A method for identifying an electronic ID card and related equipment

By obtaining the encrypted ID card information, generating a certificate identification warning model, combining feature extraction and data mining technology, the problem of poor anti-counterfeiting performance of existing certificate anti-counterfeiting methods is solved, and the accuracy and security of document identification are improved.

CN118551361BActive Publication Date: 2024-11-15BEIJING NJA INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411017771.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-15
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The existing anti-counterfeiting methods for certificates are based on printing technology, with low cost but poor anti-counterfeiting performance, low visual recognition reliability, easy to be imitated, and difficult to ensure the authenticity and effectiveness of certificates.

Method used

By obtaining the ID card information after the target user's encryption process, coarse identity positioning, generating a document identification warning model, comparing and pre-set user identity information to determine the authenticity of the document, and using feature extraction and data mining technology to generate training samples , train the certificate identification warning model, and perform the attribute information and facial identity information of the document to be identified to generate detection results.

Benefits of technology

It improves the accuracy of identification of documents, reduces the risk of identity fraud, provides more effective security protection measures, and enhances the anti-counterfeiting performance of documents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118551361B_ABST
    Figure CN118551361B_ABST
Patent Text Reader

Abstract

The present application discloses an electronic ID card recognition method and related equipment, which are applied in the field of data processing technology. The present application obtains a total sample set, the certificate information to be recognized, and the face identity information of the certificate holder; obtains a preset certificate processing rule that matches the face identity information of the certificate holder, wherein the preset certificate processing rule is used to decrypt the certificate information to be recognized; pre-processes the total sample set to generate a training sample set with identification information; obtains an initial certificate recognition warning model that matches the identification information; trains the initial certificate recognition warning model based on the training sample set with identification information to generate a target certificate recognition warning model; pre-processes the certificate information to be recognized to generate the attribute information of the certificate to be recognized; processes the attribute information of the certificate to be recognized and the face identity information of the certificate holder based on the target certificate recognition warning model to generate a detection result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for identifying an electronic identity card and related equipment. Background Art

[0002] Certificates are proof of identity for individuals or organizations, and are the basis for the normal conduct of various social and economic activities. The anti-counterfeiting and authentication of certificates is necessary for the normal conduct of social activities and is the basis for ensuring the validity of certificates. Security certificates usually refer to a type of document that can prove a person's identity, experience, or has special value. Certificates are a type of document that is a carrier of information and a voucher for proving relevant facts. For example, a passport is a typical type of certificate. Certificates can be used to confirm the nationality, identity, and travel trajectory of people entering and leaving the country. Because it is necessary to ensure the legitimacy and authenticity of the information and data carried by such certificates, strong security protection measures need to be implemented to ensure the security of certificates. Certificates contain a series of probative data and information, and their authenticity and validity need to be verified within a certain range and within a given time.

[0003] The currently commonly used document anti-counterfeiting method is mainly based on printing technology, combined with photos, signatures and seals. This method has the advantages of low cost and direct visual identification, but has poor anti-counterfeiting performance, low visual recognition reliability, and is easy to imitate.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide an electronic ID card recognition method and related equipment, which at least overcomes the problems existing in the prior art to a certain extent, by obtaining the encrypted ID card information of the target user, processing it to obtain the rough identity positioning information of the target user, and obtaining the corresponding document recognition warning model based on the rough identity positioning information. Based on the mapping table stored in the server, the user identity information matching the target user is obtained, the corresponding verification information is obtained through the document recognition warning model, and the generated verification information is compared with the user identity information preset by the target user, so as to judge the authenticity of the current document to be identified.

[0006] According to one aspect of an embodiment of the present application, a method for recognizing an electronic ID card is provided, the method comprising: obtaining a total sample set, information of an ID card to be recognized, and facial identity information of a cardholder, the total sample set being electronic ID card information of different users received within a preset time period, the ID card information to be recognized comprising encrypted ID card information of a target user; obtaining a preset ID card processing rule that matches the facial identity information of the cardholder, wherein the preset ID card processing rule is used to decrypt the ID card information to be recognized; preprocessing the total sample set to generate a training sample set with identification information, wherein the identification information The information is used to characterize that the user's electronic identity certificate information is in an abnormal state; an initial certificate recognition warning model matching the identification information is obtained, wherein the initial certificate recognition warning model is set based on the electronic identity certificate information received within a preset time period; the initial certificate recognition warning model is trained based on the training sample set with the identification information to generate a target certificate recognition warning model; the certificate information to be recognized is preprocessed to generate attribute information of the certificate to be recognized; the attribute information of the certificate to be recognized and the facial identity information of the certificate holder are processed based on the target certificate recognition warning model to generate a detection result.

[0007] In some embodiments of the present application, the total sample set is preprocessed to generate a training sample set with identification information, including: extracting features from the total sample set to determine an original feature library; dividing each feature data set according to the original feature library to generate a training data set and a test data set; using a classifier to predict each test data set divided from the original feature library to determine a prediction result; using a preset algorithm to train each training data set divided from the original feature library to obtain a test set class prediction result; and generating a training sample with identification information based on the prediction result and the test set class prediction result.

