User identification method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data prediction, and discloses a user identification method and device, equipment and a storage medium, and the method comprises the steps: collecting a face image of a user when the login information of the user on a network platform is detected; performing facial information recognition according to the face image to obtain skull growth information and a facial wrinkle index; predicting age information of the user according to the skull growth information and the facial wrinkle index; and identifying the user identity according to the age information, and controlling the use duration of the network platform by the user according to the user identity. According to the invention, the identity of the user can be accurately identified, so that the network use time of the juvenile user is supervised.

Description

Technical Field

[0001] The present application relates to the field of data prediction technology, and in particular to user identification methods, devices, equipment and storage media. Background Art

[0002] With the gradual growth of the game industry and the video industry, more and more users are relaxing through games and videos. Many primary and secondary school students are also participating in it. However, since primary and secondary school students are all minors, there is a need to restrict Internet access for minors. However, various game and video platforms cannot accurately identify whether the user is a minor, and thus cannot accurately supervise their Internet usage time.

[0003] Therefore, how to accurately identify the identity of users and thus supervise the Internet usage time of underage users is a problem that urgently needs to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a user identification method, device, equipment and storage medium, aiming to solve the technical problem of how to accurately identify the identity of the user and thus supervise the network usage time of underage users.

[0006] To achieve the above purpose, the present application proposes a user identification method, which includes: When the user's login information on the network platform is detected, the user's facial image is collected; Perform facial information recognition based on the face image to obtain skull growth information and facial wrinkle index; Predicting the user's age information based on the skull growth information and the facial wrinkle index; The user identity is identified according to the age information, and the user's use time of the network platform is controlled according to the user identity.

[0007] In one embodiment, the facial information recognition is performed based on the facial image to obtain the skull growth information and the facial wrinkle index, including: Perform facial information recognition based on the face image to obtain facial features information and overall facial feature information; Performing skull morphology simulation according to the facial features information and the overall facial feature information to obtain skull growth information; Feature points are located according to the facial features information and the overall facial feature information to obtain a facial wrinkle index.

[0008] In one embodiment, the skull morphology simulation is performed according to the facial features information and the overall facial feature information to obtain the skull growth information, including: Performing skull morphology simulation according to the facial features information and the overall facial feature information to obtain an initial skull simulation model; Registering the initial skull simulation model according to the reference skull simulation model to obtain a target skull simulation model; Extract skull features according to the target skull simulation model to obtain skull shape information and skull size information; The skull growth information is determined according to the skull shape information and the skull size information.

[0009] In one embodiment, the positioning of feature points according to the facial features information and the overall facial feature information to obtain a facial wrinkle index includes: Determine a wrinkle area according to the facial features information and the overall facial feature information; Positioning feature points of the wrinkle area to obtain a plurality of wrinkle positioning points; Calculating wrinkle curvature according to the wrinkle positioning points; A facial wrinkle index is determined based on the wrinkle curvature.

[0010] In one embodiment, predicting the user's age information based on the skull growth information and the facial wrinkle index includes: Obtain the skull growth information and facial wrinkle index of multiple users of different age groups and their corresponding real ages; Generate a data set according to the skull growth information and facial wrinkle index of the users of the multiple different age groups and the corresponding real ages; The deep learning neural network model is trained by using the data set to obtain an age prediction model; The age prediction model is used to perform age prediction based on the skull growth information and the facial wrinkle index to obtain the user's age information.

[0011] In one embodiment, the deep learning neural network model is trained by the data set to obtain an age prediction model, including: Dividing the data set into a training set and a test set according to a preset ratio; Training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model; Testing the trained deep learning neural network model using the test set to obtain a loss value; When the loss value reaches a predicted loss threshold, using the trained deep learning neural network model as an age prediction model; When the loss value does not reach the predicted loss threshold, the parameters and weights of the deep learning neural network model are updated according to the loss value, and the step of training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model is returned.

[0012] In one embodiment, identifying the user identity according to the age information and controlling the user's usage time of the network platform according to the user identity includes: comparing the age information with a preset age threshold; When the age information is less than the preset age threshold, determining the user as a minor; Obtain the time limit for underage users to use the corresponding online platform; When the duration of use of the network platform by the user reaches the limit duration, the network behavior of the user is restricted.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a user identification device, the user identification device comprising: A collection module, used to collect the user's face image when detecting the user's login information on the network platform; A recognition module, used to perform facial information recognition based on the face image to obtain skull growth information and facial wrinkle index; A prediction module, used for predicting the user's age information according to the skull growth information and the facial wrinkle index; The control module is used to identify the user's identity according to the age information, and control the user's use time of the network platform according to the user's identity.

