Vehicle insurance survey and evidence obtaining method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of vehicles and artificial intelligence, and discloses a vehicle insurance survey and evidence obtaining method and device, electronic equipment and a readable storage medium, and the method comprises the steps: responding to a case report request of a user, and displaying a virtual option whether the user is on site or not; in response to whether the user selects on-site operation in the on-site virtual options or not, entering an on-site evidence obtaining process, and in at least one link of the on-site evidence obtaining process, performing automatic framing and photographing on a framing object by using at least one of the vehicle detection model, the vehicle part segmentation model and the frame number detection model; and in response to the operation that the user selects not on the scene in the virtual option of whether the user is on the scene or not, entering a non-scene evidence obtaining process, and in at least one link of the non-scene evidence obtaining process, performing automatic framing and photographing on the framing object by using at least one of the vehicle detection model, the vehicle part segmentation model and the frame number detection model. The success rate of evidence obtaining is improved, and the error rate is reduced.

Description

Technical Field

[0001] The present application relates to the fields of vehicle technology and artificial intelligence technology, and specifically to a method, device, electronic device and readable storage medium for vehicle insurance investigation and evidence collection. Background Art

[0002] In the traditional auto insurance survey scenario, after receiving a report call, the auto insurance surveyor will use WeChat for Business to add the other party's WeChat, and then guide the user to upload photos of the on-site vehicle damage, environment, documents, etc. through WeChat dialogue. This traditional model has some problems. For example, surveying employees often communicate with multiple customers online in multiple threads, which can easily lead to "losing sight of one thing while focusing on another", increasing the user's waiting time or affecting the user experience; if users are directly asked to take photos of the on-site survey, their professional knowledge is limited and it is difficult for them to take photos that meet the requirements, which can easily cause rework or pressure on subsequent reviewers. Summary of the invention

[0003] In response to the above problems, the embodiments of the present application provide a method, device, electronic device and readable storage medium for motor vehicle insurance investigation and evidence collection, so as to apply technologies such as image recognition to promote the self-service of motor vehicle insurance investigation and collection work, so as to overcome or partially overcome the shortcomings of the existing technology.

[0004] In a first aspect, the present application provides a method for investigating and collecting evidence of motor vehicle insurance, the method being executed by a client, and the method comprising:

[0005] In response to a user's request to report a crime, a virtual option is displayed indicating whether or not to be present at the scene;

[0006] In response to the user selecting the operation of being at the scene in the virtual option of whether to be at the scene, the on-site evidence collection process is entered. In at least one link of the on-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle, a photo of the person's vehicle damage, a photo of the person's frame number, a photo of the other party's entire vehicle, a photo of the other party's vehicle damage, and a photo of the other party's frame number;

[0007] In response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene, the off-site evidence collection process is entered. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0008] In a second aspect, the present application further provides a vehicle insurance investigation and evidence collection device, the device comprising:

[0009] A display unit, for displaying a virtual option of whether to be on the scene in response to a user's request to report a case;

[0010] A first evidence collection unit is used for entering an on-site evidence collection process in response to a user selecting an on-site operation in the virtual option of whether to be on-site, wherein in at least one link of the on-site evidence collection process, automatically framing and photographing the framing object is performed using at least one of a vehicle detection model, a vehicle component segmentation model, and a frame number detection model, wherein the on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle shooting link, a photo of the person's vehicle damage shooting link, a photo of the person's vehicle frame number shooting link, a photo of the other party's entire vehicle shooting link, a photo of the other party's vehicle damage shooting link, and a photo of the other party's frame number shooting link;

[0011] The second evidence collection unit is used to enter an off-site evidence collection process in response to the user selecting an operation of not being at the scene in the virtual option of whether the user is at the scene, and use at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model to automatically frame and photograph the framing object in at least one link of the off-site evidence collection process. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes any of the above-mentioned vehicle insurance investigation and evidence collection methods.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes any of the above-mentioned vehicle insurance investigation and evidence collection methods.

[0014] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0015] By adopting the motor vehicle insurance investigation and evidence collection method provided by the present application, after the user reports the case, the user is prompted to conduct an unmanned self-service investigation first, and the customer is guided so that the user can take photos of the environment, the whole vehicle, the vehicle damage, the frame number and other photos required for the investigation by themselves according to different scenarios whether on-site or off-site, and the user is given corresponding prompts in real time, which improves the success rate of collecting orders and reduces the time the user spends waiting for the arrival of the surveyor on-site; at the same time, the quality of the taken pictures is verified and automatically framed through the vehicle detection model and the vehicle component segmentation model, and the most qualified photos are taken in an intelligent and humanized manner, which improves the success rate of evidence collection and reduces the manual operation of the user, and is highly practical; and these investigation photos are used for subsequent investigations, damage assessments, etc., which can also improve the approval timeliness, reduce the error rate, and save the investigation manpower costs of the motor vehicle insurance company, which not only improves the quality of the motor vehicle insurance investigation pictures, but also improves the efficiency of the motor vehicle insurance investigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A schematic diagram of the process of a method for investigating and collecting evidence of automobile insurance according to an embodiment of the present application is shown;

[0018] Figure 2 A schematic diagram of a page for confirming shooting instructions of an investigation and evidence collection applet according to an embodiment of the present application is shown;

[0019] Figure 3 A schematic diagram of an environment photo shooting guide page according to an embodiment of the present application is shown;

