Identity information updating method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides an identity information updating method and device, electronic equipment and a medium, belongs to the technical field of artificial intelligence, and is suitable for financial scenes. The method comprises the following steps: performing identity information extraction on an identity document image to obtain initial identity information of a target user; performing identity authenticity prediction on the target user according to the initial identity information, chip analysis data obtained by identity document verification, biological characteristic verification data obtained by biological characteristic verification and mechanism identity verification data obtained by mechanism identity authenticity verification to obtain an identity risk level; and performing identity updating on the initial identity information according to the identity risk level. According to the embodiment of the invention, identity authenticity prediction is carried out on the target user according to the certificate identity verification data, the biological characteristic verification data and the mechanism identity verification data, the authenticity of the user identity can be comprehensively evaluated, and the reliability of identity information updating is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and is applied in financial scenarios, particularly to a method and device for updating identity information, an electronic device, and a medium. Background Technology

[0002] Traditional methods for updating identity information typically involve manually comparing the information on the surface of an ID document (such as name, ID number, and photo) with the information recorded in the database. For example, in a financial scenario, during insurance renewal, when a user's ID document expires, insurance personnel need to compare the information on the copy of the ID document to be updated with the information recorded in the insurance company's database. If the ID information (name, ID number, and photo) confirms the same person, the verification is passed, and the identity information is updated. However, this method relies solely on manual comparison of the identity information to be updated with the original information. If the user's facial features differ significantly from the archived ID photo, it cannot accurately identify whether identity theft has occurred, resulting in poor reliability of identity updates. Therefore, improving the reliability of identity updates has become an urgent problem to be solved. Summary of the Invention

[0003] The main objective of this application is to provide an identity information update method, apparatus, electronic device, and medium, which aims to improve the reliability of identity updates.

[0004] To achieve the above objectives, a first aspect of this application proposes an identity information updating method, the method comprising:

[0005] Obtain the target user's ID card and obtain an image of the ID card;

[0006] The identity information of the target user is extracted from the document image;

[0007] The identity document is verified to obtain identity verification data;

[0008] Collect the biometric information of the target user, and perform biometric verification based on the biometric information and the initial identity information to obtain biometric verification data;

[0009] The initial identity information is verified to obtain the organization identity verification data.

[0010] Based on the document identity verification data, the biometric verification data, and the institution identity verification data, the authenticity of the target user's identity is predicted to obtain the identity risk level.

[0011] The initial identity information is updated based on the identity risk level to obtain the target identity information.

[0012] In some embodiments, the document identity verification data includes chip parsing data, document watermark verification data, and document microtext verification data;

[0013] The step of verifying the identity document to obtain identity verification data includes:

[0014] The chip of the ID card is parsed to obtain chip parsing data; wherein, the chip parsing data indicates that the ID card parsing failed;

[0015] If the chip parsing data indicates that the ID card parsing failed, then the ID card is subjected to ID card watermark verification to obtain ID card watermark verification data; wherein, the ID card watermark verification data indicates whether the ID card watermark verification passed or failed.

[0016] If the document watermark verification data indicates that the document watermark verification failed, then the document microtext verification is performed on the document to obtain document microtext verification data; wherein, the document microtext verification data indicates whether the document microtext verification passed or failed.

[0017] In some embodiments, the identification document includes an identification chip;

[0018] The step of performing chip analysis on the ID card chip to obtain chip analysis data includes:

[0019] Establish a communication connection between the document chip and the preset card reader to obtain a communication channel;

[0020] The system receives an information reading instruction sent by the card reader, and reads the data of the document chip according to the information reading instruction and the communication channel to obtain the document chip data.

[0021] The data of the certificate chip is parsed to obtain the chip parsing data.

[0022] In some embodiments, collecting the target user's biometric information includes:

[0023] The target video frames of the target user are collected, and the target video frames are subjected to liveness detection using a pre-trained biometric recognition model to obtain liveness detection information.

[0024] Face recognition is performed on the target video frame to obtain facial feature information;

[0025] Voiceprint recognition is performed on the target video frame to obtain voiceprint feature information;

[0026] Iris recognition is performed on the target video frame to obtain iris feature information;

[0027] The identity biometric information is determined based on the liveness detection information, the facial feature information, the voiceprint feature information, and the iris feature information.

[0028] In some embodiments, the step of performing biometric matching based on the identity biometric information and the initial identity information to obtain biometric verification data includes:

[0029] The target user is subjected to liveness verification based on the liveness detection information in the biometric identity information to obtain liveness verification data; the liveness verification data indicates that the target user has passed the liveness verification.

[0030] If the liveness verification data indicates that the target user's liveness verification has passed, then the identity biometric information is compared with the initial identity information to obtain the biometric verification data; the biometric verification data indicates whether the target user's biometric verification has passed or failed.

