TW201947455A - Processing method and processing equipment for vehicle damage identification, client and server - Google Patents

Abstract

The embodiment of the present specification discloses a processing method, a processing device, a client and a server for vehicle damage identification. The method provides an implementation scheme for automatically identifying whether the vehicle damage is the same accident damage on the terminal device, and real-time identification of whether the damage is not the same accident damage when photographing or video shooting, without human intervention, can effectively reduce the survey personnel Requirements for skills. At the same time, information that identifies suspected non-same accident damage can be automatically recorded and transmitted to a designated server system, such as to an insurance company. In this way, even if surveyors or malicious users delete photos or videos of non-same accident damage, It is also impossible to conceal the information that the damage was identified as a non-same accident damage, which can effectively reduce the risk of fraud, improve the reliability of damage identification, and further improve the reliability of the fixed damage result.

Description

Processing method, processing equipment, client and server for vehicle damage recognition

The solutions in the embodiments of the present specification belong to the technical field of computer terminal insurance business data processing, and in particular, to a method, a processing device, a client, and a server for processing vehicle damage identification.

Motor vehicle insurance, or car insurance for short, refers to a type of commercial insurance that is liable for compensation for personal injury or property damage caused by a natural disaster or accident in a motor vehicle. With the development of the economy, the number of motor vehicles continues to increase. At present, auto insurance has become one of the largest types of insurance in China's property insurance business.
In the auto insurance industry, when an owner applies for a claim in a vehicle accident, the insurance company needs to evaluate the degree of damage to the vehicle to determine the list of items that need to be repaired and the amount of compensation. The current assessment methods mainly include: conducting on-site assessments of vehicles in accidents through surveyors of insurance companies or third-party assessment agencies, or taking pictures of accidental vehicles by users under the guidance of insurance company personnel and passing them to insurance companies via the Internet Then, the damage identification is performed by the fixed-loss personnel through photos. At present, in automobile insurance applications, the identification of damage, such as confirming the degree of damage, the type of damage, and whether it is non-same accident damage, etc., mainly rely on the manual judgment of the investigator's experience. However, in actual processing, because different surveyors have different experiences and discriminative scales, they are highly subjective. Especially, it is harder for the surveyors to identify malicious fraud in the damage determination.
Therefore, there is an urgent need in the industry for a processing solution that can more efficiently and reliably identify vehicle damage.

The purpose of the embodiments of the present specification is to provide a method, a processing device, a client, and a server for vehicle damage identification. Users can automatically identify whether the vehicle damage is the same accident damage on the terminal device, and can be used when taking pictures or videos. The identified non-same accident damage will provide immediate feedback, reduce the requirements for the experience of the investigator, and reduce the loss caused by the insurance company due to the non-same accident damage claim.
A method, a processing device, a client, and a server for vehicle damage identification provided by the embodiments of this specification are implemented in the following ways:
A processing method for vehicle damage identification, the method includes:
Get the captured images of the vehicle;
If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage;
If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
A processing method for vehicle damage identification, the method includes:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage. At least one of the network data of related parties;
Returns the recognition result to the client.
A processing device for vehicle damage recognition, the device includes:
A shooting module for obtaining a shooting image of the vehicle;
A damage determination module is used to determine whether the damage is a non-same accident damage by using a pre-trained machine learning module if a damage is recognized in the captured image;
The prominent display module is used for determining that the damage is a non-same accident damage, and displaying the prompt information that the damage is suspected to be a non-same accident damage in the shooting window, and the reminder information is rendered in a prominent way in the shooting window.
A processing device for vehicle damage recognition, the device includes:
The result receiving module is used to receive the judgment result that the damage sent by the client is not the same accident damage;
The non-same accident damage identification module is used to identify whether the damage is a non-same accident damage using the preset damage. The preset algorithm determines whether the damage is a non-same accident damage. The information used at least includes the owner's history. At least one of the risk record, the owner's credit record, and the relationship network information between the owner and the fixed loss related party;
The result feedback module is used to return the recognition result to the client.
A processing device for vehicle damage recognition includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the processor implements:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage. At least one of the network data of related parties;
Returns the recognition result to the client.
A data processing device for vehicle damage determination includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the processor realizes:
Get the captured images of the vehicle;
If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage;
If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
A client includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:
Get the captured images of the vehicle;
If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage;
If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
A server includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the server implements:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage At least one of the network data of related parties;
Returns the recognition result to the client.
A fixed loss processing system, the system includes a client and a server, and when the processor of the client executes a storage processor executable instruction, the method steps described in any one of the client embodiments of this specification are implemented;
When the processor of the server executes the executable instructions of the processor, the method steps described on any server side are implemented.
A method, a processing device, a client, and a server for identifying vehicle damage are provided in the embodiments of the present specification. The method provides an implementation scheme for automatically identifying whether the vehicle damage is the same accident damage on the terminal device, and real-time identification of whether the damage is not the same accident damage when photographing or video shooting, without human intervention, can effectively reduce the survey personnel Requirements for skills. At the same time, information that identifies suspected non-same accident damage can be automatically recorded and transmitted to a designated server system, such as to an insurance company. In this way, even if surveyors or malicious users delete photos or videos of non-same accident damage, It is also impossible to conceal the information that the damage was identified as a non-same accident damage, which can effectively reduce the risk of fraud, improve the reliability of damage identification, and further improve the reliability of the fixed damage result.

