CN119478994A

CN119478994A - Method, device, equipment and storage medium for reviewing images of automobile insurance certificates

Info

Publication number: CN119478994A
Application number: CN202411491129.7A
Authority: CN
Inventors: 严立
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2024-10-23
Filing date: 2024-10-23
Publication date: 2025-02-18

Abstract

The application belongs to the field of artificial intelligence and insurance, and relates to an auditing method of a vehicle insurance certificate image, which comprises the steps of obtaining the vehicle insurance certificate image to be audited, adopting a certificate type identification model to carry out type identification on the vehicle insurance certificate image to obtain the certificate type of the vehicle insurance certificate image, adopting a certificate content identification model to carry out content identification on the vehicle insurance certificate image according to the certificate type to extract the certificate information of the vehicle insurance certificate image, obtaining the application information corresponding to the vehicle insurance certificate image to be audited, carrying out consistency check on the certificate information and the application information, and judging that the vehicle insurance certificate image passes the automatic auditing if the consistency check is passed, so as to confirm that the certificate corresponding to the vehicle insurance certificate image is a compliance certificate. The application also provides a checking device, equipment and storage medium of the vehicle insurance certificate image. In addition, the application also relates to blockchain technology, certificate information and the like can be stored in the blockchain. The application can improve the auditing efficiency of the vehicle insurance certificate image.

Description

Method, device, equipment and storage medium for auditing vehicle insurance certificate image

Technical Field

The application relates to the field of artificial intelligence and insurance, in particular to a method for auditing images of a car insurance certificate.

Background

In the field of insurance, checking the certificates uploaded by clients is one of the key links, and the traditional vehicle insurance certificate checking mode is completed manually.

However, the traditional manual auditing mode is long in time consumption and easy to make mistakes, a large number of application and application are difficult to deal with, the consistency verification of certificate information and application information is complex, important details are easy to miss, the insurance application flow is complex, time and labor are consumed, the operation efficiency of insurance companies is affected, and the satisfaction degree of clients is influenced;

Therefore, an automatic auditing method for the images of the vehicle insurance certificates is needed to improve the auditing efficiency of the vehicle insurance certificates.

Disclosure of Invention

The embodiment of the application aims to provide a method, a device, equipment and a storage medium for auditing a vehicle insurance certificate image, and the main purpose of the method, the device and the equipment is to improve the efficiency of auditing the vehicle insurance certificate.

In order to solve the technical problems, the embodiment of the application provides a method for auditing images of vehicle insurance certificates, which adopts the following technical scheme:

acquiring a vehicle insurance certificate image to be checked, and performing type recognition on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate type recognition model to obtain the certificate type of the vehicle insurance certificate image;

According to the certificate type, adopting a pre-trained certificate content recognition model to perform content recognition on the to-be-checked vehicle insurance certificate image, and extracting the certificate information of the to-be-checked vehicle insurance certificate image;

acquiring application information corresponding to the vehicle insurance certificate image to be checked, and carrying out consistency check on the certificate information and the application information;

And if the consistency check is passed, judging that the vehicle insurance certificate image to be checked passes the automatic check, and determining that the certificate corresponding to the vehicle insurance certificate image to be checked is a compliance certificate.

Further, the method for identifying the type of the vehicle insurance certificate image to be checked by adopting a pre-trained certificate type identification model to obtain the certificate type of the vehicle insurance certificate image comprises the following steps:

performing convolution operation on the vehicle insurance certificate image to be audited by utilizing a convolution layer in the pre-trained certificate type identification model, and extracting target type characteristics of the vehicle insurance certificate image to be audited;

Performing dimension reduction operation on the target type features by using a pooling layer in the pre-trained certificate type recognition model to obtain dimension-reduced target type features;

And calculating the probability of each type of the target type characteristic after dimension reduction by using an output layer in the pre-trained certificate type recognition model, and selecting the type with the maximum probability to obtain the certificate type of the vehicle insurance certificate image.