[0008] In some embodiments of the present application, feature extraction is performed on the total sample set to determine an original feature library, including: obtaining a historical electronic identity certificate data set that has the same provincial information as the information of the certificate to be identified, wherein the historical electronic identity certificate data set includes electronic identity certificate information of a target group within the province; processing the historical electronic identity certificate data set to obtain abnormal text features and correlation co-occurrence frequencies; processing the abnormal text features and the correlation co-occurrence frequencies to generate correlation matrix information; generating a number of text feature data based on the correlation matrix information; and generating an original feature library based on the number of text feature data.

[0009] In some embodiments of the present application, the feature extraction of the total sample set to determine the original feature library further includes: the method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is: ;in, represents the number of times concept i and concept j co-occur in the report set, represents the total number of times concept j appears, represents the frequency of concept i appearing when concept j appears, and a correlation matrix A can be constructed based on the co-occurrence frequency P: the method includes a calculation formula for calculating the correlation matrix, and the calculation formula is: ;in, is the co-occurrence frequency threshold, if Greater than or equal to threshold , then it is considered that there is a correlation from concept i to concept j, otherwise there is no correlation.

[0010] In some embodiments of the present application, the certificate information to be identified is preprocessed to generate attribute information of the certificate to be identified, including: processing the certificate information to be identified based on preset certificate processing rules to generate identity attribute information of a target user; obtaining a preset user identity information table, wherein the preset user identity information table includes physical examination information and work information of the target user within a preset time period; processing the identity attribute information of the target user based on the preset user identity information table to generate work attribute information of the target user, wherein the work attribute information of the target user includes the latest facial image information of the target user within the preset time period and the physical condition information of the target user.

[0011] In some embodiments of the present application, the certificate information to be identified is preprocessed to generate attribute information of the certificate to be identified, which also includes: processing the certificate information to be identified to generate reception time information of the certificate information to be identified, residence information of the target user and purpose information of the certificate to be identified; generating purpose information of the certificate information to be identified based on the reception time information of the certificate information to be identified, the residence information of the target user and the use information of the certificate to be identified based on preset certificate processing rules; obtaining validity period information of the identity document corresponding to the certificate information to be identified; processing the purpose information of the certificate information to be identified based on the validity period information of the identity document and the work attribute information of the target user to generate attribute information of the certificate information to be identified.

[0012] In some embodiments of the present application, the attribute information of the certificate to be identified and the facial identity information of the certificate holder are processed based on the target certificate recognition warning model to generate a detection result, including: processing the usage information of the certificate to be identified and the work attribute information of the target user based on the target certificate recognition warning model to generate a first matching value; processing the facial identity information of the certificate holder based on the target certificate recognition warning model to generate a second matching value; processing the first matching value and the second matching value based on the target certificate recognition warning model to generate a detection result, wherein the detection result is an identity matching result between the certificate to be identified and the certificate holder.

[0013] According to another aspect of the embodiment of the present application, there is provided an electronic ID card recognition device, the device comprising: an acquisition module, for acquiring a total sample set, information of an ID card to be recognized, and facial identity information of a cardholder, the total sample set being electronic ID card information of different users received within a preset time period, the ID card information to be recognized comprising encrypted ID card information of a target user; obtaining a preset ID card processing rule that matches the facial identity information of the cardholder, wherein the preset ID card processing rule is used to decrypt the ID card information to be recognized; obtaining an initial ID card recognition warning model that matches the identification information, wherein the initial ID card recognition warning model is used to decrypt the ID card information to be recognized; obtaining an initial ID card recognition warning model that matches the identification information, wherein the initial ID card recognition warning model is used to decrypt the ID card information to be recognized; obtaining an initial ID card recognition warning model that matches the identification information; ... The warning model is set based on the electronic identity certificate information received within a preset time period; the processing module is used to pre-process the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's electronic identity certificate information is in an abnormal state; based on the training sample set with identification information, the initial certificate recognition warning model is trained to generate a target certificate recognition warning model; the certificate information to be recognized is pre-processed to generate attribute information of the certificate to be recognized; based on the target certificate recognition warning model, the attribute information of the certificate to be recognized and the facial identity information of the certificate holder are processed to generate a detection result.

[0014] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising a computer-readable storage medium storing a computer program and a processor, wherein when the computer program is read and executed by the processor, any of the above methods is implemented.

[0015] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, any of the above methods is implemented.

[0016] According to another aspect of an embodiment of the present application, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to implement any of the methods described above.

[0017] The technical solution provided by one aspect of the embodiments of the present application may include the following beneficial effects: the electronic ID card recognition method provided by the embodiments of the present application obtains the identity information of the cardholder and the card recognition warning model, obtains the corresponding card processing rules based on the cardholder's identity information, and then processes the card information to be recognized. If the card processing rules can successfully decrypt the card information to be recognized, the attribute information of the card to be recognized and the facial identity information of the cardholder are processed based on the card recognition warning model to generate corresponding detection results. By obtaining the work information and corresponding physical examination information of the target user on the card information to be recognized, the latest facial image information of the target user and the daily itinerary of the target user and the occasions in which the target user may appear in what time period are obtained, and then compared with the current information of the cardholder, the accuracy of card recognition is effectively improved and the risk of identity fraud is reduced.

[0018] Other features and advantages of the present application will be described in the subsequent description, and some of them will become obvious from the description, or some of them can be inferred or determined unambiguously from the description, or can be understood by implementing the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flowchart showing a method for identifying an electronic ID card provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram showing the structure of an electronic ID card recognition device provided in one embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0025] 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 those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0026] By obtaining the identity information of the certificate holder, the corresponding certificate processing rules are obtained, and then the certificate information to be identified is processed.

