Certificate authenticity identification method and system based on multi-source data and AI

Abstract

The invention relates to the technical field of certificate authenticity identification, in particular to a certificate authenticity identification method and system based on multi-source data and AI. The method comprises the following steps: acquiring a certificate picture of a to-be-handled service uploaded by a user; extracting character information in the certificate picture through an OCR technology to obtain user identity information; obtaining a face feature vector in the certificate picture through a face recognition technology; searching and matching the obtained user identity information in a pre-constructed certificate information base; searching and matching the obtained face feature vectors in a pre-constructed face database; the authenticity of the certificate is identified according to the search matching result in the certificate information base and the search matching result in the face database; according to the invention, through a clear logical judgment and data comparison evaluation mechanism, the decision process of judgment is explainable and more transparent, and the problem of a black box existing in certificate authenticity judgment based on a deep learning method in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of document authenticity identification, and in particular to a document authenticity identification method and system based on multi-source data and AI. Background Art

[0002] Existing methods for document authenticity recognition often use deep learning-based methods to determine whether an ID image has been altered. If so, the document is identified as a forgery. However, this method has long suffered from issues such as poor interpretability and low accuracy. Furthermore, with the continuous development of AI technology and the increasing sophistication of AI forged image processing, existing image forgery detection capabilities are unable to meet practical needs. Furthermore, the deep learning models used in these methods suffer from the black box problem, meaning the model's decision-making process is opaque and difficult to explain. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for document authenticity identification based on multi-source data and AI, which can automatically process and verify document images provided by users, improve the accuracy of document authenticity identification, improve the security of business processes, and have the advantages of explainable and more transparent decision-making process.

[0004] In order to achieve the purpose of the present invention, the following technical solutions are adopted:

[0005] The first aspect of the present invention provides a method for document authenticity identification based on multi-source data and AI, comprising the following steps:

[0006] Get the ID picture uploaded by the user for the business to be processed;

[0007] Use OCR technology to extract text information from ID images to obtain user identity information;

[0008] Obtain facial feature vectors from ID images using face recognition technology;

[0009] Search and match the acquired user identity information in the pre-built certificate information database;

[0010] Search and match the acquired facial feature vector in a pre-built facial database;

[0011] The authenticity of the certificate is identified based on the search and matching results in the certificate information database and the search and matching results in the face database.

[0012] A further improvement is that the specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database includes:

[0013] If the ID number in the obtained user identity information cannot be found in the ID information database and facial feature data similar to the obtained facial feature vector cannot be found in the facial database, the ID is identified as a new ID and a real ID, and the obtained user identity information is stored in the ID information database, the obtained facial feature vector is stored in the facial database and marked as a real ID, the verification mark of the facial feature vector is set to unverified, and the process is entered into manual review. If the manual review passes, the verification mark is set to verified. If the manual review fails, the mark is changed to a forged ID.

[0014] A further improvement is that the specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database also includes:

[0015] If the ID number in the obtained user identity information is found in the ID information database but no facial feature data similar to the obtained facial feature vector is found in the face database, the ID is identified as a high-risk ID.

[0016] A further improvement is that the specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database also includes:

[0017] If the ID number in the obtained user identity information is found in the ID information database and facial feature data similar to the obtained facial feature vector is found in the face database, then it is determined whether all the information data in the obtained user identity information is completely consistent with the information data corresponding to the ID number in the ID information database. If all the information data in the obtained user identity information is inconsistent with the information data corresponding to the ID number in the ID information database, then the ID is identified as a high-risk ID.

[0018] A further improvement is that if all the information data in the obtained user identity information is consistent with the information data corresponding to the ID number in the ID information database, it is determined whether the facial feature vector is identified as a real ID in the face database. If the facial feature vector is not identified as a real ID in the face database, the ID is identified as a high-risk ID.

[0019] A further improvement is that if the facial feature vector is identified as a real document in the face database, it is determined whether the verification mark of the facial feature vector in the face database has been set to verified. If the verification mark of the facial feature vector in the face database has not been set to verified, the document is identified as a high-risk document.

[0020] A further improvement is that if the verification mark of the facial feature vector in the facial database has been set to verified, the document is identified as a genuine document.

