Data processing method and device, equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a data processing method and device, equipment and a computer readable storage medium. The method comprises the steps that a to-be-verified picture corresponding to a target vehicle is acquired, the to-be-verified picture at least comprises certification information corresponding to the target vehicle and signature information corresponding to the certification information, then light and shadow analysis processing is carried out on the to-be-verified picture through a light and shadow analysis model, and a light and shadow effect score of the to-be-verified picture is obtained; the method comprises the following steps: firstly, obtaining a to-be-verified picture, verifying the signature information to obtain a verification result corresponding to the signature information, and then, determining a risk assessment result of the to-be-verified picture according to a shadow effect score of the to-be-verified picture and the verification result corresponding to the signature information.

Description

Technical Field

[0001] This application relates to information security technology, and more particularly to a data processing method, apparatus, device, and computer-readable storage medium. Background Technology

[0002] With the development of digital information, some enterprises need to verify business information during their operations to ensure information security. For example, in the automotive sales industry, it is often necessary to verify and bind vehicle certificates of conformity when conducting vehicle sales transactions.

[0003] In related technologies, images of certificates of conformity are typically sent to verification staff via pre-set social media software, who then manually verify the content of the images.

[0004] However, the image processing methods in related technologies suffer from low processing efficiency. Summary of the Invention

[0005] This application provides a data processing method, apparatus, device, and computer-readable storage medium that can improve data processing efficiency.

[0006] The technical solution of this application embodiment is implemented as follows: In a first aspect, embodiments of this application provide a data processing method, the method comprising: Obtain the image to be verified corresponding to the target vehicle. The image to be verified must include at least the certificate of conformity information corresponding to the target vehicle and the signature information corresponding to the certificate of conformity information. The light and shadow analysis model is used to analyze and process the light and shadow effects of the image to be verified, and the light and shadow effect score of the image to be verified is obtained. Verify the signature information to obtain the verification result corresponding to the signature information; Based on the lighting effect score of the image to be verified and the verification results corresponding to the signature information, the risk assessment result of the image to be verified is determined.

[0007] Secondly, embodiments of this application provide a data processing apparatus, including: The acquisition module is used to acquire the image to be verified corresponding to the target vehicle. The image to be verified includes at least the certificate information corresponding to the target vehicle and the signature information corresponding to the certificate information. The light and shadow analysis module is used to perform light and shadow analysis on the image to be verified using a light and shadow analysis model, and obtain a light and shadow effect score for the image to be verified. The signature verification module is used to verify the correctness of the signature information and obtain the verification result corresponding to the signature information. The risk assessment module is used to determine the risk assessment result of the image to be verified based on the lighting effect score of the image and the verification result corresponding to the signature information.

[0008] Thirdly, embodiments of this application provide a computer device including a memory and a processor. The memory stores a computer program that can run on the processor, and the processor executes the computer program as any step in the methods described above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the data processing method provided in embodiments of this application when executed by a processor.

[0010] This application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, they implement the data processing method provided in this application.

[0011] This application provides a data processing scheme, specifically including a data processing method, apparatus, device, and computer-readable storage medium. The data processing method includes at least: acquiring a verification image of a target vehicle, wherein the verification image includes at least the vehicle's certificate of conformity information and the signature information corresponding to the certificate of conformity information; then, performing light and shadow analysis processing on the verification image using a light and shadow analysis model to obtain a light and shadow effect score for the verification image; and verifying the signature information to obtain a verification result corresponding to the signature information. Finally, based on the light and shadow effect score of the verification image and the verification result corresponding to the signature information, the risk assessment result of the verification image can be determined.

[0012] In the above embodiments, the images of the certificate information are inspected automatically. During the verification process, not only is the corresponding signature information verified, but the lighting and shadow effects when the image was captured are also analyzed and scored. The risk assessment result of the image to be verified is determined by combining the verification results of the signature information and the lighting and shadow effect score. On the one hand, compared with the manual verification method in related technologies, the technical solution provided by this application improves the processing efficiency of the images to be verified through automation. On the other hand, the automatic assessment of whether the images to be verified have security risks such as forgery or tampering based on the verification results of the signature information and the lighting and shadow effect score further improves the accuracy and objectivity of the image processing process.

[0013] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of this application. Attached Figure Description

[0014] Figure 1 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 1 ; Figure 2 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 2 ; Figure 3 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 3 ; Figure 4 This application provides a schematic diagram of a verification process. Figure 5 This is a schematic diagram of the composition structure of a temperature data processing device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the hardware entity of a computer device provided in an embodiment of this application.

[0015] It should be noted that the terms "first" and "second" mentioned above are only used to distinguish between different options and do not represent the degree of superiority or inferiority of the options or their priority in the implementation process. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application are further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] In the following description, references to "some embodiments" refer to a subset of all possible embodiments. It is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0018] Unless otherwise defined, 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 pertains. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this application.

[0019] With the widespread application of digital technology in the automotive sales sector, the demand for automated vehicle information processing is increasing. As a crucial document confirming vehicle legality, the verification and binding process of the vehicle certificate of conformity significantly impacts business efficiency and accuracy. Currently, related data processing relies heavily on manual operation, resulting in low efficiency and susceptibility to errors. A more efficient and reliable technological approach is urgently needed to improve overall processing capabilities.

[0020] In related technologies, key fields in images are typically identified manually and compared to verify certificate information. For example, staff need to check information such as vehicle model and VIN in the image and match them one by one with the purchase contract and order system. In addition, some solutions introduce image recognition technology for preliminary extraction of text content, but lack an image quality assessment mechanism, making it difficult to effectively identify image quality problems caused by uneven lighting, blurriness, etc., thus affecting the reliability of signature verification and overall risk assessment.

[0021] While the above methods improve processing efficiency to some extent, they still have problems such as insufficient image quality assessment, unstable signature verification results, and a single dimension of overall risk assessment, which cannot meet the needs of high-precision and high-stability data processing.