[0027] like Figure 1 As shown, an embodiment of the present application provides a method for identifying an electronic ID card photo, which is applied to a server. In some implementations, the method includes:

[0028] S101. Obtain the total sample set, the document information to be identified, and the facial identity information of the holder.

[0029] In one implementation, the total sample set is the electronic certificate information of different users received within a preset time period, which includes both real and forged electronic certificate information. In addition, the certificate information to be identified includes the encrypted ID card information of the target user, and the electronic chip is processed by character recognition technology and radio frequency reading technology to obtain the encrypted ID card information of the target user in the electronic chip.

[0030] The encrypted ID card information can be partially encrypted or fully encrypted. For example, only the user name and the first / last few digits of the ID card number are not encrypted, and the other information is encrypted, or all the information is encrypted. This application does not limit this, and the applicant can set it according to actual needs. This application does not limit how to obtain the encrypted ID card information of the target user. The applicant can set it according to actual needs. For example, the encrypted ID card information of the target user is written into the electronic chip of the certificate for subsequent anti-counterfeiting detection of the certificate information to be identified. By encrypting the ID card information written into the chip, the content of the chip can be effectively prevented from being tampered with.

[0031] S102: Obtain preset document processing rules that match the facial identity information of the cardholder.

[0032] In one implementation, the preset certificate processing rules are used to decrypt the certificate information to be identified, and the certificate information to be identified is processed based on the preset certificate processing rules, and the user private key preset by the certificate holder is obtained, wherein the user private key is used to decrypt the encrypted certificate information to be identified. The preset certificate processing rules are set by the certificate holder based on the preset certificate information encryption rules, that is, the user private key is sent to the server by the certificate holder in advance. Before obtaining the certificate information to be identified sent by the client, the client is authenticated first, and the identity information of the client is obtained, thereby obtaining the user private key of the certificate holder based on the preset identity information mapping table, and by obtaining the identity information of the certificate holder, the corresponding certificate processing rules are obtained, and then the certificate information to be identified is processed.

[0033] S103: Preprocess the total sample set to generate a training sample set with identification information.

[0034] In one implementation, feature extraction is performed on the total sample set to determine the original feature library, and the electronic ID card information is processed based on preset processing rules to generate standardized features, wherein the standardized features are text format features of encrypted ID card information customized by different authorities or different companies; the standardized features are processed based on preset feature screening and dimensionality reduction rules to generate original features; and the original feature library is generated from a number of original features. Each feature data set is divided according to the original feature library to generate a training data set and a test data set; a classifier is used to predict each test data set divided from the original feature library to determine the prediction result; a preset algorithm is used to train each training data set divided from the original feature library to obtain a test set class prediction result; a training sample with identification information is generated based on the prediction result and the test set class prediction result, wherein the identification information is used to characterize that the user's identity electronic certificate information is in an abnormal state, as described below for details.

[0035] In another embodiment, a historical electronic identity certificate data set with the same province information as the certificate information to be identified is obtained, wherein the historical electronic identity certificate data set includes the electronic identity certificate information of the target group in the province, that is, the identity information of all or some people in different periods. Since the identity card has a certain validity period, the facial information of different periods may change to a certain extent. The historical electronic identity certificate data set is processed to obtain abnormal text features and correlation co-occurrence frequency; the abnormal text features and correlation co-occurrence frequency are processed to generate correlation matrix information; a number of text feature data are generated based on the correlation matrix information; and an original feature library is generated based on a number of text feature data. The abnormal text type and its correlation are extracted from the electronic identity certificate data set by data mining, the relationship between the identity document and the user is established, and the identity information prior knowledge graph is formed. Then, the relevant department heads check whether the correlation between concepts is established one by one, complete the calibration of the correlation matrix, and complete the screening of the text feature data.

[0036] In another embodiment, the present invention further includes a calculation formula for calculating the correlation co-occurrence frequency, and the specific calculation formula is: ;in, represents the number of times concept i and concept j co-occur in the report set, represents the total number of times concept j appears, It represents the frequency of concept i appearing when concept j appears. Based on the co-occurrence frequency P, the correlation matrix A can be constructed:

[0037] In another embodiment, the present invention also includes a calculation formula for calculating the correlation matrix, and the specific calculation formula is: ;in, is the co-occurrence frequency threshold, if Greater than or equal to threshold , then it is considered that there is a correlation from concept i to concept j, otherwise there is no correlation.

[0038] S104: Acquire an initial document recognition warning model that matches the identification information.

[0039] In one embodiment, the initial certificate recognition warning model is set based on the electronic identity certificate information received within a preset time period, that is, the corresponding certificate recognition warning model is set according to the authenticity of the electronic identity certificate information received at different times. For example, identity card information has a corresponding validity period, and the facial information of the same user at different times may change to varying degrees. The initial certificate recognition information will obtain the latest facial information of each user within the preset time period.

[0040] S105: Training the initial certificate recognition warning model based on the training sample set with identification information to generate a target certificate recognition warning model.