[0021] A second aspect of the present invention provides a document authenticity verification system based on multi-source data and AI, comprising:

[0022] The image acquisition module is used to obtain the ID card images uploaded by users for the business to be processed;

[0023] The OCR module is used to extract text information from ID images using OCR technology to obtain user identity information;

[0024] Face recognition module, used to obtain facial feature vectors in ID images through face recognition technology;

[0025] A first matching module is used to search and match the user identity information obtained by the OCR module in a pre-built document information database;

[0026] The second matching module is used to search and match the facial feature vector obtained by the face recognition module in a pre-built face database;

[0027] The identification module is used to identify the authenticity of the certificate based on the search and matching results of the first matching module in the certificate information database and the search and matching results of the second matching module in the face database.

[0028] The third aspect of the present invention proposes an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a document authenticity identification method based on multi-source data and AI as described in any one of the first aspects.

[0029] The fourth aspect of the present invention proposes a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a document authenticity identification method based on multi-source data and AI as described in any one of the first aspects.

[0030] The beneficial effects of the present invention are:

[0031] The present invention constructs an ID information database and a face database. When identifying the authenticity of an ID, it compares the user identity information in the ID information database and the face feature vector in the face database, as well as verifies historical records. This determines the authenticity of the ID. Through clear logical judgment and data comparison and evaluation mechanisms, the decision-making process is explainable and more transparent, solving the black box problem that exists in the existing deep learning-based methods for determining the authenticity of IDs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1This is a flowchart of a method for document authenticity identification based on multi-source data and AI in an embodiment of the present application;

[0033] Figure 2 This is a schematic diagram of a document authenticity identification system based on multi-source data and AI according to an embodiment of the present application;

[0034] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following describes embodiments of the present application in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are illustrative only and are intended to explain the present application only and are not to be construed as limiting the present application.

[0036] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0037] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0038] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0039] Unless expressly stated to be mutually exclusive, the various embodiments disclosed in this application may be cross-combined with the relevant technical features of the various embodiments to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or resolve certain deficiencies in the prior art. Those skilled in the art should be aware of such flexibility.

[0040] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application.

[0041] The first aspect of the embodiment of the present invention proposes a method for identifying the authenticity of a certificate based on multi-source data and AI, such as Figure 1 As shown, the method includes the following steps:

[0042] Step S1: Obtain the ID card picture uploaded by the user for the business to be processed.

[0043] It is understandable that when a user needs to handle a certain business, the authenticity of the certificate held by the user needs to be verified before continuing to handle the business. At this time, the user is required to upload a picture of the certificate used to handle the business, that is, the user takes a photo of the certificate and uploads it. By obtaining the certificate picture provided by the user, a data basis is provided for subsequent identification work.

[0044] Step S2: Extract text information from the ID image using OCR technology to obtain user identity information.

[0045] It is understandable that OCR (Optical Character Recognition) technology is used to automatically read and parse the text content on the certificate, such as name, gender, date of birth, certificate number, certificate validity period, etc., and convert it into an editable and searchable data format. OCR technology can quickly and accurately extract text information on the certificate.

[0046] Step S3: Obtain the facial feature vector in the ID image through face recognition technology.

[0047] It is understandable that the face part in the ID image is analyzed through face recognition technology, unique facial feature points are extracted, and these feature points are encoded into a face feature vector value.

[0048] Step S4: Search and match the acquired user identity information in a pre-built certificate information database.

[0049] Step S5: searching and matching the acquired facial feature vector in a pre-built facial database.

[0050] Step S6: Authenticate the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database.

[0051] It can be understood that the present invention combines OCR technology, face recognition technology and database comparison technology, and can automatically identify ID information and facial features. Through the combination of multi-source data and multiple technologies, the reliability and accuracy of ID identification results are improved, and the authenticity of ID pictures uploaded by users can be accurately identified.

[0052] In a preferred solution of this embodiment, when obtaining the ID card picture uploaded by the user for the business to be processed and extracting the text information in the ID card picture through OCR technology to obtain the user's identity information, when the user takes the ID card picture, the preview image is first pre-processed in real time using a lightweight OCR engine to help the system quickly determine the text position and quality in the ID card picture. If the lightweight OCR detects in real time that the text area is blurred or incomplete, the system will immediately prompt the user to adjust the shooting angle or lighting. After the user takes and successfully uploads the ID card picture, the system will subsequently call the high-performance OCR engine to perform detailed text information recognition on the ID card picture.