Further, according to the type of the certificate, the content recognition is performed on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate content recognition model, and the certificate information of the vehicle insurance certificate image to be checked is extracted, including:

according to the certificate type, detecting the content key position of the vehicle insurance certificate image to be checked by utilizing a text detection module of the pre-trained certificate content recognition model to obtain a content key area;

performing OCR processing on the content key area by using a text recognition module of the pre-trained certificate content recognition model, and extracting key texts of the content key area;

And carrying out format conversion on the key text according to a predefined data format by using the structuring processing module utilizing the pre-trained certificate content recognition model to obtain the certificate information of the vehicle insurance certificate image to be checked.

Further, after the text recognition module utilizing the pre-trained certificate content recognition model performs OCR processing on the content key area and extracts the key text of the content key area, the method further includes:

Performing field verification on the key text by utilizing a post-processing module of the pre-trained certificate content recognition model, and inquiring whether a predefined character segment to be filled is filled;

when the predefined necessary-filling fields are filled in completely, verifying all the predefined necessary-filling fields with texts corresponding to the vehicle insurance certificate image to be checked one by one;

And inputting the verified key text into the structuring processing module utilizing the pre-trained certificate content recognition model.

Further, after the extracting the certificate information of the vehicle insurance certificate image to be audited, the method further comprises:

acquiring current time, and verifying the validity period of the vehicle insurance certificate image to be audited according to the certificate information and the current time;

And when the current time is not within the valid period of the vehicle insurance certificate image to be audited, judging that the vehicle insurance certificate image to be audited is not compliant, and prompting a user to upload other types of certificate images again.

Further, the performing consistency check on the certificate information and the application information includes:

Carrying out structuring treatment on the insuring information according to a predefined structure template to obtain structure insuring information;

and carrying out consistency check on the certificate information and the information of the same prefix in the structure application information.

Further, after the certificate corresponding to the vehicle insurance certificate image to be audited is determined to be a compliant certificate, the method further includes:

the certificate information of the compliance certificate is stored in a preset certificate information database;

When a renewal request is received, certificate information corresponding to the renewal request is obtained from the preset certificate information database;

judging whether the certificate information corresponding to the renewal request is in the valid period or not;

and when the certificate information corresponding to the renewal request is within the valid period, invoking the certificate information corresponding to the renewal request to complete renewal operation.

In order to solve the technical problems, the embodiment of the application also provides a checking device for the vehicle insurance certificate image, which adopts the following technical scheme:

The type identification module is used for acquiring a vehicle insurance certificate image to be checked, and carrying out type identification on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate type identification model to obtain the certificate type of the vehicle insurance certificate image;

the content extraction module is used for carrying out content identification on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate content identification model according to the certificate type, and extracting the certificate information of the vehicle insurance certificate image to be checked;

the information verification module is used for acquiring the application information corresponding to the vehicle insurance certificate image to be verified, and carrying out consistency verification on the certificate information and the application information;

And the compliance judging module is used for judging that the vehicle insurance certificate image to be checked passes the automatic check if the consistency check passes, and determining that the certificate corresponding to the vehicle insurance certificate image to be checked is a compliance certificate.

In order to solve the technical problems, the embodiment of the application also provides equipment, which adopts the following technical scheme:

In order to solve the above technical problems, the embodiments of the present application further provide a storage medium, which adopts the following technical schemes:

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

The method and the device for verifying the vehicle insurance certificate image by using the pre-trained certificate type recognition model perform type recognition on the vehicle insurance certificate image to be verified to obtain the certificate type of the vehicle insurance certificate image, solve the problems that a traditional manual verification mode is long in time consumption and easy to make mistakes and is difficult to deal with a large number of application and application, and improve verification efficiency and accuracy in the application and verification process and user experience.

According to the certificate type, a pre-trained certificate content identification model is adopted to conduct content identification on the vehicle insurance certificate image to be checked, certificate information of the vehicle insurance certificate image to be checked is extracted, the problems of low efficiency and low precision caused by manual checking are avoided, the automation degree of checking is improved, the checking efficiency and accuracy are improved, detailed records are generated in the checking process of the certificate through the model, the checking is traceable, and unnecessary disputes are avoided.

