electronic device can obtain original images containing various angles and damage conditions of the target vehicle.

[0065] Step S120: Input the original image into the image recognition model to obtain a recognition result. The image recognition model is obtained by training a first basic model with multiple first training samples. The multiple first training samples include multiple vehicle images. Each vehicle image includes a damaged area of ​​the vehicle and description information of the damaged area. The description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree.

[0066] The electronic device then inputs the original image into an image recognition model to obtain a recognition result. The image recognition model is obtained by training a first basic model with a plurality of first training samples, wherein the samples include a plurality of vehicle images, each of which is annotated with a damage area, and relevant description information for the damage area, such as at least one of a damage location, a damage type, and a damage degree.

[0067] Exemplarily, the electronic device uploads the original image taken by the surveyor to the image recognition model. After image segmentation and image recognition processing, the image recognition model segmented and extracted the image of the damaged area of ​​the vehicle in the original image, and identified that the damaged location of the vehicle is the front bumper, the damage type is scratches, and the degree of damage is minor damage based on the image of the damaged area.

[0068] The model type of the first basic model may be any one of the following model types, or other model types suitable for vehicle damage area extraction and assessment:

[0069] Convolutional Neural Network: Convolutional neural network is widely used in image processing tasks, can effectively extract image features, and is suitable for vehicle damage identification.

[0070] Support vector machine: Support vector machine is often used for classification problems. It can map image feature vectors into high-dimensional space to identify damage types.

[0071] Decision tree: Decision tree makes decisions by building a tree model, which can be used to determine the type and extent of vehicle damage.

[0072] Random forest: Random forest integrates multiple decision tree models and improves recognition accuracy through a voting mechanism, making it suitable for complex damage assessment tasks.

[0073] Step S130: when the recognition result indicates that there is a damaged area in the original image, obtain description information of the damaged area of ​​the target vehicle from the recognition result.

[0074] When the electronic device determines that the recognition result indicates that the original image has a damaged area (the image recognition model successfully segments and extracts the damaged area image from the original image), the electronic device obtains description information of the damaged area of ​​the target vehicle from the recognition result. For example, when the recognition result indicates that the front bumper of the vehicle has damage, the electronic device obtains description information for the damaged area, that is, the damage location is "front bumper", the damage type is "scratches", and the damage degree is "mild".

[0075] Through the above steps S110 to S130, the electronic device first obtains the original image of the captured target vehicle and inputs the original image into a pre-trained image recognition model. After learning from multiple training samples, the image recognition model can accurately identify the damaged area in the vehicle image and can accurately extract descriptive information related to the damaged area, such as the damage location, damage type and damage degree. When the damaged area is identified in the original image, the electronic device extracts the descriptive information of the damaged area of ​​the target vehicle from the recognition result. In this way, the vehicle damage determination process is completed by the electronic device, and there is no need to manually determine the damage to the vehicle, which improves the efficiency of vehicle damage determination and speeds up the vehicle damage assessment process.

[0076] In some embodiments, the target vehicle has a plurality of damaged areas;

[0077] After obtaining description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes:

[0078] Displays description information of the target vehicle's damage area;

[0079] In response to the first user input, correcting the description information of the first damaged area of ​​the target vehicle using the first user input;

[0080] A damage investigation report is generated according to the description information of the first damage area and the description information of the second damage area of ​​the target vehicle, wherein the second damage area is a damage area other than the first damage area among the damage areas of the plurality of target vehicles.

[0081] In this embodiment, there may be multiple damaged areas on the target vehicle. After the image recognition model extracts and identifies multiple damaged areas from the image of the vehicle, the electronic device will display the description information of these damaged areas for the surveyor to view. If the surveyor finds that the description information of certain damaged areas (recorded as the first damaged area) is inaccurate (such as location, type or degree of damage), it can be corrected by user input (recorded as the first user input). The electronic device will respond to the user input, update the description information of the damaged area, and retain the description information of other unmodified damaged areas (recorded as the second damaged area). Finally, the electronic device generates a complete damage investigation report based on the updated description information of the first damaged area and the other unmodified description information of the second damaged area. The investigation report comprehensively evaluates all damaged areas of the vehicle and provides a basis for subsequent claims and repairs.