[0041] In one embodiment, feature extraction is performed on the total sample set to determine the original feature library, wherein the feature extraction includes four features: original features, statistical features, frequency domain features, and time domain features. The commonly used features extracted are specifically introduced as follows: Original features: The original features are the collected data, after preprocessing, using all the information in each sample data matrix for model training. In order not to lose sample information, each curve of sample Xi is directly unfolded and stretched into a row vector. Statistical features: Statistical features consider the change trend of all data points on the curve. By extracting statistical features, the dimension of the data sample can be reduced, which is convenient for analyzing genetic data and accelerating the convergence speed during model training. The extracted statistical features include maximum value, minimum value, mean, variance, and standard deviation. Frequency domain features: Wavelet transform is performed on the data set, and the coefficients obtained by the second-order wavelet transform are used as new features to constitute frequency domain features. Time domain features: Time domain features are mainly based on the time perspective, and the law of change of the invention signal and system. Time domain features can reflect the information of curve data in time change. This process mainly extracts the first-order forward difference of the data set to form the first-order difference time domain features, and uses the exponential moving average feature processing method.

[0042] According to the original feature library, each feature data set is divided to generate a training data set and a test data set; the classifier is used to predict each test data set divided by the original feature library to determine the prediction result; the preset algorithm is used to train each training data set divided by the original feature library to obtain the test set class prediction result; according to the prediction result and the test set class prediction result, a training sample with identification information is generated, and the identification information is used to characterize that the user's identity electronic certificate information is in an abnormal state. Specifically, the data classification result corresponding to the training set is obtained, because the classification result of each training set can be determined in advance, and the data can be directly obtained from the outside. Compare the prediction result with the data classification result to determine the first comparison result; compare the test set class prediction result with the data classification result to determine the second comparison result; judge whether the second comparison result meets the preset requirements with the first comparison result. When the preset requirements are met, it indicates that the detection result of the current certificate recognition warning model is relatively accurate. At this time, the current certificate recognition warning model can be used as the target certificate recognition warning model.

[0043] S106: Preprocess the document information to be identified to generate attribute information of the document to be identified.

[0044] In one implementation, the identification document information is processed based on a preset document processing rule to generate the identity attribute information of the target user, and a preset user identity information table is obtained, wherein the preset user identity information table includes the physical examination information and work information of the target user within a preset time period. The identity attribute information of the target user is processed based on the preset user identity information table to generate the work attribute information of the target user, wherein the work attribute information of the target user includes the latest facial image information of the target user within a preset time period and the physical condition information of the target user.

[0045] That is, the work information and corresponding physical examination information of the target user on the ID card to be identified are obtained, so as to obtain the target user's latest facial image information and the target user's daily itinerary, as well as the time period and occasions in which he may appear, so as to provide a theoretical basis for the subsequent target ID card recognition early warning model to process, and effectively avoid the deviation in recognition results due to the facial image being too different from the image on the ID card photo when the user is sick or has undergone relevant facial surgery.

[0046] In another embodiment, the identification document information is processed to generate the information of the receipt time of the identification document information, the residence information of the target user and the usage information of the identification document to be identified, and the information of the receipt time of the identification document information, the residence information of the target user and the usage information of the identification document to be identified are processed based on the preset document processing rules to generate the usage information of the identification document information. In addition, the validity period information of the identity document corresponding to the identification document information is obtained, and the usage information of the identification document information is processed based on the validity period information of the identity document and the work attribute information of the target user to generate the attribute information of the identification document information to be identified.

[0047] Attribute information is mainly used to assist in identifying the target user, for example, what is the purpose of the certificate information to be identified sent by the certificate holder, the real ID information of the target user on the certificate information to be identified, whether the certificate holder has the authority to identify the certificate information to be identified, and what is the purpose of identifying the certificate information to be identified.

[0048] By counting the ID information to be identified sent by each client in the past certain period of time, including the client IP address, the number of sends, and the sending time, the sending time is introduced to distinguish between normal office hours, overtime office hours, and other time periods, and different calculation weights are assigned. The newly received ID information to be identified is compared with the historical data that has been counted, and finally it is determined whether the received ID information to be identified is a spam request. In addition, if it has been determined to be a spam request, the client will be set to a frozen state. The next time any ID information to be identified is sent through the client, the user's identity must be additionally verified before normal use can be resumed. The judgment of the client address ownership is introduced, and the automatic blocking and release process design for the theft of the company's internal email account is added, which fundamentally solves the problem of the company's internal email being continuously used for malicious purposes after being stolen.

[0049] In addition, the validity period information of the received certificate information to be identified will also be determined. If the validity period information of the certificate information to be identified has expired beyond the preset time when the certificate information to be identified is received, even if the certificate information to be identified is correct, it will be determined that the certificate information to be identified is forged.

[0050] S107, processing the attribute information of the document to be identified and the facial identity information of the holder based on the target document recognition warning model to generate a detection result.

[0051] In one implementation, the purpose information of the identification document information and the work attribute information of the target user are processed based on the target document identification warning model to generate a first matching value, that is, to judge the rationality of the current user's possible actions, that is, to judge the possibility of the user making actions that require identification of the ID card information within the time period based on the user's working hours, and to judge whether the user's current physical state is likely to complete the purpose for which the identification information will be used. The server will generate a first matching value based on the user's working hours, behavioral habits and other information to judge the rationality of the user's use of the document within a specific time period, and whether the user's current physical state is suitable for completing the purpose for which the document will be used.

