WO2019214321A1 - Procédé de traitement d'identification de dommage à véhicule, dispositif de traitement, client et serveur - Google Patents

Procédé de traitement d'identification de dommage à véhicule, dispositif de traitement, client et serveur Download PDF

Info

Publication number
WO2019214321A1
WO2019214321A1 PCT/CN2019/076032 CN2019076032W WO2019214321A1 WO 2019214321 A1 WO2019214321 A1 WO 2019214321A1 CN 2019076032 W CN2019076032 W CN 2019076032W WO 2019214321 A1 WO2019214321 A1 WO 2019214321A1
Authority
WO
WIPO (PCT)
Prior art keywords
damage
same accident
client
vehicle
owner
Prior art date
Application number
PCT/CN2019/076032
Other languages
English (en)
Chinese (zh)
Inventor
周凡
Original Assignee
阿里巴巴集团控股有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019214321A1 publication Critical patent/WO2019214321A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior

Definitions

  • the embodiment of the present specification belongs to the technical field of data processing of computer terminal insurance services, and in particular, to a method, a processing device, a client and a server for processing a vehicle damage identification.
  • Motor vehicle insurance that is, automobile insurance (or car insurance) refers to a type of commercial insurance that is liable for personal injury or property damage caused by natural disasters or accidents. With the development of the economy, the number of motor vehicles is increasing. At present, auto insurance has become one of the biggest insurances in China's property insurance business.
  • the current assessment methods mainly include: conducting an on-site assessment of the vehicle in which the accident occurred through an insurance company or a third-party assessment agency, or by taking pictures of the accident vehicle under the guidance of the insurance company personnel, and transmitting it to the insurance company through the network.
  • the damage is identified by the person in the position of the damage.
  • the identification of damage such as confirming the degree of damage, the type of damage, whether it is a non-identical accident, etc., depends mainly on the artificial judgment of the surveyor's experience.
  • the subjectivity is strong, especially for the investigators, it is less difficult to identify malicious fraudulent acts in the fixed damage.
  • the embodiment of the present specification aims to provide a processing method, a processing device, a client, and a server for identifying a vehicle damage.
  • the user can automatically identify whether the vehicle damage is the same accident damage on the terminal device, and can be used when taking a picture or video.
  • the identified non-same accident damage gives immediate feedback, reduces the requirements for the surveyor's experience, and reduces the losses incurred by the insurance company due to non-same accident damage claims.
  • a method, a processing device, a client, and a server for processing a vehicle damage identification provided by an embodiment of the present specification are implemented by the following methods:
  • a method for processing vehicle damage identification comprising:
  • the prompt information indicating that the damage is suspected to be the same accident is displayed in the shooting window, and the prompt information is rendered in a significant manner in the shooting window.
  • a method for processing vehicle damage identification comprising:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using the preset damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • a processing device for vehicle damage recognition comprising:
  • a shooting module for acquiring a captured image of the vehicle
  • the damage determining module is configured to determine, by using a pre-trained machine learning module, whether the damage is a non-same accident damage if the damage is detected in the captured image;
  • a display module for determining that the damage is a non-identical accident damage, and displaying, in the photographing window, the damage information as a suspected non-same accident damage, the prompt information being in a prominent manner in the photographing window Rendering.
  • a processing device for vehicle damage recognition comprising:
  • a result receiving module configured 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 is used to identify whether the damage is a non-identical accident damage by using the preset damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least the owner history. At least one of the risk record, the owner's credit record, and the relationship network data between the owner and the associated party;
  • a result feedback module configured to return a recognition result to the client.
  • a processing device for vehicle damage identification includes a processor and a memory for storing processor-executable instructions, the processor implementing the instructions to:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using the preset damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • a data processing device for vehicle damage comprising a processor and a memory for storing processor executable instructions, the processor implementing the instructions to:
  • the prompt information indicating that the damage is suspected to be the same accident is displayed in the shooting window, and the prompt information is rendered in a significant manner in the shooting window.
  • a client comprising a processor and a memory for storing processor executable instructions, the processor implementing the instructions to:
  • the prompt information indicating that the damage is suspected to be the same accident is displayed in the shooting window, and the prompt information is rendered in a significant manner in the shooting window.
  • a server comprising a processor and a memory for storing processor-executable instructions, the processor implementing the instructions to:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using the preset damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • a fixed loss processing system comprising a client and a server, the processor of the client executing the method steps of any one of the client embodiments of the present specification when executing the processor executable instructions;
