Minor Identification Method and Device Based on Facial Recognition

Abstract

The present invention belongs to the field of information security technology. The present invention provides a method and device for identifying the identity of minors based on face recognition. The method for identifying the identity of minors based on face recognition includes: receiving the facial data of minors and a transaction request; determining the facial data of the guardians of minors according to the transaction request; generating the facial data of minors at a preset moment and the facial data of guardians at the preset moment according to the facial data of minors and the facial data of guardians, and comparing the facial data of minors at the preset moment with the facial data of guardians at the preset moment. The method and device for identifying the identity of minors based on face recognition provided by the present invention improve the security of face brushing for minors and effectively reduce the risk of theft of minors' accounts by optimizing the face brushing process for minors.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, especially the technical field of information security, and specifically relates to a method and device for identifying the identity of minors based on face recognition. Background Art

[0002] With the rapid development of Internet technology, face recognition authentication has become a fast and crucial authentication method in many applications. However, the existing applications only focus on the face feature recognition of adults, ignoring the authentication of minors whose facial features change rapidly (caused by rapid physical development). The face-swiping process for minors in most applications is no different from that of ordinary customers. Since minors are too young, their faces may not be recognizable for comparison. In addition, the face-swiping transactions triggered by minors may involve account-related operations, and these transactions need to be specially monitored and traced. Therefore, optimizing the method of minor face recognition is an urgent problem to be solved. Summary of the Invention

[0003] The present invention can be used in the technical field of the application of information security technology in finance, and can also be used in any field other than the financial field. The method and device for identifying the identity of minors based on face recognition provided by the present invention improve the security of minor face-swiping by optimizing the face-swiping process for minors, and effectively reduce the risk of minor accounts being stolen.

[0004] To solve the above technical problems, the present invention provides the following technical solutions:

[0005] In a first aspect, the present invention provides a method for identifying the identity of minors based on face recognition, including:

[0006] Receiving the face data of a minor and a transaction request;

[0007] Determining the face data of the minor's guardian according to the transaction request;

[0008] Generating the face data of the minor at a preset moment and the face data of the guardian at the preset moment according to the face data of the minor and the face data of the guardian respectively, and comparing the face data of the minor at the preset moment with the face data of the guardian at the preset moment.

[0009] In an embodiment, the generating the face data of the minor at a preset moment and the face data of the guardian at the preset moment respectively includes:

[0010] Generate the facial data of the minor at a preset moment according to a pre-generated facial prediction model and the facial data of the minor;

[0011] Generate the facial data of the guardian at the preset moment according to the facial prediction model and the facial data of the guardian.

[0012] In one embodiment, the method for generating the facial prediction model includes:

[0013] Based on a deep learning algorithm, establish an initial model of the facial prediction model;

[0014] Train the initial model according to the facial data of multiple minors and the facial data of the same minors after they become adults, so as to generate the facial prediction model.

[0015] In one embodiment, the method for identifying the identity of a minor based on facial recognition further includes: optimizing the facial prediction model, including:

[0016] Alternately stack the convolutional layer and the max pooling layer in the facial prediction model;

[0017] Generate the optimized facial prediction model according to the facial data of the minor and the stacked facial prediction model.

[0018] In one embodiment, the step of generating the facial data of the minor at a preset moment according to a pre-generated facial prediction model and the facial data of the minor includes:

[0019] Input the facial data of the minor into the stacked facial prediction model to determine the last convolutional layer of the stacked facial model;

[0020] Generate the facial data of the minor corresponding to the preset moment according to the output end of the last convolutional layer.

[0021] In one embodiment, the step of generating the facial data of the guardian at the preset moment according to the facial prediction model and the facial data of the guardian includes:

[0022] Input the facial data of the guardian into the stacked facial prediction model to determine the last convolutional layer of the stacked facial model;

[0023] Generate the facial data of the guardian corresponding to the preset moment according to the output end of the last convolutional layer.

[0024] Second aspect, the present invention provides a minor identity recognition device based on face recognition, and the device includes:

[0025] A data receiving module, configured to receive the face data and transaction requests of minors;

[0026] A guardian data search module, configured to determine the face data of the guardian of the minor according to the transaction request;

[0027] A dual-face data comparison module, configured to respectively generate the face data of the minor at a preset moment and the face data of the guardian at the preset moment according to the face data of the minor and the face data of the guardian, and compare the face data of the minor at the preset moment with the face data of the guardian at the preset moment.

[0028] In one embodiment, the dual-face data comparison module includes:

[0029] A minor data generation unit, configured to generate the face data of the minor at a preset moment according to a pre-generated face prediction model and the face data of the minor;

[0030] A guardian data generation unit, configured to generate the face data of the guardian at the preset moment according to the face prediction model and the face data of the guardian.