[0020] Figure 4 A schematic diagram of a page for entering the next step guide in one embodiment of the present application is shown;

[0021] Figure 5 A schematic diagram of a guide page for taking a front-end photo of a vehicle according to an embodiment of the present application is shown;

[0022] Figure 6 A schematic diagram of a page for switching to a manual shooting mode according to an embodiment of the present application is shown;

[0023] Figure 7 A schematic diagram of a page for opening a guide for taking a rear-end full-vehicle photo according to an embodiment of the present application is shown;

[0024] Figure 8 A schematic diagram of a guide page for taking a full-body photo of the rear of a vehicle according to an embodiment of the present application is shown;

[0025] Fig. 9 A schematic diagram of a page showing a guide for taking a photo of a damaged vehicle according to an embodiment of the present application is shown;

[0026] Fig.10 A schematic diagram of a page showing a guide for taking a picture of a vehicle frame number according to an embodiment of the present application is shown;

[0027] Fig.11 A schematic diagram of the structure of a vehicle insurance investigation and evidence collection device according to an embodiment of the present application is shown;

[0028] Fig.12 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0030] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0031] With the development of the Internet and artificial intelligence technology, more and more businesses in various industries have been moved online, and auto insurance investigation and claims are gradually adopting online models. However, in the existing technology, in the auto insurance investigation scene, auto insurance investigation staff usually communicate with users through chat software to guide users to take photos and collect evidence. This form has many problems. In this regard, this application provides a method for auto insurance investigation and evidence collection. Figure 1 The flowchart of the method for investigating and collecting evidence of automobile insurance according to an embodiment of the present application is shown. The method can be executed by a client. Figure 1 It can be seen that this embodiment includes steps S110 to S130:

[0032] Step S110, in response to the user's request to report a case, a virtual option of whether to be on the scene is displayed.

[0033] The method of the present application can be applied to a client, and the client can be installed on a user's mobile terminal, such as a mobile phone, tablet computer, etc. The client can be in various forms, including but not limited to: application APP, mini-program, public account, etc., which is not limited in the present application. For the sake of convenience, the following description will be based on the client as a mini-program, and the mini-program will be named as the Investigation and Evidence Collection Mini-Program.

[0034] The relevant inspection pictures that can be taken will be different depending on whether the user is still at the accident scene. For example, if the user is still at the accident scene, it is necessary to take pictures of the accident environment and the other party's vehicle; if the user is not at the accident scene, he can only take pictures of his own car. Therefore, this application divides the evidence collection process into different categories according to whether the user is still at the scene.

[0035] When a user encounters an accident, the user can report the incident on the client. When the user enters the investigation and evidence collection applet, the investigation and evidence collection applet will first display a virtual button "Are you at the scene" to guide the user to select "Are you still at the scene". When the user is at the scene, the user enters the "on-site evidence collection process"; when the user is not at the scene, the user enters the "off-site evidence collection process".

[0036] In some embodiments, in order to confirm that the user can take pictures, before entering the subsequent on-site evidence collection process or the step of entering the off-site evidence collection process, the method also includes: displaying a virtual option for confirming whether to start shooting; in response to the user selecting the operation of confirming to start shooting in response to the virtual option for confirming whether to start shooting, entering the step of entering the on-site evidence collection process or the step of entering the off-site evidence collection process.

[0037] Please refer to Figure 2 , Figure 2 A page schematic diagram of the confirmation shooting instructions of the investigation and evidence collection applet according to an embodiment of the present application is shown. In this page, a virtual button "Confirm, you can shoot" is displayed. When the user clicks "Confirm, start shooting", the investigation photo evidence collection shooting process begins.

[0038] Step S120, in response to the user selecting the on-site operation in the virtual option of whether to be on-site, the on-site evidence collection process is entered. In at least one link of the on-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle shooting link, a photo of the person's vehicle damage shooting link, a photo of the person's frame number shooting link, a photo of the other party's entire vehicle shooting link, a photo of the other party's vehicle damage shooting link, and a photo of the other party's frame number shooting link.

[0039] In this application, according to the needs of car insurance investigation and evidence collection, the on-site evidence collection process is divided into multiple links, including but not limited to: environmental photo shooting link, personal vehicle photo shooting link, personal vehicle damage shooting link, personal vehicle frame number shooting link, other party vehicle photo shooting link, other party vehicle damage shooting link, and other party frame number shooting link. This application does not limit the order of the above links. In some embodiments, based on the principle of user convenience, it is designed to be carried out in the order of environmental photo shooting -> personal vehicle photo shooting -> personal vehicle damage shooting -> personal frame number shooting -> other party vehicle photo shooting -> other party vehicle damage shooting -> other party frame number shooting. For the convenience of explanation, the following will be explained in this order. The shooting process guidance of each link is introduced below.

[0040] (I) Environmental photography

[0041] In some embodiments of the present application, in the environmental photo shooting link, the environmental photo is obtained according to the following method: displaying the environmental photo shooting guidance page, the environmental photo shooting guidance page includes: environmental photo shooting requirements, and environmental photo shooting example pictures; using the vehicle detection model to verify the number of vehicles, vehicle integrity, and physical size in the current picture obtained by the client, if the verification passes, the current picture is automatically captured as the environmental photo; if the verification fails within the preset time, switching to manual shooting mode, obtaining a picture manually taken by the user according to the environmental photo shooting guidance page as the environmental photo.