In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described in combination with the drawings in the embodiments of this specification. Obviously, the described The examples are only a part of examples in this specification, but not all examples. Based on one or more embodiments in the present specification, all other embodiments obtained by a person having ordinary skill in the art without creative efforts should fall within the protection scope of the embodiments of the present specification.
An embodiment provided in this specification can be applied to a client / server system architecture. The client may include a terminal device with a photographing function, such as a smart phone, a tablet computer, used by a person at the scene of the car damage (may be the owner of the accident car, or an insurance company person or other person who performs the damage treatment process). , Smart wearable devices, dedicated fixed loss terminals, etc. The client may have a communication module, and may communicate with a remote server to achieve data transmission with the server. The server may include a server on the insurance company side or a server on the fixed loss service side. In other implementation scenarios, it may also include a server on the other service side, for example, there is a communication link with the server on the fixed loss service side. Terminal of auto parts supplier, terminal of vehicle repair shop, etc. The server may include a single computer device, or a server cluster composed of multiple servers, or a server of a distributed system. In some application scenarios, the client side can send the image data collected on-site to the server in real time, and the server side can identify the damage, and the recognition result can be returned to the client. In the implementation of the processing on the server side, processing such as damage identification is performed by the server side, and the processing speed is usually higher than that on the client side, which can reduce the processing pressure on the client side and improve the speed of damage recognition. Of course, this description does not exclude that all or part of the processing described above is implemented by the client side in other embodiments, such as the client side performing instant detection and identification of damage.
In general, the damage caused by a vehicle in the same accident is regularly followed. For example, if a scratch has occurred on the left front side, it is unlikely that a scratch may also occur on the right rear side at the same time. In one or more embodiments of the present specification, the accumulated data of a large number of historical cases can be used to calculate the joint probability of damage to each component, so as to determine the specified components at the same time through a machine learning model such as a Bayesian network. The probability of damage, thereby determining whether it is the same accident. As a supplement, a preset rule for determining whether the damage is the same accident can be artificially set, as shown in FIG. 1, for example, “the left front leaf plate and the right front leaf plate cannot be damaged simultaneously”. In one or more embodiments provided in this specification, a machine learning model may be pre-trained, and the machine learning model may use joint historical probability of each component to send damage, which is calculated from the data of historical cases, or it may be combined with a manual preset to determine whether the damage is Information for general accident rules. The machine learning model may include a learning model constructed based on the Bayesian network, and may also include other machine learning models such as a deep neural network.
The deep neural network is trained using pre-collected data letters of historical non-same accident injuries. This training sample picture can manually mark multiple injuries of non-same accidents in advance. Through deep neural network sample training, a recognition model including a classifier that predicts whether the car damage is a non-same accident damage can be obtained. After determining that the damage is a non-same accident damage through the machine learning model, you can use a significant way to prompt in the viewfinder window processed by the terminal, which can not only clearly remind the user that the damage is a non-same accident damage, but also reduce the use of malicious users The initiative to claim compensation for the non-same accident damage (the malicious user has learned that the damage was determined by the system as a non-same accident damage, and the use value has been greatly reduced).
In one or more embodiments of the present specification, the machine learning model, such as a Bayesian network, may be generated in an offline pre-built manner, and then used online after training is completed. This manual does not exclude that the machine learning model can be constructed or updated / maintained online. With sufficient computer capabilities, the client or server side can build a machine learning model online. The machine learning model can be constructed online in real time. Use to identify whether the image recognized by the captured image is a non-same accident damage.
The following describes a specific implementation scenario of a mobile phone client as an example. Specifically, FIG. 2 is a schematic flowchart of an embodiment of a data processing method for a vehicle's fixed loss provided in this specification. Although the present specification provides method operation steps or device structures as shown in the following embodiments or drawings, based on conventional or no creative labor, the method or device may include more or partially merged fewer operation steps. Or module unit. Among the steps or structures that do not logically have the necessary causal relationship, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or the drawings of this specification. When the described method or module structure is applied to an actual device, server, or end product, the method or module structure shown in the embodiment or the diagram may be executed sequentially or in parallel (for example, a parallel processor or Multi-threaded processing environment, even decentralized processing, server cluster implementation environment). Of course, the description of the following embodiments does not limit other technical solutions that can be extended based on this specification. For example in other implementation scenarios. A specific embodiment is shown in FIG. 1. In an embodiment of a method for processing data for determining a vehicle's damage provided in this specification, the method may include:
S0: Acquire a captured image of the vehicle;
S2: If it is identified that there is a damage in the captured image, use a pre-trained machine learning module to determine whether the damage is a non-same accident damage;
S4: If yes, prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