[0031] In one embodiment, the minor identity recognition device based on face recognition further includes: a face prediction model generation module, configured to generate the face prediction model, and the face prediction model generation module includes:

[0032] An initial model generation unit, configured to establish an initial model of the face prediction model based on a deep learning algorithm;

[0033] An initial model training unit, configured to train the initial model according to the face data of multiple minors and the face data of the adults corresponding to the multiple minors to generate the face prediction model.

[0034] In one embodiment, the minor identity recognition device based on face recognition further includes: a model optimization module, configured to optimize the face prediction model, and the model optimization module includes:

[0035] A layer stacking unit, configured to alternately stack the convolutional layer and the max pooling layer in the face prediction model;

[0036] A model optimization unit for generating an optimized face prediction model based on the face data of a minor and the superimposed face prediction model.

[0037] In one embodiment, the minor data generation unit includes:

[0038] A minor convolution layer determination unit for inputting the face data of the minor into the superimposed face prediction model to determine the last convolution layer of the superimposed face model;

[0039] A minor face generation unit for generating the face data of the minor corresponding to the preset moment according to the output end of the last convolution layer.

[0040] In one embodiment, the guardian data generation unit includes:

[0041] A guardian convolution layer determination unit for inputting the face data of the guardian into the superimposed face prediction model to determine the last convolution layer of the superimposed face model;

[0042] A guardian face generation unit for generating the face data of the guardian corresponding to the preset moment according to the output end of the last convolution layer.

[0043] In one embodiment, the guardian data search module includes:

[0044] A minor identity information determination unit for determining the identity information of the minor according to the transaction request;

[0045] A guardian data search unit for determining the face data of the guardian of the minor in a preset database according to the identity information of the minor.

[0046] In one embodiment, the minor identity recognition device based on face recognition further includes: a preset moment determination module for determining the preset moment according to the minor age and the guardian age;

[0047] A facial feature extraction module for respectively extracting the face data of the minor at the preset moment and the face data of the guardian at the preset moment to generate the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment;

[0048] A local cutting module for respectively performing local cutting on the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment;

[0049] A facial feature comparison module, configured to compare the facial features of the minor at a preset moment after local cutting and the facial features of the guardian at the preset moment, and identify the identity of the minor according to the comparison result.

[0050] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method for identifying the identity of a minor based on face recognition are implemented.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for identifying the identity of a minor based on face recognition are implemented.

[0052] As can be seen from the above description, the embodiments of the present invention provide a method and device for identifying the identity of a minor based on face recognition. First, the face data of the minor and a transaction request are received; then, the face data of the guardian of the minor is determined according to the transaction request; finally, based on the face data of the minor and the face data of the guardian, the face data of the minor at a preset moment and the face data of the guardian at the preset moment are respectively generated, and the face data of the minor at the preset moment is compared with the face data of the guardian at the preset moment. The present invention improves the security of face brushing for minors, complies with legal norms and regulatory requirements, and effectively reduces the risk of minor accounts being stolen. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 Schematic flowchart of the method for identifying the identity of a minor based on face recognition in the embodiments of the present invention Figure 1 ;

[0055] Figure 2 Schematic flowchart of step 100 in the embodiments of the present invention;

[0056] Figure 3 Schematic flowchart of the method for identifying the identity of a minor based on face recognition in the embodiments of the present invention Figure 2 ;

[0057] Figure 4 Schematic flowchart of step 400 in the embodiments of the present invention;

[0058] Figure 5 Flow schematic of the minor identity recognition method based on face recognition in the embodiments of the present invention Figure 3 ;

[0059] Figure 6 Flow schematic diagram of step 500 in the embodiments of the present invention;

[0060] Figure 7 Flow schematic of step 102 in the embodiments of the present invention Figure 1 ;

[0061] Figure 8 Flow schematic of step 102 in the embodiments of the present invention Figure 2 ;

[0062] Figure 9 Flow schematic diagram of step 200 in the embodiments of the present invention;

[0063] Figure 10 Flow schematic of the minor identity recognition method based on face recognition in the embodiments of the present invention Figure 4 ;

[0064] Figure 11 Flow schematic diagram of the minor identity recognition method based on face recognition in the specific implementation manners of the present invention;

[0065] Figure 12 Block diagram of the minor identity recognition device based on face recognition in the embodiments of the present invention Figure 1 ;

[0066] Figure 13 Block diagram of the dual face data comparison module 30 in the embodiments of the present invention;

[0067] Figure 14 Block diagram of the minor identity recognition device based on face recognition in the embodiments of the present invention Figure 2 ;

