Underwriting information verification method and device based on artificial intelligence, equipment and medium

Abstract

The invention relates to the field of image processing and the field of financial science and technology businesses, and discloses an artificial intelligence-based underwriting information verification method, device and equipment and a medium, and the method comprises the steps: carrying out the image recognition processing of a to-be-underwritten image through an image recognition model, and extracting the underwriting image content of the to-be-underwritten image; checking the insurance policy content in the pre-acquired insurance order and the underwriting image content to generate current underwriting information; and generating an underwriting information verification result of the to-be-underwritten image based on the historical underwriting information and the current underwriting information. According to the method, the image to be underwritten is subjected to image recognition processing, and the image to be underwritten is verified with the insurance policy content in the insurance order, so that the underwriting information can be acquired more accurately. Meanwhile, the underwriting information verification result is generated based on the historical underwriting information and the current underwriting information, so that risk control and insurance fraud prevention can be better carried out, and the underwriting efficiency in the digital financial service is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing and the field of financial technology business, and in particular to an underwriting information verification method, device, equipment and medium based on artificial intelligence. Background Art

[0002] With the rapid development of artificial intelligence technology and digital financial services, underwriting, a crucial part of traditional insurance business, has also developed rapidly along with the development of these technologies. In traditional insurance business, underwriting is the process of assessing the risk of insurance applicants and deciding whether to accept their policies. This process usually relies on insurance company underwriters to conduct manual review, data collection and risk assessment. However, with the sharp increase in data volume and the improvement of customer expectations, traditional manual underwriting methods can no longer meet the needs of quickly and accurately processing large amounts of information.

[0003] Improving the efficiency of manual underwriting is one of the key areas of technological innovation in the insurance industry. By using artificial intelligence assistance and automated process optimization and other technical means, the efficiency, accuracy and customer experience of the underwriting process can be improved. For example, image recognition is performed on the information submitted by the insured, and data such as ID number, name and address are automatically verified; and damage assessment analysis is performed on the vehicle inspection and damage assessment pictures uploaded by the insured, and total or partial damage and damage level are automatically identified to assist the underwriter in making a judgment on whether to underwrite. Therefore, how to improve the underwriting efficiency in digital financial services through artificial intelligence technology has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides an artificial intelligence-based underwriting information verification method, device, equipment and medium to improve the underwriting efficiency in digital financial services through artificial intelligence technology.

[0005] In a first aspect, the present application provides an underwriting information verification method based on artificial intelligence, the method comprising:

[0006] Performing image recognition processing on the image to be underwritten by using a preset image recognition model to extract underwriting image content of the image to be underwritten;

[0007] Generate current underwriting information based on the insurance policy content in the pre-acquired insurance order and the underwriting image content;

[0008] Based on the historical underwriting information and the current underwriting information, an underwriting information verification result of the image to be underwritten is generated. In a second aspect, the present application also provides an underwriting information verification device based on artificial intelligence, the device comprising:

[0009] An underwriting image content extraction module, used to perform image recognition processing on the image to be underwritten by using a preset image recognition model, and extract the underwriting image content of the image to be underwritten;

[0010] A current underwriting information generation module, used to generate current underwriting information based on the policy content in the pre-acquired insurance order and the underwriting image content;

[0011] The underwriting information verification result generation module is used to generate the underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information.

[0012] In a third aspect, the present application also provides a computer device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the above-mentioned artificial intelligence-based underwriting information verification method when executing the computer program.

[0013] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the above-mentioned artificial intelligence-based underwriting information verification method.

[0014] The present application discloses an artificial intelligence-based underwriting information verification method, device, equipment and medium, wherein the artificial intelligence-based underwriting information verification method includes performing image recognition processing on the image to be underwritten through a preset image recognition model, extracting the underwriting image content of the image to be underwritten; generating current underwriting information based on the policy content in the pre-acquired insurance order and the underwriting image content; generating an underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information. Through the above-mentioned method, the present application can obtain underwriting information more accurately by performing image recognition processing on the image to be underwritten and verifying it with the policy content in the insurance order. At the same time, generating an underwriting information verification result based on historical underwriting information and current underwriting information can better perform risk control and insurance fraud prevention, thereby improving the underwriting efficiency in digital financial services. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 is a schematic flow chart of an artificial intelligence-based underwriting information verification method provided in the first embodiment of the present application;