  • a method, a processing device, a client, and a server for processing a vehicle damage identification provided by 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 in the photograph or video shooting, without human intervention, can effectively reduce the survey Requirements for personnel skills.
  • information identifying suspected non-identical accidents can be automatically recorded and transmitted to a designated server system, such as to an insurance company, so that even if the surveyor or malicious user deletes photos or videos that are not the same accident, It is impossible to cover up the information that the damage has been identified as non-identical damage, which can effectively reduce the risk of fraud, improve the reliability of damage identification, and improve the reliability of the damage result.
  • a designated server system such as to an insurance company
  • FIG. 1 is a schematic diagram showing a rule relationship in which an artificially determined predetermined damage is the same accident in one embodiment of the present specification
  • FIG. 2 is a schematic flow chart of an embodiment of a data processing method for a vehicle loss according to the present specification
  • FIG. 3 is a schematic diagram of a deep neural network model for damage in the damage used in the method embodiment of the present specification
  • FIG. 4 is a schematic diagram of an application scenario in which a non-identical accident damage is identified by using a solid origin and a red background text;
  • Figure 5 is a schematic flow chart of another embodiment of the method provided by the present specification.
  • FIG. 6 is a block diagram showing the hardware structure of a client for interactive processing of vehicle damage using the method or apparatus embodiment of the present invention
  • FIG. 7 is a schematic block diagram showing an embodiment of a processing apparatus for vehicle damage recognition provided by the present specification.
  • the client may include a terminal device with a shooting function, such as a smart phone or a tablet computer, used by a vehicle loss site personnel (which may be an accident vehicle owner user or an insurance company personnel or other personnel performing a loss processing process). Smart wearable devices, dedicated loss terminals, etc.
  • the client may have a communication module, and may communicate with a remote server to implement data transmission with the server.
  • the server may include a server on the insurance company side or a server on the service side of the service provider.
  • Other implementation scenarios may also include servers of other service parties, such as a component supplier that has a communication link with the server of the fixed service provider. Terminal, terminal of vehicle repair shop, etc.
  • the server may include a single computer device, or may include a server cluster composed of a plurality of servers, or a server of a distributed system.
  • the client side can send the image data collected by the live shooting to the server in real time, and the server side performs the damage identification, and the recognition result can be fed back to the client.
  • the processing on the server side, the damage recognition and the like are performed by the server side, and the processing speed is usually higher than the client side, which can reduce the processing pressure of the client and improve the speed of damage recognition.
  • this specification does not exclude that all or part of the above processing in other embodiments is implemented by the client side, such as real-time detection and identification of damage on the client side.
  • the damage that can be caused by the vehicle in the same accident is regularly ruled. For example, in the case where the left front side has been paralyzed, it is impossible for the right rear side to simultaneously occur.
  • data accumulated in a large number of historical cases can be utilized, and the joint probability of damage of each component can be counted, thereby determining the simultaneous damage of the specified component through a machine learning model such as a Bayesian network. The probability of determining whether it is the same accident.
  • a preset rule for determining whether the damage is the same accident may be manually set, as shown in FIG. 1 , for example, “the left front fender and the right front fender cannot simultaneously be damaged”.
  • the machine learning model may be pre-trained, and the machine learning model may use the statistics of the historical case to collect the joint probability of the damage of each component, or combined with the manual preset to determine whether the damage is determined. Data information for normal 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 uses the pre-collected data letters of historical non-identical accident cases to train.
  • This training sample picture can manually mark multiple injuries of non-identical accidents in advance.
  • an identification model including a classifier for predicting whether the vehicle loss is a non-same accident damage can be obtained.
  • the machine learning model can be used in a framing window processed by the terminal to prompt the user in a significant manner, which not only can clearly indicate that the damage is not the same accident, but also can reduce the use of malicious users.
  • the initiative of the non-same accident damage claim (the malicious user has learned that the damage is determined by the system to be non-identical damage, and the utilization value is greatly reduced).
  • the machine learning model such as a Bayesian network
  • the machine learning model may be generated in an offline pre-built manner, and then used online after the training is completed. This specification does not exclude that the machine learning model can be built or updated/maintained online.
  • the client or server side can construct a machine learning model online, and the machine learning model can be built online. Use to identify whether the image recognized by the captured image is a non-identical accident.
  • FIG. 2 is a schematic flowchart diagram of an embodiment of a data processing method for a vehicle loss according to the present disclosure.