[0068] Figure 15 Block diagram of the face prediction model generation module 40 in the embodiments of the present invention;

[0069] Figure 16 Block diagram of the minor identity recognition device based on face recognition in the embodiments of the present invention Figure 3 ;

[0070] Figure 17 Block diagram of the model optimization module 50 in the embodiments of the present invention;

[0071] Figure 18Block diagram of the minor data generation unit 301 in the embodiments of the present invention;

[0072] Figure 19 Block diagram of the guardian data generation unit 302 in the embodiments of the present invention;

[0073] Figure 20 Block diagram of the guardian data search module 20 in the embodiments of the present invention;

[0074] Figure 21 Block diagram of the minor identity recognition device based on face recognition in the embodiments of the present invention Figure 4 ;

[0075] Figure 22 Structural schematic diagram of the electronic device in the embodiments of the present invention. Detailed implementation manners

[0076] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0077] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0079] The acquisition, storage, use, processing, etc. of data in the technical solutions of this application all comply with the relevant regulations of national laws and regulations.

[0080] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0081] An embodiment of the present invention provides a specific implementation manner of a minor identity recognition method based on face recognition. Refer to Figure 1 and the method specifically includes the following contents:

[0082] Step 100: Receive the face data of the minor and the transaction request;

[0083] With the rapid development of the Internet economy and the increasing improvement of people's living standards, minors also have an increasingly strong demand for online transactions, but the supervision methods for them are still blank. Additionally, it can be understood that the transaction request includes not only the items and prices that the minor wants to trade, but also information corresponding to the adult, such as identity ID and other information. When the minor sends a transaction request to the server, it is also necessary to upload their face data.

[0084] Step 200: Determine the face data of the minor's guardian according to the transaction request;

[0085] The specific implementation steps are as follows: Collect the face data of the guardians of multiple minors in advance to generate a face database (it should be noted that this collection is informed to the corresponding guardians in advance and carried out under the permission of the law). After receiving the transaction request of the minor, parse it to obtain the minor's information, and based on the above face database, find the corresponding face data of the guardian.

[0086] Step 300: Generate the face data of the minor at a preset moment and the face data of the guardian at the preset moment according to the face data of the minor and the face data of the guardian respectively, and compare the face data of the minor at the preset moment with the face data of the guardian at the preset moment.

[0087] From a genetic perspective, there is a certain degree of similarity between the facial data of the children of the guardian and the guardian. For example, the mandible is a dominant inheritance. If either parent has a prominent large chin, the child will also have a large chin. Another example is that for the color of the eyes, dark colors such as blue and black are dominant over light colors. If one parent has blue eyes and the other has black eyes, the child will surely have black eyes, and so on. By presetting a moment, for example, the average value of the sum of the current age of the minor and the current age of the guardian, and respectively generating the facial data of the minor and the facial data of the guardian corresponding to this moment, and finally comparing the facial data of the minor and the facial data of the guardian (including fixed facial features and variable facial features) at this moment to determine the authenticity of the facial data of the minor.

[0088] As can be seen from the above description, the embodiment of the present invention provides a method for identifying the identity of minors based on face recognition. First, the facial data of the minor and a transaction request are received; then, according to the transaction request, the facial data of the guardian of the minor is determined; finally, according to the facial data of the minor and the facial data of the guardian, the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment are respectively generated, and the facial data of the minor at the preset moment is compared with the facial data of the guardian at the preset moment. The present invention improves the security of face swiping for minors, complies with legal norms and regulatory requirements, and effectively reduces the risk of minors' accounts being stolen.

[0089] In one embodiment, referring to Figure 2 , step 300 further includes:

[0090] Step 101: Generate the facial data of the minor at the preset moment according to the pre-generated face prediction model and the facial data of the minor;

[0091] In the technical field of facial data prediction, the traditional method is to use many facial features that describe facial geometry, color, and texture to predict facial data. In recent years, convolutional neural networks (CNNs) have shown great performance in face recognition and understanding and have been proven to be an effective method for exploring facial features. On the one hand, through its well-designed network and effective structure, better representation performance can be achieved. On the other hand, an effective information transmission path is established. Otherwise, it is easy to lead to the inability to find the internal correlation of feature mapping, resulting in suboptimal feature representation.

[0092] Step 102: Generate the facial data of the guardian at the preset moment according to the face prediction model and the facial data of the guardian.

[0093] In one embodiment, referring to Figure 3, the method for identifying the identity of minors based on face recognition further includes:

[0094] Step 400: Generate the face prediction model. See Figure 4 , further, Step 400 includes:

[0095] Step 401: Based on the deep learning algorithm, establish an initial model of the face prediction model;

[0096] Step 402: Train the initial model according to the face data of multiple minors and the face data of these minors corresponding to their adulthood to generate the face prediction model.