[0052] The first matching value = w1×time rationality + w2×behavior pattern matching + w3×work attribute matching, where: time rationality: calculated based on the matching degree between the user’s working time and the time of using the ID card, logistic regression or other classification algorithms can be used; behavior pattern matching: based on the similarity between the user’s past behavior pattern and the current ID card usage behavior, cosine similarity and other measurement methods can be used; work attribute matching: based on the correlation between the user’s work attributes and the ID card usage scenario, a simple attribute matching algorithm may be used; weights w1, w2, w3 can be adjusted according to actual importance.

[0053] Specifically, the calculation formula for time rationality is as follows:

[0054] logit(P(time rationality=1))==β0+β1×working time+β2×document usage time; where logit is the link function of logistic regression, usually using the natural logarithm; β0, β1, β2 are model parameters, which can be learned through methods such as maximum likelihood estimation.

[0055] Specifically, the calculation formula for the behavior pattern matching degree is as follows:

[0056]

[0057] Among them, A and B represent the user's historical behavior pattern and current behavior pattern respectively; A⋅B is the dot product of the vectors, and ∥A∥ and ∥B∥ are the Euclidean norms of the vectors.

[0058] Specifically, the calculation formula for job attribute matching is as follows:

[0059]

[0060] Among them, the work attribute vector W=[W1,W2,...,Wn], where Wn represents the value of the nth work attribute (for example, working hours, work location, nature of work, etc.), Wideal is the document usage scenario, W⋅Wideal is the dot product of two vectors, and ∥W∥ and ∥Wideal∥ are the Euclidean norms of the vectors.

[0061] The facial identity information of the cardholder is processed based on the target document recognition warning model to generate a second matching value, and the latest facial image information of the cardholder and the user on the ID card is compared to determine the similarity between the two, rather than directly comparing the cardholder with the photo information on the ID card. The server will process the latest facial image information of the cardholder and compare it with the latest facial image on the ID card to generate a second matching value. This step is not a simple comparison of the cardholder and the photo on the document, but a more in-depth similarity analysis.

[0062] The second matching value = face similarity = 1 / (1+d(face image A, face image B)); wherein face image A is the real-time face image of the cardholder, face image B is the face image on the card, and d is the distance measurement between the face images, which can be Euclidean distance, cosine distance or other similarity measurement methods.

[0063] The first matching value and the second matching value are processed based on the target certificate recognition warning model to generate a test result, wherein the test result is the identity matching result of the certificate to be identified and the certificate holder, to determine whether there is a person with a similar appearance or a person who has undergone plastic surgery who has obtained the certificate to be identified and then done something unfavorable. If the test result is that the information does not match, even if the certificate to be identified is true and accurate, it will be prompted that the certificate to be identified is wrong. In addition, different display screens will be generated according to the test results, showing the certificate holder that the certificate to be identified is wrong, and showing the person-certificate information mismatch to the management personnel. This embodiment does not limit the calculation method for generating the first matching value and the second matching value, and the applicant can set it according to actual needs.

[0064] This method can effectively improve the accuracy of document recognition, reduce the risk of identity fraud, and provide real-time security warnings when necessary. By combining multiple information sources and advanced recognition technology, the model can support a variety of security-sensitive application scenarios, such as financial institutions, border control, and access control of important facilities.

[0065] The present invention obtains the identity information of the certificate holder and the certificate recognition warning model, obtains the corresponding certificate processing rules based on the identity information of the certificate holder, and then processes the certificate information to be identified. If the certificate processing rules can successfully decrypt the certificate information to be identified, the attribute information of the certificate to be identified and the face identity information of the certificate holder are processed based on the certificate recognition warning model to generate corresponding detection results. By obtaining the work information and corresponding physical examination information of the target user on the certificate information to be identified, the latest face image information of the target user and the daily itinerary of the target user and the occasions in which the target user may appear in what time period are obtained, and then compared with the current information of the certificate holder, the accuracy of certificate recognition is effectively improved and the risk of identity fraud is reduced.

[0066] The electronic ID card identification method provided in the embodiment of the present application is through obtaining a total sample set, the ID card information to be identified and the face identity information of the cardholder, wherein the total sample set is the identity electronic ID card information of different users received within a preset time period, and the ID card information to be identified includes the ID card information of the target user after encryption processing; obtaining a preset ID card processing rule matching the face identity information of the cardholder, wherein the preset ID card processing rule is used to decrypt the ID card information to be identified; pre-processing the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's identity electronic ID card information is in an abnormal state; obtaining an initial ID card identification warning model matching the identification information, wherein the initial ID card identification warning model is set based on the identity electronic ID card information received within a preset time period; training the initial ID card identification warning model based on the training sample set with identification information to generate a target ID card identification warning model; pre-processing the ID card information to be identified to generate attribute information of the ID card to be identified; processing the attribute information of the ID card to be identified and the face identity information of the cardholder based on the target ID card identification warning model to generate a detection result. Obtain the identity information of the cardholder and the card recognition warning model, obtain the corresponding card processing rules based on the cardholder's identity information, and then process the card information to be identified. If the card processing rules can successfully decrypt the card information to be identified, then process the attribute information of the card to be identified and the cardholder's facial identity information based on the card recognition warning model to generate the corresponding detection results. By obtaining the work information and corresponding physical examination information of the target user on the card information to be identified, the latest facial image information of the target user and the target user's daily itinerary and the possible time period and occasions in which he may appear are obtained, and then compared with the current information of the cardholder, effectively improving the accuracy of card recognition and reducing the risk of identity fraud.