Through carrying out consistency check with certificate information with the insurance information, avoided the manual work to cause inefficiency and the low problem of precision when carrying out disposable check-up, improved consistency check-up's efficiency and accuracy to user experience has been promoted.

And whether the vehicle insurance certificate image passes the automatic verification is judged through the consistency verification, so that whether the certificate corresponding to the vehicle insurance certificate image is a compliant certificate is further determined, the verification efficiency is improved, the verification cost is reduced, and the user experience is improved.

Drawings

In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a method of auditing images of a vehicle insurance certificate in accordance with the present application;

FIG. 3 is a schematic structural view of one embodiment of an auditing apparatus for vehicle insurance certificate images in accordance with the present application;

fig. 4 is a schematic structural view of an embodiment of the device according to the application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, the terms used in the description herein are used for the purpose of describing particular embodiments only and are not intended to limit the application, and the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the above description of the drawings are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, the system architecture 100 may include a terminal device 101, a network 102, and a server 103, where the terminal device 101 may be a notebook 1011, a tablet 1012, or a cell phone 1013. Network 102 is the medium used to provide communication links between terminal device 101 and server 103. Network 102 may include various connection types such as wired, wireless communication links, or fiber optic cables.

A user may interact with the server 103 via the network 102 using the terminal device 101 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, and the like, may be installed on the terminal device 101.

The terminal device 101 may be various electronic devices having a display screen and supporting web browsing, and the terminal device 101 may be an electronic book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, moving picture experts compression standard audio layer III), an MP4 (Moving Picture Experts Group Audio Layer IV, moving picture experts compression standard audio layer IV) player, a laptop portable computer, a desktop computer, or the like, in addition to the notebook 1011, the tablet 1012, or the mobile phone 1013.

The server 103 may be a server providing various services, such as a background server providing support for pages displayed on the terminal device 101.

It should be noted that, the method for acquiring the vehicle insurance investigation evidence provided by the embodiment of the application is generally executed by a server/terminal device, and correspondingly, the device for acquiring the vehicle insurance investigation evidence is generally arranged in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of a method of auditing a vehicle insurance certificate image in accordance with the present application is shown. The auditing method of the vehicle insurance certificate image comprises the following steps:

s201, acquiring a vehicle insurance certificate image to be checked, and performing type identification on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate type identification model to obtain the certificate type of the vehicle insurance certificate image.

In this embodiment, the vehicle insurance certificate image to be checked refers to a vehicle insurance certificate image uploaded by a user when applying for insurance, or may be a certificate image recorded in a vehicle insurance issuing process, and the pre-trained certificate type identification model refers to a pre-trained convolution model, where the pre-trained convolution model includes an output layer, a convolution layer, a maximum pooling layer, a full connection layer, and an output layer.

In the embodiment, a vehicle insurance certificate image to be checked is obtained, the vehicle insurance certificate image to be checked is preprocessed to obtain a standard vehicle insurance certificate image, the standard vehicle insurance certificate image is input into a pre-trained certificate type recognition model, and the certificate type of the standard vehicle insurance certificate image is recognized through the pre-trained certificate type recognition model.

In this embodiment, the preprocessing step includes:

and performing image denoising, gray processing, image enhancement and normalization processing on the vehicle insurance certificate image to be audited to obtain a standard vehicle insurance certificate image.

In the embodiment, the noise in the vehicle insurance certificate image to be audited is reduced by utilizing an image denoising mode, the image quality is improved, the vehicle insurance certificate image is processed by utilizing a gray level processing mode, the calculated amount of subsequent processing can be reduced, the efficiency and accuracy of the subsequent recognition step are improved, the contrast and definition of the image are improved by utilizing an image enhancement mode, the information in the image is more outstanding, the subsequent certificate recognition step and the content extraction step are facilitated, the vehicle insurance certificate image can be converted into a numerical range which can be recognized by a model by utilizing a normalization processing mode, and the problem that the vehicle insurance certificate image cannot be recognized subsequently is avoided.