[0017] Figure 2 is a schematic flow chart of an artificial intelligence-based underwriting information verification method provided in the second embodiment of the present application;

[0018] Figure 3 is a schematic flow chart of an artificial intelligence-based underwriting information verification method provided in the third embodiment of the present application;

[0019] Figure 4 A schematic block diagram of an underwriting information verification device based on artificial intelligence provided in an embodiment of the present application;

[0020] Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0023] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0024] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] The embodiments of the present application provide an artificial intelligence-based underwriting information verification method, device, equipment and medium. Among them, the artificial intelligence-based underwriting information verification method can be applied to a server. By performing image recognition processing on the image to be underwritten and verifying it with the policy content in the insurance order, the underwriting information can be obtained more accurately. At the same time, based on the historical underwriting information and the current underwriting information, the underwriting information verification result is generated, which can better control risks and prevent insurance fraud, and improve the underwriting efficiency in digital financial services. Among them, the server can be an independent server or a server cluster.

[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0027] See also Figure 1 , Figure 1 This is a schematic flow chart of an artificial intelligence-based underwriting information verification method provided by the first embodiment of the present application. The artificial intelligence-based underwriting information verification method can be applied to a server, and is used to obtain underwriting information more accurately by performing image recognition processing on the image to be underwritten and verifying it with the policy content in the insurance order. At the same time, the underwriting information verification result is generated based on historical underwriting information and current underwriting information, which can better control risks and prevent insurance fraud, and improve the underwriting efficiency in digital financial services.

[0028] like Figure 1 As shown, the artificial intelligence-based underwriting information verification method specifically includes steps S10 to S30.

[0029] Step S10: performing image recognition processing on the image to be underwritten by using a preset image recognition model to extract underwriting image content of the image to be underwritten;

[0030] Step S20: generating current underwriting information based on the insurance policy content in the pre-acquired insurance order and the underwriting image content;

[0031] Step S30: Generate an underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information.

[0032] In one embodiment, the scenarios for manual underwriting of auto insurance are mainly divided into two categories. One is to identify the degree of damage to the vehicle logo in the photo, and the other is to verify the authenticity and correctness of the content in the certificate information uploaded by the insured. Since these two categories are the scenarios with the largest number of orders and the longest time in the traditional process, this embodiment introduces AI image recognition capabilities for these two scenarios.

[0033] The system grabs the orders that need manual review from the manual task pool, and first performs PS trace identification. If the image is found to have PS traces, it will be directly transferred to human review. Otherwise, it will determine the image type to determine whether it is an image to be reviewed or a vehicle inspection image, and then enter the subsequent task flow;

[0034] When the image to be reviewed is a document image, the pixels of the image will first be proportionally adjusted to a standard size, and then the most suitable document type will be selected by identifying the pixels in a specific area of ​​the image. For example, for an ID card, the pixels corresponding to the name area, address area, and ID card number area will be extracted to generate the field content of the corresponding document model.

[0035] Compare the field contents extracted by image recognition with the content of the order uploaded by the policyholder to determine the authenticity and correctness of the information. If the verification is passed, the underwriting is passed. If there is a field mismatch, the field attributes of the comparison difference will be prompted to the underwriter's review page. The underwriter only needs to verify the content in a targeted manner;

[0036] When the image to be underwritten is a vehicle damage image, the system matches it according to the damage model in the historical image library to determine the location and severity of the damage to the current vehicle model. It then automatically gives the result of the report with the highest similarity based on the previous manually given damage reports. Finally, the recommended report results and vehicle inspection pictures are provided to the underwriter to assist in decision-making, thereby improving the accuracy and timeliness of the underwriter's judgment. Finally, the results and pictures of the manual review are returned to the historical image library and historical manual review records again, continuously increasing the accuracy of the system's recommendations.

[0037] The present embodiment discloses an artificial intelligence-based underwriting information verification method, device, equipment and medium, the artificial intelligence-based underwriting information verification method includes performing image recognition processing on the image to be underwritten through a preset image recognition model, extracting the underwriting image content of the image to be underwritten; generating current underwriting information based on the policy content in the pre-acquired insurance order and the underwriting image content; generating an underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information. Through the above manner, the present application can obtain underwriting information more accurately by performing image recognition processing on the image to be underwritten and verifying it with the policy content in the insurance order. At the same time, generating an underwriting information verification result based on historical underwriting information and current underwriting information can better perform risk control and insurance fraud prevention, thereby improving the underwriting efficiency in digital financial services.