The client on the user side in this embodiment may be a smart phone, and the smart phone may have a shooting function. The user can open a mobile phone application that implements the implementation of this specification at the scene of the vehicle accident to take a shot of the scene of the vehicle accident. After the client opens the application, the shooting window can be displayed on the client display screen, and the vehicle can be captured through the shooting window. The shooting window can be a video shooting window, which can be used by the terminal to view the scene of the car damage (image acquisition), and the image information obtained through the client-integrated shooting device can be displayed in the shooting window. The specific interface structure of the shooting window and related information displayed can be customized.
During the shooting of the vehicle, a captured image of the vehicle can be acquired, and it can be identified whether there is damage in the image.
In some embodiments of the present specification, the damage identification processing may be implemented by the client side or the server side. The server at this time may be referred to as a damage identification server. In some application scenarios or computing capabilities, the images collected by the client can be directly used to identify the damage locally on the client, or other fixed loss data processing can reduce network transmission overhead. Of course, as mentioned earlier, the computing power on the server side is usually stronger than the client. In another embodiment of the method provided in this specification, the processing of damage identification may be processed by the server side. Specifically, identifying the damage in the captured image may include:
S20: Send the captured images obtained by shooting to the damage recognition server;
S22: Receive the damage recognition result returned by the server, and the damage recognition result includes that the damage recognition server uses a pre-built damage recognition model to identify whether there is damage in the acquired image.
In the above embodiment, the client or the server can use a deep neural network constructed in advance or in real time to identify the damage in the image, such as the location of the damage, the damage component, and the type of damage.
Deep neural networks can be used for target detection and semantic segmentation. For the input picture, find the position of the target in the picture and confirm the damage position relationship. FIG. 3 is a schematic diagram of a deep neural network model of whether there is an injury used in the method embodiment described in the specification. Depicted in Figure 3 is a typical deep neural network Faster R-CNN. A deep neural network can be trained by marking a large number of pictures of the damaged area in advance. The extent of the damage area. In addition, in some embodiments of this specification, a network structure customized for a mobile device can be used, such as based on a typical MobileNet, SqueezeNet, or an improved network structure, so that the model for identifying whether to store calculations can be used in mobile devices with lower power It consumes less internal memory and has a slower processor, such as the mobile terminal operating environment of the client.
After determining that the damage is a non-same accident damage, the prompt information that the damage is a non-same accident damage can be displayed in the shooting window of the client. The damage identified here is a non-same accident. The damage is obtained based on the data of the captured image. In some implementation scenarios, the characteristics of the new injury and the non-same accident may be very close, so that even a new injury may be identified as Non-identical injuries. Therefore, the non-same accident damage identified here in the embodiment of the present specification may be displayed as a suspected non-same accident damage when displayed on the client. The information indicating that the damage is non-same accident damage can be rendered in the display mode and displayed in the shooting window. The above-mentioned rendering in a prominent manner mainly refers to using some special rendering methods to mark a damaged area in a shooting picture, so that the damaged area is easy to identify or more prominent. In this embodiment, the specific rendering method is not limited, and specifically, a constraint condition or a condition that achieves rendering in a significant manner can be set.
In another embodiment of the method provided in this specification, the rendering in a salient manner may include:
S40: The preset information is used to identify the prompt information. The preset symbol includes one of the following:
Text, dots, guides, regular graphic squares, irregular graphic squares, custom graphics.
Figure 4 is a schematic diagram of a commonly used application program that uses intermittent rectangles and red background text to identify non-same accident damage. The front bumper and left rear leaflet in Figure 4 are new injuries identified, and the prompt information is Green text. Of course, in other embodiments, the preset symbol may also include other forms, such as guide lines, regular graphic squares, irregular graphic squares, custom graphics, etc. In other embodiments, text, Characters, data, etc. mark the damaged area and guide the user to shoot the damaged area. You can use one or more preset characterizations when rendering. In this embodiment, a preset symbol is used to identify the damage area, and the location area of the damage can be more clearly displayed in the shooting window, which assists the user to quickly locate and guide the shooting.
In another embodiment of the method provided in this specification, a dynamic rendering effect may also be used to identify the prompt information, in a more obvious way to prompt the user that the damage is a non-same accident damage. Specifically, in another embodiment, the rendering in a prominent manner includes:
S400: Perform at least one of animated display of color transformation, size transformation, rotation, and beating on the preset representative symbol.
In some embodiments of the present specification, AR may be superimposed to display the boundary of damage. The augmented reality AR generally refers to a technical implementation solution that calculates the position and angle of the camera image in real time and adds corresponding images, videos, and 3D models. This solution can put the virtual world on the screen in the real world And interact. The AR model can be matched with the real vehicle position during the shooting time. For example, the constructed 3D contour is superimposed on the contour position of the real vehicle. When the two completely match or the degree of matching reaches a threshold, the matching can be considered to be completed. In the specific matching process, the framing direction can be guided, and the user can move the shooting direction or angle through the guide to align the constructed contour with the contour of the real vehicle photographed. The embodiment of this specification combines the augmented reality technology to not only display the real information of the vehicle photographed by the user's actual client, but also display the information of the augmented reality spatial model of the vehicle constructed at the same time. The two types of information complement and superimpose each other. Can provide a better loss-of-loss service experience.