[0082] In this way, the electronic equipment improves the accuracy of vehicle damage assessment by allowing surveyors to correct the description information of the damaged area, and combines the analysis of multiple damaged areas to generate a more complete and accurate damage investigation report, thereby optimizing the efficiency of claims and repair decisions.

[0083] For example, the target vehicle has a side collision, and the electronic device identifies two damaged areas, the door and the rear wing, through the image recognition model. The electronic device displays the description information of the two damaged areas, with the door damage marked as a medium dent and the rear wing marked as a slight scratch. After checking the information, the surveyor found that the description of the door damage was inaccurate and it was actually a severe dent. The surveyor inputted modification suggestions, and the electronic device updated the description information of the door to "severe dent" based on this correction, and retained the slight scratch information on the rear wing. Finally, the electronic device generated an inspection report containing these two damaged areas for vehicle damage assessment and subsequent repairs.

[0084] Those skilled in the art will appreciate that, when there is only one damaged area, the electronic device may also correct the description information of the damaged area by obtaining user input from the surveyor.

[0085] See also Figure 2 , Figure 2 : is a flowchart of a description information correction process provided by an embodiment of the present application. In some embodiments, in response to a first user input, the description information of the first damaged area of ​​the target vehicle is corrected using the first user input, including:

[0086] Step S210: in response to the first user input, when the first user input is a voice input, performing voice recognition on the audio input by the voice input to obtain a recognized text;

[0087] Step S220: performing semantic analysis on the recognized text to obtain analysis results;

[0088] Step S230: if the analysis result includes preset information, obtaining correction information of the first damage area from the analysis result, the correction information of the first damage area including at least one of a damage position, a damage type, and a damage degree of the first damage area;

[0089] Step S240: Correct the description information of the first damaged area using the correction information of the first damaged area.

[0090] In this embodiment, the electronic device allows the user to correct the damage area description information of the target vehicle by voice input. When the user inputs information by voice, the electronic device first recognizes the voice and converts it into corresponding text (recorded as recognized text). Then, the electronic device performs semantic analysis on the recognized text to determine whether the text contains preset information. The preset information can be the damage description information (such as the damage location, type or degree) itself, or some keywords that represent the purpose of correction or errors in the description information of the first damage area (such as "modification", "errors exist", etc.). The preset information is used to trigger the electronic device to extract the correction information. If the analysis result contains preset information, the electronic device will extract the corresponding correction information (such as the damage location, type or degree), and use this correction information to modify or update the original description of the first damage area.

[0091] This makes it convenient for surveyors to correct erroneous damage descriptions through voice, and also ensures that the corrected description information is accurate and comprehensive.

[0092] For example, the rear bumper of the target vehicle was damaged due to a rear-end collision, and the electronic device initially described the damaged area as a slight scratch. However, the surveyor corrected it through voice input, pointing out that the actual damage was a "severe dent." The electronic device first recognized the surveyor's voice content and converted it into text. Then, through semantic analysis, the electronic device determined that the "severe dent" in the voice input belonged to preset information, triggering the electronic device to extract the corrected information and extract "severe dent." Finally, the electronic device corrected the information originally described as "slight scratches" to "severe dents" and automatically updated the description information of the damaged area.

[0093] In some embodiments, after obtaining description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes:

[0094] Inputting description information of the damaged area of ​​the target vehicle into the repair cost prediction model to obtain the repair cost of the target vehicle output by the repair cost prediction model;

[0095] The repair cost prediction model is obtained by training the second basic model using a plurality of second training samples, and the plurality of second training samples include a plurality of repair costs and description information of the damaged area of ​​the vehicle corresponding to each of the plurality of repair costs.