  • the present specification provides method operation steps or device structures as shown in the following embodiments or figures, there may be more or partial merged fewer operational steps in the method or device based on conventional or no inventive labor. Or module unit.
  • the execution order of the steps or the module structure of the device is not limited to the execution order or the module structure shown in the embodiment or the drawings.
  • the client on the user side may be a smart phone, and the smart phone may have a shooting function.
  • the user can open the mobile phone application that implements the implementation of the present specification at the scene of the vehicle accident to take a framing shot of the vehicle accident scene.
  • the shooting window can be displayed on the client display, and the vehicle can be photographed through the shooting window.
  • the shooting window may be a video shooting window, which may be used for framing (image capturing) of the vehicle damage scene by the terminal, and image information acquired by the client-integrated camera device may be displayed in the shooting window.
  • the specific interface structure of the shooting window and the related information displayed can be customized.
  • a captured image of the vehicle can be acquired during vehicle shooting, and it can be identified whether there is damage in the image.
  • the process of damage identification may be performed by the client side or by the server side, and the server at this time may be referred to as a damage identification server.
  • the images collected by the client can be directly identified in the client for damage detection, or other fixed loss data processing, which can reduce network transmission overhead.
  • the process of damage identification can be processed by the server side.
  • the identifying that the damage exists in the captured image may include:
  • S22 Receive a damage recognition result returned by the server, where the damage recognition result comprises the damage identification server identifying whether the captured image has damage by using a pre-built damage recognition model.
  • the client or server side may use a deep neural network constructed in advance or in real time to identify damage in the image, such as damage location, damaged component, damage type, and the like.
  • the deep neural network can be used for target detection and semantic segmentation. For the input picture, the position of the target in the picture is found, and the damage position relationship is confirmed.
  • Fig. 3 is a schematic diagram of a deep neural network model for the presence or absence of damage in the method used in the method embodiment of the specification. Figure 3 depicts a typical deep neural network, Faster R-CNN.
  • a deep neural network can be trained by pre-labeling a large number of pictures of the damaged area, and the damage is given to the pictures of various directions and illumination conditions of the vehicle. The extent of the area.
  • a network structure customized for a mobile device may be used, such as based on a typical MobileNet, SqueezeNet or its improved network structure, so that identifying whether the stored model can be used in a mobile device with lower power consumption, Running in a less memory, slower processor environment, such as the client's mobile terminal operating environment.
  • the information indicating that the damage is not the same accident damage may be displayed in the shooting window of the client.
  • the damage identified here is that the non-same accident damage is obtained based on the data processing of the captured image.
  • 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 accidents. Therefore, the non-same accident damage identified herein in the embodiment of the present specification may be displayed as a suspected non-same accident damage when displayed on the client.
  • the prompt information indicating that the damage is not the same accident damage can be displayed in the display mode after being rendered in the display mode.
  • the salient mode rendering mainly refers to the use of some features of the rendering mode to mark the damage area, so that the damage area is easy to identify, or more prominent.
  • the specific rendering manner is not limited, and specific constraints or conditions for achieving rendering in a significant manner may be set.
  • the salient mode rendering may include:
  • S40 Identify the prompt information by using a preset characterization symbol, where the preset characterization symbol includes one of the following:
  • the preset characterization symbols may also include other forms, such as a guide line, a rule graphic frame, an irregular graphic frame, a customized graphic, etc., and other embodiments may also use text, Characters, data, etc. identify the damaged area and direct the user to take pictures of the damaged area.
  • One or more preset characterization symbols can be used for rendering. In this embodiment, the preset characterization symbol is used to identify the damaged area, and the location area where the damage is located can be more clearly displayed in the shooting window, thereby assisting the user in quickly positioning and guiding shooting.
  • the dynamic rendering effect may also be used to identify the prompt information, and the user is prompted to detect the damage as a non-same accident in a more obvious manner.
  • the salient mode rendering includes:
  • S400 Perform at least one animation display of color conversion, size conversion, rotation, and jitter on the preset characterization symbol.
  • the AR overlay may be displayed to superimpose the boundaries of the lesion.
  • the augmented reality AR generally refers to a technical implementation scheme for calculating the position and angle of the camera image in real time and adding corresponding images, videos, and 3D models, which can put the virtual world on the screen in the real world and Engage.
  • the AR model can be matched with the real vehicle position during the shooting duration, such as superimposing the constructed 3D contour to the contour position of the real vehicle, and the matching can be considered when the two match or the matching degree reaches the threshold.