The above embodiment describes the implementation of the prompt information displayed by text. In an expandable embodiment, the prompt information may further include a display manner of an image, a voice, an animation, a vibration, and the like, and an arrow or a voice prompt is used to align a current shooting frame to a certain area. Therefore, in another embodiment of the method, the form of the prompt information displayed in the current shooting window includes at least one of symbols, text, voice, animation, video, and vibration.
The client application can automatically return the identification results identified as non-same accident damage to the system background for storage for subsequent manual or automatic damage determination. It can also avoid or reduce the risk of users using non-same accident damage for fraud protection. Therefore, in another embodiment of the method provided in this specification, after determining that the injury is a non-same accident injury, the method further includes:
S6: Send the information including identifying the damage to the non-same accident damage to a predetermined server.
FIG. 5 is a schematic flowchart of another embodiment of the method provided in this specification. The predetermined server may include a server on the insurance company side, or it may be replaced on the client side first, and then sent back to the insurance company's back-end system by asynchronous transmission if the network conditions permit. The result It can be used for further review of the case. Even if the on-site investigator deletes the photo and shoots elsewhere, the recognition result is also seen in the back-end system, which further increases the difficulty of counterfeiting.
It should be noted that the real-time described in the above embodiments may include sending, receiving, or displaying immediately after acquiring or determining certain information. Those skilled in the art can understand that after caching memory or expected calculations and waiting, Sending, receiving, or displaying after time can still fall within the scope of this instant definition. The images described in the embodiments of the present specification may include video, and the video may be regarded as a continuous image set.
In addition, the identification result determined as a non-same accident damage in the solution of the embodiment of the present specification can be sent to a predetermined server for storage, which can effectively prevent insurance fraud where the fixed damage data is tampered with. Therefore, the embodiments of the present specification can also improve the data security of the fixed loss processing and the reliability of the fixed loss results.
In another embodiment, because the processing performance of the mobile terminal is limited, when the back-end system receives photos or videos uploaded by the APP, it can further utilize the more powerful processing capabilities of the server and use a deep neural network with higher accuracy (in the This can be called a second deep neural network) for analysis. The aforementioned client or server's judgment results using the first deep neural network can be used as input features, and possessed by insurance companies, or legally obtain other information through third-party authorization (such as vehicle owner credit records, vehicle historical risk records, vehicle owners Together with the surveyor, the relationship network of the maintenance plant, geographic location information, etc.), the machine learning method is used to make a more comprehensive and accurate judgment on whether the damage is not the same accident. It should be noted that the server can use other machine learning algorithms to further determine whether it is the same accident damage. Therefore, in another embodiment of the method provided in this specification, after determining that the injury is a non-same accident injury, the method may further include:
S80: Send the judgment result of judging the damage as a non-same accident damage to the server;
S82: The receiving server uses a preset algorithm to identify whether the damage is a non-same accident damage. The data used in the preset algorithm to determine whether the damage is a non-same accident damage includes at least the owner ’s historical risk record and the owner ’s credit At least one of records, network data of the relationship between the owner and the fixed loss related party.
As mentioned above, the preset algorithm may include a deep neural network, or may include other machine learning algorithms, such as a Bayesian network, or a custom-set algorithm.
The foregoing embodiment describes the implementation of a data processing method for determining a vehicle's damage by a user on a mobile client. It should be noted that the method described in the embodiments of this specification can be used in a variety of processing equipment, such as a dedicated fixed loss terminal, and an implementation scenario including a client and server architecture.
Based on the foregoing description, this specification also provides a processing method for vehicle damage recognition that can be used on the server side, which specifically includes:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage. At least one of the network data of related parties;
Returns the recognition result to the client.
Each embodiment of the above method in this specification is described in a progressive manner, and the same or similar parts between the various embodiments may refer to each other. Each embodiment focuses on the differences from other embodiments. For related points, refer to the description of the method embodiments.
The method embodiments provided in the embodiments of the present invention may be executed in a mobile terminal, a PC terminal, a dedicated fixed loss terminal, a server, or a similar computing device. Taking running on a mobile terminal as an example, FIG. 6 is a block diagram of a hardware structure of a client to which an interactive process of vehicle damage determination is applied according to the method or device embodiment of the present invention. As shown in FIG. 6, the client 10 may include one or more (only one shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) ), A memory 104 for storing data, and a transmission module 106 for communication functions. Persons of ordinary skill in the art can understand that the structure shown in FIG. 6 is only schematic, and it does not limit the structure of the electronic device. For example, the client 10 may further include more or fewer components than those shown in FIG. 6, for example, may further include other processing hardware, such as a GPU (Graphics Processing Unit, image processor), Shows different configurations.