[0042] For example, please refer to Figure 3 , Figure 3 FIG. 4 shows a schematic diagram of an environment photo shooting guide page according to an embodiment of the present application. Figure 3 As shown, at the top of the page are the requirements for taking environmental photos, such as taking a panoramic photo of the accident scene 2-3 meters away from the front or rear of the vehicle. Optionally, the user can be prompted by voice for the shooting requirements at the same time. In the middle of the page is an example picture of environmental photo shooting.

[0043] When you enter this page, the vehicle detection model built into the Investigation and Evidence Collection applet starts to detect and verify the current image. The vehicle detection model is pre-trained and built into the Investigation and Evidence Collection applet. When the Investigation and Evidence Collection applet is started, it can be automatically loaded and started. The vehicle detection model can be a detection model based on any deep learning mechanism and network training, and is mainly used for the identification of the entire vehicle.

[0044] In actual scenarios, users can point their handheld terminal devices at the accident scene, and the vehicle detection model verifies the number of vehicles, vehicle integrity, and entity size in the current screen obtained by the investigation and evidence collection applet. The verification of the number of vehicles mainly detects whether the number of vehicles is greater than or equal to the preset threshold. For example, when more than or equal to two vehicles are detected, the vehicle number requirement is met; the verification of vehicle integrity is mainly based on the distance between the four sides of the vehicle detection frame and the four sides of the screen, and detects whether the distance is greater than or equal to the preset threshold. For example, when the distance between the four sides of the vehicle detection frame and the four sides of the screen is greater than 10 pixels respectively, the vehicle is complete and meets the vehicle integrity requirement; the verification of entity size mainly checks whether the proportion of the vehicle detection frame to the screen size is within the preset threshold range, such as the proportion of the vehicle detection frame to the screen size is 10%-80%, which meets the entity size requirement. When the integrity and size of the two largest vehicle detection frames in the picture are judged to be qualified, the detected environment photo is considered to be a qualified environment photo, and the investigation and evidence collection applet will automatically capture this frame of image as the environment photo. The above are the specific requirements for the number of vehicles, vehicle integrity, and physical size recommended by this application. This application does not impose any restrictions on this and can be set according to business needs.

[0045] If the vehicle detection model still fails to detect a qualified environmental photo after a preset time, such as 10 seconds, a virtual button "Switch to Manual" and a corresponding prompt "Failed to shoot? Click to switch to manual shooting" will appear on the page. The user can manually take an environmental photo by clicking this button. In this case, the vehicle detection model is not used for verification, and the picture taken by the user is directly used as the environmental photo.

[0046] When the investigation and evidence collection applet captures a qualified environmental photo, or the user manually takes an environmental photo, a virtual button "Go take a photo of your entire vehicle" will appear on the page, and the user will be prompted that "the environmental photo has been taken and qualified, you can click to take a photo of your entire vehicle." The user clicks the virtual button to enter the whole vehicle photo shooting stage. You can also click anywhere other than the virtual button to stay in that stage and continue taking environmental photos, such as Figure 4 As shown, Figure 4 A schematic diagram of a page for entering the next step guidance of an embodiment of the present application is shown.

[0047] (II) Taking a photo of the whole vehicle

[0048] In some embodiments, in the process of taking the whole vehicle photo of the user and the process of taking the whole vehicle photo of the other party, the whole vehicle photo is obtained according to the following method, and the whole vehicle photo at least includes the whole vehicle photo of the front of the vehicle: displaying the whole vehicle photo shooting guidance page of the front of the vehicle, and the whole vehicle photo shooting guidance page of the front of the vehicle includes: the whole vehicle photo shooting requirements and the whole vehicle photo shooting example picture of the front of the vehicle; using the vehicle detection model to verify the integrity and entity size of the vehicle in the current picture obtained by the client, if the verification passes; using the vehicle parts segmentation model to verify the existence of the front bumper, engine hood and front windshield in the current picture obtained by the client, if the verification passes, the current picture is automatically captured as the whole vehicle photo of the front of the vehicle; if the verification fails within the preset time, it switches to the manual shooting mode, and obtains the picture manually taken by the user according to the whole vehicle photo shooting guidance page of the front of the vehicle as the whole vehicle photo of the front of the vehicle. That is, in the process of taking the whole vehicle photo of the user and the whole vehicle photo of the other party, it is necessary to take a whole vehicle photo of the front and rear of the vehicle.

[0049] Taking the photo shooting of my whole car as an example, please refer to Figure 5 , Figure 5 A schematic diagram of a guide page for taking a front-end photo of a vehicle according to an embodiment of the present application is shown. Figure 5 As shown, the whole vehicle photo shooting guidance page is as follows: the top of the page is the shooting requirements for the whole vehicle photo from the front of the vehicle, such as please shoot the whole vehicle photo from the front of the vehicle, with the license plate and revealing the entire vehicle outline. Optionally, the user can be prompted by voice at the same time for the shooting requirements; the middle of the page is an example picture of the whole vehicle photo taken from the front of the vehicle.

[0050] When entering this page, the vehicle detection model and vehicle parts segmentation model built into the investigation and evidence collection applet will simultaneously detect the current captured image. The vehicle detection model is the same as before, and the vehicle parts segmentation model is also trained in advance and built into the investigation and evidence collection applet. When the investigation and evidence collection applet is started, it can be automatically loaded and started. The vehicle parts segmentation model can be a detection model based on any deep learning mechanism and network training, and is mainly used for the segmentation and identification of vehicle parts.