[0038] See also Figure 2 , Figure 2This is a schematic flow chart of an underwriting information verification method based on artificial intelligence provided in the second embodiment of the present application. The underwriting information verification method based on artificial intelligence can be applied to a server, and can more accurately determine the document type and key information of the document image to be reviewed through image recognition technology and automated processing, and verify it with the policy content in the insurance order to improve the accuracy and efficiency of underwriting. The traditional manual underwriting method is affected by human factors, such as personnel fatigue and negligence, while automated processing can reduce the impact of human factors, improve the quality of underwriting, better control risks and prevent insurance fraud, and improve the operating efficiency of insurance companies.

[0039] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S10 includes step S101 to step S102.

[0040] Step S101, performing image preprocessing on the image of the document to be verified, and determining the document type of the image of the document to be verified by using the preset image recognition model and the image of the document to be verified after the image preprocessing;

[0041] Step S102: based on the document type, extract key information of the document image to be verified, and determine the key information as the verification image content.

[0042] In one embodiment, when the image to be verified is a certificate image, the pixels of the image will first be proportionally adjusted to a standard size, and then the most suitable certificate type will be screened out by identifying the pixels in a specific area of ​​the image; for example, for an ID card, the pixels in the corresponding name area, address area, and ID card number area will be extracted to generate the field content of the corresponding certificate model.

[0043] Specifically, the image to be reviewed and approved can be preprocessed by using methods such as image enhancement, denoising, and binarization to improve image quality and facilitate subsequent processing. The image of the document to be reviewed and approved is identified using a preset image recognition model to determine its document type. The model can be a convolutional neural network (CNN) based on deep learning, which can learn the features of various document types through training and achieve automatic classification.

[0044] According to the determined document type, extract the key information of the document image to be verified. For example, if it is an ID card, extract the name, ID card number, gender, date of birth and other information; if it is a driving license, extract the license plate number, vehicle type, owner's name and other information. Use the extracted key information as the content of the underwriting image, and verify it with the policy content in the insurance order to generate the current underwriting information. Based on the historical underwriting information and the current underwriting information, generate the underwriting information verification result of the image to be verified. The authenticity and consistency of the key information can be compared to determine whether there is risk or fraud.

[0045] This embodiment discloses an underwriting information verification method, device, equipment and medium based on artificial intelligence. The underwriting information verification method based on artificial intelligence includes image preprocessing of the image of the document to be verified, determining the document type of the image of the document to be verified through the preset image recognition model and the image of the document to be verified after the image preprocessing; extracting the key information of the image of the document to be verified based on the document type, and determining the key information as the content of the underwriting image; generating current underwriting information based on the policy content in the insurance order obtained in advance and the content of the underwriting image; generating the underwriting information verification result of the image to be verified based on the historical underwriting information and the current underwriting information. In the above manner, the present application can more accurately determine the document type and key information of the image of the document to be verified through image recognition technology and automated processing, and verify it with the policy content in the insurance order, thereby improving the accuracy and efficiency of underwriting. The traditional manual underwriting method is affected by human factors, such as personnel fatigue, negligence, etc., while automated processing can reduce the impact of human factors, improve underwriting quality, better control risks and prevent insurance fraud, and improve the operating efficiency of insurance companies.

[0046] based on Figure 2 In the embodiment shown, in this embodiment, step S101 includes:

[0047] Adjusting the size of the image of the document to be verified to a preset image size;

[0048] Identify pixel points in a target area of ​​the document image to be verified of the preset image size;

[0049] The document type is determined according to the pixels of the preset area of ​​each preset document image in the preset document image library and the pixels of the target area.

[0050] In a specific embodiment, the size of the document image to be verified is adjusted to a preset image size. The preset image size can be a fixed size or a size that is adaptively adjusted according to the document type. The pixel points of the target area are identified for the adjusted document image to be verified. The pixel points of the target area can be extracted using methods based on edge detection, color segmentation, etc. The document type is determined based on the preset area pixel points and the target area pixel points of each preset document image in the preset document image library. The target area pixel points can be compared with the preset area pixel points of each preset document image to determine the document type of the document image to be verified. After determining the document type, the key information of the document image to be verified is extracted and used as the content of the verification image for subsequent processing.