[0022] In view of this, embodiments of this application provide a data processing method, apparatus, device, and computer-readable storage medium. The data processing method includes at least: acquiring a verification image corresponding to a target vehicle, wherein the verification image includes at least the vehicle's certificate of conformity information and the signature information corresponding to the certificate of conformity information; then, performing light and shadow analysis processing on the verification image using a light and shadow analysis model to obtain a light and shadow effect score for the verification image; verifying the signature information to obtain a verification result corresponding to the signature information; and finally, determining the risk assessment result of the verification image based on the light and shadow effect score of the verification image and the verification result corresponding to the signature information.

[0023] In the above embodiments, the images of the certificate information are inspected automatically. During the verification process, not only is the corresponding signature information verified, but the lighting and shadow effects when the image was captured are also analyzed and scored. The risk assessment result of the image to be verified is determined by combining the verification results of the signature information and the lighting and shadow effect score. On the one hand, compared with the manual verification method in related technologies, the technical solution provided by this application improves the processing efficiency of the images to be verified through automation. On the other hand, the automatic assessment of whether the images to be verified have security risks such as forgery or tampering based on the verification results of the signature information and the lighting and shadow effect score further improves the accuracy and objectivity of the image processing process.

[0024] This application provides a data processing method that can be applied to computer devices with independent data processing capabilities. These devices may include, but are not limited to, servers, laptops, tablets, desktop computers, smart TVs, set-top boxes, mobile devices (such as mobile phones, portable video players, personal digital assistants, dedicated messaging devices, portable gaming devices), and smart vehicles (cars, sports cars, SUVs, commercial vehicles, engineering vehicles, etc.).

[0025] Figure 1 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 1 ,like Figure 1 As shown, the method includes the following steps S101 to S104: Step S101: Obtain the image to be verified corresponding to the target vehicle.

[0026] The images to be verified must include at least the certificate of conformity information corresponding to the target vehicle and the signature information corresponding to the certificate of conformity information.

[0027] Here, the target vehicle may refer to, but is not limited to, a specific vehicle that needs to complete the certificate verification. The information corresponding to the target vehicle usually includes key fields such as the chassis number, model number, and engine number.

[0028] Here, the image to be verified may be, but is not limited to, image data used to verify the target vehicle. In this embodiment, the image to be verified may, but may not, include the vehicle's certificate of conformity information and signature information generated based on the certificate of conformity information. It is understood that the certificate of conformity information may include information corresponding to the target vehicle, including but not limited to the vehicle identification number (VIN), model number, and engine number; the signature information may be a digital signature generated based on the specific content of the certificate of conformity information, which may be added to the image during its generation.

[0029] Regarding the method of obtaining the image to be verified, in one possible implementation, the user can upload the image to be verified through an external input device connected to the computer device, so that the computer device can obtain the image to be verified.

[0030] It is understandable that users may not be able to directly upload the image to be verified through a device connected to a computer. In some scenarios, users usually transmit the image of the certificate information through some specific social software, so that the computer device can obtain the image to be verified including the certificate information transmitted by the user. Therefore, in another possible implementation, the process of step S101 "obtaining the image to be verified corresponding to the target vehicle" may include: detecting the storage space corresponding to the target software through a first preset interface to obtain the image to be verified.

[0031] Here, the target software may be, but is not limited to, software that enables data interaction between computer devices and other user devices.

[0032] In this embodiment of the application, the image to be verified can be obtained from the target software through a first preset interface.

[0033] Here, the first preset interface can be a communication protocol interface or application programming interface (API) pre-defined for the target software. Through the first preset interface, the computer device can perform real-time detection of the storage space corresponding to the target software, thereby scanning whether a user has sent an image to be verified.

[0034] The storage space corresponding to the target software may, but is not limited to, a pre-defined standard path or folder within the target software for storing specific types of files (such as vehicle certificate images). In this embodiment, a unified storage path can be configured according to pre-defined business rules, enabling the target software to store and manage all different types of data for subsequent automated processing. In some examples, the target software is a social media application that can uniformly store data sent by specific social groups or users in a corresponding data folder. The storage location of this data folder is the storage space corresponding to the target software that can be detected. The data sent by the specific social group or user may, but is not limited to, images to be verified.

[0035] Regarding the process of identifying the image to be verified through the first preset interface, in some embodiments, a preset recognition model can be used to identify newly stored images in the storage space corresponding to the target software, thereby determining whether the image is the image to be verified corresponding to the certificate of conformity. This preset recognition model can be a binary classification model, etc., to accurately read the image to be verified corresponding to the certificate of conformity.

[0036] In this embodiment, the storage space corresponding to the target software is detected through a first preset interface. This allows for automatic identification and download of the image to be verified, eliminating the need for manual searching or filtering. The process of detecting the storage space corresponding to the target software through the first preset interface and automatically identifying and extracting compliant certificate images not only improves information acquisition efficiency but also avoids omissions or errors caused by human negligence. Furthermore, accessing the data through the first preset interface instead of manual operation ensures the compliance and security of the data source.

[0037] It is understandable that before the computer device obtains the image to be verified through the first preset interface, the image to be verified is obtained by processing the certificate image. Regarding the generation process of the image to be verified, in one possible implementation, the certificate image is processed to add a corresponding digital signature, thereby generating the processed image to be verified.

[0038] In this application embodiment, regarding the process of adding a digital signature to the certificate of conformity image, in some embodiments, the text content on the certificate of conformity image can be recognized according to a preset recognition method to obtain the corresponding certificate of conformity information. It is understood that this certificate of conformity information may include, but is not limited to, vehicle identification number (VIN), model number, engine number, and other information unique to the target vehicle. Regarding the recognition method, for example, it can be to recognize the certificate of conformity image using a text recognition model. In this application embodiment, to facilitate subsequent processing, after recognizing the certificate of conformity information, it can be output according to a preset structure. It is understood that due to the confusion between some letters and numbers, based on some rules governing the composition of certificate of conformity information, such as the VIN, certain character conversion work can be performed on the recognized VIN string. The character conversion content can be referred to in the following table: Table 1

[0039] As shown in Table 1, the uppercase letter O can be converted to the number 0, the uppercase letter I to the number 1, the uppercase letter Q to the number 9, and the uppercase letter Z to the number 2.

