WO2020024407A1

WO2020024407A1 - Electronic device, method for intelligently processing car insurance claim, and storage medium

Info

Publication number: WO2020024407A1
Application number: PCT/CN2018/107711
Authority: WO
Inventors: 张发友; 陈宗阳
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-08-03
Filing date: 2018-09-26
Publication date: 2020-02-06
Also published as: CN109035041A

Abstract

An electronic device, a method for intelligently processing a car insurance claim, and a storage medium. The method comprises: upon receiving a claim request submitted by a terminal user for a car accident, acquiring, from the request, image information containing basic information of the car and image information of damaged parts of the car (S301); using an OCR recognition method to recognize basic information of the car from the image information containing the basic information of the car (S302); generating a corresponding policy on the basis of the recognized basic information of the car, calling, on the basis of the generated policy, a pre-trained claim amount analysis model to analyze the image information of the damaged parts of the car so as to determine an claim amount corresponding to the policy, and transmitting the claim amount to the terminal user, such that the terminal user can apply a claim on the basis of the claim amount (S303). The invention can increase the speed and accuracy of claim settlement and loss assessment, thereby improving client experience.

Description

Electronic device, automobile insurance intelligent claim method and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on August 3, 2018 with the application number 201810876532.X and the invention name "Electronic Device, Auto Insurance Intelligent Claims Method and Storage Medium", the entire contents of which are incorporated by reference Incorporated in this application.

Technical field

The present application relates to the field of auto insurance claims, and in particular, to an electronic device, an auto insurance smart claims method, and a storage medium.

Background technique

In the field of auto insurance, making fixed claims for the vehicles in danger is an important part of the field of auto insurance. At present, after receiving an insurance case, an insurance company needs a professional to manually enter the basic information of the vehicle out of the vehicle, such as the vehicle number, to generate an insurance policy, and then through the claims reviewer or the system to determine the damage and claims for the insurance vehicle corresponding to the policy, It requires the participation of a large number of professionals, causing insurance companies to pay a large amount of manpower and operating costs in the auto insurance claims link, inefficient loss compensation claims, and making customers unable to understand the loss and claims situation in a timely manner, and experience poor results.

Summary of the invention

In view of this, in order to solve the above technical problems, this application first proposes an electronic device, the electronic device includes a memory, and a processor connected to the memory, the processor is configured to execute automobile insurance intelligence stored in the memory Claims procedure, when the car insurance intelligent claims procedure is executed by the processor, the following steps are implemented:

A1. After receiving an insurance vehicle claim request sent by an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

A2. According to the OCR identification method, the basic vehicle information is identified from the obtained image information containing the basic information of the vehicle in danger;

A3. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the acquired image information of the damaged parts of the vehicle in danger to determine the claim amount corresponding to the policy ;

A4. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.

In addition, in order to solve the above technical problems, this application also proposes a method for intelligent auto insurance claims, which is characterized in that the method includes the following steps:

S1. After receiving an insurance vehicle claim request from an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

S2. According to the OCR identification method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger;

S3. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the image information of the damaged component of the out of vehicle vehicle to determine the claim amount corresponding to the policy ;

S4. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.

In addition, in order to solve the above technical problems, the present application also proposes a computer-readable storage medium that stores a car insurance intelligent claims program, and the car insurance intelligent claims program can be executed by at least one processor so that The at least one processor performs the following steps:

After receiving a claim for a vehicle out of danger sent by an end user, obtaining image information containing basic information of the vehicle in danger and image information of damaged parts of the vehicle from the request;

According to the OCR recognition method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger;

Generating a corresponding insurance policy based on the identified basic vehicle information, invoking a pre-trained claim amount analysis model based on the generated policy, and analyzing the image information of the damaged component of the out of vehicle vehicle to determine the claim amount corresponding to the policy;

Sending the claim amount to the end user for the end user to initiate a car insurance claim request to an insurance claimant based on the claim amount.