[0053] In one feasible solution of this embodiment, the specific method of verifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database in step S6 includes:

[0054] If the ID number in the obtained user identity information cannot be found in the ID information database and facial feature data similar to the obtained facial feature vector cannot be found in the facial database, the ID is identified as a new ID and a real ID, and the obtained user identity information is stored in the ID information database, the obtained facial feature vector is stored in the facial database and marked as a real ID, the verification mark of the facial feature vector is set to unverified, and the process is entered into manual review. If the manual review passes, the verification mark is set to verified. If the manual review fails, the mark is changed to a forged ID.

[0055] It's understandable that storing the acquired user identity information in the ID information database and storing the facial feature vector in the face database and identifying it as a genuine ID is intended to record and archive new ID information so that subsequent encounters with the same ID information can be directly matched. Setting the facial feature vector's verification flag to "unverified" indicates that, although initially determined to be authentic, further manual review is required to ensure accuracy. Assume that the user identity information extracted from the ID image via OCR technology in step S2 is as follows: (Name: Zhang Hua; Gender: Male; Date of Birth: January 1, 1990; ID Number: 12345678). If no record with the ID number 12345678 is found in the ID information database, and no facial feature data similar to the acquired facial feature vector is found in the facial database, the system will assume that this ID is a new ID (used for the first time to handle this business), and the system will store the user's identity information (name: Zhang Hua; gender: male; date of birth: January 1, 1990; ID number: 12345678) in the ID information database and the acquired facial feature vector in the facial database, and preliminarily identify it as a real ID. Since it is a new ID, the system will set the verification mark of the facial feature vector to unverified, and at the same time enter the manual review process. If the manual review passes, the verification mark will be set to verified. If the manual review fails, the mark will be changed to a forged ID.

[0056] In addition, the system adds a timestamp to each verification mark to track the verification history and status changes of the certificate, facilitating subsequent audits and problem tracing.

[0057] In a feasible solution of this embodiment, in step S6, the specific method of identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database further includes:

[0058] If the ID number in the obtained user identity information is found in the ID information database but no facial feature data similar to the obtained facial feature vector is found in the face database, the ID is identified as a high-risk ID and the identification result is output.

[0059] It is understandable that this situation is likely to occur because the ID number has been misused but a different face has been used. Assume that the user identity information extracted from the ID image by OCR technology in step S2 is as follows: (Name: Zhang Hua; Gender: Male; Date of Birth: January 1, 1990; ID Number: 12345678). If a record with ID number 12345678 is found in the ID information database, but no facial feature data similar to the obtained facial feature vector is found in the face database, the ID is identified as a high-risk ID and the identification result is output.

[0060] In a feasible solution of this embodiment, in step S6, the specific method of identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database further includes:

[0061] If the ID number in the obtained user identity information is found in the ID information database and facial feature data similar to the obtained facial feature vector is found in the face database, then it is determined whether all the information data in the obtained user identity information is completely consistent with the information data corresponding to the ID number in the ID information database. If there is any inconsistency between all the information data in the obtained user identity information and the information data corresponding to the ID number in the ID information database, then the ID is identified as a high-risk ID and the identification result is output.

[0062] It is understandable that by first verifying the ID number in the user identity information and then verifying other information in the user identity information, it is possible to quickly screen out obviously erroneous IDs in the early stages and reduce unnecessary consumption of computing resources. Assume that the user identity information extracted from the ID image by OCR technology in step S2 is as follows: (name: Zhang Hua; gender: male; date of birth: January 1, 1990; ID number: 12345678). If a record with an ID number of 12345678 is found in the ID information database and facial feature data similar to the acquired facial feature vector is found in the face database, then the acquired user identity information (name, date of birth, gender) is further checked to see if it is completely consistent with the information data corresponding to the ID number in the ID information database. If not, the ID is identified as a high-risk ID and the identification result is output.

[0063] Furthermore, if all the information data in the obtained user identity information is completely consistent with the information data corresponding to the certificate number in the certificate information database, then it is determined whether the facial feature vector is identified as a real certificate in the face database. If the facial feature vector is not identified as a real certificate in the face database, then the certificate is identified as a high-risk certificate. If the facial feature vector is identified as a real certificate in the face database, then it is determined whether the verification mark of the facial feature vector in the face database has been set to verified. If the verification mark of the facial feature vector in the face database has not been set to verified, then the certificate is identified as a high-risk certificate. If the verification mark of the facial feature vector in the face database has been set to verified, then the certificate is identified as a real certificate, and the identification result is output.