The memory 104 may be used to store software programs and modules of application software, such as program instructions / modules corresponding to the search method in the embodiment of the present specification. The processor 102 runs the software programs and modules stored in the memory 104 , So as to execute various functional applications and data processing, that is, to achieve the above-mentioned processing method of navigation interactive interface content display. The memory 104 may include high-speed random memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely disposed with respect to the processor 102, and these remote memories may be connected to the client 10 through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
The transmission module 106 is used to receive or send data through a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network controller (NIC), which can be connected to other network devices through the base station to communicate with the Internet. In one example, the transmission module 106 may be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.
Based on the image object positioning method described above, this specification also provides a processing device for vehicle damage recognition. The device may include a system (including a decentralized system), software (application), a module, a component, a server, a client, and the like using the method described in the embodiments of the present specification, and a device incorporating necessary implementation hardware Device. Based on the same innovative concept, the processing device in one embodiment provided in this specification is as follows in the following embodiments. Since the implementation solution of the device to solve the problem is similar to the method, the implementation of the specific processing device in the embodiment of this specification may refer to the implementation of the foregoing method, and the duplicated details are not described again. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and conceived. Specifically, as shown in FIG. 7, FIG. 7 is a schematic diagram of a module structure of an embodiment of a processing device for vehicle damage recognition provided in this specification, and may specifically include:
The shooting module 201 may be used to obtain a shooting image of a vehicle;
The damage determination module 202 can be used to determine whether the damage is a non-same accident damage by using a pre-trained machine learning module if a damage is recognized in the captured image;
The prominent display module 203 can be used to determine when the damage is a non-same accident damage, and display in the shooting window the prompt information that the damage is suspected to be a non-same accident damage, and the reminder information is rendered in a prominent way in the shooting window .
Based on the foregoing method embodiment description, a processing device that can be used for vehicle damage identification on the server side is also provided. Specific can include:
The result receiving module 301 can be used to receive a judgment result that the damage sent by the client is a non-same accident damage;
The non-same accident damage identification module 302 can be used to identify whether the damage is a non-same accident damage using a preset algorithm. The preset algorithm determines whether the damage is a non-same accident damage. The information used at least includes At least one of the vehicle owner's historical risk record, the vehicle owner's credit record, and the relationship network information between the vehicle owner and the fixed loss related party;
The result feedback module 303 may be used to return the recognition result to the client.
It should be noted that the device described in the foregoing embodiment according to the description of the related method embodiment may further include other implementation manners, such as a rendering processing module that performs rendering, and an AR display module that performs AR processing. For specific implementation manners, reference may be made to the description of the method embodiments, and details are not described herein.
The device model identification method provided in the embodiments of this specification can be implemented by a processor executing corresponding program instructions in a computer, such as using the c ++ / java language of the windows / Linux operating system on the PC / server side, or other such as android 2. The necessary hardware implementation of the application programming language corresponding to the iOS system, or the implementation of processing logic based on quantum computers. Specifically, in the embodiment of the method for realizing the above-mentioned method of a data processing device for vehicle damage provided in this specification, the processing device may include a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, achieve:
Get the captured images of the vehicle;
If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage;
If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the processor further executes:
Sending the judgment result of judging the damage as a non-same accident damage to the server;
The receiving server uses a preset algorithm to identify whether the damage is a non-same accident damage. The information used in the preset algorithm to determine whether the damage is a non-same accident damage includes at least the owner's historical risk record, the owner's credit record, At least one of the network data of the relationship between the owner and the fixed loss related party.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the rendering in a prominent manner includes:
The reminder information is identified by a preset symbol, which includes one of the following:
Text, dots, guides, regular graphic squares, irregular graphic squares, custom graphics.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the rendering in a prominent manner includes:
At least one of the color transformation, size transformation, rotation, and beating animation display is performed on the preset representative symbol.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the processor further executes:
The information including identifying the damage as a non-same accident damage is sent to a predetermined server.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the form of the prompt information includes at least one of a symbol, a text, a voice, an animation, a video, and a vibration.
Based on the foregoing method embodiment description, in another embodiment of the processing device, the processing device may include a processor and a memory for storing processor-executable instructions, and the processor implements when the instructions are executed:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of a preset algorithm to identify whether the injury is a non-same accident injury is the recognition result. The information used in the preset algorithm to determine whether the injury is a non-same accident injury includes at least the owner's historical risk record, the owner's credit record, the owner's and Damage at least one of the related party network data;