[0040] Then, based on the certificate information, a code to be signed can be generated. This code can be obtained through a preset code mapping method, such as BASE64 encoding. After obtaining the code to be signed, it can be signed according to a preset signature algorithm to obtain a digital signature. After obtaining the digital signature, it can be attached to a preset position on the certificate image according to a preset format. This preset format can be, for example, font size, watermark format, etc. The preset position can be the lower right corner of the image or other positions, and the number of lines can be multiple.

[0041] In this way, by adding a digital signature to the certificate image, the image to be verified can be obtained. It can be understood that in addition to the certificate information and digital signature corresponding to the certificate image, the image to be verified can also carry some metadata information, such as the production factory and the shooting time.

[0042] In this embodiment, after acquiring the image to be verified, the computer device first identifies the image to extract the certificate information and signature information. Regarding the identification process, in this embodiment, a trained text recognition model can be used to extract text from the image to obtain the digital signature and certificate information.

[0043] Regarding the training process of the text recognition model, a preset model can be selected as the base model, and supervised fine-tuning can be performed based on different images. For the parameter settings in the specific fine-tuning process, such as the number of training sample items, batch size, and learning rate, these parameters can be set according to the actual application scenario. In some examples, the following table can be used as a reference for setting: Table 2

[0044] Step S102: Perform light and shadow analysis on the image to be verified using a light and shadow analysis model to obtain a light and shadow effect score for the image to be verified.

[0045] Here, the light and shadow analysis model can be, but is not limited to, a deep learning-based image quality assessment model. The light and shadow analysis model can provide a comprehensive score by quantitatively analyzing features such as illumination uniformity, shadow distribution, and contrast in an image.

[0046] In this embodiment of the application, by performing light and shadow analysis on the image to be verified, a score for the light and shadow effect of the certificate in the image to be verified can be obtained.

[0047] Understandably, certificates of conformity are often produced in batches. Based on the light and shadow effect score of the certificate of conformity in the image to be verified, it can be compared with the light and shadow effect scores of other certificates of conformity in the same batch. This allows us to determine whether the difference between the light and shadow effect scores of the certificate of conformity in the image to be verified and other certificates of conformity in the same batch meets the requirements. If it does, it can be determined that the certificate of conformity in the image to be verified has not been tampered with or is not at risk.

[0048] In this embodiment of the application, the branch range of the light and shadow effect score can be set according to a preset precision, for example, the range can be 1-10 points; when comparing, a difference threshold can be set to determine whether the difference between the light and shadow effect scores of the certificate of conformity in the image to be verified and other certificates of conformity in the same batch meets the requirements. For example, when it is determined that the difference between the light and shadow effect scores of the certificate of conformity in the image to be verified and other certificates of conformity in the same batch exceeds the preset difference threshold (1 point or 2 points, which can be set according to the actual application scenario), it can be determined that there is a security risk in the certificate of conformity in the image to be verified.

[0049] In this embodiment, the lighting analysis model is trained based on a lightweight convolutional neural network architecture and adjusted through supervised fine-tuning, thereby enabling the model to possess strong lighting perception capabilities. In this embodiment, researchers selected a preset base model and optimized its parameters based on the lighting features in the certificate image, allowing the lighting analysis model to stably output reliable scoring results under different lighting conditions.

[0050] Step S103: Verify the signature information to obtain the verification result corresponding to the signature information.

[0051] In this embodiment, the identified signature information can be compared with the signature corresponding to the original file to obtain a verification result. Here, the verification result can be used to characterize whether the image to be verified is at risk of being tampered with, and can include verification passed or verification failed.

[0052] In one possible implementation, the computer device can obtain the signature of the original file and then compare it with the signature information identified in the image to be verified, thereby determining whether there is a security risk. In some examples, if the signature information identified in the image to be verified matches the signature of the original file, it indicates that the image to be verified has not been tampered with, and the verification result is determined to be successful; if the signature information identified in the image to be verified does not match the signature of the original file, it is determined that the image to be verified has been tampered with during transmission or recognition.

[0053] In this embodiment of the application, the recognition of signature information can be based on a pre-trained recognition model. Regarding the recognition process, a trained text recognition model can be used to extract text from the image to be verified, thereby obtaining the digital signature and certificate information in the image to be verified.

[0054] Step S104: Determine the risk assessment result of the image to be verified based on the light and shadow effect score of the image to be verified and the verification result corresponding to the signature information.

[0055] Here, the risk assessment result can be, but is not limited to, a comprehensive judgment on whether the image to be verified has any abnormal risks, and is mainly determined based on two dimensions: the lighting effect score and the signature verification result.

[0056] Understandably, the risk assessment result can include either "pass" or "fail". If the risk assessment result is "pass", it can be determined that the image to be verified does not have any abnormal risks. If the risk assessment result is "fail", it can be determined that the image to be verified has any abnormal risks.

[0057] In some examples, when the risk assessment result is that the assessment fails, the computer device can generate a risk warning message and display the message to indicate that the image to be verified has an information security problem.

[0058] Regarding the process of determining the risk assessment result of the image to be verified based on the verification results corresponding to the light and shadow effect score and signature information of the image to be verified, in one possible implementation, the verification results corresponding to the light and shadow effect score and signature information can be directly input into a preset risk assessment model to obtain the risk assessment result output by the model.

[0059] In another possible implementation, the lighting effect score of the image to be verified can be compared with the lighting effect score of the certificates of conformity in the same batch to determine if the difference is too large. If the difference is too large, it can be determined that the image to be verified is at risk of being tampered with. Therefore, a comprehensive evaluation can be conducted based on the comparison results between the lighting effect scores of the image to be verified and the lighting effect scores of the certificates of conformity in the same batch, as well as the verification results corresponding to the signature information, resulting in a more accurate risk assessment.