[0031] In some embodiments, the step of predicting the authenticity of the target user's identity based on the document verification data, the biometric verification data, and the institution's identity verification data to obtain an identity risk level includes:

[0032] A multidimensional confidence assessment is performed based on the chip parsing data, the biometric verification data, and the institution identity verification data to obtain the multidimensional identity confidence score.

[0033] The identity risk level of the target user is obtained by assessing the authenticity of the identity based on the multidimensional confidence level and the preset risk confidence threshold.

[0034] In some embodiments, updating the initial identity information according to the identity risk level to obtain the target identity information includes:

[0035] An update strategy is generated based on the identity risk level and the initial identity information to obtain the identity update strategy.

[0036] The updated identity policy is identified by policy type to obtain the target policy category;

[0037] Based on the target strategy category, the initial identity information is updated to obtain updated identity information;

[0038] The initial identity information is updated based on the updated identity information to obtain the target identity information.

[0039] To achieve the above objectives, a second aspect of this application provides an identity information updating apparatus, the apparatus comprising:

[0040] The document image acquisition module is used to acquire the target user's ID card and to acquire an image of the ID card.

[0041] An identity information extraction module is used to extract identity information from the document image to obtain the initial identity information of the target user.

[0042] The document verification module is used to verify the identity document and obtain document identity verification data.

[0043] The biometric verification module is used to collect the identity biometric information of the target user, and perform biometric verification based on the identity biometric information and the initial identity information to obtain biometric verification data.

[0044] The organization identity verification module is used to verify the authenticity of the organization identity based on the initial identity information and obtain organization identity verification data.

[0045] The identity verification module is used to predict the authenticity of the target user's identity based on the document identity verification data, the biometric verification data, and the institution identity verification data, and to obtain the identity risk level.

[0046] The identity update module is used to update the initial identity information according to the identity risk level to obtain the target identity information.

[0047] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0048] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of the first aspect described above.

[0049] The identity information updating method, apparatus, electronic device, and medium proposed in this application first acquire the target user's ID card and its image, and extract identity information from the image, providing a solid identity data foundation for subsequent identity verification. Second, the ID card is verified, including biometric verification based on the user's identity biometrics and initial identity information. Furthermore, the initial identity information undergoes institutional identity verification, enabling multi-dimensional verification of the document's authenticity. Biometric verification, combined with institutional identity verification, further ensures the authenticity of the identity information. Integrating institutional identity verification ensures the up-to-date status and legality of the identity information, further improving the reliability of identity verification. Finally, based on the ID card verification data, biometric verification data, and institutional identity verification data, the target user's identity is predicted to obtain an identity risk level. This multi-dimensional cross-verification comprehensively assesses the authenticity and reliability of the identity information, effectively preventing identity theft. Finally, the initial identity information is updated based on the identity risk level, significantly improving the reliability of identity information updates. Attached Figure Description

[0050] Figure 1 This is a flowchart of the identity information updating method provided in the embodiments of this application;

[0051] Figure 2 yes Figure 1 The flowchart of step S103 in the process;

[0052] Figure 3 yes Figure 2 The flowchart of step S201 in the text;

[0053] Figure 4 yes Figure 1 The flowchart of step S104 in the process;

[0054] Figure 5 yes Figure 4 The flowchart of step S401 in the process;

[0055] Figure 6 yes Figure 1 The flowchart of step S106 in the process;

[0056] Figure 7 yes Figure 1 The flowchart of step S107 in the process;

[0057] Figure 8 This is a schematic diagram of the structure of the identity information updating device provided in the embodiments of this application;

[0058] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0061] 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 belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0062] First, let's analyze some of the terms used in this application:

[0063] Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.

[0064] This application provides an identity information update method, apparatus, electronic device, and medium, aiming to improve the reliability of identity updates.

[0065] The identity information updating method, apparatus, electronic device, and medium provided in this application are specifically described through the following embodiments. First, the identity information updating method in this application is described.

[0066] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0067] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0068] The identity information updating method provided in this application relates to the field of artificial intelligence technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the identity information updating method, but is not limited to the above forms.

[0069] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0070] Figure 1 This is an optional flowchart of the identity information update method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S107.

[0071] Step S101: Obtain the target user's ID card and obtain an image of the ID card.

[0072] Step S102: Extract identity information from the document image to obtain the initial identity information of the target user.

[0073] Step S103: Verify the identity document to obtain identity verification data.

[0074] Step S104: Collect the target user's identity biometric information, and perform biometric verification based on the identity biometric information and the initial identity information to obtain biometric verification data.

[0075] Step S105: Verify the authenticity of the organization's identity based on the initial identity information to obtain organization identity verification data;

[0076] Step S106: Based on the identity verification data of the document, biometric verification data and the identity verification data of the institution, predict the authenticity of the target user's identity and obtain the identity risk level.

[0077] Step S107: Update the initial identity information according to the identity risk level to obtain the target identity information.