[0067] Optionally, in another embodiment of the above method of the present application, before obtaining the total sample set, the document information to be identified and the face identity information of the holder, the method further includes:

[0068] Receive the digital certificate information, client unique identification information, client random number and client key-share information sent by the client;

[0069] Get the target server random number and target server key-share information;

[0070] Generate a pre-master key according to the client key-share information and the target server key-share information;

[0071] Generate a temporary session key based on the client random number, the target server random number and the pre-master key;

[0072] Processing the digital certificate information and the device unique identification information based on a preset pairing rule to generate a processing result;

[0073] If the processing result is to allow the target server to pair with the client, sending a certificate information encryption rule request to the client;

[0074] Receive the preset certificate processing rule sent by the client based on the certificate information encryption rule request, wherein the preset certificate processing rule is set based on the face identity information of the certificate holder.

[0075] In one implementation, the client random number may be 32 bytes generated by a secure random number generator, the device unique identification information may be the client's MAC address, key_share is the public key corresponding to the elliptic curve type, and the specific presentation form of the key_share information is not repeated here, and the key-share information includes but is not limited to preset parameters for calculating the pre-master key; for example: the client sends a request (Client Hello), the extension part carries the supported elliptic curve type, and calculates the client public key (POINT) for each elliptic curve type supported by itself, and the client public key is placed in the key-share information in the extension information; after the target server selects the elliptic curve parameter, it multiplies it by the base point of the elliptic curve to obtain the target server public key (POINT); then extracts the corresponding client public key in the key_share information in the Client Hello, and calculates the pre-master key; after the client receives the target server public key (POINT) of the target server, it calculates the pre-master key. The client random number and the client key-share information are generated by the client; the target server random number and the target server key-share information are generated by the target server, and the specific generation method is not limited here. By using the pre-information of the session key transmitted by the client and the target server during the handshake process (connection establishment process), the session key can be quickly determined without affecting the handshake process (connection establishment process), greatly shortening the time for communication between the two ends after the handshake (connection establishment). After the connection between the client and the target server is established, when the server receives the face identity information of the certificate holder, it will obtain the preset certificate processing rules pre-set by the certificate holder, that is, the encryption and decryption habits of the certificate holder, and use them to decrypt the certificate information to be identified.

[0076] By applying the above technical solution, the server obtains the identity information of the certificate holder and the certificate recognition warning model, obtains the corresponding certificate processing rules based on the identity information of the certificate holder, and then processes the certificate information to be identified. If the certificate processing rules can successfully decrypt the certificate information to be identified, the attribute information of the certificate to be identified and the face identity information of the certificate holder are processed based on the certificate recognition warning model to generate the corresponding detection results. By obtaining the work information and corresponding physical examination information of the target user on the certificate information to be identified, the latest face image information of the target user and the daily itinerary of the target user and the occasions in which the target user may appear in what time period are obtained, and then compared with the current information of the certificate holder, the accuracy of certificate recognition is effectively improved and the risk of identity fraud is reduced.

[0077] refer to Figure 2 As shown, another embodiment of the present application provides an electronic ID card recognition device, which is applied to an edge device. In some embodiments, the device includes:

[0078] The acquisition module 201 is used to acquire the total sample set, the certificate information to be identified and the face identity information of the certificate holder, wherein the total sample set is the identity electronic certificate information of different users received within a preset time period, and the certificate information to be identified includes the encrypted identity card information of the target user; acquire the preset certificate processing rules that match the face identity information of the certificate holder, wherein the preset certificate processing rules are used to decrypt the certificate information to be identified; acquire the initial certificate recognition warning model that matches the identification information, wherein the initial certificate recognition warning model is set based on the identity electronic certificate information received within a preset time period;

[0079] The processing module 202 is used to pre-process the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's electronic identity certificate information is in an abnormal state; based on the training sample set with identification information, the initial certificate recognition warning model is trained to generate a target certificate recognition warning model; pre-process the certificate information to be identified to generate attribute information of the certificate to be identified; based on the target certificate recognition warning model, the attribute information of the certificate to be identified and the facial identity information of the certificate holder are processed to generate a detection result.

[0080] In another embodiment of the present application, the processing module 202 is configured to pre-process the total sample set to generate a training sample set with identification information, including:

[0081] Extracting features from the total sample set to determine an original feature library;

[0082] Divide each feature data set according to the original feature library to generate a training data set and a test data set;

[0083] Use the classifier to divide the original feature library into various test data sets for prediction and determine the prediction results;

[0084] Use the preset algorithm to divide each training data set in the original feature library for training, and obtain the prediction results of the test set class;

[0085] Based on the prediction results and the test set class prediction results, training samples with identification information are generated.

[0086] In another embodiment of the present application, the processing module 202 is configured to extract features from the total sample set to determine an original feature library, including:

[0087] Acquire a historical identity electronic certificate data set with the same province information as the certificate information to be identified, wherein the historical identity electronic certificate data set includes the identity electronic certificate information of the target group in the province;

[0088] Processing the historical identity electronic certificate dataset to obtain abnormal text features and related co-occurrence frequencies;

[0089] Processing the abnormal text features and the correlation co-occurrence frequency to generate correlation matrix information;

[0090] Generate a number of text feature data based on the correlation matrix information;

[0091] An original feature library is generated based on the plurality of text feature data.