[0064] It can be understood that the present invention determines the nature of the document more accurately by identifying the facial feature vector in the facial database and judging the verification mark. Only when all conditions are met, that is, the facial feature vector is identified as a real document and the verification mark is verified, it is finally identified as a real document. This multi-dimensional judgment method can greatly improve the accuracy and reliability of document identification and reduce the possibility of misjudgment.

[0065] In a preferred solution of this embodiment, in step S1, after the user uploads the ID image, the system automatically calls the cloud-based quantum random number generation service to generate a security verification code. The security verification code is embedded in the ID image uploaded by the user as a watermark and displayed on the web page. The user needs to read and enter this verification code on the web page. The specific method is as follows:

[0066] User uploads ID image: Users upload ID images for pending transactions through the web interface. The system receives the ID images and performs a preliminary quality check to ensure that the images are clear, complete, and meet verification requirements.

[0067] Calling the quantum random number generation service: The system automatically calls the quantum random number generator service in the cloud and requests the generation of a unique security verification code. The verification code consists of an unpredictable string of numbers and letters, and the length can be set according to security requirements (for example, 6-8 digits).

[0068] Embed watermark: The generated security verification code is embedded in the ID image uploaded by the user in the form of a transparent watermark. The position and transparency of the watermark are optimized to ensure that it does not affect the OCR technology's recognition of the ID content, while ensuring that the verification code is clear and readable.

[0069] Return the ID image with a watermark: The system will return the ID image with the verification code watermark embedded in it and display it on the web interface. The user needs to carefully view the ID image, find and remember the specific content of the verification code.

[0070] User input verification code: The user manually enters the verification code read from the ID image through the input box provided in the web interface.

[0071] Verification code verification: The system receives the verification code entered by the user and compares it with the previously generated verification code. If the two are consistent, the verification is successful and the system continues with the subsequent document authenticity verification process. If they are inconsistent, the system will prompt the user to re-upload the document image or try to enter the verification code again.

[0072] It is understandable that by requiring users to read and enter the verification code immediately after uploading the ID picture, it can be ensured that the operation is completed by a real user rather than by an automated script or robot program. This real-time interaction increases the "human factor" in the verification process and improves the system's anti-fraud ability.

[0073] In general, the present invention constructs an ID information database and a face database, and when identifying the authenticity of the ID, simultaneously compares the user identity information in the ID information database and the face feature vector in the face database, as well as verifies the historical records to judge the authenticity of the ID. Through clear logical judgment and data comparison and evaluation mechanisms, the decision-making process of the judgment is explainable and more transparent, solving the black box problem of the existing deep learning-based method in judging the authenticity of the ID (that is, the decision-making process of the model is opaque and difficult to explain).

[0074] The second aspect of the embodiment of the present application proposes a certificate authenticity identification system based on multi-source data and AI, such as Figure 2 As shown, it is a structural diagram of a certificate authenticity identification system based on multi-source data and AI provided in accordance with an embodiment of the present invention, which corresponds to the certificate authenticity identification method based on multi-source data and AI provided in the above-mentioned embodiment of the present invention. Since the certificate authenticity identification system based on multi-source data and AI provided in the embodiment of the present invention corresponds to the certificate authenticity identification method based on multi-source data and AI provided in the above-mentioned embodiment of the present invention, the implementation method of the above-mentioned certificate authenticity identification method based on multi-source data and AI is also applicable to the certificate authenticity identification system based on multi-source data and AI provided in this embodiment.

[0075] Specifically, if Figure 2 As shown in FIG, a document authenticity identification system based on multi-source data and AI includes:

[0076] The image acquisition module is used to obtain the certificate images uploaded by users for the business to be processed.

[0077] The OCR module is used to extract text information from ID images using OCR technology to obtain user identity information.

[0078] The face recognition module is used to obtain the facial feature vector in the ID image through face recognition technology.

[0079] The first matching module is used to search and match the user identity information obtained by the OCR module in a pre-built certificate information database.

[0080] The second matching module is used to search and match the facial feature vector obtained by the face recognition module in a pre-built face database.

[0081] The identification module is used to identify the authenticity of the certificate based on the search and matching results of the first matching module in the certificate information database and the search and matching results of the second matching module in the face database.

[0082] See also Figure 3 , the embodiments of the present application also provide an electronic device and a computer-readable storage medium.