[0078] Steps S101 to S107 of this embodiment first acquire the target user's ID card and its image, and extract identity information from the image, providing a solid foundation of identity data for subsequent identity verification. Second, the ID card is verified, including biometric verification based on the user's identity biometrics and initial identity information, and institutional identity verification. This multi-dimensional verification of the document's authenticity, combined with biometric verification, further ensures the authenticity of the identity information. In addition, institutional identity verification ensures the up-to-date status and legality of the identity information, further improving the reliability of identity verification. Finally, based on the ID card verification data, biometric verification data, and institutional identity verification data, the target user's identity is predicted to obtain an identity risk level. This multi-dimensional cross-verification comprehensively assesses the authenticity and reliability of the identity information, effectively preventing identity theft. Furthermore, the initial identity information is updated based on the identity risk level, significantly improving the reliability of identity information updates.

[0079] In step S101 of some embodiments, specifically, the identity document is an important carrier of personal identity information, which usually includes name, ID number, photo and expiration date.

[0080] Specifically, an image of the ID card can be obtained by taking pictures of the front and back of the ID card with a camera.

[0081] For example, in insurance scenarios, when users apply for policy renewal or insurance claims, it is necessary to verify the ID documents and photocopies provided by the users to avoid policy invalidation or service disputes caused by the inability to synchronize identity information such as expired ID cards or changes in household registration in real time.

[0082] In this embodiment, by obtaining the target user's ID card and the image of the ID card, basic identity data is provided for subsequent identity information extraction and verification.

[0083] In step S102 of some embodiments, specifically, the initial identity information refers to the target user's identity document information, including but not limited to name, ID number, photo and expiration date.

[0084] Specifically, the YOLOv5 model, an object detection algorithm, can be used to locate key fields in document images. Specifically, the YOLOv5 model can be used to detect document information in the image, outputting detection areas including the name, ID number, and expiration date. Then, the Tesseract-OCR (Optical Character Recognition) engine is used to recognize the text in the detection areas to identify the name, ID number, and expiration date, and performs error correction (such as replacing the letter O with the number 0) to determine the final initial identity information such as name, ID number, and expiration date.

[0085] In this embodiment, the initial identity information of the target user is obtained by extracting identity information from the document image, ensuring the accuracy and completeness of the extracted initial identity information and providing a solid identity data foundation for subsequent identity verification.

[0086] Please see Figure 2 In some embodiments, the document identity verification data includes chip parsing data, document watermark verification data, and document microtext verification data. Step S103 includes, but is not limited to, steps S201 to S203:

[0087] Step S201: Perform chip parsing on the ID card chip to obtain chip parsing data; wherein, chip parsing data indicates that the ID card parsing failed.

[0088] Step S202: If the chip parsing data indicates that the ID card parsing failed, then the ID card is subjected to ID card watermark verification to obtain ID card watermark verification data; wherein, the ID card watermark verification data indicates whether the ID card watermark verification passed or failed.

[0089] Step S203: If the document watermark verification data indicates that the ID card watermark verification failed, then perform document microtext verification on the ID card to obtain document microtext verification data; wherein, document microtext verification data indicates whether the ID card microtext verification passed or failed.

[0090] Please see Figure 3 In some embodiments, the identification document includes an identification chip, and step S201 includes, but is not limited to, steps S301 to S303:

[0091] Step S301: Establish a communication connection between the document chip and the preset card reader to obtain a communication channel.

[0092] Step S302: Receive the information reading instruction sent by the card reader, and read the data of the document chip according to the information reading instruction and the communication channel to obtain the document chip data.

[0093] Step S303: Parse the identity information data from the ID chip to obtain chip parsing data.

[0094] In step S301 of some embodiments, specifically, the communication channel refers to the connection channel established between the certificate chip and the card reader for data transmission.

[0095] Specifically, an RFID (Radio Frequency Identification) card reader can transmit a wireless signal at a specific frequency through its built-in antenna. When the ID card is brought close to the card reader, the antenna inside the card chip receives the wireless signal transmitted by the card reader and establishes a communication channel with the card chip.

[0096] For example, in an insurance scenario, when an insurance agent places a user's ID card on an RFID reader, the reader uses its built-in communication module to transmit wireless signals and establish a communication connection with the ID card chip.

[0097] In step S302 of some embodiments, specifically, the information reading instruction is used to read binary information in the certificate chip.

[0098] Specifically, the data in the ID card chip refers to the binary information stored in the ID card chip, including binary information such as name, ID number, photo, and validity period.

[0099] Specifically, the communication channel receives a series of information reading instructions sent by the card reader to the document chip, such as APDU (Application Protocol Data Unit) instructions. The APDU instructions can be: "SELECT MF" to select the main file; "SELECT EF(ID)" to select the file containing identity information; and "READ BINARY" to read binary data from the file, including name, ID number, photo, and document validity period.

[0100] In step S303 of some embodiments, chip parsing data refers to readable identity information parsed from the ID card chip, which indicates whether the ID card parsing failed or succeeded.