[0051] In actual scenarios, users can point their handheld terminal devices at their own vehicles, and the vehicle detection model will determine whether the largest vehicle detected in the picture is a qualified front-end vehicle. Specifically, in some embodiments, the judgment of the qualification of the front-end vehicle mainly includes the vehicle integrity and physical size. As before, for the vehicle detection frame, when the distance between the four sides and the four sides of the screen is greater than 10 pixels respectively, the vehicle is complete, that is, it meets the vehicle integrity requirement; the vehicle detection frame occupies 10%-80% of the screen size, which meets the physical size requirement.

[0052] Then, the vehicle parts segmentation model judges the segmented vehicle parts and needs to be able to segment the front bumper, engine hood and front windshield at the same time. When the above three conditions are met at the same time, the frame is a qualified front vehicle photo. The investigation and evidence collection applet will automatically capture this frame of image as the front vehicle photo.

[0053] If the vehicle detection model and the vehicle component segmentation model still fail to detect a qualified front vehicle photo after a preset time, such as 10 seconds, a virtual "Switch to Manual" button and a corresponding prompt "Photography failed? Click to switch to manual photography" will appear on the page. Figure 6 As shown, Figure 6 A schematic diagram of a page for switching to manual shooting mode according to an embodiment of the present application is shown. The user clicks the virtual button to manually take a photo of the entire front of the vehicle. In this case, the vehicle detection model and the vehicle parts segmentation model are not used for verification, and the picture taken by the user is directly used as the photo of the entire front of the vehicle.

[0054] When the front photo is taken, the page can guide the user to take the rear photo. For example, a prompt "My front photo has been saved successfully! Please move to the rear of the car and take the rear photo!" appears. Figure 7 As shown, Figure 7 A schematic diagram of a page for opening guidance on taking a full-vehicle photo at the rear of a vehicle according to an embodiment of the present application is shown. After the user clicks "I understand", an example picture of a full-vehicle photo at the rear of the vehicle appears on the page, and the user can refer to the example picture to take a full-vehicle photo at the rear of the vehicle.

[0055] In some embodiments, the whole vehicle photo also includes a rear whole vehicle photo, and the method also includes: displaying a rear whole vehicle photo shooting guidance page, the rear whole vehicle photo shooting guidance page including: rear whole vehicle photo shooting requirements, and rear whole vehicle photo shooting example pictures; using the vehicle detection model to verify the integrity and physical size of the vehicle in the current picture obtained by the client, if the verification passes; using the vehicle parts segmentation model to verify the existence of the rear bumper, trunk lid and rear windshield in the current picture obtained by the client, if the verification passes, automatically capturing the current picture as the rear whole vehicle photo; if the verification fails within a preset time length, switching to manual shooting mode, obtaining a picture manually taken by the user according to the rear whole vehicle photo shooting guidance page as the rear whole vehicle photo.

[0056] Figure 8A schematic diagram of a guidance page for taking a rear-end whole vehicle photo according to an embodiment of the present application is shown. When entering the page, the same as the front-end whole vehicle photo, the vehicle detection model and the vehicle component segmentation model built into the investigation and evidence collection applet simultaneously detect the photographed page. When a vehicle is detected, it is then determined whether the largest detected vehicle is a qualified rear-end whole vehicle. Specifically, in some embodiments, a. For the qualification judgment of the rear-end whole vehicle, for the vehicle detection frame, when the distances between the four sides and the four sides of the screen are respectively greater than 10 pixels, the vehicle is complete, i.e., it meets the vehicle integrity requirement; b. The detection frame occupies 10%-80% of the screen size, i.e., it meets the entity size requirement; c. The vehicle components segmented by the vehicle component segmentation model are judged, and the rear bumper, trunk lid and rear windshield must be segmented at the same time; when the above three conditions are met, the frame is a qualified rear-end whole vehicle photo, and the investigation and evidence collection applet will automatically capture this frame of image as the rear-end whole vehicle photo.

[0057] Similarly, if the preset time, such as 10 seconds, the vehicle detection model and the vehicle parts segmentation model still have not detected a qualified rear end whole vehicle photo, a "Switch to Manual" button and a corresponding prompt "Failed to shoot? Click to switch to manual shooting" will appear on the page. The user clicks this button to manually take a rear end whole vehicle photo. In this case, the vehicle detection model and the vehicle parts segmentation model are not used for verification, and the picture taken by the user is directly used as the rear end whole vehicle photo.

[0058] As for the taking of photos of the other party’s entire vehicle and the taking of photos of your own entire vehicle, I will not go into details here.

[0059] When the rear-end photo is taken, the investigation and evidence collection applet captures qualified photos or takes photos manually, and the whole car photo is taken. A virtual button "Go to take photos of the damage to my car" appears on the page, and prompts the user "The whole car photo has been taken, you can click to take photos of the damage to my car". The user clicks the virtual button to enter the stage of taking photos of the damage to the car, and the user can also click the part other than the virtual button to stay in this stage and continue taking photos of the rear-end of the car.