The electronic device, smart insurance claim, and storage medium proposed in this application first obtain the image information containing the basic information of the out of the vehicle and the damaged parts of the out of the vehicle from the request after receiving the request for the out of vehicle from the end user. Image information; and then according to the OCR recognition method, identify the basic vehicle information from the acquired image information containing the basic information of the vehicle in danger;

Secondly, a corresponding insurance policy is generated based on the identified basic vehicle information, and a pre-trained claim amount analysis model is invoked based on the generated policy to analyze the image information of the damaged component of the out of vehicle vehicle to determine the corresponding claim amount of the policy; Finally, the claim amount is sent to the end user, so that the end user can initiate a car insurance claim request to an insurance claimant based on the claim amount. It can reduce manual participation in the process of auto insurance claims, improve the speed and accuracy of claim settlement, enable customers to understand the claim situation in time, and improve the experience.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of an optional hardware architecture of an electronic device proposed by the present application; FIG.

FIG. 2 is a schematic diagram of a program module of a car insurance intelligent claim procedure in an embodiment of the electronic device of the present application; FIG.

FIG. 3 is an implementation flowchart of a preferred embodiment of the automobile insurance intelligent claims method of the present application.

The implementation, functional features and advantages of the purpose of this application will be further described with reference to the embodiments and the drawings.

detailed description

In order to make the purpose, technical solution, and advantages of the present application clearer, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

It should be noted that the descriptions related to "first" and "second" in this application are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but must be based on those that can be realized by a person of ordinary skill in the art. When the combination of technical solutions conflicts or cannot be achieved, it should be considered that such a combination of technical solutions does not exist. Is not within the scope of protection claimed in this application.

Refer to FIG. 1, which is a schematic diagram of an optional hardware architecture of an electronic device according to the present application. In this embodiment, the electronic device 10 may include, but is not limited to, a memory 11, a processor 12, and a network interface 13 which may communicate with each other through a communication bus 14. It should be noted that FIG. 1 only shows the electronic device 10 having components 11-14, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.

The memory 11 includes at least one type of computer-readable storage medium. The computer-readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), and a static memory. Random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 10, such as a hard disk or a memory of the electronic device 10. In other embodiments, the memory 11 may also be an outsourced storage device of the electronic device 10, such as a plug-in hard disk, a smart memory card (SMC), and a secure digital (SD) device. ) Cards, flash cards, etc. Of course, the memory 11 may also include both the internal storage unit of the electronic device 10 and its outsourced storage device. In this embodiment, the memory 11 is generally used to store an operating system and various application software installed on the electronic device 10, such as a car insurance intelligent claims program. In addition, the memory 11 can also be used to temporarily store various types of data that have been output or will be output.

The processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 12 is generally used to control the overall operation of the electronic device 10. In this embodiment, the processor 12 is configured to run program code or process data stored in the memory 11, such as a running automobile insurance intelligent claims program.

The network interface 13 may include a wireless network interface or a wired network interface. The network interface 13 is generally used to establish a communication connection between the electronic device 10 and other electronic devices.

The communication bus 14 is used to implement a communication connection between the components 11-13.

FIG. 1 only shows the electronic device 10 having the components 11-14 and the automobile insurance intelligent claims program, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.

Optionally, the electronic device 10 may further include a user interface (not shown in FIG. 1). The user interface may include a display, an input unit such as a keyboard, and the user interface may further include a standard wired interface, a wireless interface, and the like.

Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-type liquid crystal display, an OLED touch device, or the like. Further, the display may also be referred to as a display screen or a display unit for displaying a user interface for processing information in the electronic device 10 and for displaying a visualization.

Optionally, in some embodiments, the electronic device 10 may further include an audio unit (the audio unit is not shown in FIG. 1), and the audio unit may be in the electronic device 10 in a call signal receiving mode, a call mode, a recording mode, and voice recognition. In the mode, the broadcast receiving mode, and the like, the received or stored audio data is converted into an audio signal. Further, the electronic device 10 may further include an audio output unit, and the audio output unit outputs the audio signal converted by the audio unit, and The audio output unit may also provide audio output (such as call signal reception sound, message reception sound, etc.) related to a specific function performed by the electronic device 10, and the audio output unit may include a speaker, a buzzer, and the like.