[0101] Specifically, after the card reader receives the binary data returned by the ID card chip, it decodes and analyzes the data through its built-in parsing module. The parsing module extracts chip parsing data such as name, ID card number, and validity period from the binary data according to a preset format (such as the ID card number field format). If the parsing module returns a None field, the chip parsing data indicates that the parsing failed and the ID card may have a certain risk of being counterfeited.

[0102] Through steps S301 to S303, the chip analysis of the ID card effectively ensures the reliability of the ID card, which not only improves the efficiency of obtaining identity information, but also effectively prevents the use of counterfeit ID cards.

[0103] In step S202 of some embodiments, the document watermark verification data refers to the data used to determine the authenticity of an ID card by detecting the watermark features on the ID card. This document watermark verification data indicates whether the ID card watermark verification has passed or failed.

[0104] Specifically, the document image can be converted into a grayscale image, and a Discrete Fourier Transform (DFT) can be performed on the grayscale image to transform it from the spatial domain to the frequency domain. The amplitude value in the frequency domain is calculated. Since periodic watermark features will exhibit specific characteristics in the frequency domain, the presence of a watermark can be determined by comparing the calculated amplitude value with a preset amplitude threshold (e.g., 45). If the amplitude value is greater than 45, it indicates that the watermark exists, and the document watermark verification data indicates that the document watermark verification has passed; if the amplitude value is less than or equal to 45, it indicates that the watermark does not exist, and the document watermark verification data indicates that the document watermark verification has failed.

[0105] In step S203 of some embodiments, the document microtext verification data refers to the data used to determine the authenticity of the document by recognizing the microtext on the document. The document microtext verification data indicates whether the document microtext verification has passed or failed.

[0106] Specifically, the process first identifies the microtext region and performs augmented binarization to obtain a binarized image region. Then, Tesseract-OCR technology is used to recognize the microtext content in the binarized image region to obtain the target microtext. It is then determined whether the microtext contains anti-counterfeiting mosquitoes. If it does, the microtext verification data of the ID card passes the verification; otherwise, the verification fails.

[0107] Through steps S201 to S203, multi-dimensional document verification, including chip analysis, document watermark verification, and document microtext verification, effectively ensures the authenticity, validity, and legality of the ID card, thereby improving the accuracy of document verification.

[0108] Please see Figure 4 In some embodiments, step S104 includes, but is not limited to, steps S401 to S404:

[0109] Step S401: Collect target video frames of the target user, and perform liveness detection on the target video frames using a pre-trained biometric recognition model to obtain liveness detection information.

[0110] Step S402: Perform face recognition on the target video frame to obtain face feature information.

[0111] Step S403: Perform voiceprint recognition on the target video frame to obtain voiceprint feature information.

[0112] Step S404: Perform iris recognition on the target video frame to obtain iris feature information.

[0113] Step S405: Determine the identity biometric information based on the liveness detection information, facial feature information, voiceprint feature information, and iris feature information.

[0114] In step S401 of some embodiments, specifically, the target video frame refers to the user's biometric video collected by the acquisition device (such as a camera, fingerprint scanner, and iris scanner), and the target video frame is selected from the video.

[0115] Specifically, a pre-trained biometric recognition model refers to a trained neural network model, which includes a liveness detection network, a face recognition network, a voiceprint recognition network, and an iris recognition network. The liveness detection network is used to recognize facial movement features; the face recognition network is used to recognize the user's facial features; the voiceprint recognition network is used to recognize the user's voiceprint features; and the iris recognition network is used to recognize the user's iris features.

[0116] Specifically, liveness detection information refers to facial motion feature information extracted from target video frames for identity recognition. This liveness detection information includes, but is not limited to, facial expression information (such as blinking) and head motion information (such as shaking head and nodding).

[0117] Specifically, a liveness detection network (such as a convolutional neural network) can be used to obtain images of the user's head region from the target video frame. Then, facial expression recognition can be performed on the user's head region image to obtain facial expression features. Finally, facial motion recognition can be performed on the user's head region image to obtain facial motion features. Based on the facial expression features and facial motion features, liveness detection information can be determined.

[0118] In this embodiment, a pre-trained biometric recognition model is used to perform liveness detection on the target video frame to obtain liveness detection information, which can provide liveness detection data support for subsequent biometric verification.

[0119] In step S402 of some embodiments, specifically, facial feature information refers to a set of feature points extracted from the target video frame for identity recognition. These feature points include, but are not limited to, the geometric shape and texture information of facial contours, eyes, nose, mouth, and other parts.

[0120] Specifically, an initial face convolution process can be performed on the target video frame using a face recognition network (such as the MobileNetV2 model) to obtain an initial face feature map. Then, a local convolution process is performed on the initial face feature map to obtain a local face feature map. Further point-by-point convolution is performed on the local face feature map to obtain a global face feature map. Attention processing is performed on the global face feature map to obtain an enhanced face feature map. Finally, activation processing is performed on the enhanced face feature map to obtain face feature information.

[0121] In this embodiment, face recognition is performed on the target video frame to obtain face feature information, providing face data support for subsequent biometric verification.