[0060] (III) Taking photos of the damaged vehicle

[0061] In some embodiments, during the vehicle damage photographing phase and the other party's vehicle damage photographing phase, vehicle damage photos are obtained according to the following method: a vehicle damage photo photographing guidance page is displayed, the vehicle damage photo photographing guidance page including: a prompt for the specific location of the damage, a prompt for the damage marks, and a prompt for multiple losses; a manual shooting mode is used to obtain a picture manually taken by the user according to the displayed vehicle damage photo photographing guidance page as the vehicle damage photo.

[0062] The method of obtaining the damage photos of your own vehicle and the damage photos of the other party's vehicle is the same. Here, I will take the damage photos of my own vehicle as an example. Since the damage forms of vehicles vary and the small damage models are difficult to identify, in order to ensure a good user experience and a smooth evidence collection process, the vehicle damage shooting link is set to allow users to shoot manually.

[0063] When the car damage photo shooting process begins, a virtual button prompting the user to "click the button to shoot" is displayed on the manual shooting button. The user clicks the virtual button to shoot the car damage photo. Fig. 9 As shown, Fig. 9 A schematic diagram of a page for taking a personal car damage photo according to an embodiment of the present application is shown. The car damage photo taking guidance page includes a prompt for the specific location of the damage, a prompt for the damage traces, and a prompt for multiple losses to prompt the user to take photos, such as "Please take photos of all the losses caused by this accident from multiple angles, including the specific location of the damage and the specific damage traces." The pictures manually taken by the user according to the car damage photo taking guidance page are used as car damage photos.

[0064] The photos of the damage to the other car are the same as those of my own car, so I will not go into details here.

[0065] After the user takes a photo of the car damage, a prompt "If all the damage to your car has been photographed, you can click to take a photo of your frame number" will appear at the virtual button of "Go take a photo of your frame number". The user clicks the virtual button to enter the stage of taking the frame number. The user can also click other parts of the virtual button to stay in this stage and continue taking photos of the damage to his car.

[0066] (IV) Take a photo of your own vehicle frame number

[0067] In some embodiments of the present application, in the phase of photographing the own frame number and the phase of photographing the other party's frame number, a frame photo is obtained according to the following method: a frame number photographing guidance page is displayed, the frame number photographing guidance page including: a frame number position prompt and a frame number position example; the frame number detection model is used to verify the existence of the frame number, the integrity of the frame number, and the rationality of the frame number position in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the frame photo; if the verification fails within a preset time, the manual shooting mode is switched to obtain a picture manually taken by the user according to the frame number photographing guidance page as the frame photo.

[0068] In the vehicle frame number phase, you need to take a photo of your vehicle frame number. Fig.10 As shown, Fig.10A schematic diagram of a page for guidance on photographing one's own vehicle frame number according to an embodiment of the present application is shown. The frame number photographing guidance page is as follows: at the top of the page is a prompt for the location of the frame number, such as "Please move to the windshield and photograph the frame number below the wiper". Optionally, a voice prompt of the user's frame number location may be provided at the same time. An example of the frame number location is at the lower left corner of the page.

[0069] The investigation and evidence collection applet starts to call the frame number detection model to detect and identify the current image. The frame number detection model is trained in advance and built into the investigation and evidence collection applet. When the investigation and evidence collection applet is started, it can be automatically loaded and started. The frame number detection model can be a detection model based on any deep learning mechanism and network training, and is mainly used to identify the frame number.

[0070] When the frame number of the frame number detection model is identified, the frame number existence requirement is met; then the integrity of the frame number is checked, which is mainly based on the distance between the four sides of the frame number detection frame and the four sides of the screen being greater than or greater than or equal to the preset threshold. If the distance between the four sides of the frame number detection frame and the four sides of the screen are respectively greater than 10 pixels, the frame number is considered to be complete, which meets the frame number integrity requirement; finally, the rationality of the frame number position is checked. If it is required to be located in the middle of the page, it is mainly based on the ratio of the overlap between the frame number detection frame and the middle guide dotted line frame to the detection frame being greater than the preset threshold. If the overlap between the frame number detection frame and the middle guide dotted line frame accounts for more than 50% of the detection frame, the frame number position is considered to be reasonable, meeting the frame number position rationality requirement.

[0071] When the VIN detection model determines that the detected VIN meets the above three requirements at the same time, the VIN is considered qualified, and the investigation and evidence collection applet automatically captures the frame as the VIN picture.

[0072] Similarly, if the preset time, such as 10 seconds, the frame number detection model still fails to detect a qualified frame number photo, a virtual button "Switch to Manual" and a corresponding prompt "Failed to shoot? Click to switch to manual shooting" will appear on the page. The user can manually take a frame number photo by clicking the virtual button. In this case, the frame number detection model is not used for verification, and the picture taken by the user is directly used as the frame number photo.

[0073] When the investigation and evidence collection applet captures a qualified frame number photo, or the user manually takes a frame number photo, a "Go take a photo of the other party's entire vehicle" button will appear on the page, and the user will be prompted that "My frame number has been taken and it is qualified. You can click to take a photo of the other party's entire vehicle." The user clicks this button to enter the other party's entire vehicle photo shooting stage. You can also stay in this stage and continue taking frame number photos.

[0074] (V) Taking photos of the other party’s vehicle

[0075] The guidance on taking photos of the other party's vehicle and the judgment on its eligibility are the same as those for taking photos of your own vehicle mentioned above, so they will not be repeated here.