[0097] Specifically, collect the face photos of multiple customers at different age stages (which can also be obtained from public channels). The different age stages include 5 - 10 years old, 10 - 13 years old, 13 - 15 years old, 15 - 17 years old, 17 - 18 years old, and 18 - 20 years old. In addition, these customers need to be evenly divided into male and female groups, and these photos are divided into a training set and a test set. During the training process, use the Pearson correlation coefficient as the threshold for stopping training, and test the trained face prediction model through the test set. Specifically, test the trained model according to the root mean square error of the test set.

[0098] In one embodiment, see Figure 5 , the method for identifying the identity of minors based on face recognition further includes:

[0099] Step 500: Optimize the face prediction model. See Figure 6 , further, Step 500 includes:

[0100] Step 501: Alternately stack the convolutional layer and the max pooling layer in the face prediction model;

[0101] Step 502: Generate the optimized face prediction model according to the face data of minors and the stacked face prediction model.

[0102] In Step 501 and Step 502, preferably, several convolutional layers and max magnetization layers can be selected for alternate stacking to form a deep convolutional network and a face region pooling layer, and the deep convolutional network and the face region pooling layer are used as the output end of the last convolutional layer. The face data of minors is used as the input end of the last convolutional layer.

[0103] In one embodiment, see Figure 7 , Step 102 includes:

[0104] Step 1021: Input the face data of the minor into the superimposed face prediction model to determine the last convolutional layer of the superimposed face model;

[0105] Based on Steps 501 and 502, first divide the face data of the minor into multiple face attributes. Each face attribute is a vector, and the vector corresponds to multiple value probabilities. Inputting multiple face attributes into the superimposed face prediction model can obtain the last convolutional layer of the face prediction model.

[0106] Step 1022: Generate the face data of the minor corresponding to the preset moment according to the output end of the last convolutional layer.

[0107] According to the preset moment and the output of the last convolutional layer in the face prediction model, the face data of the minor corresponding to the preset moment can be determined. It can be understood that after optimizing the face prediction model in the above manner, the following technical effects are achieved: adding face region search, face region pooling layer, and multiple parallel loss layers can make the model more accurately predict the facial development trend of the minor.

[0108] In one embodiment, refer to Figure 8 , Step 102 further includes:

[0109] Step 1023: Input the face data of the guardian into the superimposed face prediction model to determine the last convolutional layer of the superimposed face model;

[0110] Step 1024: Generate the face data of the guardian corresponding to the preset moment according to the output end of the last convolutional layer.

[0111] It is not difficult to understand that the implementation manners of Steps 1023 and 1024 respectively correspond to those of Steps 1021 and 1022, except that the implementation object changes from the face data of the minor to the face data of the guardian, so it will not be repeated here.

[0112] In one embodiment, refer to Figure 9 , Step 200 includes:

[0113] Step 201: Determine the identity information of the minor according to the transaction request;

[0114] It is not difficult to understand that the transaction request includes the transaction information corresponding to the minor and the identity information of the minor. Specifically, the transaction request can be parsed to obtain the identity information of the minor. In addition, it should be noted that the minor identity information refers to the identity information of the minor corresponding to the account of the transaction request, and it is not necessarily the identity information of the minor currently undergoing face recognition (there may be cases of identity theft).

[0115] Step 202: Determine the facial data of the guardian of the minor in a preset database according to the identity information of the minor.

[0116] Specifically, when a minor creates an account, their guardian information is associated, and the facial data of both is collected and stored, or the facial data of their guardian is obtained from a third-party facial database, such as a judicial agency, a social security system, etc.

[0117] In one embodiment, refer to Figure 10 , the method for identifying the identity of a minor based on face recognition further includes:

[0118] Step 600: Determine the preset moment according to the age of the minor and the age of the guardian;

[0119] Preferably, the preset moment can be the average age of the current minor and their guardian.

[0120] Step 700: Extract the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment respectively to generate the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment;

[0121] It should be noted that the facial features include fixed facial features and facial features that change with age. Fixed facial features such as moles, birthmarks, etc., and facial features that change with age such as cheek muscles, nose contours, and wrinkle trends, etc.