Optionally, in some embodiments, the electronic device 10 may further include an alarm unit (not shown in the figure), and the alarm unit may provide an output to notify the electronic device 10 of the occurrence of the event. Typical events may include call reception, message reception, key signal input, touch input, and so on. In addition to audio or video output, the alarm unit can provide output in different ways to notify the occurrence of an event. For example, the alarm unit may provide an output in the form of a vibration, and upon receiving a call, a message, or some other that may cause the electronic device 10 to enter the communication mode, the alarm unit may provide a tactile output (ie, vibration) to notify the user.

In an embodiment, when the automobile insurance intelligent claim program stored in the memory 11 is executed by the processor 12, the following operations are implemented:

A. After receiving an insurance vehicle claim request sent by an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

Specifically, in this embodiment, the end user may install and run a vehicle damage application (auto insurance app) on the terminal device, take basic information of the accident vehicle at the scene of the accident, and take photos of the damaged components of the accident vehicle, and Generate image information. Optionally, a shooting guide interface can be provided in the vehicle damage application. The interface is an application based on a mobile device camera. That is, after the mobile device enters the shooting guide interface, the camera is turned on, and an interface is displayed on the interface. The user is prompted to take a first selection box of basic information of the dangerous vehicle. After the user clicks the first selection box, a first floating frame of a first preset size is generated. When the user takes an image of the basic information of the dangerous vehicle, the user needs to take The basic information of the vehicle is completely contained in the first floating frame, and shooting is performed based on the first floating frame to obtain a photo that meets the requirements, that is, the image information of the basic information of the vehicle is obtained. Further, after the user has taken the basic information of the vehicle, , The interface displays a second selection box prompting the user to take pictures of the damaged parts of the dangerous vehicle. After clicking the second selection box, a second floating frame of a second preset size is generated. When the user takes an image of the damaged part of the dangerous vehicle, the damaged part needs to be completely contained in the second floating frame. The second floating frame is photographed to take a photo that meets the requirements, that is, to obtain image information of the damaged part of the vehicle, and generate a claim for claiming an insurance vehicle based on the captured basic information of the vehicle and the image information of the damaged part of the vehicle. The above method can avoid the situation that the photographed vehicle information or damaged parts are incomplete and cannot be recognized normally.

Preferably, the end-user can also complete the reporting of claims for insurance vehicles by accessing an auto insurance claim applet in an existing application such as WeChat. Specifically, the auto insurance claim application can be accessed through the application A shooting guide interface is provided in the program, and the basic information of the vehicle and the photos of the damaged parts of the accident vehicle can also be directly guided through the seat.

Optionally, in some embodiments, according to the needs of specific accident cases, it is also possible to guide the emergency users on the shooting guide interface or directly through the agent, to take the ID of the driver of the dangerous vehicle, and to identify the user such as bank card. information.

It can be understood that the claim request for an out-of-vehicle vehicle includes image information of the out-of-vehicle basic information and image information of damaged parts of the out-of-vehicle vehicle. The out-of-vehicle basic information includes the vehicle type, license plate number, and vehicle identification code (VIN code).

B. According to the OCR (optical character) recognition method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger;

Specifically, the OCR (Optical Character Recognition) technology refers to an electronic device (such as a scanner or a digital camera) that checks characters printed on paper, determines the shape by detecting dark and light patterns, and then uses character recognition Methods The process of translating shapes into computer text; that is, the process of scanning text data and then analyzing and processing image files to obtain text and layout information. In this embodiment, according to the OCR recognition method, the process of identifying the basic vehicle information from the acquired image information containing the basic information of the dangerous vehicle includes: locating character string information in the image information including the basic information of the dangerous vehicle. Obtaining the positioned character string information and performing character segmentation to split the character string into multiple single characters; identifying each single character separately to identify basic vehicle information.

C. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the image information of the damaged parts of the out of vehicle vehicle to determine the claim amount corresponding to the policy ;

Specifically, the pre-trained claim amount analysis model is a neural network model. The claim amount analysis model includes a training process and a test process of the model. The training process of the model includes:

E1. Obtain a preset number of sampled claims for car insurance compensation case information that matches the basic information of the vehicle, and extract from the information samples the image information collection of the damaged parts of the vehicle for each of the insurance claims cases;

F1. Divide the image information set of the vehicle damaged parts corresponding to the information samples of each car insurance claim case into a first proportion of the training subset and a second proportion of the testing subset;

G1: training the claim amount analysis model by using image information of vehicle damaged parts of each car insurance payment case in the training subset to obtain a trained claim amount analysis model;

H1. Use the image information of the damaged parts of the vehicle in each of the auto insurance claims cases to test the claim amount analysis model. If the test passes, the training ends, or if the test fails, increase the The number of samples of car insurance compensation cases that have been manually reviewed and the steps E1, F1, G1, and H1 described above are performed again.

Test process of the model:

The trained claim analysis model is used to analyze the image information of the damaged parts of the vehicles in each of the car insurance claims in the test subset, so as to obtain the first claim amount of each car insurance claim that passed the manual review and the claim settlement. The probability value that the second claim amount automatically reviewed by the amount analysis model is equal;

If there is a probability value that the first claim amount and the second claim amount corresponding to a car insurance claim case are greater than the preset probability threshold, a model accuracy test is performed for the car insurance claim case, and the car insurance claim case is performed Carry out manual review to obtain the first claim amount corresponding to the auto insurance claim case, and call the claim amount analysis model to automatically analyze the auto insurance claim case to obtain the second claim amount corresponding to the auto insurance claim case;

The calculated error value between the first claim amount and the second claim amount corresponding to the auto insurance claim case;

If the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the car insurance compensation case is correct, or if the calculated error value is greater than or equal to the preset error threshold, then Determine that the result of the model accuracy test for the auto insurance claim case is incorrect;

If the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, determine that the test of the claim amount analysis model passes, or if the correct model accuracy test results account for all If the percentage of the model accuracy test result is less than or equal to a preset percentage threshold, it is determined that the test of the claim amount analysis model fails.

D. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.

Specifically, the end user may initiate a claim request to an insurance claimant, such as an insurance company or an insurance service platform provided by the insurance company, based on the received claim amount.

Further, when the automobile insurance intelligent claim program is executed by the processor, the following steps are also implemented:

When receiving confirmation information from the end user who has an objection to the claim amount, obtain basic vehicle information from the confirmed information; send the basic information of the vehicle and the image information of the damaged part of the vehicle to the advance The determined claim review platform; receiving the final claim amount obtained after the claim review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.

It can be known from the foregoing embodiments that the electronic device proposed in the present application first receives an insurance vehicle claim request sent by an end user, and obtains, from the request, image information including basic information of the insurance vehicle and the damaged components of the insurance vehicle. Image information; then according to the OCR identification method, the basic information of the vehicle is identified from the acquired image information containing the basic information of the vehicle in danger; secondly, the corresponding policy is generated based on the identified basic information of the vehicle, and the pre-trained The claim amount analysis model analyzes the acquired image information of the damaged parts of the vehicle in danger to determine the claim amount corresponding to the insurance policy; and finally sends the claim amount to the end user for the end user to use based on the The claim amount initiates an auto insurance claim request to the insurance claims terminal. It can reduce manual participation in the process of auto insurance claims, improve the speed and accuracy of claim settlement, enable customers to understand the claim situation in time, and improve the experience.