  • the user can guide the framing direction, and the user aligns the constructed contour with the contour of the captured real vehicle by guiding the moving shooting direction or angle.
  • the embodiment of the present specification in combination with the augmented reality technology, not only displays the real information of the vehicle photographed by the actual client of the user, but also displays the augmented reality space model information of the vehicle that is constructed at the same time, and the two kinds of information complement each other and superimpose, and can provide more Good damage service experience.
  • the prompt information displayed by the text may further include an image, a voice, an animation, a vibration, and the like, and the current captured image is aligned to an area by an arrow or a voice prompt. Therefore, in another embodiment of the method, the form of the prompt information displayed in the current shooting window includes at least one of a symbol, a text, a voice, an animation, a video, and a vibration.
  • the client application can automatically return the recognition result identified as non-same accident damage to the background of the system for storage for subsequent manual or automatic loss processing. It can also avoid or reduce the risk of users using the same accident damage to swindle. Therefore, in another embodiment of the method provided by the present specification, after determining that the damage is a non-identical damage, the method further includes:
  • S6 Send data information including identifying the damage as a non-same accident damage to a predetermined server.
  • FIG. 5 is a schematic flow diagram of another embodiment of the method provided by the present specification.
  • the predetermined server may include a server on the insurance company side, or may be replaced on the client side, and then transmitted to the insurance company back-end system in an asynchronous transmission manner, if the network conditions permit, the result may be used for The case was further reviewed. Even if the on-site survey personnel deleted the photos of the place and took photos elsewhere, they also saw the recognition result in the back-end system, which further improved the difficulty of fraud.
  • the real-time described in the foregoing embodiments may include sending, receiving, or displaying immediately after acquiring or determining certain data information, and those skilled in the art may understand that after buffering or expected calculation, waiting time Sending, receiving, or presenting can still belong to the real-time defined range.
  • the image described in the embodiments of the present specification may include a video, and the video may be regarded as a continuous image collection.
  • the identification result determined as the non-same accident damage in the solution of the embodiment of the present specification can be sent to the predetermined server for storage, and the insurance fraud can be effectively prevented from being tampered with. Therefore, the embodiment of the present specification can also improve the data security of the loss processing and the reliability of the loss determination result.
  • the backend system can further utilize the more powerful processing capability of the server when receiving the photos or videos uploaded by the APP, and use a deeper neural network with higher precision (here) It can be referred to as a second deep neural network for analysis.
  • the foregoing client or server uses the judgment result of the first deep neural network as an input feature, and is legally acquired by the insurance company or legally obtained by the third party (such as the owner's credit record, the vehicle history risk record, the owner and the survey) The relationship between the staff, the repair shop's relationship network, geographical location information, etc., and then through machine learning, to make a more comprehensive and accurate judgment on whether or not the same accident damage.
  • the server may use other machine learning algorithms to further determine whether the same accident is the same. Therefore, in another embodiment of the method provided by the present specification, after determining that the damage is a non-identical damage, the method may further include:
  • S80 Send a judgment result that determines that the damage is a non-same accident damage to the server;
  • the receiving server uses a preset algorithm to determine whether the damage is a non-same accident damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner and a credit record of the owner. At least one of the network data of the relationship between the owner and the associated party.
  • the preset algorithm may include a deep neural network, and may also include other machine learning algorithms, such as a Bayesian network, or may be a custom set algorithm.
  • the above embodiment describes an embodiment of a data processing method in which a user performs a vehicle loss on a mobile phone client. It should be noted that the foregoing methods in the embodiments of the present specification may be implemented in various processing devices, such as dedicated loss-making terminals, and implementation scenarios including a client and server architecture.
  • the present specification further provides a processing method for vehicle damage identification that can be used on the server side, and specifically includes:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using the preset damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • FIG. 6 is a hardware structural block diagram of a client that applies the interactive processing of the vehicle loss in the embodiment of the method or apparatus of the present invention.
  • client 10 may include one or more (only one shown) processor 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA).
  • 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
  • a transmission module 106 for communication functions. It will be understood by those skilled in the art that the structure shown in FIG.
  • the client 10 may also include more or less components than those shown in FIG. 6, for example, may also include other processing hardware, such as a GPU (Graphics Processing Unit), or have the same as shown in FIG. Different configurations.