[0076] When the investigation and evidence collection applet captures a qualified photo of the other party's vehicle, or the user manually takes a photo of the other party's vehicle, a "Go take photos of the other party's vehicle damage" button will appear on the page, and the user will be prompted that "the other party's vehicle photos have been taken and qualified, you can click to take photos of the other party's vehicle damage". The user clicks this button to enter the process of taking photos of the other party's vehicle damage. The user can also click the virtual button to stay in this process and continue taking photos of the other party's vehicle.

[0077] (VI) Photographing the damage to the other vehicle

[0078] The guidelines for taking photos of the other party's vehicle damage and the qualification judgment are the same as the aforementioned steps for taking photos of your own vehicle damage, so they will not be repeated here.

[0079] When the user manually takes a photo of the other party's damaged car, a "Go take a photo of the other party's frame number" button will appear on the page, and the user will be prompted that "the other party's damaged car photo has been taken and qualified, you can click to take a photo of the other party's frame number". The user can click this virtual button to enter the stage of taking the other party's frame number photo. The user can also stay in this stage and continue taking photos of the other party's damaged car without clicking the virtual button.

[0080] (VII) Taking a photo of the other party’s vehicle frame number

[0081] The guidance and qualification assessment for taking photos of the other party's vehicle frame number plate are the same as those for taking photos of your own vehicle frame number plate plate mentioned above, so they will not be repeated here.

[0082] When the investigation and evidence collection applet captures a qualified photo of the other party's vehicle frame number, or the user manually takes a photo of the other party's vehicle frame number, the investigation and evidence collection process ends. The above seven steps constitute the user's on-site auto insurance investigation and evidence collection process. After completing the above process, the investigation and evidence collection process ends.

[0083] Step S130, in response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene, entering the off-site evidence collection process, in at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object, and the off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0084] The process of taking photos for investigation and evidence collection when not on site mainly consists of three steps, including taking photos of the whole vehicle, taking photos of the damage to the vehicle, and taking photos of the vehicle frame number. This application does not limit the order of the above steps. In some embodiments, based on the principle of convenience for users, the order of taking photos of the whole vehicle -> taking photos of the damage to the vehicle -> taking photos of the vehicle frame number is designed. For the convenience of explanation, the following will be explained in this order. The specific shooting instructions are consistent with the corresponding steps in the on-site investigation and evidence collection process, and will not be repeated here.

[0085] Depend on Figure 1 It can be seen from the method shown that, by adopting the motor vehicle insurance investigation and evidence collection method provided by the present application, after the user reports the case, the user is prompted to conduct an unmanned self-service investigation first, and the customer is guided so that the user can take photos of the environment, the whole vehicle, the vehicle damage, the frame number and other photos required for the investigation by themselves according to different scenarios at or off-site, and the user is given corresponding prompts in real time, which improves the success rate of collecting orders and reduces the time the user waits for the arrival of the investigator at the scene; at the same time, the quality of the taken pictures is verified and automatically framed through the vehicle detection model and the vehicle component segmentation model, and the most qualified photos are taken in an intelligent and humanized manner, which improves the success rate of evidence collection and reduces the manual operation of the user, and is highly practical; and these investigation photos are used for subsequent investigations, damage assessments, etc., which can also improve the approval timeliness, reduce the error rate, and save the investigation manpower costs of the motor vehicle insurance company, which not only improves the quality of the motor vehicle insurance investigation pictures, but also improves the efficiency of the motor vehicle insurance investigation.

[0086] Fig.11 A schematic diagram of the structure of a vehicle insurance investigation and evidence collection device according to an embodiment of the present application is shown. Fig.11 It can be seen that the vehicle insurance investigation and evidence collection device 1100 includes:

[0087] The display unit 1110 is used to display a virtual option of whether to be on the scene in response to the user's request to report the case;

[0088] The first evidence collection unit 1120 is used to enter the on-site evidence collection process in response to the user selecting the on-site operation in the virtual option of whether to be on-site, wherein at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object in at least one link of the on-site evidence collection process, and the on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle shooting link, a photo of the person's vehicle damage shooting link, a photo of the person's frame number shooting link, a photo of the other party's entire vehicle shooting link, a photo of the other party's vehicle damage shooting link, and a photo of the other party's frame number shooting link;

[0089] The second evidence collection unit 1130 is used to enter the off-site evidence collection process in response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0090] In some embodiments, the display unit 1110 is also used to display a virtual option for confirming whether to start shooting before the step of entering the on-site evidence collection process or the step of entering the off-site evidence collection process; in response to the user selecting the operation of confirming to start shooting in response to the virtual option for confirming whether to start shooting, the step of entering the on-site evidence collection process or the step of entering the off-site evidence collection process is entered.

[0091] In some embodiments, in the above-mentioned device, the first evidence collection unit 1120 is used to display an environmental photo shooting guidance page in the environmental photo shooting link, and the environmental photo shooting guidance page includes: environmental photo shooting requirements, and environmental photo shooting example pictures; the vehicle detection model is used to verify the number of vehicles, vehicle integrity, and physical size in the current picture obtained by the client. If the verification passes, the current picture is automatically captured as the environmental photo; if the verification fails within a preset time, it switches to manual shooting mode to obtain a picture manually taken by the user according to the environmental photo shooting guidance page as the environmental photo.