[0122] In step S403 of some embodiments, voiceprint features refer to features extracted from the speech signal of the target video frame for identity recognition. These voiceprint features include information such as the frequency, amplitude, and duration of the speech signal.

[0123] Specifically, a voiceprint recognition network can be used to map speech signals into target embedding vectors of fixed dimensions. Specifically, multiple time-delay layers of a TDNN (Time-Delay Neural Network) are used to capture the local voiceprint features of the target embedding vector within a preset time window (e.g., 5 frames). Multi-scale feature extraction is performed on the target embedding vector to obtain global voiceprint features. The global voiceprint features and local voiceprint features are then concatenated to obtain concatenated voiceprint features. Activation processing is then applied to the concatenated voiceprint features to obtain voiceprint feature information.

[0124] In step S404 of some embodiments, iris features refer to features extracted from the target video frame for identity recognition. The iris is the ring-shaped area in the eye located around the pupil, which has unique texture and structure.

[0125] Specifically, an iris image in a target video frame can be segmented into multiple image blocks using an iris recognition network (such as the Transformer model). A position matrix is ​​embedded in each image block to obtain the target position matrix. Self-attention processing is then performed on the target position matrix to obtain self-attention features. Finally, the self-attention features are decoded to obtain iris feature information.

[0126] In step S405 of some embodiments, identity biometric information refers to physiological characteristics that comprehensively consider liveness detection information, facial feature information, voiceprint feature information, and iris feature information.

[0127] For example, in insurance scenarios, when making an insurance claim, it is necessary to verify the user's identity. During the verification process, the user needs to undergo facial recognition or fingerprint recognition to ensure the authenticity of the user's identity and effectively prevent identity theft.

[0128] Through steps S401 to S405, multi-dimensional recognition of biometric information such as liveness, face, voiceprint, and iris provides comprehensive biometric data support for subsequent user authentication, which helps improve the accuracy of authentication and effectively prevents identity theft.

[0129] Please see Figure 5 In some embodiments, step S104 may include, but is not limited to, steps S501 to S502:

[0130] Step S501: Perform liveness verification on the target user based on the liveness detection information in the identity biometric information to obtain liveness verification data; the liveness verification data indicates that the target user has passed the liveness verification.

[0131] Step S502: If the liveness verification data indicates that the target user's liveness verification has passed, then the identity biometric information is compared with the initial identity information to obtain biometric verification data; the biometric verification data indicates whether the target user's biometric verification has passed or failed.

[0132] In step S501 of some embodiments, the liveness verification data refers to determining whether the user is a real living person by detecting the facial movements of the target user. The liveness verification data indicates whether the target user's liveness verification has passed or failed.

[0133] Specifically, the liveness detection information includes facial movements (such as head shaking, nodding, blinking, etc.) performed by the target user based on action commands. The yaw angle, pitch angle, and roll angle of the head are calculated based on the liveness detection information, and each angle is compared with a preset angle threshold to determine whether the user has performed the action according to the command. If the yaw angle is greater than or equal to 20°, it means that the user has performed the head shaking action; if the pitch angle is greater than or equal to 15°, it means that the user has performed the nodding action; if the roll angle is greater than or equal to 10°, it means that the user has performed the head tilting action; if the blink EAR (Eye Aspect Ratio) is less than 0.22, it is considered that the user has performed the blinking action.

[0134] In this embodiment, the liveness detection information in the identity biometric information is used to verify whether the target user is a real living person. This can ensure the authenticity of the target user during the identity verification process and effectively prevent attacks by forgery methods such as photos, videos or masks.

[0135] In step S502 of some embodiments, specifically, biometric verification data refers to determining the authenticity of a user's identity by detecting identity biometric information, and the biometric verification data indicates whether the target user's biometric verification has passed or failed.

[0136] Specifically, the cosine similarity between the identity biometric information and the initial identity information can be calculated to determine whether the identity biometric verification has passed.

[0137] Specifically, the initial identity information includes not only ID card information, but also voiceprint and iris information previously entered by the user.

[0138] Furthermore, the facial similarity between the facial features in the identity biometric information and the facial features in the ID card photo in the initial identity information can be calculated using the cosine similarity algorithm. If the facial similarity is greater than a preset facial similarity threshold (e.g., 0.75), it indicates that the target user's biometric verification has passed; if the facial similarity is less than or equal to the preset facial similarity threshold (e.g., 0.75), it indicates that the identity biometric verification has failed. Then, the voiceprint similarity between the voiceprint features in the identity biometric information and the voiceprint information features in the initial identity information can be calculated. If the voiceprint similarity is greater than a preset threshold... If the voiceprint similarity threshold (0.7) is met, it indicates that the target user's biometric verification has passed. If the voiceprint similarity is less than or equal to the preset voiceprint similarity threshold (0.7), it indicates that the identity biometric verification has failed. Then, the iris similarity between the iris feature in the identity biometric information and the iris information feature in the initial identity information is calculated. If the iris similarity is greater than the preset iris similarity threshold (0.75), it indicates that the target user's biometric verification has passed. If the iris similarity is less than or equal to the preset iris similarity threshold (0.75), it indicates that the identity biometric verification has failed.