[0096] In this embodiment, after obtaining the damage area description information of the target vehicle from the recognition result, the electronic device inputs the description information into the repair cost prediction model. The repair cost prediction model is trained based on historical data, which contains the damage area description information of the vehicle and the corresponding repair cost. Through a large number of second training samples (such as damage of different types, locations and degrees and their repair costs), the electronic device trains the second basic model so that it can automatically predict the repair cost based on the damage area of ​​the vehicle. This model will combine the damage location, type and degree to output a repair cost prediction value for the target vehicle to help insurance companies or repair shops quickly estimate the repair costs.

[0097] In this way, the solution can automatically and quickly predict the repair costs based on the damaged area description information of the target vehicle through the repair cost prediction model, thereby improving the accuracy and efficiency of repair cost estimation, reducing errors caused by human intervention, and providing a more scientific reference for claims and repairs.

[0098] For example, the left door of the target vehicle has obvious dents and scratches. The electronic device obtains the description information of the damaged area through the image recognition model, and determines that the damage location is the left door, and the degree and type of damage are moderate dents and slight scratches. Then, the electronic device inputs this description information into the repair cost prediction model. Because the model has been trained with a large amount of similar vehicle damage and repair cost data, the electronic device predicts that the repair cost is 2,000 yuan based on the damage to the door. Ultimately, this repair cost will be used as the basis for the insurance company to estimate the amount of compensation.

[0099] In some embodiments, after inputting the description information of the damaged area of ​​the target vehicle into the repair cost prediction model to obtain the repair cost of the target vehicle output by the repair cost prediction model, the method further includes:

[0100] The repair cost of the target vehicle is matched with multiple repair costs in a repair solution set, and a target repair solution is determined according to the matching result. The repair solution set includes multiple repair costs and a repair solution corresponding to each repair cost.

[0101] In this embodiment, the damage area description information of the target vehicle is input into the repair cost prediction model. After obtaining the corresponding repair cost, the electronic device will match the repair cost with multiple repair costs in the predefined repair plan set. The repair plan set contains multiple known repair costs and their corresponding specific repair plans. Based on the repair cost of the target vehicle, the electronic device matches the repair plan whose repair cost is the same as that of the target vehicle or whose difference is less than a preset threshold, and then selects the target repair plan that meets the damage condition (damage type and degree of damage) of the target vehicle from the matching results to ensure that the recommended plan not only meets the damage condition, but is also consistent with or close to the estimated repair cost.

[0102] In this way, electronic equipment can automatically determine the most appropriate repair plan by matching the repair cost with the set of repair plans, thereby improving the accuracy and efficiency of repair plan selection and ensuring that the best repair plan that meets the damage situation is provided while controlling costs.

[0103] For example, the front bumper of the target vehicle is damaged, and the electronic device predicts that its repair cost is 3,000 yuan. Next, the electronic device will match this repair cost with the costs of multiple repair solutions in the repair solution set. There may be different options in the repair solution set, such as one repair solution includes replacing the bumper and repairing the paint of the entire vehicle, which costs 3,500 yuan, and another repair solution only requires replacing part of the bumper, which costs 3,000 yuan. Through matching, the electronic device recommends a repair solution of 3,000 yuan, that is, a repair solution of partially replacing the bumper, to achieve a balance point for repair.

[0104] See also Figure 3 , Figure 3 It is a flowchart of the damage assessment process provided by the embodiments of the present application. Combining the above-mentioned multiple embodiments, after acquiring the original image of the target vehicle, the electronic device uses the image recognition model to segment and extract the damaged area, and recognizes and analyzes the image of the damaged area acquired by the segmentation and extraction to obtain the description information of the damaged area (execute step S310); the electronic device then acquires the voice input of the surveyor, performs voice recognition to acquire the recognition text, and makes corresponding corrections to the description information (execute step S320); the electronic device inputs the corrected description information into the repair cost prediction model to acquire the repair cost of the target vehicle (execute step S330); the electronic device then uses the acquired repair cost to determine the target repair plan in the repair plan set (execute step S340); finally, the electronic device displays the corrected description information of the damaged area of ​​the target vehicle, the repair cost of the target vehicle, and the target repair plan, and generates a final survey report after obtaining the confirmation instruction of the surveyor (execute step S350).