The method comprises the steps of carrying out image denoising on a vehicle insurance certificate image to be audited in a Gaussian filtering mode, scanning each pixel in the vehicle insurance certificate image, replacing the value of a central pixel point of a template with a weighted average gray value of pixels in the field determined by the template to obtain a denoised vehicle insurance certificate image, converting each pixel point of a colored vehicle insurance certificate image from an RGB color space to a gray space to obtain a vehicle insurance certificate image after gray processing, adjusting pixel distribution of the vehicle insurance certificate image by using a histogram equalization function in a histogram equalization mode to obtain a vehicle insurance certificate image after image enhancement, carrying out normalization processing on the vehicle insurance certificate image in an image normalization mode to obtain a standard vehicle insurance certificate image, and completing the preprocessing step.

In one embodiment, before the employing a pre-trained certificate type recognition model to perform type recognition on the vehicle insurance certificate image to be checked, the method includes:

Acquiring a certificate type data set, and dividing the certificate type data set into a training set and a testing set according to a preset proportion;

training the convolutional neural network model by using the training set to obtain an initial certificate type identification model;

Testing the initial certificate type identification model according to the test set to obtain a loss value;

and when the loss value is smaller than or equal to a preset loss threshold value, obtaining a trained certificate type identification model.

In the embodiment, a large number of certificate images with labels are obtained, a large number of certificate images with type labels are collected to form a certificate type data set, each certificate image is classified according to the corresponding labels to obtain a plurality of classified certificate type data sets, each classified certificate type data set is split into a plurality of training subsets and a plurality of test subsets according to a preset proportion, all the training subsets and all the test subsets are summarized to obtain a training set and a test set, an initial certificate type identification model is trained through the training set, the initial certificate type identification model is tested by the test set, the test method comprises the steps of carrying out convolution operation on the certificate images corresponding to each type label by the initial certificate type identification model to obtain test feature vectors corresponding to each type label, calculating the distances between the test feature vectors and the type feature vectors of the same type labels by using a Euclidean distance method to obtain a plurality of loss distance values, calculating the average value of all the loss distance values to obtain a loss value, judging whether the loss value is smaller than or equal to a preset loss threshold value, completing training, if the loss value is smaller than or equal to the preset loss threshold, training is completed, if the preset loss value is larger than the preset loss value is equal to the preset loss value, and the training model is continued until the training is finished, if the loss value is smaller than the preset, and the training threshold is equal to the training threshold is continued.

In one embodiment, the performing type recognition on the vehicle insurance certificate image to be checked by using a pre-trained certificate type recognition model to obtain the certificate type of the vehicle insurance certificate image includes:

In this embodiment, the pre-trained certificate recognition model is used to perform type recognition on the vehicle insurance certificate image to be checked, so that the problems of poor accuracy and low efficiency caused by manual checking can be avoided, the overall efficiency and accuracy of vehicle insurance verification are improved, the labor cost is reduced, and the model can be further trained and optimized by the model to further recognize more types of certificates, so that the degree of automation of recognition is improved.

In the embodiment, preprocessing operation is carried out on a vehicle insurance certificate image to be audited to obtain a standard vehicle insurance certificate image, the standard vehicle insurance certificate image is input into a certificate type recognition model with a pre-trained value, convolution operation is carried out on the standard vehicle insurance certificate image by using a convolution layer of the pre-trained certificate type recognition model to extract target type characteristics of the standard vehicle insurance certificate image, dimension reduction operation is carried out on the target type characteristics by using a pooling layer in the pre-trained certificate type recognition model to obtain dimension reduced target type characteristics, the output layer refers to a softmax classifier, probability that the dimension reduced target type characteristics belong to each type is calculated by using an output layer in the pre-trained certificate type recognition model, probability distribution of a certificate type is obtained, and a type with the largest probability is selected from the probability distribution of the certificate type to obtain the certificate type of the vehicle insurance certificate image.

In another embodiment, if the identified certificate type is inconsistent with the certificate type preselected by the user, or any probability in the probability distribution is smaller than a preset probability threshold, judging that the certificate type uploaded by the client is not a conventional type certificate, and prompting the user to re-upload or transfer manual verification.