[0139] Through steps S501 to S502, the authenticity of the target user's identity can be comprehensively verified from multiple biometric dimensions such as liveness, face, voiceprint, and iris, which further improves the accuracy of user identity verification and ensures the authenticity of identity information, thus helping to improve the reliability of subsequent identity information updates.

[0140] In step S105 of some embodiments, specifically, the initial identity information is verified to determine the authenticity of the organization's identity, resulting in organization identity verification data. This organization identity verification data indicates whether the verification of the organization's identity has passed or failed.

[0141] Specifically, institutional identity verification refers to verifying initial identity information through official institutions (such as public security agencies) to confirm the latest status and legality of the target user's identity information.

[0142] Specifically, through the enterprise authorization interface issued by the public security agency, the enterprise can verify the validity of the initial identity information (such as whether it has been reported lost / cancelled) and verify whether the target user's registered address has changed, so as to confirm the latest status of the target user's identity information.

[0143] For example, when renewing an insurance policy, the insurance company connects to the identity database of the public security agency through an authorized interface to compare the initial identity information (including the validity period of the certificate, the status of the certificate, and the registered address) with the identity information in the agency's database. If the identity information matches, it means that the agency's identity verification has passed; if the identity information does not match, it means that the agency's identity verification has failed.

[0144] In this embodiment, by verifying the authenticity of the initial identity information to obtain the organization identity verification data, the up-to-date status and legality of the initial identity information can be ensured, further improving the reliability of identity information updates.

[0145] Please see Figure 6 In some embodiments, step S106 includes, but is not limited to, steps S601 to S602:

[0146] Step S601: Perform a multidimensional confidence assessment based on the document identity verification data, biometric verification data, and institution identity verification data to obtain the multidimensional identity confidence score.

[0147] Step S602: Based on the multidimensional confidence level and the preset risk confidence threshold, the identity of the target user is assessed for authenticity risk to obtain the identity risk level.

[0148] In step S601 of some embodiments, specifically, multidimensional identity confidence refers to a quantitative indicator of the authenticity of the target user's identity obtained by comprehensively evaluating document identity verification data, biometric verification data, and institutional identity verification data.

[0149] Specifically, the confidence level of document identity verification data can be assessed to obtain document identity confidence level; the confidence level of biometric verification data can be assessed to obtain biometric confidence level; the confidence level of institution identity verification data can be assessed to obtain institution identity confidence level; and the multidimensional identity confidence level can be obtained by weighted summation of document identity confidence level, biometric confidence level, and institution identity confidence level.

[0150] For example, regarding identity verification data, if the identity verification data matches the initial identity information, the identity verification confidence level is high (e.g., 0.95); otherwise, the identity verification confidence level is high (e.g., 0.3). Regarding biometric verification data, if the similarity between the biometric verification data and the initial identity information is greater than a preset biometric threshold (e.g., 0.75), the biometric confidence level is high (e.g., 0.90); otherwise, the biometric confidence level is low (e.g., 0.40). If the institutional identity verification data indicates that the identity document is valid and has not been reported lost or cancelled, and the registered address has not changed, the institutional identity confidence level is high (e.g., 0.98); otherwise, the institutional identity confidence level is high (e.g., 0.20).

[0151] Specifically, if the confidence level of the identification document is 0.9, the confidence level of the biometric feature is 0.85, and the confidence level of the institutional identity is 0.95, then due to the higher authority of the institution, the institutional weight is 0.45. The next most important is the confidence level of the biometric feature, so the biometric weight is 0.3, and the confidence level of the institutional identity is 0.25. Therefore, the multidimensional identity confidence level = 0.45 × 0.9 + 0.3 × 0.85 + 0.25 × 0.95 = 0.90.

[0152] In step S602 of some embodiments, specifically, the identity risk level refers to the risk rating obtained after assessing the authenticity of the target user's identity based on multidimensional identity confidence and a preset risk confidence threshold. The identity risk level includes low risk, medium risk and high risk.

[0153] Specifically, the risk confidence thresholds include a low-risk threshold (e.g., 0.85) and a medium-risk threshold (0.7). If the multidimensional identity confidence score is higher than 0.85, the target user's identity risk level is determined to be low-risk; if the multidimensional identity confidence score is between 0.7 and 0.85, the target user's identity risk level is determined to be medium-risk; and if the multidimensional identity confidence score is lower than 0.7, the target user's identity risk level is determined to be high-risk.

[0154] Through steps S601 to S602, the authenticity of identity is verified by combining ID card documents, biometrics, and official institutions, eliminating the need for manual verification, thus improving the efficiency of identity verification. It also comprehensively assesses the authenticity of identity information and effectively solves the problem of not being able to accurately identify identity fraud when there are significant differences between the user's facial features and the archived ID photo. This significantly improves the accuracy of identity verification and helps to improve the reliability of subsequent identity information updates.