[0060] Understandably, the generation of the above risk assessment results relies on the synergistic effect of lighting analysis and signature verification. Lighting analysis provides objective indicators of image quality, while signature verification ensures the integrity of image content. The combination of lighting analysis and signature verification enables the system to effectively identify potential risks without affecting processing efficiency, thereby improving the overall security and accuracy of processing.

[0061] In the above embodiments, the images of the certificate information are inspected automatically. During the verification process, not only is the corresponding signature information verified, but the lighting and shadow effects when the image was captured are also analyzed and scored. The risk assessment result of the image to be verified is determined by combining the verification results of the signature information and the lighting and shadow effect score. On the one hand, compared with the manual verification method in related technologies, the technical solution provided by this application improves the processing efficiency of the images to be verified through automation. On the other hand, the automatic assessment of whether the images to be verified have security risks such as forgery or tampering based on the verification results of the signature information and the lighting and shadow effect score further improves the accuracy and objectivity of the image processing process.

[0062] Figure 2 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 2 ,like Figure 2 As shown, the process of step S104 above, "determining the risk assessment result of the image to be verified based on the light and shadow effect score of the image to be verified and the verification result corresponding to the signature information," may include the following steps: Step S201: Determine at least one associated image that is related to the image to be verified.

[0063] Among them, the associated images are those produced in the same batch as the images to be verified.

[0064] It is understandable that the images of the certificates of conformity for each vehicle are usually produced in batches. Here, the certificate of conformity information in the associated image and the certificate of conformity information in the image to be verified are from the same batch.

[0065] In one possible implementation, the computer device can directly obtain the associated images corresponding to the certificate information of the same batch through an external input device.

[0066] In another possible implementation, the computer device can retrieve pre-archived associated images from a preset storage space (such as a storage location on a hard drive or in memory).

[0067] Understandably, the certificate of conformity information corresponding to the image to be verified also includes data such as production time or production batch code that can uniquely identify its production batch, thereby determining at least one associated image based on this data.

[0068] Step S202: Obtain the lighting effect score corresponding to each associated image.

[0069] Regarding the process of obtaining the scores for each lighting and shadow effect, in one possible implementation, the lighting and shadow analysis of each associated image can be performed based on a lighting and shadow analysis model to obtain the lighting and shadow effect scores corresponding to each associated image.

[0070] Here, the light and shadow analysis model can be, but is not limited to, a deep learning-based image quality assessment model. The light and shadow analysis model can provide a comprehensive score by quantitatively analyzing features such as illumination uniformity, shadow distribution, and contrast in an image.

[0071] In another possible implementation, each associated image and its corresponding lighting effect score are stored together. Therefore, when obtaining an associated image, the lighting effect score corresponding to each associated image can be obtained directly.

[0072] Step S203: Evaluate the verification results based on the lighting effect score of the image to be verified and the lighting effect scores of each associated image, and determine the risk assessment result corresponding to the image to be verified.

[0073] It is understandable that the risk assessment results can be, but are not limited to, a comprehensive judgment on whether the image being verified has any abnormal risks, and are mainly determined based on two dimensions: the lighting effect score and the signature verification results.

[0074] In this embodiment of the application, the risk assessment result may include assessment passed or assessment failed. When the risk assessment result is assessment passed, it can be determined that the image to be verified does not have any abnormal risks. When the risk assessment result is assessment failed, it can be determined that the image to be verified has abnormal risks.

[0075] Regarding the process of evaluating the verification results based on the lighting effect scores of the image to be verified and the lighting effect scores of each associated image, and determining the risk assessment result corresponding to the image to be verified, in one possible implementation, when there are multiple associated images, the standard value of the lighting effect of the certificate information of the same batch as the image to be verified can be determined first based on the lighting effect of each associated image. Based on this standard value, the lighting effect score of the image to be verified can be evaluated to determine whether the difference between the lighting effect score of the image to be verified and the associated images in the same batch is too large. Based on this result, the verification result corresponding to the signature information is evaluated to determine the risk assessment result corresponding to the image to be verified.

[0076] In another possible implementation, the process of "evaluating the verification results based on the lighting effect score of the image to be verified and the lighting effect scores of each associated image, and determining the risk assessment result corresponding to the image to be verified" in step S203 above may include the following steps: Step S2031: Based on the difference between the lighting effect score of the image to be verified and the lighting effect scores of each associated image, determine whether the image to be verified is produced in the same batch as the associated images.

[0077] If, in step S2032, the image to be verified and the associated image are produced in the same batch, and the verification result is successful, then the risk assessment result of the image to be verified is determined to be passed.

[0078] Step S2033: If the image to be verified and the associated image are not produced in the same batch, or if the verification result is verification failure, then the risk assessment result of the image to be verified is determined to be assessment failure.

[0079] Here, the lighting effect score refers to the numerical value obtained by quantifying and evaluating the visual features of an image, such as light intensity, shadow distribution, and contrast, through an image processing model. The lighting effect score measures the overall brightness and light consistency of an image, typically ranging from 1 to 10 points. The differences in lighting effect scores among certificate images produced in the same batch will be within a preset threshold. In this embodiment, the lighting effect score can be, but is not limited to, the result output after analyzing and processing the image based on a preset lighting effect analysis model. The training objective of the lighting effect score is to identify the differences in lighting between different production batches, thereby assisting in determining whether images belong to the same batch.

[0080] Therefore, in this embodiment, the difference between the lighting effect score of the image to be verified and the lighting effect scores of each associated image can be detected to determine whether the image to be verified is produced in the same batch as the associated images. When the difference between the lighting effect score of the image to be verified and the lighting effect scores of each associated image is less than a certain preset threshold, it can be determined that the image to be verified and the associated images have the same characteristics as each other from the same batch; if the difference between the lighting effect score of the image to be verified and the lighting effect scores of each associated image is greater than the preset threshold, it can be determined that the image to be verified and the associated images are not produced in the same batch, and there is a risk of tampering.