[0105] See also Figure 4 , Figure 4 : is a flow chart of a shooting guidance process provided in an embodiment of the present application. In some implementations, obtaining an original image obtained by shooting a target vehicle includes:

[0106] Step S410: Acquire a first image obtained by photographing a target vehicle using a photographing device;

[0107] Step S420: comparing the resolution of the first image with a resolution threshold;

[0108] Step S430: when the resolution of the first image is less than the resolution threshold, outputting a shooting guidance prompt, where the shooting guidance prompt is used to prompt the user to adjust the shooting focal length;

[0109] Step S440: in response to the second user input, adjusting the shooting focal length of the shooting device, shooting the target vehicle through the shooting device, obtaining a second image, using the second image as the first image, and performing the step of comparing the resolution of the first image with the resolution threshold until the resolution of the first image is greater than or equal to the resolution threshold;

[0110] Step S450: determining the first image as the original image.

[0111] In this embodiment, first, the electronic device obtains a first image of the target vehicle through a shooting device. Then, the electronic device automatically compares the resolution of the image with a preset resolution threshold. If the resolution of the first image is lower than the set threshold, the electronic device will output a shooting guidance prompt to prompt the surveyor to adjust the focal length of the shooting device. The surveyor adjusts the focal length of the shooting device according to the prompt input (recorded as the second user input), and shoots the vehicle again to obtain a second image. The electronic device uses the second image as the new first image and continues to check whether its resolution meets the standard until the resolution of the image reaches or exceeds the threshold. Finally, the image that meets the resolution requirements is determined as the original image for subsequent analysis and processing.

[0112] In this way, the electronic device ensures that the image quality of the acquired original image is high enough by automatically detecting the image resolution and providing shooting guidance, thereby improving the accuracy and efficiency of subsequent target vehicle damage analysis and reducing reshooting or misjudgment due to poor image quality.

[0113] For example, the surveyor uses the camera integrated in the electronic device to take a photo of the target vehicle. The electronic device acquires the first image, but because the surveyor is far away from the vehicle, the electronic device detects that the resolution of the image is lower than the set standard. The electronic device automatically prompts the surveyor to adjust the focal length or get closer to the vehicle to take the photo. According to the prompt of the electronic device, the surveyor adjusts the focal length of the camera and retakes the photo of the target vehicle. The electronic device detects the resolution of the new image again and finds that the image is clear and the resolution meets the standard, so the image is used as the original image for subsequent damage analysis and processing.

[0114] In some implementations, obtaining an original image obtained by photographing a target vehicle includes:

[0115] Acquire a first image obtained by photographing a target vehicle through a photographing device;

[0116] Comparing the brightness of the first image with the brightness threshold;

[0117] When the brightness of the first image is less than the brightness threshold, outputting a shooting guidance prompt, where the shooting guidance prompt is used to prompt the user to adjust the shooting fill light intensity;

[0118] In response to the second user input, the fill light intensity of the shooting device is adjusted, and the target vehicle is photographed by the shooting device to obtain a second image, and the second image is used as the first image, and the step of comparing the brightness of the first image with the brightness threshold is performed until the brightness of the first image is greater than or equal to the brightness threshold;

[0119] The first image is determined as the original image.

[0120] In this embodiment, the electronic device first obtains a first image of the target vehicle taken by the shooting device. Then, the electronic device automatically compares the brightness value of the first image with the preset brightness threshold for size comparison. If the brightness of the first image is lower than the set threshold, the electronic device will give a shooting guidance prompt, prompting the surveyor to adjust the fill light intensity of the shooting device. The surveyor adjusts the fill light intensity of the device according to the prompt (recorded as the second user input) and re-shoots the target vehicle. The electronic device uses the obtained second image as the new first image and continues to detect its brightness until the brightness of the image reaches or exceeds the threshold. The first image that meets the brightness requirements is finally determined as the original image, which serves as the basic data for subsequent damage analysis.