[0155] Please see Figure 7 In some embodiments, step S107 includes, but is not limited to, steps S701 to S704:

[0156] Step S701: Generate an update strategy based on the identity risk level and initial identity information to obtain the updated identity strategy.

[0157] Step S702: Identify the policy type of the identity update policy to obtain the target policy category.

[0158] Step S703: Perform information update detection on the initial identity information according to the target policy category to obtain updated identity information.

[0159] Step S704: Update the initial identity information according to the updated identity information to obtain the target identity information.

[0160] In step S701 of some embodiments, specifically, the identity update strategy refers to a specific identity information update scheme generated according to the identity risk level, which is used to guide the initial identity information to be updated.

[0161] For example, in an insurance scenario, when making an insurance claim, if the insured user's identity risk level is low, the identity update strategy can be to directly update the identity information; if the identity risk level is medium, the identity update strategy can be to perform secondary verification via SMS for the insured user, as well as to strengthen the identity through voiceprint and iris biometric recognition; if the identity risk level is high, the identity update strategy can be to force a manual review and suspend the policy claim service.

[0162] In step S702 of some embodiments, specifically, the target policy category refers to the result of classifying the identity update policy, which is used to determine the specific update operation type. The target policy category may include direct identity information update, additional identity verification, or rejection of identity update and verification of identity.

[0163] For example, in an insurance claims scenario, the identity update policy is analyzed to identify the update information in the policy. If the identity update policy contains instructions for direct update, the target policy category is direct update. If the identity update policy contains instructions for secondary verification of the insured user's SMS and for strengthening the identification of voiceprint and iris biometric features, the target policy category is additional verification. If the identity update policy contains instructions for forced transfer to manual review and suspension of policy claims service, the target policy category is reject identity update and verify identity.

[0164] In step S703 of some embodiments, specifically, updating identity information refers to obtaining new identity information after detecting and updating the initial identity information according to the target policy category.

[0165] For example, in insurance claims scenarios, if the target policy category is direct update, the identity information will be updated directly; if the target policy category is additional verification, the user will be required to provide additional identity verification information; if the target policy category is refuse update and verify identity, the insurance agent will be required to suspend the claims service and verify the user's identity. This effectively avoids the problem of policy invalidation or service disputes caused by the inability to synchronize information such as expired ID cards or changes in household registration in real time.

[0166] In this embodiment, the initial identity information is updated based on the updated identity information, which eliminates the need for manual identity detection and updating. This effectively avoids the problem of information such as expired ID cards or changes in household registration not being synchronized in real time, and significantly improves the efficiency and accuracy of identity information updates.

[0167] In step S704 of some embodiments, specifically, the target identity information refers to the updated user identity information, which includes, but is not limited to, name, ID number, ID validity period, household registration information, biometrics, etc.

[0168] Through steps S701 to S704, specific identity update strategies can be generated based on the identity risk level and initial identity information. The initial identity information can be automatically verified and updated according to the strategy category, which improves the efficiency of identity information update. Furthermore, corresponding identity update measures can be taken according to different risk levels to ensure the security and up-to-date status of identity information, thereby improving the accuracy and reliability of identity information updates.

[0169] This application first acquires the target user's ID card and its image, and extracts identity information from the image, providing a solid foundation for subsequent identity verification. Second, it verifies the ID card, performing biometric verification based on the user's biometric information and initial identity information, and further verifies the initial identity information against an organization. This multi-dimensional verification of the document's authenticity, combined with biometric verification, further ensures the authenticity of the identity information. The organization verification further ensures the up-to-date status and legality of the identity information, enhancing the reliability of identity verification. Finally, based on the ID card verification data, biometric verification data, and organization verification data, it predicts the target user's identity to obtain an identity risk level. This multi-dimensional cross-verification comprehensively assesses the authenticity and reliability of the identity information, effectively preventing identity theft. Finally, it updates the initial identity information based on the risk level, significantly improving the reliability of identity updates.

[0170] Please see Figure 8 This application also provides an identity information updating device that can implement the above-described identity information updating method. The device includes:

[0171] The document image acquisition module is used to acquire the target user's ID card and the image of the ID card.

[0172] The identity information extraction module is used to extract identity information from the document image to obtain the initial identity information of the target user;

[0173] The document verification module is used to verify ID documents and obtain document identity verification data.

[0174] The biometric verification module is used to collect the target user's identity biometric information and perform biometric verification based on the identity biometric information and the initial identity information to obtain biometric verification data.

[0175] The organization identity verification module is used to verify the authenticity of the initial identity information and obtain the organization identity verification data.

[0176] The identity verification module is used to predict the authenticity of a target user's identity based on document verification data, biometric verification data, and institutional identity verification data, and to obtain the identity risk level.

[0177] The identity update module is used to update the initial identity information according to the identity risk level to obtain the target identity information.