  • a GPU Graphics Processing Unit
  • the memory 104 can 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, and the processor 102 executes various functions by running software programs and modules stored in the memory 104.
  • Application and data processing that is, a processing method for realizing the content display of the above navigation interaction interface.
  • Memory 104 may include high speed random access 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.
  • memory 104 may further include memory remotely located relative to processor 102, which may be connected to client 10 over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission module 106 is configured to receive or transmit data via a network.
  • the network specific examples described above may include a wireless network provided by a communication provider of the computer terminal 10.
  • the transport module 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet.
  • the transmission module 106 can be a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the present specification also provides a processing device for vehicle damage recognition.
  • the apparatus may include a system (including a distributed system), software (applications), modules, components, servers, clients, etc., using the methods described in the embodiments of the present specification, in conjunction with necessary device hardware for implementing the hardware.
  • the processing device in one embodiment provided by this specification is as described in the following embodiments.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • FIG. 7 is a schematic structural diagram of a module of a device for processing a vehicle damage identification provided by the present specification.
  • the specific structure may include:
  • the shooting module 201 can be used to acquire a captured image of the vehicle
  • the damage determining module 202 may be configured to determine, by using a pre-trained machine learning module, whether the damage is a non-same accident damage if the damage is detected in the captured image;
  • the display module 203 is configured to: when the damage is a non-same accident, display the prompt information that the damage is a suspected non-same accident in the shooting window, where the prompt information is in the shooting window Significantly rendered.
  • a processing apparatus that can be used for vehicle damage identification on the server side. Specific can include:
  • the result receiving module 301 can be configured to receive a determination 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 by using a preset algorithm, and the preset algorithm determines whether the data used for the non-same accident damage includes at least a vehicle owner. At least one of a historical risk record, a credit record of the owner, and a network data of the relationship between the owner and the associated party;
  • the result feedback module 303 can be configured to return a recognition result to the client.
  • the foregoing apparatus may further include other implementation manners, such as a rendering processing module that performs rendering, an AR display module that performs AR processing, and the like, according to the description of the related method embodiments.
  • a rendering processing module that performs rendering
  • an AR display module that performs AR processing
  • the device model identification method provided by the embodiment of the present specification may be implemented by a processor executing a corresponding program instruction in a computer, such as using a C++/java language of a Windows/Linux operating system on a PC/server side, or other such as android,
  • the iOS system corresponds to the necessary hardware implementation of the application design language set, or the processing logic based on quantum computers.
  • the data processing device of the vehicle fixed loss provided by the present specification may include a processor and a memory for storing processor executable instructions, where the processor executes When the instruction is implemented:
  • the prompt information indicating that the damage is suspected to be the same accident is displayed in the shooting window, and the prompt information is rendered in a significant manner in the shooting window.
  • the processor further performs:
  • the receiving server uses the preset algorithm to determine whether the damage is a non-identical accident damage, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner. At least one of the network data of the relationship with the loss-related party.
  • the salient mode rendering includes:
  • the prompt information is identified by using a preset characterization symbol, and the preset characterization symbol includes one of the following:
  • the salient mode rendering includes:
  • the processor further performs:
  • Data information including identifying the damage as a non-same accident damage is transmitted to a predetermined server.
  • the form of the prompt information includes at least one of a symbol, a text, a voice, an animation, a video, and a vibration.
  • the processing device may include a processor and a memory for storing processor-executable instructions, when the processor executes the instructions:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using a preset algorithm, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • processing device described above in the above embodiments may further include other scalable embodiments according to the description of the related method embodiments.
  • the above instructions may be stored in a variety of computer readable storage media.
  • the computer readable storage medium may include physical means for storing information, which may be digitized and stored in a medium utilizing electrical, magnetic or optical means.
  • the computer readable storage medium of this embodiment may include: means for storing information by means of electrical energy, such as various types of memories, such as RAM, ROM, etc.; means for storing information by magnetic energy means, such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk; means for optically storing information such as CD or DVD.