[0121] In this way, the electronic device automatically detects the brightness of the image and provides fill light adjustment prompts to ensure that the original image captured is still clear enough in low-light environments, thereby improving the accuracy of vehicle damage analysis and overall inspection efficiency.

[0122] For example, the surveyor uses the camera integrated in the electronic device to photograph the target vehicle at night or in a poorly lit environment. The electronic device automatically detects that the brightness of the first image is insufficient, and displays a prompt asking the surveyor to adjust the brightness of the flash of the camera. The surveyor increases the brightness of the flash of the camera according to the prompt and photographs the target vehicle again. The electronic device checks the brightness of the new image and finds that the brightness has reached the set threshold, determines that the image is the original image, and continues to analyze the vehicle damage.

[0123] See also Figure 5 The embodiment of the present application further provides a vehicle damage determination device 500, which can implement the above-mentioned vehicle damage determination method, and the device 500 includes:

[0124] An image acquisition module 510 is used to acquire an original image obtained by photographing a target vehicle;

[0125] An image recognition module 520 is used to input the original image into an image recognition model to obtain a recognition result, wherein the image recognition model is obtained by training a first basic model through a plurality of first training samples, wherein the plurality of first training samples include a plurality of vehicle images, each of which includes a damaged area of ​​the vehicle and description information of the damaged area, wherein the description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree;

[0126] The information acquisition module 530 is used to acquire description information of the damaged area of ​​the target vehicle from the recognition result when the recognition result indicates that the original image has a damaged area.

[0127] The specific implementation of the vehicle damage determination device 500 is basically the same as the specific implementation of the above-mentioned vehicle damage determination method, and will not be repeated here.

[0128] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned vehicle damage determination method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0129] See also Figure 6 , Figure 6 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0130] The processor 601 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0131] The memory 602 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 602, and the processor 601 calls and executes the vehicle damage determination method of the embodiment of this application;

[0132] Input / output interface 603, used to implement information input and output;

[0133] Communication interface 604, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0134] Bus 605 , which transmits information between various components of the device (e.g., processor 601 , memory 602 , input / output interface 603 , and communication interface 604 );

[0135] The processor 601 , the memory 602 , the input / output interface 603 and the communication interface 604 are connected to each other in communication within the device via a bus 605 .

[0136] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned vehicle damage determination method is implemented.

[0137] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The vehicle damage determination method, device, electronic device and medium provided in the embodiments of the present application first obtain the original image of the captured target vehicle and input the original image into a pre-trained image recognition model. After learning from multiple training samples, the image recognition model can accurately identify the damaged area in the vehicle image and can accurately extract descriptive information related to the damaged area, such as the damage location, damage type and damage degree. When the damaged area is identified in the original image, the electronic device extracts the descriptive information of the damaged area of ​​the target vehicle from the recognition result. In this way, the vehicle damage determination process is completed by the electronic device, and there is no need to manually determine the damage to the vehicle, which improves the efficiency of vehicle damage determination and speeds up the vehicle damage assessment process.

[0139] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0140] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0141] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0143] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0144] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0145] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0146] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0147] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0148] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0149] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A vehicle damage determination method, characterized in that: The method comprises: Acquire an original image obtained by photographing the target vehicle; Inputting the original image into an image recognition model to obtain a recognition result, wherein the image recognition model is obtained by training a first basic model through a plurality of first training samples, wherein the plurality of first training samples include a plurality of vehicle images, each of the vehicle images includes a damaged area of ​​the vehicle, and description information of the damaged area, wherein the description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree; When the recognition result indicates that a damaged area exists in the original image, description information of the damaged area of ​​the target vehicle is obtained from the recognition result.