Returns the recognition result to the client.
It should be noted that, in the processing device described in the foregoing embodiment, the description of the related method embodiment may further include other expandable implementations. For specific implementation manners, reference may be made to the description of the method embodiments, and details are not described herein.
The above instructions can be stored in a variety of computer-readable storage media. The computer-readable storage medium may include a physical device for storing information, and the information may be digitized and then stored using a medium using electricity, magnetism, or optics. The computer-readable storage medium described in this embodiment may include: a device for storing information using electric energy, such as various types of memory, such as RAM, ROM, etc .; a device for storing information using magnetic energy, such as hard disk, floppy disk, Magnetic tapes, core memory, bubble memory, flash drives; devices that use optical means to store information, such as CDs or DVDs. Of course, there are other ways of readable storage media, such as quantum memory, graphene memory, and so on. The instructions in the device or server or client or system described in the embodiments of this specification are as described above.
The above method or device embodiment can be used for a client on the user side, such as a smart phone. Therefore, this specification provides a client, including a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:
Get the captured images of the vehicle;
If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage;
If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window.
This specification provides a server including a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements:
The damage sent by the receiving client is the result of the judgment of a non-same accident damage;
The use of a preset algorithm to identify whether the injury is a non-same accident injury is the recognition result. The information used in the preset algorithm to determine whether the injury is a non-same accident injury includes at least the owner's historical risk record, the owner's credit record, the owner's and Damage at least one of the related party network data;
Returns the recognition result to the client.
Based on the foregoing, an embodiment of the present specification also provides a fixed loss processing system. The system includes a client and a server. When the processor of the client executes a storage processor executable instruction, it can be implemented on the client side in this specification. The method steps of any one of the embodiments;
When the processor of the server executes the executable instructions of the processor, the method steps of any one of the embodiments in the specification that can be implemented on the server side are implemented.
The various embodiments of the device, client, server, system, etc. described in this specification are described in a progressive manner. The same and similar parts between the various embodiments can be referred to each other. The focus of each embodiment is Differences from other embodiments. In particular, for the hardware + programming embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts may refer to the description of the method embodiment.
The specific embodiments of the present specification have been described above. Other embodiments are within the scope of the appended patent applications. In some cases, the actions or steps described in the scope of the patent application may be performed in a different order than in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired result. In some embodiments, multiplexing and parallel processing are also possible or may be advantageous.
Although the present invention provides the operation steps of the method as described in the embodiment or the flowchart, more or less operation steps may be included based on conventional or non-creative labor. The sequence of steps listed in the embodiments is only one way of executing the steps, and does not represent the only sequence of execution. When the actual device or client product is executed, it may be executed sequentially or in parallel according to the method shown in the embodiment or the diagram (for example, a parallel processor or a multi-threaded processing environment).
Although the content of the embodiments of this specification mentions AR technology, CNN network training, client or server damage identification processing, client and server message interaction, data acquisition, location arrangement, interaction, calculation, judgment, etc. Operation and data description, however, the embodiments of the present specification are not limited to the situations that must conform to industry communication standards, standard image data processing protocols, communication protocols, and standard data models / templates, or the embodiments described in this specification. Certain industry standards or implementations that are slightly modified based on implementations described in custom methods or embodiments can also achieve the same, equivalent or similar, or predictable implementation effects of the above embodiments. Embodiments obtained by applying these modified or deformed data acquisition, storage, judgment, processing methods, etc., may still fall within the scope of optional implementations of this specification.
In the 1990s, for a technical improvement, it can be clearly distinguished whether it is an improvement in hardware (for example, the improvement of circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (for method and process Improve). However, with the development of technology, the improvement of many methods and processes can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. It is programmed by the designer to "integrate" a digital system on a PLD, without having to ask a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of making integrated circuit chips by hand, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing, and requires compilation. The previous original code must also be written in a specific programming language. This is called the Hardware Description Language (HDL). There is not only one kind of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are commonly used. Those skilled in the art should also be clear that the hardware circuit that implements the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with the above-mentioned several hardware description languages.
The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable storage of computer-readable program code (such as software or firmware) executable by the (micro) processor. Media, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in pure computer-readable program code, it is entirely possible to make the controller logic gates, switches, dedicated integrated circuits, and programmable logic controllers by logically programming the method steps. And embedded microcontroller to achieve the same function. Therefore, the controller can be considered as a hardware component, and the device included in the controller for implementing various functions can also be considered as a structure in the hardware component. Or even, a device for implementing various functions can be regarded as a structure that can be both a software module implementing the method and a hardware component.