[0122] When step 600 is implemented, it is determined to extract geometric features or algebraic features based on the essential attributes and properties of the facial data, and then the facial data is extracted according to the prior rules, which is an empirical description and representation of the facial feature points of the human face. Common natural face images have some obvious basic features. Common facial regions mainly include features such as eyes, eyebrows, nose, and mouth, and their brightness values are generally lower than the surrounding nearby regions. In addition, the two eyes in the human face are symmetric, and the mouth and nose are approximately distributed on its axis of symmetry. Although the facial surfaces of different individuals vary greatly, there is a typical standard of "three courts and five eyes" for the human face. This basic and universal standard provides a reasonable feature distribution basis for facial feature extraction of the human face. According to this rule, the feature extraction of the corresponding organs can be carried out. Specifically, first, preprocessing and transformation are performed on the target image to enhance or strengthen the features to be extracted, and then candidate target points or candidate feature regions are selected from the facial image according to the rules.

[0123] Step 800: Locally cut the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment respectively;

[0124] Specifically, cut and analyze the facial data features of the minor and the guardian, that is, refine and divide the sampling points on the human face, and perform aging / younging prediction fitting on each part of the human face. If it is found that a certain facial information sampling point is very different from the general sample, and both the guardian and the minor conform to this feature (such as the cheekbones of the parents and children are very prominent, the eyebrow spacing of the parents and children far exceeds that of ordinary people, etc., facial special features), it means that the credibility of this face prediction and recognition is greatly increased.

[0125] Step 900: Compare the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment after local cutting, and identify the identity of the minor according to the comparison result.

[0126] Specifically, compare the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment in regions, and compare the comparison result with a preset threshold to judge the authenticity of the minor's identity.

[0127] In a specific implementation manner, taking the bank's app as an example, the present invention provides a specific implementation manner in the method for identifying the identity of a minor based on face recognition. See Figure 11 and the specific content is as follows.

[0128] S1: Determine the identity information of the minor according to the transaction request data of the minor, and initiate face verification.

[0129] For minors who have registered for e-banking at offline outlets, when conducting transaction operations on the online app, face recognition will be performed soon. Note that when registering for e-banking offline, the minor must reserve the information of their guardian. On the other hand, it is also necessary to compare the time corresponding to the pre-stored face data of the minor in this system with the time of the minor's current transaction request. If the time interval between the two is short, the pre-stored face data will be used for comparison to verify whether they match. If the current number of face recognition errors exceeds a certain number, the guardian intervention process will be carried out. If the time interval is too long (e.g., more than 3 years), step S2 needs to be performed.

[0130] S2: The App system background queries the guardian information and generates the corresponding face recognition data at a preset moment based on the pre-stored face recognition data of the guardian.

[0131] Regarding the face recognition of minors, especially when the guardian is not around and face recognition cannot be completed immediately, it can be verified through the method provided by the specific application example of the present invention. First, the guardian of the minor is the biological parent, and the registration information is complete. Especially, the quality of the face reference photo is high, and the guardian authorizes the institution to analyze and research it.

[0132] Preferably, the preset moment can be the average age of the current minor and their guardian. First, the guardian information is manually entered in the background system, so it is very reliable. Second, swiping the guardian's face also meets the requirements of laws, regulations and supervision, which improves the security of minor face recognition. There are two cases for choosing the guardian:

[0133] Only one guardian is reserved: At this time, it is necessary to check the number of face recognition errors of the guardian. Since the current scenario is that the guardian uses their own face information to guarantee the financial transactions of the minor, it is necessary to add some additional verification mechanisms based on the current number of face recognition errors of the guardian. Because the more errors there are, the more likely the current account is under attack, and more other verification means should be added. Specifically, it can be summarized as the following piecewise function, taking the maximum number of face recognition errors as 10 times as an example:

[0134]

[0135] The above piecewise function represents that the closer the number of errors is to the threshold, the more verification means there are, and the higher the security of the minor's account.

[0136] There are multiple guardians: If the minor has reserved multiple guardians, a guardian needs to be recommended for authentication based on two conditions: the guardian with fewer face recognition errors; if the number of errors is the same, the guardian who has performed face recognition authentication for the minor more times will be selected; if the above two conditions cannot be distinguished, the customer can select any one person for authentication.

[0137] S3: Generate the facial recognition data corresponding to the preset moment according to the facial data of the minor received in step S1.

[0138] S4: Compare the facial data generated in step S2 and step S4 respectively.

[0139] When the comparison between the two is successful, it means that the identity information of the minor is reliable. A virtual account of the minor can be added under the guardian's account, and the payment, transfer and other operation records of the minor's account can be viewed. If the guardian's account has abnormal behavior, the background system will automatically freeze the minor's account if necessary, so as to achieve interconnection between accounts and linkage of security mechanisms.