2. The method according to claim 1, characterized in that The target vehicle has a plurality of damaged areas; After acquiring the description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes: Displaying description information of the damaged area of ​​the target vehicle; In response to a first user input, correcting the description information of a first damaged area of ​​the target vehicle using the first user input; A damage investigation report is generated based on the description information of the first damage area and the description information of the second damage area of ​​the target vehicle, wherein the second damage area is a damage area among the damage areas of the target vehicles except the first damage area.

3. The method according to claim 2, characterized in that In response to the first user input, correcting the description information of the first damaged area of ​​the target vehicle using the first user input includes: In response to a first user input, when the first user input is a voice input, performing voice recognition on the audio input by the voice input to obtain a recognized text; Performing semantic analysis on the recognized text to obtain an analysis result; If the analysis result includes preset information, obtaining correction information of the first damage area from the analysis result, the correction information of the first damage area including at least one of a damage position, a damage type, and a damage degree of the first damage area; The description information of the first damaged area is corrected using the correction information of the first damaged area.

4. The method according to claim 1, characterized in that: After acquiring the description information of the damaged area of ​​the target vehicle from the recognition result, the method further includes: Inputting description information of the damaged area of ​​the target vehicle into a repair cost prediction model to obtain a repair cost of the target vehicle output by the repair cost prediction model; The repair cost prediction model is obtained by training a second basic model using a plurality of second training samples, wherein the plurality of second training samples include a plurality of repair costs and description information of a damaged area of ​​the vehicle corresponding to each of the plurality of repair costs.

5. The method according to claim 4, characterized in that After inputting the description information of the damaged area of ​​the target vehicle into the repair cost prediction model to obtain the repair cost of the target vehicle output by the repair cost prediction model, the method further includes: The repair cost of the target vehicle is matched with a plurality of repair costs in a repair solution set, and a target repair solution is determined according to the matching result. The repair solution set includes a plurality of repair costs and a repair solution corresponding to each repair cost.

6. The method according to claim 1, characterized in that The step of acquiring an original image obtained by photographing the target vehicle includes: Acquire a first image obtained by photographing a target vehicle through a photographing device; comparing the resolution of the first image with a resolution threshold; When the resolution of the first image is less than a resolution threshold, outputting a shooting guidance prompt, wherein the shooting guidance prompt is used to prompt the user to adjust the shooting focal length; In response to a second user input, adjusting the shooting focal length of the shooting device, shooting the target vehicle by the shooting device, obtaining a second image, taking the second image as the first image, and performing the step of comparing the resolution of the first image with a resolution threshold until the resolution of the first image is greater than or equal to the resolution threshold; The first image is determined as the original image.

7. The method according to claim 1, characterized in that The step of acquiring an original image obtained by photographing the target vehicle includes: Acquire a first image obtained by photographing a target vehicle through a photographing device; comparing the brightness of the first image with a brightness threshold; When the brightness of the first image is less than the brightness threshold, outputting a shooting guidance prompt, wherein the shooting guidance prompt is used to prompt the user to adjust the shooting fill light intensity; In response to a second user input, the fill light intensity of the shooting device is adjusted, and the target vehicle is photographed by the shooting device to obtain a second image, and the second image is used as the first image, and the step of comparing the brightness of the first image with the brightness threshold is performed until the brightness of the first image is greater than or equal to the brightness threshold; The first image is determined as the original image.

8. A vehicle damage determination device, characterized in that: The device comprises: An image acquisition module is used to acquire an original image obtained by photographing a target vehicle; an image recognition module, configured to input the original image into an image recognition model to obtain a recognition result, wherein the image recognition model is obtained by training a first basic model through a plurality of first training samples, wherein the plurality of first training samples include a plurality of vehicle images, each of the vehicle images includes a damaged area of ​​the vehicle, and description information of the damaged area, wherein the description information of the damaged area includes at least one of a damage location, a damage type, and a damage degree; The information acquisition module is used to acquire description information of the damaged area of ​​the target vehicle from the recognition result when the recognition result indicates that the original image has a damaged area.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the vehicle damage determination method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle damage determination method according to any one of claims 1 to 7 is implemented.

Images