[0092] In another embodiment of the present application, the processing module 202 is configured to extract features from the total sample set to determine an original feature library, and further includes:

[0093] The method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is:

[0094] ;

[0095] in, represents the number of times concept i and concept j co-occur in the report set, represents the total number of times concept j appears, It represents the frequency of concept i appearing when concept j appears. Based on the co-occurrence frequency P, the correlation matrix A can be constructed:

[0096] The method includes a calculation formula for calculating a correlation matrix, which is:

[0097] ;

[0098] in, is the co-occurrence frequency threshold, if Greater than or equal to threshold , then it is considered that there is a correlation from concept i to concept j, otherwise there is no correlation.

[0099] In another embodiment of the present application, the processing module 202 is configured to pre-process the document information to be identified to generate attribute information of the document to be identified, including:

[0100] Processing the to-be-identified certificate information based on preset certificate processing rules to generate identity attribute information of the target user;

[0101] Obtaining a preset user identity information table, wherein the preset user identity information table includes physical examination information and work information of the target user within a preset time period;

[0102] The identity attribute information of the target user is processed based on the preset user identity information table to generate work attribute information of the target user, wherein the work attribute information of the target user includes the latest facial image information of the target user within a preset time period and the physical condition information of the target user.

[0103] In another embodiment of the present application, the processing module 202 is configured to pre-process the document information to be identified to generate attribute information of the document to be identified, and further includes:

[0104] Processing the certificate information to be identified to generate reception time information of the certificate information to be identified, residence information of the target user, and usage information of the certificate to be identified;

[0105] Generate usage information of the certificate information to be identified based on the reception time information of the certificate information to be identified, the residence information of the target user and the usage information of the certificate to be identified according to the preset certificate processing rules;

[0106] Obtaining the validity period information of the identity document corresponding to the identity document information to be identified;

[0107] The purpose information of the certificate information to be identified is processed based on the validity period information of the identity document and the work attribute information of the target user to generate attribute information of the certificate information to be identified.

[0108] In another embodiment of the present application, the processing module 202 is configured to process the attribute information of the document to be identified and the facial identity information of the holder based on the target document recognition warning model to generate a detection result, including:

[0109] Processing the purpose information of the to-be-identified certificate information and the work attribute information of the target user based on the target certificate recognition warning model to generate a first matching value;

[0110] Processing the facial identity information of the cardholder based on the target card recognition warning model to generate a second matching value;

[0111] The first matching value and the second matching value are processed based on the target certificate recognition warning model to generate a detection result, wherein the detection result is an identity matching result between the certificate to be identified and the certificate holder.

[0112] According to another aspect of an embodiment of the present application, an electronic device is provided, including a computer-readable storage medium storing a computer program and a processor, and when the computer program is read and executed by the processor, any of the above methods is implemented.

[0113] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303. The first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, it executes the electronic identity card photo recognition method provided in any of the aforementioned embodiments of the present application.

[0114] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0115] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs, and the first processor 300 executes the programs after receiving the execution instruction. The electronic ID card identification method disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0116] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as a hardware decoding processor to execute, or a combination of hardware and software modules in the decoding processor to execute. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0117] The electronic device provided by the above-mentioned embodiments of the present application and the method for identifying the electronic ID card photo provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0118] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium stores 401 a computer program, and when the computer program is read and executed by the second processor 402, the electronic identity card photo recognition method as described above is implemented.

[0119] The technical solution of the embodiment of the present application, 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, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0120] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the electronic ID card photo recognition method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0121] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0122] The computer program product provided by the above-mentioned embodiments of the present application and the electronic ID card photo recognition method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0123] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0124] Each embodiment in this application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the method for evaluating the recognition of electronic ID card photos, electronic devices, electronic devices, and readable storage media, since they are basically similar to the embodiment of the method for recognizing electronic ID card photos described above, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the method for recognizing electronic ID card photos described above.

[0125] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

[0126] It should be noted that:

[0127] The term "module" is not intended to be limited to a specific physical form. Depending on the specific application, a module can be implemented as hardware, firmware, software and / or a combination thereof. In addition, different modules can share a common cache component or even be implemented by the same component. There may or may not be a clear boundary between different modules. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the above description of specific languages ​​is to disclose the best mode of implementation of the present application.