[0081] Understandably, only when it is confirmed that the image to be verified and all related images are produced in the same batch, and the verification result of the signature information is successful, can it be determined from multiple aspects that the image to be verified is not at risk of being tampered with. At this point, the risk assessment result can be determined as passed.

[0082] If the image to be verified and the associated image are not from the same batch, or if the verification result is verification failure, it can be determined that the image to be verified is at risk of being tampered with. In this case, the risk assessment result is determined to be assessment failure.

[0083] In this embodiment of the application, when the risk assessment result is that the assessment fails, a risk warning message can be generated to remind the user that the image to be verified has an information security problem.

[0084] In the above embodiments, by introducing the concept of associated images and combining them with the lighting effect score for cross-comparison, it is possible to more accurately identify whether there are any abnormalities or tampering traces in the image, thereby improving the credibility of image verification and optimizing the efficiency and security of the entire certificate verification process.

[0085] Figure 3 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 3 ,like Figure 3 As shown, the data processing method provided in this application may further include the following steps: Step S301: If the risk assessment result is that the assessment is passed, determine the first vehicle information corresponding to the target vehicle based on the certificate information in the image to be verified.

[0086] In this embodiment of the application, if the risk assessment result of the image to be verified is that the assessment is passed, the relevant binding log of the image to be verified can be generated to facilitate subsequent business development.

[0087] However, if the risk assessment result of the image to be verified is "passed", it is impossible to determine whether there is a risk of tampering with the certificate information in the image to be verified. Therefore, it is necessary to verify the first vehicle information corresponding to the certificate information in the image to be verified.

[0088] In this embodiment of the application, the first vehicle information is the geometry of key information identifying the target vehicle included in the certificate information in the image to be verified, including at least the chassis number, model number, engine number, etc.

[0089] In one possible implementation, the first vehicle information corresponding to the target vehicle can be determined by identifying and extracting the certificate information in the image to be verified.

[0090] Regarding the identification process, in this embodiment of the application, the certificate information can be identified by a preset identification model to determine the first vehicle information. The identification model can be a text recognition model, etc.

[0091] After obtaining the first vehicle information, the first vehicle information can be verified.

[0092] In one possible implementation, the most accurate original vehicle information corresponding to the target vehicle uploaded by the user can be obtained, and the first vehicle information can be verified based on the original vehicle information.

[0093] In another possible implementation, the verification process may include the following steps: Step S3011: Obtain the order data corresponding to the target vehicle.

[0094] Step S3012: Determine the second vehicle information corresponding to the target vehicle based on the order data.

[0095] Step S3013: Verify the information of the first vehicle based on the second vehicle information to obtain the verification result corresponding to the first vehicle information.

[0096] In this embodiment of the application, order data may refer to the information submitted when the vehicle is sold, and may include, but is not limited to, key fields such as contract number, buyer information, vehicle model, chassis number, and engine number.

[0097] In one possible implementation, order data corresponding to the target vehicle can be obtained from a database; in another possible implementation, order data uploaded by the user can be obtained through an external input device.

[0098] Based on order data, second vehicle information related to the vehicle can be extracted and parsed. It is understood that the second vehicle information is absolutely accurate and may include, but is not limited to, vehicle model, chassis number, engine number, etc.

[0099] In one possible implementation, the consistency of each piece of information included in the first vehicle information can be verified based on the second vehicle information. When the first vehicle information and the second vehicle information are inconsistent, the verification result can be determined as verification failure; when the first vehicle information and the second vehicle information are consistent, the verification result can be determined as verification success.

[0100] In another possible implementation, the first vehicle information and the second vehicle information can be input into a preset verification model to obtain the verification result output by the verification model.

[0101] Step S302: If the verification result corresponding to the first vehicle information is successful, the image to be verified is associated with and stored with the order information corresponding to the target vehicle through the second preset interface.

[0102] In this embodiment of the application, if the verification result corresponding to the first vehicle information is determined to be successful, the image to be verified can be associated with and stored with the order information corresponding to the target vehicle through the second preset interface.

[0103] In this embodiment of the application, a successful verification indicates that the consistency between the first vehicle information and multi-source data such as contracts and orders has been verified, and no contradictions or errors have been found. For example, it confirms that the vehicle identification number (VIN) exists and is unique in the order system, and that the vehicle model in the contract matches the certificate of conformity.

[0104] Here, the second preset interface may, but is not limited to, a pre-configured standardized API interface used to associate and store the certificate image, the first vehicle information, and the order information. In this embodiment, the second preset interface typically connects to an internal file system and a database, and the association between the two enables persistent data storage.

[0105] Step S303: Generate the binding logs corresponding to the associated stored procedure.

[0106] In this embodiment of the application, after the image to be verified is associated with and stored with the order information corresponding to the target vehicle, a binding log corresponding to the associated storage process can be generated to facilitate subsequent verification and tracing.

[0107] Here, the binding log can be, but is not limited to, a record automatically generated after the data binding operation is completed. This record can include, but is not limited to, information such as the operation time, operation content, operation status, and related data identifiers that associate the image to be verified with the order information corresponding to the target vehicle.

[0108] In this embodiment of the application, the binding log is used to track the execution of the entire associated storage process and serves as an important audit basis for subsequent operation processing.

[0109] In practice, after the image to be verified is associated with the order information corresponding to the target vehicle, a binding log will be generated immediately. This binding log record can be stored in a log server or database for subsequent viewing and analysis.

[0110] In the above embodiments, the setting of associated storage and the subsequent binding log generation steps constitute a specific tracking mechanism that ensures the entire associated storage process has good traceability. When problems occur, the cause can be quickly located, thereby improving the stability and security of data association.

[0111] In this application embodiment, there are also cases where the risk assessment result is "assessment failed" and / or the verification result corresponding to the first vehicle information is "verification failed". In this scenario, the data processing method provided by this application may further include the following steps: Step S304: If the risk assessment result is "assessment failed" and / or the verification result corresponding to the first vehicle information is "verification failed", generate binding failure information based on the risk assessment result and / or the verification result corresponding to the first vehicle information.