[0092] In some embodiments, in the above-mentioned device, the first evidence collection unit 1120 and the second evidence collection unit 1130 are respectively used to obtain whole vehicle photos according to the following method in the whole vehicle photo shooting stage of the person themselves and the whole vehicle photo shooting stage of the other party, and the whole vehicle photo at least includes the front whole vehicle photo: displaying the front whole vehicle photo shooting guidance page, the front whole vehicle photo shooting guidance page including: front whole vehicle photo shooting requirements, and front whole vehicle photo shooting example picture; using the vehicle detection model to verify the integrity and physical size of the vehicle in the current picture obtained by the client, if the verification passes; using the vehicle part segmentation model to verify the existence of the front bumper, engine hood and front windshield in the current picture obtained by the client, if the verification passes, automatically capture the current picture as the front whole vehicle photo; if the verification fails within the preset time, switch to manual shooting mode, and obtain the picture manually taken by the user according to the front whole vehicle photo shooting guidance page as the front whole vehicle photo.

[0093] In some embodiments, in the above-mentioned device, the whole vehicle photo also includes a whole vehicle photo of the rear end, and the first evidence collection unit 1120 and the second evidence collection unit 1130 are respectively used to display a guidance page for shooting the whole vehicle photo of the rear end, and the guidance page for shooting the whole vehicle photo of the rear end includes: requirements for shooting the whole vehicle photo of the rear end, and example pictures of shooting the whole vehicle photo of the rear end; the vehicle detection model is used to verify the integrity and entity size of the vehicle in the current picture obtained by the client, and if the verification passes; the vehicle parts segmentation model is used to verify the existence of the rear bumper, trunk lid and rear windshield in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the whole vehicle photo of the rear end; if the verification fails within the preset time, it is switched to manual shooting mode to obtain a picture manually taken by the user according to the guidance page for shooting the whole vehicle photo of the rear end as the whole vehicle photo of the rear end.

[0094] In some embodiments, in the above-mentioned device, in the stage of photographing the damage to the own vehicle and the stage of photographing the damage to the other vehicle, the first evidence collection unit 1120 and the second evidence collection unit 1130 are respectively used to display a vehicle damage photo shooting guidance page, and the vehicle damage photo shooting guidance page includes: a prompt for the specific location of the damage, a prompt for the traces of the damage, and a prompt for multiple losses; a manual shooting mode is used to obtain a picture manually taken by the user according to the displayed vehicle damage photo shooting guidance page as the vehicle damage photo.

[0095] In some embodiments, in the above-mentioned device, in the phase of photographing the own frame number and the phase of photographing the other party's frame number, the first evidence collection unit 1120 and the second evidence collection unit 1130 are respectively used to display a frame number photographing guidance page, and the frame number photographing guidance page includes: a frame number location prompt, and a frame number location example; the frame number detection model is used to verify the existence of the frame number, the integrity of the frame number, and the rationality of the frame number position in the current picture obtained by the client. If the verification passes, the current picture is automatically captured as the frame photo; if the verification fails within a preset time, it switches to manual shooting mode to obtain a picture manually taken by the user according to the frame number shooting guidance page as the frame photo.

[0096] It can be understood that the above-mentioned vehicle insurance investigation and evidence collection method device can implement each step of the vehicle insurance investigation and evidence collection method provided in the aforementioned embodiment, and the relevant explanations about the vehicle insurance investigation and evidence collection method are applicable to the vehicle insurance investigation and evidence collection method device, and will not be repeated here.

[0097] Fig.12 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Fig.12At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0098] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.12 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0099] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0100] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a vehicle insurance investigation and evidence collection method device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0101] In response to a user's request to report a crime, a virtual option is displayed indicating whether or not to be present at the scene;

[0102] In response to the user selecting the operation of being at the scene in the virtual option of whether to be at the scene, the on-site evidence collection process is entered. In at least one link of the on-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle, a photo of the person's vehicle damage, a photo of the person's frame number, a photo of the other party's entire vehicle, a photo of the other party's vehicle damage, and a photo of the other party's frame number;

[0103] In response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene, the off-site evidence collection process is entered. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0104] The above application Fig.11 The method performed by the vehicle insurance investigation and evidence collection method device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0105] The electronic device may also perform Fig.11 The method for executing the vehicle insurance investigation and evidence collection method device in the vehicle insurance investigation and evidence collection method device is realized in Figure 3 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0106] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Fig.11 The method executed by the vehicle insurance investigation and evidence collection method device in the embodiment shown is specifically used to execute:

[0107] In response to a user's request to report a crime, a virtual option is displayed indicating whether or not to be present at the scene;

[0108] In response to the user selecting the operation of being at the scene in the virtual option of whether to be at the scene, the on-site evidence collection process is entered. In at least one link of the on-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle, a photo of the person's vehicle damage, a photo of the person's frame number, a photo of the other party's entire vehicle, a photo of the other party's vehicle damage, and a photo of the other party's frame number;

[0109] In response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene, the off-site evidence collection process is entered. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0119] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for investigating and collecting evidence of motor vehicle insurance, characterized in that: The method is executed by a client, and includes: In response to a user's request to report a crime, a virtual option is displayed indicating whether or not to be present at the scene; In response to the user selecting the operation of being at the scene in the virtual option of whether to be at the scene, the on-site evidence collection process is entered. In at least one link of the on-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle, a photo of the person's vehicle damage, a photo of the person's frame number, a photo of the other party's entire vehicle, a photo of the other party's vehicle damage, and a photo of the other party's frame number; In response to the user selecting the operation of not being at the scene in the virtual option of whether the user is at the scene, the off-site evidence collection process is entered. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

2. The method according to claim 1, characterized in that Before the step of entering the on-site evidence collection process or the step of entering the off-site evidence collection process, the method further includes: Display a virtual option to confirm whether to start shooting; In response to the user selecting the operation of confirming to start filming in response to the virtual option of confirming whether to start filming, the step of entering the on-site evidence collection process or the step of entering the off-site evidence collection process is entered.