[0128] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

Claims

1. A method for identifying an electronic ID card, characterized in that: The method comprises: Obtaining a total sample set, the document information to be identified, and the face identity information of the certificate holder, wherein the total sample set is the electronic identity certificate information of different users received within a preset time period, and the document information to be identified includes the encrypted identity card information of the target user; Obtaining a preset document processing rule that matches the facial identity information of the certificate holder, wherein the preset document processing rule is used to decrypt the document information to be identified; Preprocessing the total sample set to generate a training sample set with identification information, wherein the identification information is used to indicate that the user's electronic identity certificate information is in an abnormal state; Acquire an initial document recognition warning model that matches the identification information, wherein the initial document recognition warning model is set based on the identity electronic certificate information received within a preset time period; Training the initial document recognition warning model based on the training sample set with identification information to generate a target document recognition warning model; Preprocessing the information of the document to be identified to generate attribute information of the document to be identified; Processing the attribute information of the document to be identified and the facial identity information of the holder based on the target document identification warning model to generate a detection result; Preprocessing the total sample set to generate a training sample set with identification information includes: Extracting features from the total sample set to determine an original feature library; Divide each feature data set according to the original feature library to generate a training data set and a test data set; Use the classifier to divide the original feature library into various test data sets for prediction and determine the prediction results; Use the preset algorithm to divide each training data set in the original feature library for training, and obtain the prediction results of the test set class; Generate training samples with identification information based on the prediction results and the test set prediction results; Extracting features from the total sample set to determine an original feature library includes: Acquire a historical identity electronic certificate data set with the same province information as the certificate information to be identified, wherein the historical identity electronic certificate data set includes the identity electronic certificate information of the target group in the province; Processing the historical identity electronic certificate dataset to obtain abnormal text features and related co-occurrence frequencies; Processing the abnormal text features and the correlation co-occurrence frequency to generate correlation matrix information; Generate a number of text feature data based on the correlation matrix information; An original feature library is generated based on the plurality of text feature data.

2. The method according to claim 1, characterized in that The extracting features from the total sample set to determine the original feature library also includes: The method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is: ; in, Representation concept and Concept The number of times they co-occur in the report set, Representation concept The total number of occurrences, Representation concept Concept of appearance Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix : The method includes a calculation formula for calculating a correlation matrix, which is: ; in, is the co-occurrence frequency threshold, if Greater than or equal to threshold , then the concept With concept There is a correlation, otherwise there is no correlation.

3. The method according to claim 1, characterized in that: Preprocessing the document information to be identified to generate attribute information of the document to be identified includes: Processing the to-be-identified certificate information based on preset certificate processing rules to generate identity attribute information of the target user; Obtaining a preset user identity information table, wherein the preset user identity information table includes physical examination information and work information of the target user within a preset time period; The identity attribute information of the target user is processed based on the preset user identity information table to generate work attribute information of the target user, wherein the work attribute information of the target user includes the latest facial image information of the target user within a preset time period and the physical condition information of the target user.

4. The method according to claim 3, characterized in that Preprocessing the document information to be identified to generate attribute information of the document to be identified also includes: Processing the certificate information to be identified to generate reception time information of the certificate information to be identified, residence information of the target user, and usage information of the certificate to be identified; Generate usage information of the certificate information to be identified based on the reception time information of the certificate information to be identified, the residence information of the target user and the usage information of the certificate to be identified according to the preset certificate processing rules; Obtaining the validity period information of the identity document corresponding to the identity document information to be identified; The purpose information of the certificate information to be identified is processed based on the validity period information of the identity document and the work attribute information of the target user to generate attribute information of the certificate information to be identified.

5. The method according to claim 4, characterized in that Based on the target document recognition warning model, the attribute information of the document to be recognized and the facial identity information of the holder are processed to generate a detection result, including: Processing the purpose information of the to-be-identified certificate information and the work attribute information of the target user based on the target certificate recognition warning model to generate a first matching value; Processing the facial identity information of the cardholder based on the target card recognition warning model to generate a second matching value; The first matching value and the second matching value are processed based on the target certificate recognition warning model to generate a detection result, wherein the detection result is an identity matching result between the certificate to be identified and the certificate holder.

6. An electronic ID card recognition device, characterized in that: The device comprises: An acquisition module is used to acquire a total sample set, the certificate information to be identified, and the face identity information of the certificate holder, wherein the total sample set is the identity electronic certificate information of different users received within a preset time period, and the certificate information to be identified includes the encrypted identity card information of the target user; acquire a preset certificate processing rule that matches the face identity information of the certificate holder, wherein the preset certificate processing rule is used to decrypt the certificate information to be identified; acquire an initial certificate recognition warning model that matches the identification information, wherein the initial certificate recognition warning model is set based on the identity electronic certificate information received within a preset time period; The processing module is used to pre-process the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's identity electronic certificate information is in an abnormal state; based on the training sample set with identification information, the initial certificate recognition warning model is trained to generate a target certificate recognition warning model; the certificate information to be recognized is pre-processed to generate attribute information of the certificate to be recognized; based on the target certificate recognition warning model, the attribute information of the certificate to be recognized and the face identity information of the certificate holder are processed to generate a detection result; the total sample set is pre-processed to generate a training sample set with identification information, including: extracting features from the total sample set to determine an original feature library; dividing each feature data set according to the original feature library to generate a training data set and a test data set; using a classifier to divide the original feature library Predictions are made on each test data set to determine prediction results; a preset algorithm is used to divide each training data set in the original feature library for training to obtain test set class prediction results; training samples with identification information are generated based on the prediction results and the test set class prediction results; feature extraction is performed on the total sample set to determine the original feature library, including: obtaining a historical electronic identity certificate data set that has the same provincial information as the information of the certificate to be identified, wherein the historical electronic identity certificate data set includes electronic identity certificate information of a target group within the province; processing the historical electronic identity certificate data set to obtain abnormal text features and correlation co-occurrence frequencies; processing the abnormal text features and the correlation co-occurrence frequencies to generate correlation matrix information; generating a number of text feature data based on the correlation matrix information; and generating an original feature library based on the number of text feature data.

7. An electronic device, characterized in that: The invention comprises a computer-readable storage medium storing a computer program and a processor, wherein when the computer program is read and executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the method according to any one of claims 1 to 5 is implemented.