In addition, according to the different functions implemented by the various parts of the automobile insurance intelligent claims procedure of the present application, program modules with the same functions can be used for description. Please refer to FIG. 2, which is a schematic diagram of a program module of a car insurance intelligent claim procedure in an embodiment of the electronic device of the present application. In this embodiment, the automobile insurance intelligent claims program can be divided into an acquisition module 201, an identification module 202, an analysis module 203, and a sending module 204 according to different functions implemented by its various parts. It can be known from the above description that the program module referred to in the present application refers to a series of computer program instruction segments capable of performing specific functions, and is more suitable for describing the execution process of the automobile insurance intelligent claims program in the electronic device 10 than the program. The functions or operation steps implemented by the modules 201-204 are similar to the above, which will not be described in detail here. By way of example, for example:

The obtaining module 201 is configured to obtain, from the request, the image information including the basic information of the vehicle in danger and the image information of the damaged component of the vehicle after receiving the request for claiming the vehicle from the terminal;

The identification module 202 is configured to identify the basic vehicle information from the acquired image information containing the basic information of the vehicle in danger according to the OCR identification method;

The analysis module 203 is configured to generate a corresponding insurance policy based on the identified basic vehicle information, invoke a pre-trained claim amount analysis model based on the generated policy, and analyze the acquired image information of the damaged component of the out of vehicle vehicle to determine the corresponding policy The amount of claims

The sending module 204 is configured to send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.

In addition, this application also proposes a car insurance intelligent claims method, as shown in FIG. 3. The car insurance intelligent claims method includes the following steps:

S301. After receiving an insurance vehicle claim request sent by an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

Specifically, in this embodiment, the end user may install and run a vehicle damage application (auto insurance app) on the terminal device, take basic information of the accident vehicle at the scene of the accident, and take photos of the damaged components of the accident vehicle, and Generate image information. Optionally, a shooting guide interface can be provided in the vehicle damage application. The interface is an application based on a mobile device camera. That is, after the mobile device enters the shooting guide interface, the camera is turned on, and an interface is displayed on the interface. The user is prompted to take a first selection box of basic information of the dangerous vehicle. After the user clicks the first selection box, a first floating frame of a first preset size is generated. When the user takes an image of the basic information of the dangerous vehicle, the user needs to take The basic information of the vehicle is completely contained in the first floating frame, and shooting is performed based on the first floating frame to obtain a photo that meets the requirements, that is, the image information of the basic information of the vehicle is obtained. Further, after the user has taken the basic information of the vehicle, , The interface displays a second selection box prompting the user to take pictures of the damaged parts of the dangerous vehicle. After clicking the second selection box, a second floating frame of a second preset size is generated. When the user takes an image of a damaged part of a dangerous vehicle, the user needs to completely contain the damaged part in the second floating frame. The second floating frame is photographed to take a photo that meets the requirements, that is, to obtain image information of the damaged part of the vehicle, and generate a claim for claiming an insurance vehicle based on the captured basic information of the vehicle and the image information of the damaged part of the vehicle. The above method can avoid the situation that the photographed vehicle information or damaged parts are incomplete and cannot be recognized normally.

It can be understood that the claim request for an out-of-vehicle vehicle includes image information of the out-of-vehicle basic information and image information of damaged parts of the out-of-vehicle vehicle. The out-of-vehicle basic information includes a vehicle type, a license plate number, and a vehicle identification code (VIN code).

S302. According to the OCR (optical character) recognition method, identify basic vehicle information from the acquired image information that includes basic information about the vehicle in danger;

S303. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the acquired image information of the damaged component of the vehicle in danger to determine the claim amount corresponding to the policy. ;

Specifically, the pre-trained claim amount analysis model is a neural network model, the claim amount analysis model includes a training process and a test process of the model, and the training process of the model includes:

E2. Obtaining a preset number of claims for information samples of automobile insurance claims that match the basic information of the vehicle, and extracting from the information samples the image information set of the damaged parts of the vehicle for each automobile insurance claim;

F2. Divide the image information set of the vehicle damaged parts corresponding to the information sample of each car insurance claim case into a first proportion training subset and a second proportion testing subset;

G2: training the claim amount analysis model by using image information of vehicle damaged parts of each car insurance payment case in the training subset to obtain a trained claim amount analysis model;

H2. Use the image information of the damaged parts of the vehicle in each of the car insurance claims in the test subset to test the claim amount analysis model. If the test passes, the training ends, or if the test fails, increase the The number of car insurance compensation case information samples that have been manually reviewed and the steps E2, F2, G2, and H2 described above are performed again.