In an embodiment a, when a user applies for insurance, the user is prompted to upload a car insurance certificate image, the user uploads an identity card photo according to the prompt, the car insurance certificate image uploaded by the user is obtained, firstly, preprocessing operation is performed on the car insurance certificate image uploaded by the user, image denoising, gray processing, image enhancement and normalization processing are performed on the car insurance certificate image uploaded by the user, a standard car insurance certificate image is obtained, the standard car insurance certificate image is input into a pre-trained certificate type recognition model, target characteristics of the standard car insurance certificate image are extracted, the probability that the target characteristics of the standard car insurance certificate image are an identity card is calculated according to an output layer of the pre-trained certificate type recognition model, the probability that the target characteristics of the standard car insurance certificate image is an identity card is 0.95, and the car insurance certificate image uploaded by the user is judged to be the identity card.

In this embodiment, a pre-trained certificate type recognition model is adopted to perform type recognition on the vehicle insurance certificate image to be checked, so as to obtain the certificate type of the vehicle insurance certificate image, thereby avoiding the problems that the traditional manual checking mode is long in time consumption and easy to make mistakes, and is difficult to deal with a large number of application applications, and improving checking efficiency and accuracy in the application process and user experience.

S202, carrying out content recognition on the vehicle insurance certificate image to be checked by adopting a pre-trained certificate content recognition model according to the certificate type, and extracting the certificate information of the vehicle insurance certificate image to be checked.

In this embodiment, the pre-trained document content recognition model includes a text detection module, a text recognition module, a post-processing module, and a structured processing module.

In one embodiment, the content recognition of the vehicle insurance certificate image to be audited by adopting a pre-trained certificate content recognition model according to the certificate type, and extracting the certificate information of the vehicle insurance certificate image to be audited, includes:

In this embodiment, the location of the key content corresponding to each certificate type is different, the text detection module of the pre-trained certificate content identification model is used to locate the key location of the content, for example, the name area, the gender area, the certificate number area, the validity area, etc. according to the located key location of the content, the text recognition module of the pre-trained certificate content identification model is used to extract the content contained in the key location of the content and convert the text of the key location of the content in the image into a preset text format to obtain the key text, and the structured processing module of the pre-trained certificate content identification model is used to convert the format of the key text according to a predefined structural template (such as name: XXX, gender: XXX, certificate number: XXX, validity: XXX, etc.), so as to obtain structured data, and finally obtain the certificate information of the certificate image of the vehicle insurance certificate to be audited.

In this embodiment, according to the type of the certificate, a pre-trained certificate content recognition model is adopted to perform content recognition on the to-be-checked vehicle insurance certificate image, and the certificate information of the to-be-checked vehicle insurance certificate image is extracted, so that the manual extraction of the content of the identity card is avoided, the efficiency and the precision of the certificate information extraction are improved, and the processing of subsequent steps is facilitated through the certificate information which is output in a structuring mode.

The content contained in the content key region extracted by adopting OCR (optical character recognition) technology may have the phenomena of not extracting necessary filling fields, extracting errors and the like;

In another embodiment, therefore, after performing OCR processing on the content key area by the text recognition module that uses the pre-trained certificate content recognition model to extract key text of the content key area, the method further includes:

when the necessary filling fields are filled in completely, verifying all the necessary filling fields with texts corresponding to the vehicle insurance certificate images to be checked one by one;

In this embodiment, the pre-defined field is filled up, the post-processing module of the pre-trained certificate content recognition model is used to perform field verification on the key text, whether all the filling up fields exist or not is queried, when any one filling up frame lacks a numerical value, the OCR processing step is returned to reprocess until all the filling up frames have corresponding filling up fields, all the filling up fields are verified one by one with text fields corresponding to the to-be-verified vehicle insurance certificate image, when verification fails, the error fields are deleted and filled up until verification passes, and the key text passing verification is input into the structured processing module of the pre-trained certificate content recognition model.