[0140] In addition, the facial information fitting results in the present invention are only predictions made through technical means, and cannot be used as the only criterion for the identity check of minors. Moreover, because it involves a deep learning prediction model, the facial recognition results must be combined with other verification methods as the final result of the identity check of minors. The credibility of this facial recognition can be expressed by formula (1):

[0141]

[0142] In the above formula, Trust level is the credibility of the face recognition results, diff 年龄差 is the age difference between the minor and his / her guardian; βQ 数据质量 To improve the quality of facial data of minors and their guardians, Const 特征部位 It is the characteristic part for comparing the two.

[0143] If the face recognition is successful, the greater the age difference between the parents and the child, the lower the credibility of the recognition, and the more additional means of auxiliary verification are needed. If the face recognition is successful, the higher the quality of the photos reserved by the parents and the child (including pixels, shooting angle, clothing color, etc.), the higher the credibility of the recognition, and the less additional means of verification are needed.

[0144] In a specific application example of the present invention, face recognition uses a prediction algorithm of deep learning for face fitting. Therefore, it will perform cutting analysis on the facial features of parents and children, that is, refine and divide the sampling points on the human face, and perform aging / younging prediction fitting on each part of the face. If it is found that a certain facial information sampling point is very different from the public sample, and both the guardian and the minor meet this characteristic (such as both the parents and the child have very prominent cheekbones, the distance between the eyebrows of the parents and the child is much larger than that of ordinary people, etc.), then this indicates that the credibility of this face prediction recognition is greatly increased.

[0145] Calculate the corresponding credibility score according to formula (1), and judge whether other verification means (for guardians) need to be added according to the score, such as the need for guardians to assist in sending SMS verification codes for verification, the need to verify the guardian's card number and card password, the need to answer the security questions reserved in the guardian's account, etc., to enhance the reliability and security of the minor's identity check.

[0146] As can be seen from the above description, since the age gap between minors and their parents may be very large, a method for identifying the identity of minors based on face recognition provided by a specific application example of the present invention innovatively improves the face simulation algorithm, and uses the big data training analysis of neural networks and the theory of deep learning to simulate the face fitting pattern of minors when they grow up and the face fitting pattern of guardians when they are young in two aspects. The fitting time node is selected as the average age of the minors and their guardians.

[0147] It avoids the errors caused by using a single fitting algorithm in the industry. In the face image simulation algorithm, the greater the simulated age gap, the lower the credibility of the face fitting image obtained by the algorithm. Therefore, we set the age as the average age of the minors and the guardians, and use a relatively mature face aging / younging picture fitting algorithm in the industry, which can reduce the error of the algorithm and improve the credibility of face comparison. In addition, the guardian's information is also involved in this solution for verification, meeting the requirements of laws and regulations.

[0148] Based on the same inventive concept, an embodiment of the present application further provides a minor identity recognition device based on face recognition, which can be used to implement the method described in the above embodiments, such as the following embodiments. Since the principle of the minor identity recognition device based on face recognition for solving problems is similar to that of the minor identity recognition method based on face recognition, the implementation of the minor identity recognition device based on face recognition can refer to the implementation of the minor identity recognition method based on face recognition, and the repeated parts will not be described again. As used hereinafter, the term "unit" or "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0149] An embodiment of the present invention provides a specific implementation manner of a minor identity recognition device based on face recognition that can implement the minor identity recognition method based on face recognition. Refer to Figure 12 , the minor identity recognition device based on face recognition specifically includes the following:

[0150] A data receiving module 10, configured to receive the face data of the minor and the transaction request;

[0151] A guardian data searching module 20, configured to determine the face data of the guardian of the minor according to the transaction request;

[0152] A dual-face data comparison module 30, configured to generate the face data of the minor at a preset moment and the face data of the guardian at the preset moment according to the face data of the minor and the face data of the guardian, and compare the face data of the minor at the preset moment with the face data of the guardian at the preset moment.

[0153] In one embodiment, refer to Figure 13 , the dual-face data comparison module 30 includes:

[0154] A minor data generation unit 301, configured to generate the face data of the minor at a preset moment according to a pre-generated face prediction model and the face data of the minor;

[0155] A guardian data generation unit 302, configured to generate the face data of the guardian at the preset moment according to the face prediction model and the face data of the guardian.

[0156] In one embodiment, refer to Figure 14, the minor identity recognition device based on face recognition further includes: a face prediction model generation module 40, configured to generate the face prediction model, see Figure 15 , the face prediction model generation module 40 includes:

[0157] An initial model generation unit 401, configured to establish an initial model of the face prediction model based on a deep learning algorithm;

[0158] An initial model training unit 402, configured to train the initial model according to the face data of multiple minors and the face data of the corresponding adults after reaching adulthood of the multiple minors, so as to generate the face prediction model.