[0112] Understandably, when a risk assessment or vehicle information verification fails, the two will not be associated and stored. In this case, data binding fails, and corresponding binding failure information can be generated to record the anomaly and provide a basis for subsequent anomaly handling. For example, if the VIN in a certificate of conformity does not match the VIN in the order system, the system will generate a binding failure message containing a description of the VIN mismatch.

[0113] In this embodiment of the application, the binding failure information may include, but is not limited to, the type of exception (such as failure to verify the vehicle identification number, inconsistent contract information, etc.); the specific time of the exception event that occurred during the user's use of the device; the vehicle information involved (such as vehicle identification number, contract number, etc.); the source of the exception (such as incorrect recognition of certificate information, mismatch of signature information, etc.); and the suggested handling method (such as manual review, re-uploading the certificate of conformity, etc.).

[0114] In this embodiment of the application, binding failure information can be stored in a database in a structured format and pushed to the relevant responsible persons through WeChat or other messaging platforms.

[0115] Step S305: Perform exception handling by binding failure information.

[0116] It is understandable that the exception handling corresponds to the content in the binding failure message, and is the measure taken to deal with the abnormal situation based on the content of the binding failure message.

[0117] For example: if an error occurs during the identification of vehicle certificate information, resulting in a discrepancy between the VIN identified by the system and the actual information, the user can be advised to re-upload the image of the vehicle certificate for re-identification; if the verification result of the signature information is found to be unsuccessful, a second verification operation can be performed on the image to be verified, and if the second verification operation also fails, a verification failure message can be generated; if an inconsistency is found between the first vehicle information and the second vehicle information, staff can be notified to verify the authenticity of the contract information; if the light and shadow scores of the same batch differ too much, all images in this batch can be marked as a suspicious batch, and further investigation procedures can be initiated.

[0118] In the above embodiments, by performing exception handling operations based on binding failure information, it can be ensured that unqualified data will not enter the formal business flow, thereby avoiding subsequent disputes caused by incorrect binding and ensuring the compliance and security of the entire business process.

[0119] The following describes the application of the embodiments of this application in a real-world scenario.

[0120] With the digitalization of the automotive sales industry, vehicle conformity certificates, as crucial documents for vehicle production, directly impact business flow speed through efficient information verification and binding. Currently, these certificates are mostly submitted as photos via WeChat, Lark, or other digital material systems. Staff must manually complete the following tedious process: first, visually identify key fields (such as vehicle model and VIN); second, compare the image with the purchase contract to ensure consistency; and finally, search the corresponding order in the order system and verify the VIN match. This process is highly reliant on manual operation, resulting in time-consuming, error-prone, and limited processing capacity. For example, processing 300 certificates per day would take approximately 300 minutes, and manual verification is susceptible to errors due to fatigue or negligence, affecting the accuracy of subsequent stages such as vehicle sales and registration.

[0121] Based on this, this application presents a vehicle certificate intelligent verification and binding system built on an AI-based large-scale model, achieving full-process automation through multi-module collaboration. The core idea is to utilize computer vision and natural language processing models to automatically capture, identify, and parse key information from certificate images and contract texts, and connect to the order system via the MCP tool to achieve data comparison and binding. Specifically, the following technical points are included: Image intelligent recognition and classification: Automatically capture images in groups through WeChat / Lark interfaces, use AI models to determine whether they are certificates of conformity, and extract structured data (such as vehicle identification number, vehicle model code, etc.).

[0122] Multi-source data collaborative comparison: Analyze the contract content and certificate of conformity information to verify consistency, and at the same time use the MCP tool to query the order system to verify the vehicle identification number matching; Automated binding decision: If all verifications pass, the system will automatically link and store the certificate of conformity, contract, and order data to form a complete digital archive.

[0123] This method minimizes human intervention and relies on the high-precision recognition and reasoning capabilities of AI large models to achieve one-stop processing of "capture-recognition-verification-binding".

[0124] The architecture provided in this application embodiment specifically includes the following: 1. Certificate of Conformity Image Capture Module.

[0125] (1) Image capture: Through the specific open interface of the target social software, monitor the specified group or folder in real time and automatically download newly uploaded images.

[0126] (2) Certificate of conformity judgment: A lightweight convolutional neural network model is used to classify images into two categories (certificate of conformity / non-certificate of conformity), and images of non-certificate of conformity are directly filtered out.

[0127] (3) Adding a trust watermark: To ensure that subsequent steps confirm that the certificate image has not been tampered with, the image file will be processed according to the following procedure before being uploaded to the internal file system: A. Convert the file content to BASE64 encoding.

[0128] B. Encode the file content in BASE64 and sign it using the national standard SM2 algorithm.

[0129] C. The signature result will be attached as a small-font (font size: 5) watermark to the lower right corner of the original text of the image, and can be presented in multiple lines.

[0130] D. Upload Image File: Upload the processed certificate image to our internal file system. During the upload process, additional metadata information is required, including: Table 3

[0131] 2. AI Information Extraction Module.

[0132] Key Information Extraction: The vehicle identification number (VIN), model number, and engine number are located and identified from the certificate image using recognition technology (such as a deep learning-based text recognition model). Structured data is then output. Note that some English letters and numbers are easily confused; based on the rules governing the VIN's structure, certain character conversions are performed on the identified VIN string.

[0133] 3. Multi-source data verification module (1) Signature Comparison: During the OCR process, in addition to the vehicle identification number, the system also extracts the signature watermark content. By comparing the original document signature with the OCR signature watermark, it can be clearly identified whether the image has been tampered with before the OCR process. To ensure the accuracy of OCR recognition of the watermark content, we performed supervised fine-tuning based on the open-source Qwen2.5-VL-72B model, and the final recognition accuracy of the signature watermark content can reach 98.7%. (2) Lighting and Shadow Comparison: Certificates of conformity are produced in batches. Generally, the lighting and shadow effects of certificates of conformity images in the same batch should be similar. Our approach is to fine-tune a small model (Qwen2.5-VL-7B) to enable it to understand lighting and shadow effects and score them (1~10). Then, based on this model, the lighting and shadow effects of certificates of conformity in the same batch are scored. The difference between the lighting and shadow scores of each image and the average score of the batch should not exceed 1 point. After testing, the accuracy of this comparison is about 70%, and there is still some potential to be explored. Therefore, the results of this anti-counterfeiting comparison work are only for reference and not as an absolute indicator.