In one embodiment, after the extracting the certificate information of the vehicle insurance certificate image to be audited, the method further includes:

In the embodiment, the current time is acquired and is the real-time when the vehicle insurance certificate image to be audited is processed, the current time is compared with the valid period time on the certificate information of the vehicle insurance certificate image to be audited, whether the current time is within the valid period time on the certificate information of the vehicle insurance certificate image to be audited or not is judged, when the current time is not within the valid period time on the certificate information of the vehicle insurance certificate image to be audited, the fact that the vehicle insurance certificate image to be audited uploaded by a user is not compliant is judged, the user is prompted to upload other types of vehicle insurance certificate images within the valid period again, and when the current time is within the valid period time on the certificate information of the vehicle insurance certificate image to be audited, the vehicle insurance certificate image to be audited is authenticated through the valid period.

In the embodiment, the validity of the certificate is ensured by comparing the certificate information with the current time, the cost of manual auditing is reduced, the risk rate of the validity period of the certificate due to missed judgement is reduced, and the compliance of the certificate and the efficiency of certificate auditing are improved.

After recognizing that the type of the certificate uploaded by the user is the type of the identity card, the embodiment A inputs the identity card image into a trained content recognition model, determines each content key area of the identity card image through a text detection module of the content recognition model according to the type of the identity card, determines a name area, a gender area, a certificate number area, a valid period area and an address area, performs OCR processing on each key area according to the determined key area by utilizing the text recognition module of the pre-trained content recognition model, extracts key texts corresponding to each key area, the name xxx, the gender x, the certificate number xxx, the valid period xxx and the address xxx, verifies the key texts and texts corresponding to the identity card image, and when verification passes, performs structural conversion on the key texts according to the formats of the name xxx, the gender xxx, the certificate number xxx, the valid period xxx and the address xxx to obtain certificate information of the identity card, and performs validity verification on the certificate information and the current time to obtain a verification result.

In this embodiment, according to the document type, a pre-trained document content recognition model is adopted to perform content recognition on the vehicle insurance document image to be checked, and the document information of the vehicle insurance document image to be checked is extracted, so that the problems of low efficiency and low precision caused by manual checking are avoided, the automation degree of checking is improved, the checking efficiency and accuracy are improved, and detailed records are generated in the checking process of the document through the model, so that checking has traceability, and unnecessary disputes are avoided.

S203, acquiring the application information corresponding to the vehicle insurance certificate image to be checked, and carrying out consistency check on the certificate information and the application information.

In this embodiment, the application information refers to information filled in by a user in an application process of application, including personal information of an insured person, such as name, birth date, identification card number, gender, etc., and the application information corresponding to a vehicle insurance certificate image is obtained, and consistency verification is performed on the certificate information and the application information.

In one embodiment, the verifying the identity information against the application information comprises:

In this embodiment, the obtained insuring information is structured according to the same structured model as the certificate information to obtain the structure insuring information, and because the same structured template is used, the prefix corresponding to the certificate information and the information contained in the prefix corresponding to the structure insuring information, such as the name of the certificate information, XXX, and the name of the structure insuring information, XXX, are verified until all consistency verification of the certificate information is completed.

In another embodiment, the verifying the identity of the certificate information and the information of the same prefix in the structure application information includes:

And if the consistency check fails, marking the vehicle insurance certificate image to be checked as a suspicious certificate image, and pushing the suspicious certificate image to manual processing.

In this embodiment, if the consistency check is not passed, there is a problem of certificate errors or a problem of filling errors in the user's insurance information, so the user is not prompted to upload again, but marked as suspicious certificate images, and the certificate images and the insurance information are pushed to the manual for review.

In the embodiment, through rechecking the suspicious certificate image, the defects of machine verification are overcome, the verification accuracy is improved, the misjudgment rate is reduced, the illegal reasons can be accurately found, the user is prompted to modify the insurance information or to reload subpoena images according to the reasons, and the experience of the user is improved.