[0159] In one embodiment, see Figure 16 , the minor identity recognition device based on face recognition further includes: a model optimization module 50, configured to optimize the face prediction model, see Figure 17 , the model optimization module 50 includes:

[0160] A layer stacking unit 501, configured to alternately stack the convolutional layer and the max pooling layer in the face prediction model;

[0161] A model optimization unit 502, configured to generate the optimized face prediction model according to the face data of minors and the stacked face prediction model.

[0162] In one embodiment, see Figure 18 , the minor data generation unit 301 includes:

[0163] A minor convolutional layer determination unit 3011, configured to input the face data of the minor into the stacked face prediction model to determine the last convolutional layer of the stacked face model;

[0164] A minor face generation unit 3012, configured to generate the face data of the minor corresponding to the preset moment according to the output end of the last convolutional layer.

[0165] In one embodiment, see Figure 19 , the guardian data generation unit 302 includes:

[0166] A guardian convolutional layer determination unit 3021, configured to input the face data of the guardian into the stacked face prediction model to determine the last convolutional layer of the stacked face model;

[0167] A guardian face generation unit 3022, configured to generate the face data of the guardian corresponding to the preset moment according to the output end of the last convolutional layer.

[0168] In one embodiment, referring to Figure 20 , the guardian data search module 20 includes:

[0169] A minor identity information determination unit 201 for determining the identity information of the minor according to the transaction request;

[0170] A guardian data search unit 202 for determining the facial data of the guardian of the minor in a preset database according to the identity information of the minor.

[0171] In one embodiment, referring to Figure 21 , the minor identity recognition device based on face recognition further includes: a preset time determination module 60 for determining the preset time according to the age of the minor and the age of the guardian;

[0172] A facial feature extraction module 70 for respectively extracting the facial data of the minor at the preset time and the facial data of the guardian at the preset time to generate the facial features of the minor at the preset time and the facial features of the guardian at the preset time;

[0173] A local cutting module 80 for respectively performing local cutting on the facial features of the minor at the preset time and the facial features of the guardian at the preset time;

[0174] A facial feature comparison module 90 for comparing the facial features of the minor at the preset time and the facial features of the guardian at the preset time after local cutting, and identifying the identity of the minor according to the comparison result.

[0175] As can be seen from the above description, the embodiment of the present invention provides a minor identity recognition device based on face recognition. First, it receives the facial data of the minor and the transaction request; then, it determines the facial data of the guardian of the minor according to the transaction request; finally, according to the facial data of the minor and the facial data of the guardian, it respectively generates the facial data of the minor at the preset time and the facial data of the guardian at the preset time, and compares the facial data of the minor at the preset time with the facial data of the guardian at the preset time. The present invention improves the security of the minor's face brushing, meets legal norms and regulatory requirements, and effectively reduces the risk of the minor's account being stolen.

[0176] The embodiment of the present application also provides a specific implementation manner of an electronic device that can implement all the steps in the above-mentioned minor identity recognition method based on face recognition. Referring to Figure 22 , the electronic device specifically includes the following content:

[0177] A processor 1201, a memory 1202, a communications interface 1203, and a bus 1204;

[0178] Among them, the processor 1201, the memory 1202, and the communications interface 1203 communicate with each other through the bus 1204; the communications interface 1203 is used to implement information transmission between related devices such as server-side devices and client-side devices;

[0179] The processor 1201 is used to call a computer program in the memory 1202. When the processor executes the computer program, all steps in the above-mentioned method for identifying the identity of minors based on face recognition in the embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0180] Step 100: Receive the face data and transaction request of the minor;

[0181] Step 200: Determine the face data of the guardian of the minor according to the transaction request;

[0182] Step 300: Generate the face data of the minor at a preset moment and the face data of the guardian at the preset moment according to the face data of the minor and the face data of the guardian respectively, and compare the face data of the minor at the preset moment with the face data of the guardian at the preset moment.

[0183] An embodiment of the present application further provides a computer-readable storage medium capable of implementing all steps in the above-mentioned method for identifying the identity of minors based on face recognition. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all steps in the above-mentioned method for identifying the identity of minors based on face recognition are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0184] Step 100: Receive the face data and transaction request of the minor;

[0185] Step 200: Determine the face data of the guardian of the minor according to the transaction request;

[0186] Step 300: Generate the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment respectively according to the facial data of the minor and the facial data of the guardian, and compare the facial data of the minor at the preset moment with the facial data of the guardian at the preset moment.

[0187] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of hardware + program, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the partial description of the method embodiments for the relevant parts.