[0051] In a more preferred embodiment, step S102 includes:

[0052] Generating text field information to be verified corresponding to the document image to be verified according to the pixel points in the target area;

[0053] The key information is determined according to a preset text field library and the text field information to be reviewed, and the review image content is generated according to the key information.

[0054] Specifically, the text field information to be underwritten is generated based on the pixel points in the target area. The OCR (Optical Character Recognition) technology can be used to convert the text in the image into text information. The key information is determined based on the preset text field library and the text field information to be underwritten. The preset text field library may include text fields for key information such as certificate type, name, ID number, license plate number, etc. Based on the key information, the underwriting image content is generated. The key information can be encoded or encrypted to obtain the underwriting image content. For example, the name, ID number and other information can be hashed to obtain unique underwriting image content.

[0055] The underwriting image content is verified with the policy content in the insurance order to generate the current underwriting information. The authenticity and consistency of key information can be compared to determine whether there is risk or fraud.

[0056] See also Figure 3 , Figure 3This is a schematic flow chart of an underwriting information verification method based on artificial intelligence provided in the third embodiment of the present application. The underwriting information verification method based on artificial intelligence can be applied to a server, and is used to more accurately determine the vehicle damage location and degree of damage corresponding to the vehicle damage image to be underwritten through image recognition technology and automated processing, and verify it with the policy content in the insurance order to improve the accuracy and efficiency of underwriting. The traditional manual underwriting method is affected by human factors, such as fatigue and negligence, while automated processing can reduce the impact of human factors and improve the quality and efficiency of underwriting.

[0057] based on Figure 1 The embodiment shown, this embodiment Figure 3 As shown, step S10 includes step S103 to step S104.

[0058] Step S103: based on the vehicle damage image to be insured, determining the vehicle damage position and vehicle damage degree corresponding to the vehicle damage image to be insured;

[0059] Specifically, a preset image recognition model is used to identify the vehicle damage image to be reviewed to determine the location and extent of the damage. The model can be a convolutional neural network (CNN) based on deep learning, which can learn the characteristics of various types of vehicle damage through training and achieve automatic classification.

[0060] Step S104: Based on the vehicle damage location and the vehicle damage degree, generate a vehicle damage report corresponding to the vehicle damage image to be insured, and use the vehicle damage report as the content of the insurance image.

[0061] Specifically, based on the determined vehicle damage location and degree of vehicle damage, a vehicle damage report corresponding to the vehicle damage image to be reviewed is generated. Based on the vehicle damage location and degree of vehicle damage, corresponding vehicle damage description and repair suggestions and other information can be generated. The vehicle damage report to be reviewed is used as the content of the review image, and is verified with the policy content in the insurance order to generate the current review information.

[0062] This embodiment discloses an artificial intelligence-based underwriting information verification method, device, equipment and medium, the artificial intelligence-based underwriting information verification method includes determining the vehicle damage position and vehicle damage degree corresponding to the vehicle damage image to be underwritten based on the vehicle damage image to be underwritten; generating a vehicle damage report to be underwritten corresponding to the vehicle damage image to be underwritten based on the vehicle damage position and the vehicle damage degree, and using the vehicle damage report to be underwritten as the content of the underwriting image; generating current underwriting information based on the policy content in the pre-acquired insurance order and the content of the underwriting image; generating an underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information. Through the above-mentioned method, the present application can more accurately determine the vehicle damage position and vehicle damage degree corresponding to the vehicle damage image to be underwritten through image recognition technology and automated processing, and verify it with the policy content in the insurance order, thereby improving the accuracy and efficiency of underwriting. The traditional manual underwriting method is affected by human factors, such as personnel fatigue, negligence, etc., while automated processing can reduce the impact of human factors and improve the quality and efficiency of underwriting.

[0063] based on Figure 3 In the embodiment shown, in this embodiment, step S30 includes:

[0064] Determining the historical insurance underwriting information having the highest similarity to the vehicle damage report to be underwritten from the historical vehicle damage report database;

[0065] Generating a current underwriting decision corresponding to the current underwriting information based on the historical underwriting decisions of the historical underwriting information;

[0066] The underwriting information verification result is generated based on the current underwriting decision and the current underwriting information.