[0014] In addition, to achieve the above objectives, the present application also proposes a user identification device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the user identification method described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the user identification method described above are implemented.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the user identification method described above are implemented.

[0017] The present application provides a user identification method. The present application first collects a facial image of the user when the user's login information on the network platform is detected; performs facial information recognition based on the facial image to obtain skull growth information and a facial wrinkle index, thereby accurately identifying the user's facial features; predicts the user's age information based on the skull growth information and the facial wrinkle index, thereby accurately predicting the user's age; identifies the user's identity based on the age information, and controls the user's use time of the network platform based on the user's identity, thereby accurately identifying the user's identity and supervising the network usage time of underage users.

[0018] In summary, the present application identifies the user's facial information when detecting the user's login information on the network platform, obtains the skull growth information and facial wrinkle index, thereby predicting the user's age information, and controls the user's Internet usage time based on the age information. This overcomes the current technical defect of being unable to accurately identify whether the user is a minor and thus being unable to accurately supervise their Internet usage time. This application can accurately identify the user's identity and thus supervise the Internet usage time of underage users. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A flowchart of the first embodiment of the user identification method of the present application is provided; Figure 2 A flowchart of the second embodiment of the user identification method of the present application is provided; Figure 3 A schematic diagram of the registration process provided in Example 2 of the user identification method of this application; Figure 4 This is a schematic diagram of the module structure of a user identification device according to an embodiment of the present application; Figure 5 A schematic diagram of the device structure of the hardware operating environment involved in the user identification method of the embodiment of the present application.

[0022] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of the embodiment of the present application is: when the user's login information on the network platform is detected, the user's facial image is collected; facial information recognition is performed based on the facial image to obtain skull growth information and facial wrinkle index; the user's age information is predicted based on the skull growth information and the facial wrinkle index; the user's identity is identified based on the age information, and the user's use time of the network platform is controlled based on the user's identity.

[0026] With the gradual increase of the game industry and the video industry, more and more users relax through games and videos, and many primary and secondary school students also participate in them. However, since primary and secondary school students are all minors, there is a need to restrict minors from accessing the Internet. However, various game and video platforms cannot accurately identify whether the user is a minor, and thus cannot accurately monitor their Internet usage time. Therefore, how to accurately identify the identity of the user and monitor the Internet usage time of minors is a problem that needs to be solved urgently.

[0027] The present application identifies the user's facial information when detecting the user's login information on the network platform, obtains skull growth information and facial wrinkle index, thereby predicting the user's age information, and controls the user's network usage time based on the age information. This overcomes the current technical defect of being unable to accurately identify whether the user is a minor and thus being unable to accurately monitor their network usage time. The application can accurately identify the user's identity and thus monitor the network usage time of underage users.

[0028] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a user identification device, etc. The following takes the user identification device as an example to illustrate this embodiment and the following embodiments.

[0029] Based on this, the present application embodiment provides a user identification method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the user identification method of the present application.

[0030] In this embodiment, the user identification method includes steps S10 to S40: Step S10, when the user's login information on the network platform is detected, the user's face image is collected.

[0031] It should be noted that a network platform refers to an online space where users can conduct various activities, communicate and obtain information, including but not limited to game platforms, social media, video playback websites or software, etc. This embodiment does not make specific restrictions on this. This embodiment takes game platforms and video playback websites or software as examples for explanation.

[0032] It is understandable that when a user tries to log in to the online platform, the platform will require the user to enter login information, such as user name and password, to verify the user's identity. After successful verification, the user's login information can be detected, and the user's facial image can be captured through a camera or other image acquisition device. It can be captured immediately when the user logs in or uses the platform, and respond quickly without the user actively cooperating or providing sensitive information. The operation is simple and fast.

[0033] It is worth noting that the user's face image is captured in real time using an image acquisition device (such as a camera). In order to ensure the quality of the image, image preprocessing, such as denoising and contrast enhancement, can be performed during the image acquisition process to improve the accuracy of subsequent facial information recognition.

[0034] Step S20, performing facial information recognition based on the face image to obtain skull growth information and facial wrinkle index.

[0035] It should be noted that facial information recognition refers to identifying and extracting key features in facial images through image processing and analysis algorithms. In this embodiment, facial information recognition mainly includes two key steps: extraction of skull growth information and evaluation of facial wrinkle index.

[0036] It is understandable that the skull growth information refers to the maturity and morphological characteristics of the user's skull development, which is usually related to age and individual differences. In this embodiment, by constructing a simulation model of the skull structure, features related to skull growth, such as bone structure, facial proportions, etc., can be extracted from the face image to obtain the user's skull growth information.