3. The method according to claim 1, characterized in that In the environmental photo shooting stage, the environmental photo is obtained according to the following method: Displaying an environment photo shooting guidance page, wherein the environment photo shooting guidance page includes: environment photo shooting requirements and environment photo shooting example pictures; The vehicle detection model is used to verify the number of vehicles, vehicle integrity, and entity size in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the environment photo; If the verification fails within the preset time, the mode is switched to manual shooting mode to obtain a picture manually shot by the user according to the environment photo shooting guide page as the environment photo.

4. The method according to claim 1, characterized in that: In the process of taking the whole vehicle photo of the person and the whole vehicle photo of the other party, the whole vehicle photo is obtained according to the following method, and the whole vehicle photo at least includes the whole vehicle photo of the front of the vehicle: Displaying a front-end vehicle photo shooting guidance page, wherein the front-end vehicle photo shooting guidance page includes: front-end vehicle photo shooting requirements and front-end vehicle photo shooting example pictures; Using the vehicle detection model to verify the integrity and entity size of the vehicle in the current image obtained by the client, if the verification passes; The vehicle parts segmentation model is used to perform existence verification on the front bumper, engine hood and front windshield in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the front vehicle photo; If the verification fails within the preset time, the mode is switched to manual shooting mode to obtain a picture manually shot by the user according to the front vehicle photo shooting guidance page as the front vehicle photo.

5. The method according to claim 4, characterized in that The whole vehicle photo also includes a rear whole vehicle photo, and the method further includes: Displaying a rear vehicle photo shooting guidance page, wherein the rear vehicle photo shooting guidance page includes: rear vehicle photo shooting requirements and rear vehicle photo shooting example pictures; Using the vehicle detection model to verify the integrity and entity size of the vehicle in the current image obtained by the client, if the verification passes; The vehicle parts segmentation model is used to perform existence verification on the rear bumper, the trunk lid and the rear windshield in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the rear whole vehicle photo; If the verification fails within the preset time, the mode is switched to manual shooting mode, and a picture manually shot by the user according to the rear vehicle photo shooting guidance page is obtained as the rear vehicle photo.

6. The method according to claim 1, characterized in that In the above-mentioned vehicle damage photographing phase and the above-mentioned vehicle damage photographing phase, vehicle damage photos are obtained according to the following method: Displaying a vehicle damage photo shooting guidance page, wherein the vehicle damage photo shooting guidance page includes: a reminder of the specific location of the damage, a reminder of the damage marks, and a reminder of multiple damages; A manual shooting mode is adopted to obtain a picture manually shot by the user according to the page showing the guidance for shooting the vehicle damage photo, as the vehicle damage photo.

7. The method according to claim 1, characterized in that In the process of photographing the vehicle frame number of the person concerned and the process of photographing the vehicle frame number of the other party concerned, the vehicle frame photos are obtained according to the following method: Displaying a frame number shooting guidance page, wherein the frame number shooting guidance page includes: a frame number location prompt and a frame number location example; The frame number detection model is used to verify the existence, integrity, and rationality of the frame number position of the frame number in the current picture obtained by the client, and if the verification passes, the current picture is automatically captured as the frame photo; If the verification fails within the preset time, the mode is switched to manual shooting mode to obtain a picture manually shot by the user according to the frame number shooting guidance page as the frame photo.

8. A vehicle insurance investigation and evidence collection device, characterized in that: The device comprises: A display unit, for displaying a virtual option of whether to be on the scene in response to a user's request to report a case; A first evidence collection unit is used for entering an on-site evidence collection process in response to a user selecting an on-site operation in the virtual option of whether to be on-site, wherein in at least one link of the on-site evidence collection process, automatically framing and photographing the framing object is performed using at least one of a vehicle detection model, a vehicle component segmentation model, and a frame number detection model, wherein the on-site evidence collection process includes the following multiple links: an environment photo shooting link, a photo of the person's entire vehicle shooting link, a photo of the person's vehicle damage shooting link, a photo of the person's vehicle frame number shooting link, a photo of the other party's entire vehicle shooting link, a photo of the other party's vehicle damage shooting link, and a photo of the other party's frame number shooting link; The second evidence collection unit is used to enter an off-site evidence collection process in response to the user selecting an operation of not being at the scene in the virtual option of whether the user is at the scene. In at least one link of the off-site evidence collection process, at least one of the vehicle detection model, the vehicle component segmentation model, and the frame number detection model is used to automatically frame and photograph the framing object. The off-site evidence collection process includes the following multiple links: a link for taking a photo of the user's entire vehicle, a link for taking a photo of the user's vehicle damage, and a link for taking a photo of the user's frame number.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, characterized in that when the executable instructions are executed, the processor executes any one of the vehicle insurance investigation and evidence collection methods described in claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, characterized in that: When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes any one of the vehicle insurance investigation and evidence collection methods described in claims 1 to 7.

Images