  • electrical energy such as various types of memories, such as RAM, ROM, etc.
  • magnetic energy means such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk
  • means for optically storing information such as CD or DVD.
  • quantum memories, graphene memories, and the like are as described above.
  • the above method or apparatus embodiment can be used for a client on the user side, such as a smart phone. Accordingly, the present specification provides a client comprising a processor and a memory for storing processor-executable instructions that, when executed by the processor, are implemented:
  • the prompt information indicating that the damage is suspected to be the same accident is displayed in the shooting window, and the prompt information is rendered in a significant manner in the shooting window.
  • the present specification provides a server comprising a processor and a memory for storing processor-executable instructions, the processor implementing the instructions to:
  • Receiving the damage sent by the client is the judgment result of the non-same accident damage
  • Whether the damage is a non-same accident damage is a recognition result by using a preset algorithm, and the data used in the preset algorithm to determine whether the non-same accident damage is used includes at least a history record of the owner, a credit record of the owner, and a vehicle owner and a predetermined At least one of the relationship network data of the associated party;
  • the recognition result is returned to the client.
  • the embodiment of the present specification further provides a fixed loss processing system, where the system includes a client and a server, and the processor of the client executes the storage processor executable instructions to implement the implementation in the present specification.
  • the processor of the server when executing a processor-executable instruction, implements the method steps of any one of the embodiments of the present invention that can be implemented on the server side.
  • embodiments of the present specification refer to AR technology, CNN network training, client or server execution damage recognition processing, client and server message interaction, and the like, data acquisition, location alignment, interaction, calculation, judgment, and the like operations and data. Description, however, embodiments of the present specification are not limited to situations that must be consistent with industry communication standards, standard image data processing protocols, communication protocols, and standard data models/templates or embodiments of the specification. Certain industry standards or implementations that have been modified in a manner that uses a custom approach or an embodiment described above may also achieve the same, equivalent, or similar, or post-deformation implementation effects of the above-described embodiments. Embodiments obtained by applying such modified or modified data acquisition, storage, judgment, processing, etc., may still fall within the scope of alternative embodiments of the present specification.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
  • computer readable program code eg, software or firmware
  • examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
  • a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a car-mounted human-machine interaction 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, a tablet.
  • the above devices are described as being separately divided into various modules by function.
  • the functions of the modules may be implemented in the same software or software, or the modules that implement the same function may be implemented by multiple sub-modules or a combination of sub-units.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical, mechanical or otherwise.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media including both permanent and non-persistent, removable and non-removable media, can be stored by any method or technology.
  • the 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 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 tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present specification can be provided as a method, system, or computer program product.
  • embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or a combination of software and hardware.
  • embodiments of the present specification can take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • Embodiments of the present description can be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • Embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Un mode de réalisation de la présente invention concerne un procédé de traitement d'identification de dommage à un véhicule, un dispositif de traitement, un client et un serveur. Le procédé fournit une solution pour identifier automatiquement si un dommage à un véhicule se produit à partir d'un seul incident de trafic, identifier en temps réel pendant la photographie ou l'enregistrement vidéo si un dommage résulte de plus d'un seul incident de trafic sans qu'une intervention humaine soit nécessaire, ce qui permet d'abaisser efficacement les exigences de compétence technique pour le personnel chargé de l'enquête. En même temps, des informations identifiant la suspicion que des dommages ne résultent pas d'un seul incident peuvent être automatiquement enregistrées et envoyées à un système serveur désigné, par exemple à une compagnie d'assurance. De cette manière, même si un enquêteur ou un utilisateur frauduleux supprime des photographies ou un film des dommages résultant de multiples incidents de trafic, il n'existe aucun moyen de couvrir des informations identifiant des dommages déterminés comme résultant de multiples incidents de trafic, réduisant ainsi le risque de fraude et améliorant la fiabilité d'identification des dommages ainsi que la fiabilité d'évaluation du préjudice.
PCT/CN2019/076032 2018-05-08 2019-02-25 Procédé de traitement d'identification de dommage à véhicule, dispositif de traitement, client et serveur WO2019214321A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810434385.0A CN108682010A (zh) 2018-05-08 2018-05-08 车辆损伤识别的处理方法、处理设备、客户端及服务器
CN201810434385.0 2018-05-08