[0037] It is worth noting that the facial wrinkle index reflects the degree of sagging and wrinkles of the user's facial skin and is an important indicator for evaluating the user's age and skin condition. In this embodiment, the facial wrinkle index of the user is evaluated by analyzing the skin texture, wrinkle quantity and distribution characteristics in the face image.

[0038] Step S30: predicting the user's age information based on the skull growth information and the facial wrinkle index.

[0039] It should be noted that by adopting advanced machine learning algorithms, such as support vector machines (SVM) or deep learning networks (such as convolutional neural networks (CNN), and by training these algorithm models, they can accurately map skull growth information and facial wrinkle index to corresponding age ranges, thereby achieving accurate prediction of user age.

[0040] In a feasible implementation, step S30 may include: obtaining skull growth information and facial wrinkle index and corresponding real age of users of multiple different age groups; generating a data set based on the skull growth information and facial wrinkle index and corresponding real age of users of multiple different age groups; training a deep learning neural network model through the data set to obtain an age prediction model; performing age prediction based on the skull growth information and the facial wrinkle index through the age prediction model to obtain the user's age information.

[0041] It should be noted that multiple users of different age groups can include teenagers, adults, middle-aged people, and the elderly, to ensure that the training data set has a wide age distribution and representativeness, improve the generalization ability and accuracy of the age prediction model, and enable it to adapt to the age prediction needs of users of different age groups. When collecting the user's skull growth information and facial wrinkle index and the corresponding real age, it is necessary to pay attention to the accuracy and privacy of the data. Therefore, when collecting this data, the user's authorization is required to ensure the user's privacy security. In addition, all collected data are strictly cleaned and verified to ensure the quality of the data.

[0042] It is understandable that in the process of generating the data set, classification and labeling are performed based on the user's skull growth information and facial wrinkle index, combined with their real age, so that the deep learning neural network model can more accurately learn the mapping relationship between features such as skull growth information and facial wrinkle index and age during training.

[0043] It is worth noting that the deep learning neural network model is a machine learning model based on a neural network, which can simulate the connection and transmission mode of neurons in the human brain. Through continuous learning and training, it can automatically extract and learn deep features in the data, thereby achieving accurate classification and prediction of the data. In this embodiment, the deep learning neural network model is used to construct an age prediction model. By training the model, it can predict the user's age information based on the input skull growth information and facial wrinkle index. During the training process, its internal parameters will be continuously iterated and optimized to minimize the error between the predicted age and the actual age. This optimization process is achieved through the back propagation algorithm and the gradient descent algorithm, so that the model can gradually learn how to extract key features from the given skull growth information and facial wrinkle index, and make accurate age predictions based on this.

[0044] In a feasible implementation manner, the deep learning neural network model is trained by the data set to obtain an age prediction model, including: dividing the data set into a training set and a test set according to a preset ratio; training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model; testing the trained deep learning neural network model by the test set to obtain a loss value; when the loss value reaches a predicted loss threshold, using the trained deep learning neural network model as an age prediction model; when the loss value does not reach the predicted loss threshold, updating the parameters and weights of the deep learning neural network model according to the loss value, and returning to the step of training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model.

[0045] It should be noted that when training a deep learning neural network model, a suitable network structure can be selected, such as a variant of a convolutional neural network (CNN) or a recurrent neural network (RNN), to adapt to the processing of image or sequence data such as skull growth information and facial wrinkle index. Appropriate activation functions and loss functions, such as the ReLU activation function and the mean square error (MSE) loss function, are used to ensure that the model can learn and predict effectively.

[0046] It can be understood that the preset ratio can be 7:3 or other ratios. This embodiment does not impose any specific limitation on this. This embodiment takes 7:3 as an example for illustration, that is, when dividing the data set into a training set and a test set, 70% of the data is used as a training set and the remaining 30% is used as a test set. This can ensure that the model has enough data for training and that the performance of the model can be evaluated through the test set.

[0047] It is worth noting that during the training process, optimization algorithms such as Mini-batch Gradient Descent are used to update the parameters and weights of the model to minimize the error between the predicted age and the actual age. In addition, in order to prevent the model from overfitting, regularization can also be used to enhance the generalization ability of the model.

[0048] In the specific implementation, when the loss value on the test set reaches the preset prediction loss threshold, the model is considered to be good enough and can be used as an age prediction model. If the loss value does not reach the prediction loss threshold, the model parameters and weights are adjusted according to the loss value, and retraining is performed until the loss value meets the requirements. In this way, not only can a high-performance age prediction model be obtained, but it can also be ensured that the model has high prediction accuracy and generalization ability on the data of users of different age groups, and the age prediction is more accurate, which can meet the age prediction needs of different user groups.