Test process of the model:

S304. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.

Further, the method further includes:

It can be known from the above-mentioned embodiments that the automobile insurance intelligent claims method proposed in the present application first receives an insurance vehicle claim request sent by an end user, and obtains image information including basic information of the insurance vehicle and the damaged vehicle from the request. Image information of parts; then, according to the OCR recognition method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger; secondly, the corresponding insurance policy is generated based on the identified basic vehicle information, and pre-training is called based on the generated policy The completed claim amount analysis model analyzes the image information of the damaged parts of the out of vehicle vehicle to determine the claim amount corresponding to the policy; and finally sends the claim amount to the end user for the end user to The claim amount initiates an auto insurance claim request to the insurance claim terminal. It can reduce manual participation in the process of auto insurance claims, improve the speed and accuracy of claim settlement, enable customers to understand the claim situation in time, and improve the experience.

In addition, the present application also proposes a computer-readable storage medium, where the computer-readable smart claim program is stored on the computer-readable storage medium, and the car insurance smart claim program is executed by a processor to implement the following operations:

After receiving an insurance vehicle claim request sent by an end user, obtaining image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

The specific implementation of the computer-readable storage medium of the present application is basically the same as the above-mentioned electronic device and each embodiment of the automobile insurance intelligent claims method, and will not be repeated here.

The above-mentioned serial numbers of the embodiments of the present application are merely for description, and do not represent the superiority or inferiority of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better. Implementation. Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, The optical disc) includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.

The above are only preferred embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the description and drawings of the present application, or directly or indirectly used in other related technical fields Are included in the scope of patent protection of this application.

Claims

An electronic device, characterized in that the electronic device includes a memory and a processor connected to the memory, the processor is configured to execute a car insurance intelligent claims program stored on the memory, and the car insurance intelligent claims program is When the processor executes, the following steps are implemented:

A1. After receiving an insurance vehicle claim request sent by an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

A2. According to the OCR identification method, the basic vehicle information is identified from the obtained image information containing the basic information of the vehicle in danger;

A3. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the acquired image information of the damaged parts of the vehicle in danger to determine the claim amount corresponding to the policy ;

A4. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.
The electronic device according to claim 1, wherein the step A2 comprises:

Locating character string information in the image information containing basic information of the vehicle in danger;

Acquiring the located string information and performing character segmentation to split the string into multiple single characters;

Recognize each single character separately to identify basic vehicle information.
The electronic device according to claim 1, wherein the pre-trained claim amount analysis model is a neural network model, the claim amount analysis model includes a training process and a test process of the model, and a training process of the model include:

E1. Obtain a preset number of sampled claims for car insurance compensation case information that matches the basic information of the vehicle, and extract from the information samples the image information collection of the damaged parts of the vehicle for each of the insurance claims cases;

F1. Divide the image information set of the vehicle damaged parts corresponding to the information samples of each car insurance claim case into a first proportion of the training subset and a second proportion of the testing subset;

G1: training the claim amount analysis model by using image information of vehicle damaged parts of each car insurance payment case in the training subset to obtain a trained claim amount analysis model;

H1. Use the image information of the damaged parts of the vehicle in each of the auto insurance claims cases to test the claim amount analysis model. If the test passes, the training ends, or if the test fails, increase the The number of car insurance compensation case information samples that have been manually reviewed and steps E1, F1, G1, and H1 are performed again.
The electronic device according to claim 3, wherein the test process of the model:

The trained claim analysis model is used to analyze the image information of the damaged parts of the vehicles in each of the car insurance claims in the test subset, so as to obtain the first claim amount of each car insurance claim that passed the manual review and the claim settlement. The probability value that the second claim amount automatically reviewed by the amount analysis model is equal;

If there is a probability value that the first claim amount and the second claim amount corresponding to a car insurance claim case are greater than the preset probability threshold, a model accuracy test is performed for the car insurance claim case, and the car insurance claim case is performed Carry out manual review to obtain the first claim amount corresponding to the auto insurance claim case, and call the claim amount analysis model to automatically analyze the auto insurance claim case to obtain the second claim amount corresponding to the auto insurance claim case;