[0178] The specific implementation of the identity information update device is basically the same as the specific embodiment of the identity information update method described above, and will not be repeated here.

[0179] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned identity information update method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0180] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0181] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0182] The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the processing system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the identity information update method of the embodiments of this application.

[0183] The input / output interface 903 is used to implement information input and output;

[0184] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0185] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0186] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0187] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described identity information update method.

[0188] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0189] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0190] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0191] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0193] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0194] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0195] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0196] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0198] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for updating identity information, characterized in that, The method includes: Obtain the target user's ID card and obtain an image of the ID card; The identity information of the target user is extracted from the document image; The identity document is verified to obtain identity verification data; Collect the biometric information of the target user, and perform biometric verification based on the biometric information and the initial identity information to obtain biometric verification data; The initial identity information is verified to obtain the organization identity verification data. Based on the document identity verification data, the biometric verification data, and the institution identity verification data, the authenticity of the target user's identity is predicted to obtain the identity risk level. The initial identity information is updated based on the identity risk level to obtain the target identity information.

2. The method according to claim 1, characterized in that, The document identity verification data includes chip parsing data, document watermark verification data, and document microtext verification data. The step of verifying the identity document to obtain identity verification data includes: The chip of the ID card is parsed to obtain chip parsing data; wherein, the chip parsing data indicates that the ID card parsing failed; If the chip parsing data indicates that the ID card parsing failed, then the ID card is subjected to ID card watermark verification to obtain ID card watermark verification data; wherein, the ID card watermark verification data indicates whether the ID card watermark verification passed or failed. If the document watermark verification data indicates that the document watermark verification failed, then the document microtext verification is performed on the document to obtain document microtext verification data; wherein, the document microtext verification data indicates whether the document microtext verification passed or failed.

3. The method according to claim 2, characterized in that, The identification document includes a chip; The step of performing chip analysis on the ID card chip to obtain chip analysis data includes: Establish a communication connection between the document chip and the preset card reader to obtain a communication channel; The system receives an information reading instruction sent by the card reader, and reads the data of the document chip according to the information reading instruction and the communication channel to obtain the document chip data. The data of the certificate chip is parsed to obtain the chip parsing data.

4. The method according to claim 1, characterized in that, The collection of the target user's biometric information includes: The target video frames of the target user are collected, and the target video frames are subjected to liveness detection using a pre-trained biometric recognition model to obtain liveness detection information. Face recognition is performed on the target video frame to obtain facial feature information; Voiceprint recognition is performed on the target video frame to obtain voiceprint feature information; Iris recognition is performed on the target video frame to obtain iris feature information; The identity biometric information is determined based on the liveness detection information, the facial feature information, the voiceprint feature information, and the iris feature information.

5. The method according to claim 1, characterized in that, The step of performing biometric matching based on the identity biometric information and the initial identity information to obtain biometric verification data includes: The target user is subjected to liveness verification based on the liveness detection information in the biometric identity information to obtain liveness verification data; the liveness verification data indicates that the target user has passed the liveness verification. If the liveness verification data indicates that the target user's liveness verification has passed, then the identity biometric information is compared with the initial identity information to obtain the biometric verification data; the biometric verification data indicates whether the target user's biometric verification has passed or failed.

6. The method according to claim 1, characterized in that, The step of predicting the authenticity of the target user's identity based on the document verification data, the biometric verification data, and the institution's identity verification data to obtain the identity risk level includes: A multidimensional confidence assessment is performed based on the chip parsing data, the biometric verification data, and the institution identity verification data to obtain the multidimensional identity confidence score. The identity risk level of the target user is obtained by assessing the authenticity of the identity based on the multidimensional confidence level and the preset risk confidence threshold.

7. The method according to any one of claims 1 to 6, characterized in that, The step of updating the initial identity information according to the identity risk level to obtain the target identity information includes: An update strategy is generated based on the identity risk level and the initial identity information to obtain the updated identity strategy. The updated identity policy is identified by policy type to obtain the target policy category; Based on the target strategy category, the initial identity information is updated to obtain updated identity information; The initial identity information is updated based on the updated identity information to obtain the target identity information.

8. An identity information updating device, characterized in that, The device includes: The document image acquisition module is used to acquire the target user's ID card and to acquire an image of the ID card. An identity information extraction module is used to extract identity information from the document image to obtain the initial identity information of the target user. The document verification module is used to verify the identity document and obtain document identity verification data. The biometric verification module is used to collect the identity biometric information of the target user, and perform biometric verification based on the identity biometric information and the initial identity information to obtain biometric verification data. The organization identity verification module is used to verify the authenticity of the organization identity based on the initial identity information and obtain organization identity verification data. The identity verification module is used to predict the authenticity of the target user's identity based on the document identity verification data, the biometric verification data, and the institution identity verification data, and to obtain the identity risk level. The identity update module is used to update the initial identity information according to the identity risk level to obtain the target identity information.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the identity information update method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the identity information update method according to any one of claims 1 to 7.

Images