Publications (1)

Publication Number Publication Date
WO2019214321A1 true WO2019214321A1 (fr) 2019-11-14

Family

ID=63805173

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/076032 WO2019214321A1 (fr) 2018-05-08 2019-02-25 Procédé de traitement d'identification de dommage à véhicule, dispositif de traitement, client et serveur

Country Status (3)

Country Link
CN (1) CN108682010A (fr)
TW (1) TWI715932B (fr)
WO (1) WO2019214321A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230026515A1 (en) * 2016-10-14 2023-01-26 Allstate Insurance Company Bilateral communication in a login-free environment

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108682010A (zh) * 2018-05-08 2018-10-19 阿里巴巴集团控股有限公司 车辆损伤识别的处理方法、处理设备、客户端及服务器
CN109447171A (zh) * 2018-11-05 2019-03-08 电子科技大学 一种基于深度学习的车辆姿态分类方法
CN110263843A (zh) * 2019-06-18 2019-09-20 苏州梧桐汇智软件科技有限责任公司 基于深度神经网络的股票k线识别方法
CN111461901B (zh) * 2020-03-31 2023-05-12 德联易控科技(北京)有限公司 车辆保险理赔信息的输出方法和装置
CN117876232B (zh) * 2024-03-11 2024-05-28 国任财产保险股份有限公司 一种基于大模型的智能交通事故保险处理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104715417A (zh) * 2013-12-12 2015-06-17 耿明生 一种远程处理车辆保险业务的系统及其方法
CN105405054A (zh) * 2015-12-11 2016-03-16 平安科技（深圳）有限公司 基于理赔照片深度学习实现保险理赔反欺诈的方法及服务器
US9886771B1 (en) * 2016-05-20 2018-02-06 Ccc Information Services Inc. Heat map of vehicle damage
CN108647712A (zh) * 2018-05-08 2018-10-12 阿里巴巴集团控股有限公司 车辆损伤识别的处理方法、处理设备、客户端及服务器
CN108682010A (zh) * 2018-05-08 2018-10-19 阿里巴巴集团控股有限公司 车辆损伤识别的处理方法、处理设备、客户端及服务器