The system, device, module, or unit described in the foregoing embodiments may be specifically implemented by a computer chip or entity, or by a product having a certain function. A typical implementation is a computer. Specifically, the computer may be, for example, a personal computer, a notebook computer, a vehicle-mounted human-machine interactive device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, Tablet, wearable, or a combination of any of these.
Although the embodiments of the present specification provide the operation steps of the method as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative means. The sequence of steps listed in the embodiments is only one way of executing the steps, and does not represent the only sequence of execution. When the actual device or terminal product is executed, it may be executed sequentially or in parallel according to the method shown in the embodiment or the diagram (for example, a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "including,""including," or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed Elements, or elements that are inherent to such a process, method, product, or device. Without further limitation, it does not exclude that there are other identical or equivalent elements in the process, method, product or equipment including the elements.
For the convenience of description, when describing the above device, the functions are divided into various modules and described separately. Of course, when implementing the embodiments of this specification, the functions of each module may be implemented in the same or multiple software and / or hardware, or the module that implements the same function may be composed of multiple submodules or subunits. Implementation etc. The device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or integrated into another unit. A system or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.
Those skilled in the art also know that in addition to implementing the controller in pure computer-readable program code, it is entirely possible to make the controller logic gates, switches, dedicated integrated circuits, and programmable logic controllers by logically programming the method steps. And embedded microcontroller to achieve the same function. Therefore, such a controller can be considered as a hardware component, and the device included in the controller for implementing various functions can also be considered as a structure within the hardware component. Or even, a device for implementing various functions can be regarded as a structure that can be both a software module implementing the method and a hardware component.
The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and a combination of the flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine for instructions executed by the processor of the computer or other programmable data processing device Generate means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.
These computer program instructions may also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including a command device , The instruction device realizes the functions specified in a flowchart or a plurality of processes and / or a block or a block of the block diagram.
These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operating steps can be performed on the computer or other programmable equipment to generate computer-implemented processing, so that the computer or other programmable equipment can The instructions executed on the steps provide steps for realizing the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.
In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and internal memory.
Internal memory may include non-persistent memory, random access memory (RAM), and / or non-volatile internal memory in computer-readable media, such as read-only memory (ROM) or flash memory (flash RAM). Internal memory is an example of a computer-readable medium.
Computer-readable media includes permanent and non-permanent, removable and non-removable media. Information can be stored by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change internal memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory (RAM ), Read-only memory (ROM), electrically erasable and programmable read-only memory (EEPROM), flash memory or other internal memory technology, read-only disc read-only memory (CD-ROM), digital Versatile optical discs (DVDs) or other optical storage, magnetic tape cartridges, magnetic disk storage or other magnetic storage devices or any other non-transmitting media may be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
Those skilled in the art should understand that the embodiments of the present specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification may use a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program codes. form.
The embodiments of this specification 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 embodiments of the present specification can also be practiced in a decentralized computing environment. In these decentralized computing environments, tasks are performed by a remote processing device connected through a communication network. In a decentralized computing environment, program modules can be located in local and remote computer storage media, including storage devices.
Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant part, refer to the description of the method embodiment. In the description of this specification, the description with reference to the terms “one embodiment”, “some embodiments”, “examples”, “specific examples”, or “some examples” and the like means specific features described in conjunction with the embodiments or examples , Structure, materials, or features are included in at least one embodiment or example of an embodiment of the present specification. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Moreover, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, without any contradiction, those skilled in the art may combine and combine different embodiments or examples and features of the different embodiments or examples described in this specification.
The above descriptions are merely examples of the embodiments of the present specification, and are not intended to limit the embodiments of the present specification. For those skilled in the art, the embodiments of the present specification may have various modifications and changes. Any modification, equivalent replacement, and improvement made within the spirit and principle of the embodiments of the present specification shall be included in the scope of patent application of the embodiments of the present specification.