[0067] In a specific embodiment, key feature information of the vehicle damage report to be insured is extracted, and the key feature information is compared one by one with each historical underwriting information in the historical vehicle damage report library, and the similarity is calculated through a specific algorithm or model to find the historical underwriting information with the highest similarity.

[0068] Analyze the historical underwriting decisions corresponding to the historical underwriting information and based on the historical underwriting decisions and the specific circumstances of the current underwriting information, generate a current underwriting decision corresponding to the current underwriting information.

[0069] Comprehensively analyze and evaluate the current underwriting decision and the current underwriting information, and generate an underwriting information verification result based on the evaluation result to indicate the underwriting status and conclusion of the vehicle damage report to be underwritten.

[0070] Based on any of the above embodiments, in this embodiment, before step S10, the following steps are included:

[0071] Detecting whether the image to be reviewed has traces of image processing;

[0072] In the case that the image to be approved does not have the image processing trace, the step of starting: performing image recognition processing on the image to be approved by using a preset image recognition model to extract the approved image content of the image to be approved;

[0073] In the case that the image to be reviewed has traces of image processing, the image to be reviewed is verified by offline review.

[0074] Specifically, the system grabs the orders that need manual review from the manual task pool, and first performs image processing trace recognition. If an image with image processing traces is identified, it will be directly transferred to real-person review. Otherwise, the image type will be determined to determine whether it is an image to be reviewed or a vehicle inspection image, and then the subsequent task flow will be entered.

[0075] See also Figure 4 , Figure 4 The embodiment of the present application provides a schematic block diagram of an underwriting information verification device based on artificial intelligence, and the underwriting information verification device based on artificial intelligence is used to execute the above-mentioned underwriting information verification method based on artificial intelligence. Among them, the underwriting information verification device based on artificial intelligence can be configured on a server.

[0076] like Figure 4 As shown, the underwriting information verification device based on artificial intelligence includes:

[0077] An underwriting image content extraction module 410 is used to perform image recognition processing on the image to be underwritten by using a preset image recognition model, and extract the underwriting image content of the image to be underwritten;

[0078] The current underwriting information generating module 420 is used to generate the current underwriting information based on the policy content in the pre-acquired insurance order and the underwriting image content;

[0079] The underwriting information verification result generating module 430 is used to generate the underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information.

[0080] Furthermore, the underwriting image content extraction module 410 includes:

[0081] A document type determination unit, configured to perform image preprocessing on the document image to be verified, and determine the document type of the document image to be verified by using the preset image recognition model and the document image to be verified after the image preprocessing;

[0082] The underwriting image content determination unit is used to extract key information of the document image to be verified based on the document type, and determine the key information as the underwriting image content.

[0083] Furthermore, the certificate type determination unit includes:

[0084] A size adjustment subunit, used for adjusting the size of the image of the document to be verified to a preset image size;

[0085] A target area pixel point recognition subunit, used to recognize the target area pixel points of the document image to be verified of the preset image size;

[0086] The certificate type determination subunit is used to determine the certificate type according to the preset area pixel points of each preset certificate image in the preset certificate image library and the target area pixel points.

[0087] Furthermore, the underwriting image content determination unit includes:

[0088] A text field information generation subunit for to-be-verified is used to generate text field information for to-be-verified corresponding to the document image for to-be-verified according to the pixel points of the target area;

[0089] The underwriting image content generating subunit is used to determine the key information according to a preset text field library and the text field information to be underwritten, and to generate the underwriting image content according to the key information.

[0090] Furthermore, the underwriting image content extraction module 410 includes:

[0091] A vehicle damage determination unit, configured to determine a vehicle damage position and a vehicle damage degree corresponding to the vehicle damage image to be insured based on the vehicle damage image to be insured;

[0092] The underwriting image content determination unit is used to generate a vehicle damage report to be insured corresponding to the vehicle damage image to be insured based on the vehicle damage location and the vehicle damage degree, and use the vehicle damage report to be insured as the underwriting image content.