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9818239B2 (en) * 2015-08-20 2017-11-14 Zendrive, Inc. Method for smartphone-based accident detection
CN107194323B (zh) * 2017-04-28 2020-07-03 阿里巴巴集团控股有限公司 车辆定损图像获取方法、装置、服务器和终端设备
CN107368776B (zh) * 2017-04-28 2020-07-03 阿里巴巴集团控股有限公司 车辆定损图像获取方法、装置、服务器和终端设备
CN107657047A (zh) * 2017-10-10 2018-02-02 民太安财产保险公估股份有限公司 保险欺诈侦测方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104715417A (zh) * 2013-12-12 2015-06-17 耿明生 一种远程处理车辆保险业务的系统及其方法
CN105405054A (zh) * 2015-12-11 2016-03-16 平安科技（深圳）有限公司 基于理赔照片深度学习实现保险理赔反欺诈的方法及服务器
US9886771B1 (en) * 2016-05-20 2018-02-06 Ccc Information Services Inc. Heat map of vehicle damage
CN108647712A (zh) * 2018-05-08 2018-10-12 阿里巴巴集团控股有限公司 车辆损伤识别的处理方法、处理设备、客户端及服务器
CN108682010A (zh) * 2018-05-08 2018-10-19 阿里巴巴集团控股有限公司 车辆损伤识别的处理方法、处理设备、客户端及服务器

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHENG HONGYAN: "Personal Injury Insurance Fraud Prevention Study", SOCIAL SCIENCE 1, CHINESE MASTER'S THESES, vol. 3, 15 March 2018 (2018-03-15), ISSN: 1674-0246 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230026515A1 (en) * 2016-10-14 2023-01-26 Allstate Insurance Company Bilateral communication in a login-free environment

Also Published As

Publication number Publication date
CN108682010A (zh) 2018-10-19
TW201947455A (zh) 2019-12-16
TWI715932B (zh) 2021-01-11

Similar Documents

Publication Publication Date Title
WO2019214320A1 (fr) Procédé de traitement d'identification de dommage de véhicule, dispositif de traitement, client et serveur
WO2019214319A1 (fr) Procédé de traitement de données d'évaluation de perte de véhicule, appareil, dispositif de traitement et client
WO2019214313A1 (fr) Procédé de traitement interactif, appareil et dispositif de traitement pour évaluer une perte de véhicule et terminal client
WO2019214321A1 (fr) Procédé de traitement d'identification de dommage à véhicule, dispositif de traitement, client et serveur
US20210158533A1 (en) Image processing method and apparatus, and storage medium
CN109145680B (zh) 一种获取障碍物信息的方法、装置、设备和计算机存储介质
WO2019024771A1 (fr) Procédé, appareil, serveur et système de traitement d'image d'assurance automobile
WO2019223391A1 (fr) Procédé et appareil d'interaction de photographie de facture, dispositif de traitement et client
WO2020134238A1 (fr) Procédé et appareil de détection de corps vivant et support d'informations
US11443438B2 (en) Network module and distribution method and apparatus, electronic device, and storage medium
CN110349161B (zh) 图像分割方法、装置、电子设备、及存储介质
CN110660102B (zh) 基于人工智能的说话人识别方法及装置、系统
CN113299073B (zh) 识别车辆违章停车的方法、装置、设备和存储介质
CN108229375B (zh) 用于检测人脸图像的方法和装置
CN110942456B (zh) 篡改图像检测方法、装置、设备及存储介质
CN114267041B (zh) 场景中对象的识别方法及装置
Balchandani et al. A deep learning framework for smart street cleaning
CN110827341A (zh) 一种图片深度估计方法、装置和存储介质
CN114663871A (zh) 图像识别方法、训练方法、装置、系统及存储介质
CN111242034A (zh) 一种单据的图像处理方法、装置、处理设备及客户端
CN117315406B (zh) 一种样本图像处理方法、装置及设备
CN111160312A (zh) 目标识别方法、装置和电子设备
CN113688839A (zh) 视频处理方法及装置、电子设备、计算机可读存储介质
CN110349108B (zh) 处理图像的方法、装置、电子设备、及存储介质
CN111753766A (zh) 一种图像处理方法、装置、设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19799884

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19799884

Country of ref document: EP

Kind code of ref document: A1