S0 ~ S6‧‧‧step

10‧‧‧Client

102‧‧‧ processor

104‧‧‧Non-volatile memory

106‧‧‧Transmission Module

201‧‧‧ shooting module

202‧‧‧ Damage Determination Module

203‧‧‧Significant display module

301‧‧‧Result receiving module

302‧‧‧ Non-same accident damage identification module

303‧‧‧Result feedback module

In order to more clearly explain the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only For some ordinary people skilled in the art, some embodiments described in the specification can also obtain other drawings according to these drawings without paying creative labor.

FIG. 1 is a schematic diagram of a rule relationship for artificially setting whether a predetermined damage is a same accident in an embodiment of the present specification; FIG.

FIG. 2 is a schematic flowchart of an embodiment of a data processing method for determining vehicle damage provided in this specification; FIG.

FIG. 3 is a schematic diagram of a deep neural network model for whether there is an injury used in the method embodiment described in this specification;

4 is a schematic diagram of an application scenario provided by the present specification to use a solid origin and red background text to identify non-same accident damage;

FIG. 5 is a schematic flowchart of another embodiment of the method provided in this specification; FIG.

FIG. 6 is a block diagram of a hardware structure of a client to which an interactive method of vehicle fixed damage is applied according to a method or device embodiment of the present invention; FIG.

FIG. 7 is a schematic diagram of a module structure of an embodiment of a processing device for vehicle damage recognition provided in this specification.

Claims (19)

A processing method for vehicle damage identification, the method includes: Get the captured images of the vehicle; If damage is identified in the captured image, a pre-trained machine learning model is used to determine whether the damage is a non-same accident damage; If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window. The method according to claim 1, after determining that the injury is a non-same accident injury, the method further includes: Sending the judgment result of judging the damage as a non-same accident damage to the server; The receiving server uses a preset algorithm to identify whether the damage is a non-same accident damage. The information used in the preset algorithm to determine whether the damage is a non-same accident damage includes at least the owner's historical risk record, the owner's credit record, At least one of the network data of the relationship between the owner and the fixed loss related party. The method according to claim 1, after determining that the injury is a non-same accident injury, the method further includes: The information including identifying the damage as a non-same accident damage is sent to a predetermined server. The method according to claim 1, wherein the rendering in a salient manner comprises: The reminder information is identified by a preset symbol, which includes one of the following: Text, dots, guides, regular graphic squares, irregular graphic squares, custom graphics. The method as claimed in claim 4, wherein the rendering in a salient manner comprises: At least one of the color transformation, size transformation, rotation, and beating animation display is performed on the preset representative symbol. According to the method of claim 1, the form of the prompt information includes at least one of a symbol, a text, a voice, an animation, a video, and a vibration. A processing method for vehicle damage identification, the method includes: The damage sent by the receiving client is the result of the judgment of a non-same accident damage; The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage At least one of the network data of related parties; Returns the recognition result to the client. A processing device for vehicle damage recognition, the device includes: A shooting module for obtaining a shooting image of the vehicle; A damage determination module is used to determine whether the damage is a non-same accident damage by using a pre-trained machine learning module if a damage is recognized in the captured image; The prominent display module is used for determining that the damage is a non-same accident damage, and displaying the prompt information that the damage is suspected to be a non-same accident damage in the shooting window, and the reminder information is rendered in a prominent way in the shooting window. A processing device for vehicle damage recognition, the device includes: The result receiving module is used to receive the judgment result that the damage sent by the client is not the same accident damage; The non-same accident damage identification module is used to identify whether the damage is a non-same accident damage using the preset damage. The preset algorithm determines whether the damage is a non-same accident damage. The information used at least includes the owner's history. At least one of the risk record, the owner's credit record, and the relationship network information between the owner and the fixed loss related party; The result feedback module is used to return the recognition result to the client. A processing device for vehicle damage recognition includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the processor implements: The damage sent by the receiving client is the result of the judgment of a non-same accident damage; The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage At least one of the network data of related parties; Returns the recognition result to the client. A data processing device for vehicle damage determination includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the processor realizes: Get the captured images of the vehicle; If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage; If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window. The processing device according to claim 11, the processor further executing: Sending the judgment result of judging the damage as a non-same accident damage to the server; The receiving server uses a preset algorithm to identify whether the damage is a non-same accident damage. The information used in the preset algorithm to determine whether the damage is a non-same accident damage includes at least the owner's historical risk record, the owner's credit record, At least one of the network data of the relationship between the owner and the fixed loss related party. The processing device according to claim 11, wherein the notable rendering includes: The reminder message is identified by a preset symbol, and the preset symbol includes one of the following: Text, dots, guides, regular graphic squares, irregular graphic squares, custom graphics. The processing device according to claim 13, wherein the notable rendering includes: At least one of the color transformation, size transformation, rotation, and beating animation display is performed on the preset representative symbol. The processing device according to claim 11, the processor further executing: The information including identifying the damage as a non-same accident damage is sent to a predetermined server. The processing device according to claim 11, wherein the form of the prompt information includes at least one of a symbol, a text, a voice, an animation, a video, and a vibration. A client includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements: Get the captured images of the vehicle; If damage is identified in the captured image, a pre-trained machine learning module is used to determine whether the damage is a non-same accident damage; If yes, the prompt information that the damage is suspected to be a non-same accident damage is displayed in the shooting window, and the prompt information is rendered in a prominent way in the shooting window. A server includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the server implements: The damage sent by the receiving client is the result of the judgment of a non-same accident damage; The use of preset damage to identify whether the damage is a non-same accident damage is the identification result. The data used in the preset algorithm to determine whether the damage is a non-same accident is at least the owner's historical risk record, the owner's credit record, the owner and the fixed damage At least one of the network data of related parties; Returns the recognition result to the client. A fixed loss processing system, the system includes a client and a server, and the processor of the client implements the method steps described in any one of the request items 1-6 when executing a processor-executable instruction; The processor of the server implements the method steps described in claim 7 when the processor-executable instructions are stored.