In the above practical example a, the insurance information corresponding to the identity card information is extracted from the database storing the user insurance information, such as the insured person XXX, the certificate number XXX, the age XXX, the sex XXX, etc., the insurance information is structured according to a preset structural template to obtain the name XXX, the certificate number XXX, the age XXX, the sex XXX, etc., the name XXX of the certificate information and the name XXX of the insurance information are subjected to consistency check, the certificate number XXX of the certificate information and the certificate number XXX of the insurance information are subjected to consistency check, the sex XXX of the certificate information and the sex XXX of the insurance information are subjected to consistency check, and the age XXX of the certificate information and the age XXX of the insurance information are subjected to consistency check.

In this embodiment, by performing consistency verification on the certificate information and the application information, the problem of low efficiency and low precision caused by manual one-time verification is avoided, and efficiency and accuracy of consistency verification are improved, so that user experience is improved.

And S204, if the consistency check is passed, judging that the vehicle insurance certificate image to be checked passes the automatic check, and determining that the certificate corresponding to the vehicle insurance certificate image to be checked is a compliant certificate.

In this embodiment, if the consistency check is passed, it is determined that the vehicle insurance certificate image to be checked passes the automatic check, and then it is determined that the certificate corresponding to the certificate image uploaded by the user is a compliant certificate.

In one embodiment, after the determining that the certificate corresponding to the vehicle insurance certificate image to be audited is a compliant certificate, the method further includes:

When a renewal request is received, certificate information corresponding to the renewal request is obtained from a preset certificate information database;

In this embodiment, after the user agrees, the certificate information of the compliance certificate is stored in a preset certificate information database, and when the next warrant period is performed, the user initiates a warrant renewal request, extracts the certificate information corresponding to the warrant renewal request from the preset certificate information database, determines whether the certificate information corresponding to the warrant renewal request is within the validity period, if so, directly uses the certificate information of the compliance certificate to complete the warrant renewal request, and if not, prompts the user to upload the compliance certificate image again for verification.

In the embodiment, the certificate information of the compliance certificate is stored and multiplexed in the renewal process, so that the renewal handling efficiency is improved, and the user experience is enhanced.

In the embodiment A, after the identity card image uploaded by the user passes the consistency check, the computer interface is provided with the option of 'whether to allow the storage of your certificate information', after the user selects the 'Yes' option, the certificate information is stored in a preset certificate information database, and in the next renewal period, the user initiates a renewal request to acquire the identity card information corresponding to the renewal request, judges whether the identity card information is in the validity period, if the identity card information is in the validity period, the user directly transacts and finishes, and then the user goes to a payment page.

In the embodiment, whether the vehicle insurance certificate image passes the automatic verification is judged through the consistency verification, so that whether the certificate corresponding to the vehicle insurance certificate image is a compliant certificate is further determined, verification efficiency is improved, verification cost is reduced, and user experience is improved.

It should be emphasized that, to further ensure the privacy and security of the credential information, user information, etc., may also be stored in a blockchain node.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a device for auditing images of a vehicle insurance certificate, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various computer devices.

As shown in fig. 3, the auditing device 300 of the vehicle insurance certificate image according to the present embodiment includes a type identification module 301, a content extraction module 302, an information verification module 303, and a compliance judgment module 304. Wherein:

the type recognition module 301 is configured to obtain a vehicle insurance certificate image to be checked, and perform type recognition on the vehicle insurance certificate image to be checked by using a pre-trained certificate type recognition model to obtain a certificate type of the vehicle insurance certificate image;

The content extraction module 302 is configured to perform content recognition on the vehicle insurance certificate image to be checked by using a pre-trained certificate content recognition model according to the certificate type, and extract certificate information of the vehicle insurance certificate image to be checked;

The information verification module 303 is configured to obtain the application information corresponding to the vehicle insurance certificate image to be verified, and perform consistency verification on the certificate information and the application information;

And the compliance judging module 304 is configured to judge that the vehicle insurance certificate image to be audited passes the automatic audit if the consistency check passes, and determine that the certificate corresponding to the vehicle insurance certificate image to be audited is a compliance certificate.