[0093] Furthermore, the underwriting information verification result generation module 430 includes:

[0094] A historical underwriting information determination unit, configured to determine the historical underwriting information having the highest similarity to the vehicle damage report to be underwritten from a historical vehicle damage report database;

[0095] A current underwriting decision generating unit, configured to generate a current underwriting decision corresponding to the current underwriting information according to the historical underwriting decisions of the historical underwriting information;

[0096] The underwriting information verification result generating unit is used to generate the underwriting information verification result according to the current underwriting decision and the current underwriting information.

[0097] Furthermore, the artificial intelligence-based underwriting information verification device includes:

[0098] An image processing trace detection module is used to detect whether the image to be reviewed and approved has image processing traces;

[0099] A first review module is used for, when the image to be reviewed does not have the image processing trace, starting the step of: performing image recognition processing on the image to be reviewed by using a preset image recognition model to extract the review image content of the image to be reviewed;

[0100] The second review module is used to verify the image to be reviewed by means of offline review if there are traces of image processing in the image to be reviewed.

[0101] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0102] The above-mentioned device can be implemented in the form of a computer program. Figure 5 Runs on the computer device shown.

[0103] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0104] See also Figure 5 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0105] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any artificial intelligence-based underwriting information verification method.

[0106] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0107] The internal memory provides an environment for the operation of computer programs in non-volatile storage media. When the computer program is executed by the processor, the processor can execute any artificial intelligence-based underwriting information verification method.

[0108] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0110] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0111] Performing image recognition processing on the image to be underwritten by using a preset image recognition model to extract underwriting image content of the image to be underwritten;

[0112] Generate current underwriting information based on the insurance policy content in the pre-acquired insurance order and the underwriting image content;

[0113] Based on the historical underwriting information and the current underwriting information, an underwriting information verification result of the image to be underwritten is generated.

[0114] In one embodiment, the image to be approved is processed by a preset image recognition model to extract the approved image content of the image to be approved, so as to achieve:

[0115] Performing image preprocessing on the image of the document to be verified, and determining the document type of the image of the document to be verified by using the preset image recognition model and the image of the document to be verified after the image preprocessing;

[0116] Based on the document type, key information of the document image to be verified is extracted, and the key information is determined as the verification image content.

[0117] In one embodiment, the image of the document to be verified is subjected to image preprocessing, and the document type of the image of the document to be verified is determined by using the preset image recognition model and the image of the document to be verified after the image preprocessing, so as to achieve:

[0118] Adjusting the size of the image of the document to be verified to a preset image size;

[0119] Identify pixel points in a target area of ​​the document image to be verified of the preset image size;

[0120] The document type is determined according to the pixels of the preset area of ​​each preset document image in the preset document image library and the pixels of the target area.

[0121] In one embodiment, based on the document type, key information of the document image to be verified is extracted, and the key information is determined as the verification image content, so as to achieve:

[0122] Generating text field information to be verified corresponding to the document image to be verified according to the pixel points in the target area;

[0123] The key information is determined according to a preset text field library and the text field information to be reviewed, and the review image content is generated according to the key information.

[0124] In one embodiment, the image to be approved is processed by a preset image recognition model to extract the approved image content of the image to be approved, so as to achieve:

[0125] Based on the vehicle damage image to be insured, determine the vehicle damage location and vehicle damage degree corresponding to the vehicle damage image to be insured;

[0126] Based on the vehicle damage location and the vehicle damage extent, a vehicle damage report to be insured corresponding to the vehicle damage image to be insured is generated, and the vehicle damage report to be insured is used as the content of the insurance image.

[0127] In one embodiment, based on the historical underwriting information and the current underwriting information, an underwriting information verification result of the image to be underwritten is generated to achieve:

[0128] Determining the historical insurance underwriting information having the highest similarity to the vehicle damage report to be underwritten from the historical vehicle damage report database;

[0129] Generating a current underwriting decision corresponding to the current underwriting information based on the historical underwriting decisions of the historical underwriting information;

[0130] The underwriting information verification result is generated based on the current underwriting decision and the current underwriting information.

[0131] In one embodiment, the image to be approved is processed by a preset image recognition model, and before the approved image content of the image to be approved is extracted, it is used to achieve:

[0132] Detecting whether the image to be reviewed has traces of image processing;

[0133] In the case that the image to be approved does not have the image processing trace, the step of starting: performing image recognition processing on the image to be approved by using a preset image recognition model to extract the approved image content of the image to be approved;

[0134] In the case that the image to be reviewed has traces of image processing, the image to be reviewed is verified by offline review.