[0134] (3) Contract Analysis: The AI ​​model analyzes the electronic version of the car purchase contract (supports PDF or image format), extracts clauses such as vehicle configuration, price, and buyer / seller information, and compares them with the information on the certificate of conformity. This indicator can achieve an accuracy rate of over 97% using a conventional language model, therefore the results of this comparison are used as an absolute indicator.

[0135] (4) Order System Interaction: By entering the contract number through the MCP tool, the corresponding vehicle order data (including order status, VIN, etc.) is retrieved from the order system. The VIN in the certificate of conformity is compared with the VIN in the order system to ensure uniqueness and consistency. This anti-tampering comparison has an accuracy rate of over 98% under conventional language models, therefore the result of this comparison is used as an absolute indicator.

[0136] 4. Vehicle identification number verification: Automatic binding and archiving module.

[0137] (1) Decision logic: If the vehicle model information and the vehicle identification number are both verified, the system will automatically call the binding interface of the MCP tool to associate and store the certificate of conformity image, contract summary and order data in the database, and generate a binding success log.

[0138] (2) Anomaly handling: If any step of the verification fails, the system will automatically push an alarm to the designated personnel and record the reason for the failure for manual review.

[0139] For details on the overall joint performance process, please refer to... Figure 4 , Figure 4This application provides a schematic diagram of a verification process, referring to... Figure 4 As can be seen, the external target social software can send the monitoring message to the vehicle certificate main unit. The vehicle certificate main unit will then send the monitoring message to the message filter so that the message filter can obtain the certificate image to be verified. The image processor will perform various processes on the certificate image, including image processor pre-preparation, downloading chat images, pushing images to the model, vehicle identification number recognition, uploading the certificate image to the internal system, binding the vehicle certificate image, and temporary resource cleanup. If any step fails, the anomaly processor will push an alarm to the anomaly notification group.

[0140] The technical advantages of the solution provided in this application compared to related technologies include the following: 1. Significantly improved efficiency: The average time for manually processing a single certificate of conformity has been reduced from 1 minute to seconds, and the time required to process 300 certificates of conformity per day has been reduced from 300 minutes to less than 10 minutes, resulting in an efficiency improvement of approximately 30 times.

[0141] 2. Extremely high accuracy: Based on a large artificial intelligence model, the text recognition and comparison algorithm has an accuracy rate of over 97% in identifying key fields, which is far higher than manual verification (which is prone to errors due to fatigue or negligence).

[0142] 3. Full-process automation: It creates a closed loop from image capture and information extraction to system binding, reducing manual intervention and lowering operating costs.

[0143] 4. Strong scalability: It is compatible with multiple order system interfaces, and the artificial intelligence model can be adapted to different certificate templates, supporting rapid deployment by car manufacturers.

[0144] 5. Controllable risks: The real-time alarm mechanism ensures that abnormal data is intercepted in a timely manner, avoiding subsequent disputes caused by incorrect binding.

[0145] Based on the foregoing embodiments, this application provides a data processing device, which includes various units and modules included in each unit. It can be implemented by a processor in a computer device; of course, it can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0146] Figure 5This is a schematic diagram of the composition structure of a temperature data processing device provided in an embodiment of this application, as shown below. Figure 5 As shown, the data processing device 500 includes: an acquisition module 501, a light and shadow analysis module 502, a signature verification module 503, and a risk assessment module 504, wherein: The acquisition module 501 is used to acquire the image to be verified corresponding to the target vehicle. The image to be verified includes at least the certificate information corresponding to the target vehicle and the signature information corresponding to the certificate information. The light and shadow analysis module 502 is used to perform light and shadow analysis processing on the image to be verified through a light and shadow analysis model to obtain a light and shadow effect score of the image to be verified. The signature verification module 503 is used to verify the correctness of the signature information and obtain the verification result corresponding to the signature information; The risk assessment module 504 is used to determine the risk assessment result of the image to be verified based on the light and shadow effect score of the image to be verified and the verification result corresponding to the signature information.

[0147] In some embodiments, the risk assessment module 504 includes: The association determination unit is used to determine at least one associated image that is associated with the image to be verified, wherein the associated image is an image produced in the same batch as the image to be verified; The associated scoring unit is used to obtain the light and shadow effect score corresponding to each of the associated images; The comprehensive evaluation unit is used to evaluate the verification result based on the light and shadow effect score of the image to be verified and the light and shadow effect scores of each associated image, and to determine the risk assessment result corresponding to the image to be verified.

[0148] In some embodiments, the comprehensive evaluation unit is specifically used to perform: Based on the difference between the lighting effect score of the image to be verified and the lighting effect score of each associated image, it is determined whether the image to be verified is produced in the same batch as the associated images; If the image to be verified and the associated image are produced in the same batch, and the verification result is successful, then the risk assessment result of the image to be verified is determined to be passed. If the image to be verified and the associated image are not produced in the same batch, or if the verification result is a verification failure, then the risk assessment result of the image to be verified is determined to be an assessment failure.

[0149] In some embodiments, the acquisition module 501 includes: An automatic capture unit is used to detect the storage space corresponding to the target software through a first preset interface to obtain the image to be verified.

[0150] In some embodiments, the device 500 further includes: The information determination module is used to determine the first vehicle information corresponding to the target vehicle based on the certificate information in the image to be verified, if the risk assessment result is that the assessment is passed. The binding module is used to associate and store the image to be verified with the order information corresponding to the target vehicle through a second preset interface when the verification result corresponding to the first vehicle information is verified as passed. The log generation module is used to generate the binding logs corresponding to the associated stored procedures.