[0083] like Figure 3 FIG2 is a schematic diagram of an electronic device provided by one embodiment of the present invention. The electronic device of this embodiment includes a processor 11, a memory 12, and a computer program stored in the memory and executable by the processor 11. When the processor 11 executes the computer program, it implements the steps of the aforementioned method for document authenticity verification based on multi-source data and AI. Alternatively, when the processor 11 executes the computer program, it implements the functions of the modules / units described in the aforementioned device embodiments.

[0084] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor 11 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0085] The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of an electronic device and does not limit the electronic device. The electronic device may include more or fewer components than shown, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0086] The processor 11 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0087] The memory 12 can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system 121, an application 122 required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0088] Wherein, if the module / unit integrated in the electronic device is implemented in the form of 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 present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0089] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the system embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without any creative work.

[0090] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0091] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for identifying the authenticity of a certificate based on multi-source data and AI, characterized in that: The following steps are involved: Get the certificate image uploaded by the user for the pending business; Use OCR technology to extract text information from the ID image to obtain user identity information; Obtain the facial feature vector in the ID image through face recognition technology; Search and match the acquired user identity information in a pre-built certificate information database; Search and match the acquired facial feature vector in a pre-built facial database; The authenticity of the certificate is identified based on the search and matching results in the certificate information database and the search and matching results in the face database.

2. According to claim 1, a method for identifying the authenticity of a certificate based on multi-source data and AI is characterized in that: The specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database includes: If the ID number in the obtained user identity information cannot be found in the ID information database and facial feature data similar to the obtained facial feature vector cannot be found in the facial database, the ID is identified as a new ID and a real ID, and the obtained user identity information is stored in the ID information database, the obtained facial feature vector is stored in the facial database and marked as a real ID, the verification mark of the facial feature vector is set to unverified, and the process is entered into manual review. If the manual review passes, the verification mark is set to verified. If the manual review fails, the mark is changed to a forged ID.

3. The method for identifying the authenticity of a certificate based on multi-source data and AI according to claim 2, characterized in that: The specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database also includes: If the certificate number in the obtained user identity information is found in the certificate information database, but the facial feature data similar to the obtained facial feature vector is not found in the face database, the certificate is identified as a high-risk certificate.

4. The method for identifying the authenticity of a certificate based on multi-source data and AI according to claim 2, characterized in that: The specific method for identifying the authenticity of the certificate based on the search and matching results in the certificate information database and the search and matching results in the face database also includes: If the ID number in the obtained user identity information is found in the ID information database and facial feature data similar to the obtained facial feature vector is found in the face database, then it is determined whether all the information data in the obtained user identity information is completely consistent with the information data corresponding to the ID number in the ID information database; if all the information data in the obtained user identity information is inconsistent with the information data corresponding to the ID number in the ID information database, then the ID is identified as a high-risk ID.

5. The method for identifying the authenticity of a certificate based on multi-source data and AI according to claim 4, characterized in that: If all the information data in the obtained user identity information is consistent with the information data corresponding to the ID number in the ID information database, it is determined whether the facial feature vector is identified as a real ID in the face database. If the facial feature vector is not identified as a real ID in the face database, the ID is identified as a high-risk ID.

6. The method for identifying the authenticity of a certificate based on multi-source data and AI according to claim 5, characterized in that: If the facial feature vector is identified as a real document in the face database, it is determined whether the verification mark of the facial feature vector in the face database has been set to verified. If the verification mark of the facial feature vector in the face database has not been set to verified, the document is identified as a high-risk document.

7. The method for identifying the authenticity of a certificate based on multi-source data and AI according to claim 6, characterized in that: If the verification mark of the facial feature vector in the facial database has been set to verified, the document is authenticated as a genuine document.

8. A certificate authenticity identification system based on multi-source data and AI, characterized in that: include: The image acquisition module is used to obtain the certificate images uploaded by the user for the business to be processed; OCR module, used to extract text information from the certificate image through OCR technology to obtain user identity information; A face recognition module is used to obtain the face feature vector in the ID card image through face recognition technology; A first matching module, used to search and match the user identity information obtained by the OCR module in a pre-built certificate information database; A second matching module is used to search and match the facial feature vector obtained by the face recognition module in a pre-built face database; The identification module is used to identify the authenticity of the certificate based on the search and matching results of the first matching module in the certificate information database and the search and matching results of the second matching module in the face database.

9. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for identifying authenticity of a certificate based on multi-source data and AI as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a method for document authenticity identification based on multi-source data and AI as described in any one of claims 1 to 7.

Images