[0135] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the artificial intelligence-based underwriting information verification methods provided in the embodiments of the present application.

[0136] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Medi a Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), etc., equipped on the computer device.

[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An artificial intelligence-based underwriting information verification method, characterized in that: include: Performing image recognition processing on the image to be underwritten by using a preset image recognition model to extract underwriting image content of the image to be underwritten; Generate current underwriting information based on the insurance policy content in the pre-acquired insurance order and the underwriting image content; Based on the historical underwriting information and the current underwriting information, an underwriting information verification result of the image to be underwritten is generated.

2. The artificial intelligence-based underwriting information verification method according to claim 1, characterized in that: The image to be reviewed includes a document image to be reviewed, and performing image recognition processing on the image to be reviewed by using a preset image recognition model to extract the review image content of the image to be reviewed includes: Performing image preprocessing on the image of the document to be verified, and determining the document type of the image of the document to be verified by using the preset image recognition model and the image of the document to be verified after the image preprocessing; Based on the document type, key information of the document image to be verified is extracted, and the key information is determined as the verification image content.

3. The artificial intelligence-based underwriting information verification method according to claim 2, characterized in that: The performing image preprocessing on the image of the document to be verified, and determining the document type of the image of the document to be verified by using the preset image recognition model and the image of the document to be verified after the image preprocessing, comprises: Adjusting the size of the image of the document to be verified to a preset image size; Identify pixel points in a target area of ​​the document image to be verified of the preset image size; The document type is determined according to the pixels of the preset area of ​​each preset document image in the preset document image library and the pixels of the target area.

4. The artificial intelligence-based underwriting information verification method according to claim 3, characterized in that: The extracting key information of the image of the document to be verified based on the document type, and determining the key information as the content of the verification image, includes: Generating text field information to be verified corresponding to the document image to be verified according to the pixel points in the target area; The key information is determined according to a preset text field library and the text field information to be reviewed, and the review image content is generated according to the key information.

5. The artificial intelligence-based underwriting information verification method according to claim 1, characterized in that: The image to be insured includes a vehicle damage image to be insured, and performing image recognition processing on the image to be insured by using a preset image recognition model to extract the insured image content of the image to be insured includes: Based on the vehicle damage image to be insured, determine the vehicle damage location and vehicle damage degree corresponding to the vehicle damage image to be insured; Based on the vehicle damage location and the vehicle damage extent, a vehicle damage report to be insured corresponding to the vehicle damage image to be insured is generated, and the vehicle damage report to be insured is used as the content of the insurance image.

6. The artificial intelligence-based underwriting information verification method according to claim 5, characterized in that: The generating the underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information includes: Determining the historical insurance underwriting information having the highest similarity to the vehicle damage report to be underwritten from the historical vehicle damage report database; Generating a current underwriting decision corresponding to the current underwriting information based on the historical underwriting decisions of the historical underwriting information; The underwriting information verification result is generated based on the current underwriting decision and the current underwriting information.

7. The artificial intelligence-based underwriting information verification method according to any one of claims 1 to 6, characterized in that: Before performing image recognition processing on the image to be underwritten by using a preset image recognition model and extracting the underwriting image content of the image to be underwritten, the method includes: Detecting whether the image to be reviewed has traces of image processing; In the case that the image to be approved does not have the image processing trace, the step of starting: performing image recognition processing on the image to be approved by using a preset image recognition model to extract the approved image content of the image to be approved; In the case that the image to be reviewed has traces of image processing, the image to be reviewed is verified by offline review.

8. An underwriting information verification device based on artificial intelligence, characterized in that: include: An underwriting image content extraction module, used to perform image recognition processing on the image to be underwritten by using a preset image recognition model, and extract the underwriting image content of the image to be underwritten; A current underwriting information generation module, used to generate current underwriting information based on the policy content in the pre-acquired insurance order and the underwriting image content; The underwriting information verification result generation module is used to generate the underwriting information verification result of the image to be underwritten based on the historical underwriting information and the current underwriting information.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the artificial intelligence-based underwriting information verification method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the artificial intelligence-based underwriting information verification method as described in any one of claims 1 to 7.

Images