[0188] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0189] Although this application provides method operation steps such as in the embodiments or flowcharts, based on routine or non-creative labor, there can be more or fewer operation steps. The order of steps listed in the embodiments is only one way among many execution orders of the steps and does not represent the only execution order. When the actual device or client product executes, it can be executed in the order shown in the embodiments or the drawings or in parallel (for example, in an environment of parallel processors or multithreaded processing).

[0190] For the convenience of description, when describing the above device, it is divided into various modules according to functions and described separately. Of course, when implementing the embodiments of this specification, the functions of each module can be realized in the same or multiple software and / or hardware, or the modules realizing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0191] Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to implement the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0192] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0193] Memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0194] Embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Embodiments of this specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0195] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for related content. In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples.

[0196] The above are only examples of the embodiments of this specification and are not used to limit the embodiments of this specification. For those skilled in the art, various changes and modifications can be made to the embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for identifying the identity of minors based on face recognition, characterized in that, Including: The facial data of the received minor and the transaction request; Determine the facial data of the minor's guardian according to the transaction request; According to the facial data of the minor and the facial data of the guardian, generate the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment respectively, and compare the facial data of the minor at the preset moment with the facial data of the guardian at the preset moment; The steps of respectively generating the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment include: generating the facial data of the minor at the preset moment according to the pre-generated face prediction model and the facial data of the minor; generating the facial data of the guardian at the preset moment according to the face prediction model and the facial data of the guardian; The method further includes: determining the preset moment according to the age of the minor and the age of the guardian; respectively extracting the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment to generate the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment; respectively performing local cutting on the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment; comparing the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment after local cutting, and identifying the identity of the minor according to the comparison result.

2. The method for identifying the identity of minors based on face recognition according to claim 1, characterized in that, The method for generating the face prediction model includes: Based on the deep learning algorithm, establish the initial model of the face prediction model; Train the initial model according to the facial data of multiple minors and the facial data of the adults corresponding to the multiple minors to generate the face prediction model.

3. The method for identifying the identity of minors based on face recognition according to claim 2, wherein, It also includes: Optimizing the face prediction model, including: Alternately stacking the convolutional layer and the max pooling layer in the face prediction model; Generate the optimized face prediction model according to the facial data of the minor and the stacked face prediction model.

4. The method for identifying the identity of minors based on face recognition according to claim 3, wherein, The step of generating the facial data of the minor at the preset moment according to the pre-generated face prediction model and the facial data of the minor includes: Input the facial data of the minor into the stacked face prediction model to determine the last convolutional layer of the stacked face model; Generate the facial data of the minor corresponding to the preset moment according to the output end of the last convolutional layer.

5. The method for identifying the identity of minors based on face recognition according to claim 3, wherein The step of generating the facial data of the guardian at the preset moment according to the face prediction model and the facial data of the guardian further includes: Input the facial data of the guardian into the stacked face prediction model to determine the last convolutional layer of the stacked face model; Generate the facial data of the guardian corresponding to the preset moment based on the output end of the last convolutional layer.

6. The method for identifying the identity of minors based on face recognition according to claim 1, wherein, The determining of the facial data of the guardian of the minor according to the transaction request includes: Determine the identity information of the minor according to the transaction request; Determine the facial data of the guardian of the minor in a preset database according to the identity information of the minor.

7. An identity recognition device for minors based on face recognition, characterized in that, Includes: A data receiving module, configured to receive the facial data of the minor and the transaction request; A guardian data searching module, configured to determine the facial data of the guardian of the minor according to the transaction request; A dual facial data comparison module, configured to generate the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment respectively according to the facial data of the minor and the facial data of the guardian, and compare the facial data of the minor at the preset moment with the facial data of the guardian at the preset moment; The dual facial data comparison module includes: a minor data generation unit, configured to generate the facial data of the minor at the preset moment according to a pre-generated face prediction model and the facial data of the minor; A guardian data generation unit, configured to generate the facial data of the guardian at the preset moment according to the face prediction model and the facial data of the guardian; The minor identity recognition device based on face recognition further includes: a preset moment determination module, configured to determine the preset moment according to the age of the minor and the age of the guardian; a facial feature extraction module, configured to extract the facial data of the minor at the preset moment and the facial data of the guardian at the preset moment respectively to generate the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment; a local cutting module, configured to perform local cutting on the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment respectively; a facial feature comparison module, configured to compare the facial features of the minor at the preset moment and the facial features of the guardian at the preset moment after local cutting, and identify the identity of the minor according to the comparison result.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, the steps of the minor identity recognition method based on face recognition according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the minor identity recognition method based on face recognition according to any one of claims 1 to 6 are implemented.

Images