[0151] In some embodiments, the device 500 further includes: The verification module is used to obtain the order data corresponding to the target vehicle; determine the second vehicle information corresponding to the target vehicle based on the order data; and perform information verification on the first vehicle information based on the second vehicle information to obtain the verification result corresponding to the first vehicle information.

[0152] In some embodiments, the device 500 further includes: An exception handling module is used to generate binding failure information based on the risk assessment result and / or the verification result corresponding to the first vehicle information when the risk assessment result is "assessment failed" and / or the verification result corresponding to the first vehicle information is "verification failed"; and to perform exception handling based on the binding failure information.

[0153] It should be noted that, in the embodiments of this application, if the above-described temperature control method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (in the embodiments of this application, the computer device can be a vehicle) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.

[0154] This application provides a computer device, which may be a vehicle, wherein the processor executes the program to implement some or all of the steps in the above method.

[0155] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium can be transient or non-transient.

[0156] This application provides a computer program including computer-readable code, wherein when the computer-readable code is executed in a computer device, a processor in the computer device performs some or all of the steps in the above-described method.

[0157] This application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium; in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0158] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between them, while their similarities or commonalities can be referred to interchangeably. The descriptions of the above embodiments of the device, storage medium, computer program, and computer program product are similar to the descriptions of the above method embodiments and have similar beneficial effects. For technical details not disclosed in the embodiments of the device, storage medium, computer program, and computer program product of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0159] Figure 6 This application provides a hardware entity diagram of a computer device as an embodiment of the present application, such as... Figure 6 As shown, the hardware entity of the computer device 600 includes: a processor 601, a communication interface 602, and a memory 603, wherein: The processor 601 executes the steps of the model adjustment method described above when executing the program. The processor 601 typically controls the overall operation of the computer device 600.

[0160] Communication interface 602 enables computer devices to communicate with other terminals or servers via a network.

[0161] The memory 603 is configured to store instructions and applications executable by the processor 601, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 601 and various modules in the computer device 600. It can be implemented using flash memory or random access memory (RAM). Data transfer between the processor 601, the communication interface 602, and the memory 603 can be performed via bus 604.

[0162] This application provides a computer storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the model adjustment method as described in any of the above embodiments.

[0163] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0164] The aforementioned processor can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that other electronic devices can also implement the functions of the aforementioned processor, and this application does not specifically limit the specific implementation.

[0165] The aforementioned computer storage media / memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various terminals that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0166] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A data processing method, characterized in that, The method includes: Obtain the image to be verified corresponding to the target vehicle. The image to be verified includes at least the certificate of conformity information corresponding to the target vehicle and the signature information corresponding to the certificate of conformity information. The image to be verified is processed by a light and shadow analysis model to obtain a light and shadow effect score for the image to be verified. The signature information is verified to obtain the verification result corresponding to the signature information; Based on the lighting effect score of the image to be verified and the verification result corresponding to the signature information, the risk assessment result of the image to be verified is determined.

2. The method according to claim 1, characterized in that, Based on the lighting effect score of the image to be verified and the verification result corresponding to the signature information, the risk assessment result of the image to be verified is determined, including: Identify at least one associated image that is related to the image to be verified, wherein the associated image is an image produced in the same batch as the image to be verified; Obtain the lighting effect score corresponding to each of the associated images; The verification results are evaluated based on the lighting and shadow effect scores of the image to be verified and the lighting and shadow effect scores of each associated image, thereby determining the risk assessment result corresponding to the image to be verified.

3. The method according to claim 2, characterized in that, The verification results are evaluated based on the lighting and shadow effect scores of the image to be verified and the lighting and shadow effect scores of each associated image to determine the risk assessment result corresponding to the image to be verified, including: Based on the difference between the lighting effect score of the image to be verified and the lighting effect score of each associated image, it is determined whether the image to be verified is produced in the same batch as the associated images; If the image to be verified and the associated image are produced in the same batch, and the verification result is successful, then the risk assessment result of the image to be verified is determined to be passed. If the image to be verified and the associated image are not produced in the same batch, or if the verification result is a verification failure, then the risk assessment result of the image to be verified is determined to be an assessment failure.

4. The method according to any one of claims 1 to 3, characterized in that, The process of obtaining the image to be verified includes: The storage space corresponding to the target software is detected through the first preset interface to obtain the image to be verified.

5. The method according to any one of claims 1 to 3, characterized in that, The method further includes: If the risk assessment result is that the assessment is passed, the first vehicle information corresponding to the target vehicle is determined based on the certificate information in the image to be verified. If the verification result corresponding to the first vehicle information is successful, the image to be verified is associated with and stored with the order information corresponding to the target vehicle through the second preset interface. Generate the binding logs corresponding to the associated stored procedure.

6. The method according to claim 5, characterized in that, The method further includes: Obtain the order data corresponding to the target vehicle; Determine the second vehicle information corresponding to the target vehicle based on the order data; The first vehicle information is verified based on the second vehicle information to obtain the verification result corresponding to the first vehicle information.

7. The method according to claim 5, characterized in that, The method further includes: If the risk assessment result is "assessment failed" and / or the verification result corresponding to the first vehicle information is "verification failed", binding failure information is generated based on the risk assessment result and / or the verification result corresponding to the first vehicle information. Exception handling is performed using the binding failure information.

8. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire the image to be verified corresponding to the target vehicle. The image to be verified includes at least the certificate information corresponding to the target vehicle and the signature information corresponding to the certificate information. The light and shadow analysis module is used to perform light and shadow analysis on the image to be verified through a light and shadow analysis model to obtain a light and shadow effect score for the image to be verified. The signature verification module is used to verify the correctness of the signature information and obtain the verification result corresponding to the signature information; The risk assessment module is used to determine the risk assessment result of the image to be verified based on the light and shadow effect score of the image to be verified and the verification result corresponding to the signature information.

9. A computer device comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images