The calculated error value between the first claim amount and the second claim amount corresponding to the auto insurance claim case;

If the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the car insurance compensation case is correct, or if the calculated error value is greater than or equal to the preset error threshold, then Determine that the result of the model accuracy test for the auto insurance claim case is incorrect;

If the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, determine that the test of the claim amount analysis model passes, or if the correct model accuracy test results account for all If the percentage of the model accuracy test result is less than or equal to a preset percentage threshold, it is determined that the test of the claim amount analysis model fails.
The electronic device according to claim 1, wherein when the car insurance intelligent claims program is executed by the processor, the following steps are further implemented:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The electronic device according to claim 2, wherein when the car insurance intelligent claims program is executed by the processor, the following steps are further implemented:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The electronic device according to claim 3, wherein when the car insurance intelligent claim program is executed by the processor, the following steps are further implemented:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The electronic device according to claim 4, characterized in that, when the car insurance intelligent claims program is executed by the processor, the following steps are further implemented:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
An automobile insurance intelligent claim method is characterized in that the method includes the following steps:

S1. After receiving an insurance vehicle claim request from an end user, obtain image information including basic information of the insurance vehicle and image information of damaged components of the insurance vehicle from the request;

S2. According to the OCR identification method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger;

S3. Generate a corresponding insurance policy based on the identified basic vehicle information, call a pre-trained claim amount analysis model based on the generated policy, and analyze the image information of the damaged component of the out of vehicle vehicle to determine the claim amount corresponding to the policy ;

S4. Send the claim amount to the end user for the end user to initiate an auto insurance claim request to an insurance claimant based on the claim amount.
The method of claim 9, wherein the step S2 comprises:

Locating character string information in the image information containing basic information of the vehicle in danger;

Acquiring the located string information and performing character segmentation to split the string into multiple single characters;

Recognize each single character separately to identify basic vehicle information.
The method of claim 9, wherein the pre-trained claim amount analysis model is a neural network model, and the claim amount analysis model includes a training process and a test process of the model. The training process includes:

E2. Obtain a preset number of sampled claims for car insurance claim information that matches the basic information of the vehicle, and extract from the information samples the image information collection of the damaged parts of the vehicle in each of the car insurance claims cases;

F2. Divide the image information set of the vehicle damaged parts corresponding to the information sample of each car insurance claim case into a first proportion training subset and a second proportion testing subset;

G2: training the claim amount analysis model by using image information of vehicle damaged parts of each car insurance payment case in the training subset to obtain a trained claim amount analysis model;

H2. Use the image information of the damaged parts of the vehicle in each of the car insurance claims in the test subset to test the claim amount analysis model. If the test passes, the training ends, or if the test fails, increase the The number of car insurance compensation case information samples that have been manually reviewed and steps E2, F2, G2, and H2 are performed again.
The method of claim 11, wherein the testing process of the model:

The trained claim analysis model is used to analyze the image information of the damaged parts of the vehicles in each of the car insurance claims in the test subset, so as to obtain the first claim amount of each car insurance claim that passed the manual review and the claim settlement. The probability value that the second claim amount automatically reviewed by the amount analysis model is equal;

If there is a probability value that the first claim amount and the second claim amount corresponding to a car insurance claim case are greater than the preset probability threshold, a model accuracy test is performed for the car insurance claim case, and the car insurance claim case is performed Carry out manual review to obtain the first claim amount corresponding to the auto insurance claim case, and call the claim amount analysis model to automatically analyze the auto insurance claim case to obtain the second claim amount corresponding to the auto insurance claim case;

The calculated error value between the first claim amount and the second claim amount corresponding to the auto insurance claim case;

If the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the car insurance compensation case is correct, or if the calculated error value is greater than or equal to the preset error threshold, then Determine that the result of the model accuracy test for the auto insurance claim case is incorrect;