In the embodiment, the pre-trained certificate type recognition model is adopted to carry out type recognition on the vehicle insurance certificate image to be checked to obtain the certificate type of the vehicle insurance certificate image, so that the problems that the traditional manual checking mode is long in time consumption and easy to make mistakes and is difficult to deal with a large number of application and application are avoided, and the checking efficiency and accuracy in the application and application process are improved, and the user experience is improved;

According to the certificate type, a pre-trained certificate content identification model is adopted to identify the content of the vehicle insurance certificate image to be checked, the certificate information of the vehicle insurance certificate image to be checked is extracted, the problems of low efficiency and low precision caused by manual checking are avoided, the automation degree of checking is improved, the checking efficiency and accuracy are improved, detailed records are generated in the checking process of the certificate through the model, the checking has traceability, and unnecessary disputes are avoided;

by carrying out consistency verification on the certificate information and the application information, the problems of low efficiency and low precision caused by manual one-time verification are avoided, and the efficiency and accuracy of the consistency verification are improved, so that the user experience is improved;

In order to solve the technical problems, the embodiment of the application also provides equipment (computer equipment). Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only a computer device 4 having a memory 41, a processor 42, a network interface 43 is shown in the figures, but it is understood that not all illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Fieid-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is generally used for storing an operating system and various application software installed on the computer device 4, such as computer readable instructions of a pet insurance adjustment method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing an auditing method of the vehicle insurance certificate image.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

In the implementation process of the electronic equipment, the type of the vehicle insurance certificate image to be checked is identified by adopting the pre-trained certificate type identification model, so that the certificate type of the vehicle insurance certificate image is obtained, the problems that the traditional manual checking mode is long in time consumption and easy to make mistakes and is difficult to deal with a large number of application and application are avoided, and the checking efficiency and accuracy in the application and application process and the user experience are improved.

The present application also provides another embodiment, namely, a storage medium (computer readable storage medium) storing computer readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the method for auditing a vehicle insurance certificate image as described above.

In the implementation process of the computer readable storage medium, the pre-trained certificate type identification model is adopted to carry out type identification on the vehicle insurance certificate image to be checked to obtain the certificate type of the vehicle insurance certificate image, so that the problems that the traditional manual checking mode is long in time consumption and easy to make mistakes and is difficult to deal with a large number of application and application are avoided, and the checking efficiency, accuracy and user experience in the application and application process are improved.

The non-native company software tools or components present in the embodiments of the present application are presented by way of example only and are not representative of actual use.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising 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 perform the method according to the embodiments of the present application.

It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims

1. An auditing method of a vehicle insurance certificate image is characterized by comprising the following steps:

2. The method for auditing the vehicle insurance certificate image according to claim 1, wherein the performing type recognition on the vehicle insurance certificate image to be audited by adopting a pre-trained certificate type recognition model to obtain the certificate type of the vehicle insurance certificate image comprises the following steps:

3. The method for auditing the vehicle insurance certificate image according to claim 1, wherein the step of performing content recognition on the vehicle insurance certificate image to be audited by adopting a pre-trained certificate content recognition model according to the certificate type, and extracting the certificate information of the vehicle insurance certificate image to be audited comprises the following steps:

4. The method of claim 3, wherein after performing OCR processing on the content key area by the text recognition module using the pre-trained document content recognition model to extract key text of the content key area, the method further comprises:

5. The method of auditing a vehicle insurance certificate image according to claim 1, characterized in that after said extracting certificate information of said vehicle insurance certificate image to be audited, the method further comprises:

6. The method of auditing images of a vehicle insurance certificate according to claim 1, wherein said verifying the identity of the certificate information and the application information includes:

7. The method for auditing a vehicle insurance certificate image according to claim 1, wherein after said determining that a certificate corresponding to the vehicle insurance certificate image to be audited is a compliant certificate, the method further comprises:

8. An auditing apparatus for a vehicle insurance certificate image, the apparatus comprising:

9. A computer device, the computer device comprising:

At least one processor, and

A memory communicatively coupled to the at least one processor, wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of auditing images of a vehicle insurance certificate as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a method of auditing images of a vehicle insurance certificate as claimed in any one of claims 1 to 7.