If the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, determine that the test of the claim amount analysis model passes, or if the correct model accuracy test results account for all If the percentage of the model accuracy test result is less than or equal to a preset percentage threshold, it is determined that the test of the claim amount analysis model fails.
The method of claim 9, further comprising the following steps:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The method of claim 10, wherein the method further comprises the following steps:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The method of claim 11, further comprising the following steps:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
The method of claim 12, further comprising the following steps:

When receiving confirmation information sent by the terminal user who has an objection to the claim amount, obtaining basic vehicle information from the confirmed information;

Sending the basic information of the vehicle and the image information of the damaged part of the vehicle to a predetermined claims review platform;

Receiving the final claim amount obtained after the claims review platform re-determines the fixed loss claim for the accident vehicle; and sending the final claim amount to the end user.
A computer-readable storage medium stores a virtual number-based monitoring and surveying program, and the car insurance intelligent claims program can be executed by at least one processor, so that the at least one processor executes the following steps:

After receiving a claim for a vehicle out of danger sent by an end user, obtaining image information containing basic information of the vehicle in danger and image information of damaged parts of the vehicle from the request;

According to the OCR recognition method, the basic vehicle information is identified from the acquired image information containing the basic information of the vehicle in danger;

Generating a corresponding insurance policy based on the identified basic vehicle information, invoking a pre-trained claim amount analysis model based on the generated policy, and analyzing the image information of the damaged component of the out of vehicle vehicle to determine the claim amount corresponding to the policy;

Sending the claim amount to the end user for the end user to initiate a car insurance claim request to an insurance claimant based on the claim amount.
The computer-readable storage medium of claim 17, wherein the step of identifying the basic information of the vehicle from the acquired image information containing the basic information of the vehicle in danger according to the OCR identification method comprises:

Locating character string information in the image information containing basic information of the vehicle in danger;

Acquiring the located string information and performing character segmentation to split the string into multiple single characters;

Recognize each single character separately to identify basic vehicle information.
The computer-readable storage medium of claim 17, wherein the pre-trained claim amount analysis model is a neural network model, and the claim amount analysis model includes a training process and a test process of the model, and the model The training process includes:

E2. Obtain a preset number of sampled claims for car insurance claim information that matches the basic information of the vehicle, and extract from the information samples the image information collection of the damaged parts of the vehicle in each case

F2. Divide the image information set of the vehicle damaged parts corresponding to the information sample of each car insurance claim case into a first proportion training subset and a second proportion testing subset;

G2: training the claim amount analysis model by using image information of vehicle damaged parts of each car insurance payment case in the training subset to obtain a trained claim amount analysis model;

H2. Use the image information of the damaged parts of the vehicle in each of the car insurance claims in the test subset to test the claim amount analysis model. If the test passes, the training ends, or if the test fails, increase the The number of car insurance compensation case information samples that have been manually reviewed and steps E2, F2, G2, and H2 are performed again.
The computer-readable storage medium of claim 19, wherein the testing process of the model:

The trained claim analysis model is used to analyze the image information of the damaged parts of the vehicles in each of the car insurance claims in the test subset, so as to obtain the first claim amount of each car insurance claim that passed the manual review and the claim settlement. The probability value that the second claim amount automatically reviewed by the amount analysis model is equal;

If there is a probability value that the first claim amount and the second claim amount corresponding to a car insurance claim case are greater than the preset probability threshold, a model accuracy test is performed for the car insurance claim case, and the car insurance claim case is performed Carry out manual review to obtain the first claim amount corresponding to the auto insurance claim case, and call the claim amount analysis model to automatically analyze the auto insurance claim case to obtain the second claim amount corresponding to the auto insurance claim case;

The calculated error value between the first claim amount and the second claim amount corresponding to the auto insurance claim case;

If the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the car insurance compensation case is correct, or if the calculated error value is greater than or equal to the preset error threshold, then Determine that the result of the model accuracy test for the auto insurance claim case is incorrect;

If the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, determine that the test of the claim amount analysis model passes, or if the correct model accuracy test results account for all If the percentage of the model accuracy test result is less than or equal to a preset percentage threshold, it is determined that the test of the claim amount analysis model fails.