[0049] Step S40, identifying the user identity according to the age information, and controlling the user's usage time of the network platform according to the user identity.

[0050] It should be noted that user identities include adult users and minor users, that is, the user's age is identified based on the trained age prediction model, and the user's identity is further determined based on the identified age information, that is, whether the user is an adult user or a minor user.

[0051] It is understandable that after identifying the user as an adult user or a minor user, the user's usage time on the network platform can be further controlled. For adult users, more freedom is given because they are considered to have sufficient self-management and decision-making capabilities. However, for minor users, stricter supervision is required to ensure that their healthy development and learning are not excessively disturbed by the use of the Internet.

[0052] In specific implementation, for adult users, the network platform can allow them to use the network freely, but can also set certain usage time limits based on platform policies or user preferences. For example, through reminders or restriction functions, help users develop good network usage habits and avoid being addicted to the online world for a long time.

[0053] In a feasible implementation, step S40 may include: comparing the age information with a preset age threshold; determining that the user is a minor user when the age information is less than the preset age threshold; obtaining the time limit for use of the network platform corresponding to the minor user; and limiting the user's network behavior when the user's use of the network platform reaches the time limit.

[0054] It should be noted that the preset age threshold is usually set to the legal age of majority, such as 18. This threshold is used to clearly distinguish between adult users and underage users, and implement different network usage policies based on this distinction.

[0055] It is understandable that the time limit for the use of the network platform corresponding to underage users can be personalized according to their age, learning tasks and other factors. For example, for younger children, the network use time should be more strictly limited to ensure that they have enough time for outdoor activities and social interaction, such as 0.5h, 1h, etc.; while for older teenagers with heavier learning tasks, the restrictions can be appropriately relaxed, but they still need to ensure that they have enough rest and entertainment time, such as 2h, 4h, etc. This embodiment does not make specific restrictions on this.

[0056] It is worth noting that the time limit for underage users can be multiple different time limits, so as to implement the corresponding supervision strategy to limit the network behavior of the user. For example, three time limits of 2h, 3h and 4h are set. When the usage time of the corresponding network platform of the underage user reaches 2h, the first reminder is made to remind the user to pay attention to the network usage time and suggest them to take a break or do other activities. When the usage time of the underage user reaches 3h, the network speed is reduced to ensure that the user will not be overly addicted to the network. When the network usage time of the underage user reaches the set maximum limit time, such as 4 hours, the user is forced to exit the network platform and is restricted from accessing the network platform again until the next usage cycle begins.

[0057] In specific implementations, the user's fatigue can also be detected through the user's facial features, and the network usage time limit for underage users can be dynamically adjusted based on the fatigue level. For example, when a user continues to use the network platform for a period of time, the user's facial features can be captured through the camera, and the user's eye fatigue level, expression changes, etc. can be analyzed to determine whether the user is in a state of fatigue.

[0058] The present embodiment provides a user identification method. The present embodiment first collects a facial image of the user when the user's login information on the network platform is detected; performs facial information recognition based on the facial image to obtain skull growth information and a facial wrinkle index, thereby accurately identifying the user's facial features; predicts the user's age information based on the skull growth information and the facial wrinkle index, thereby accurately predicting the user's age; identifies the user's identity based on the age information, and controls the user's use time of the network platform based on the user's identity, thereby accurately identifying the user's identity and supervising the network usage time of underage users.

[0059] In summary, this embodiment identifies the user's facial information when detecting the user's login information on the network platform, obtains skull growth information and facial wrinkle index, thereby predicting the user's age information, and controls the user's network usage time based on the age information. This overcomes the current technical defect of being unable to accurately identify whether the user is a minor and thus being unable to accurately supervise their network usage time. This embodiment can accurately identify the user's identity and thus supervise the network usage time of underage users.

[0060] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 , the step S20 further includes steps S201-S203: Step S201, performing facial information recognition based on the face image to obtain facial features information and overall facial feature information.

[0061] It should be noted that facial features usually include the outline and size of eyes, nose, mouth, ears and eyebrows, which are key components of facial recognition features. Overall facial feature information includes more extensive facial features such as face shape, skin texture and skin color.

[0062] It can be understood that local facial features are extracted from facial images to obtain facial information, including: feature extraction of the eyes can identify the outline, size, and whether glasses are worn; feature extraction of the nose can obtain features such as the straightness of the nose bridge and the width of the nose wings; feature extraction of the mouth can analyze the shape of the mouth and whether the corners of the mouth are upturned; feature extraction of the ears can note the size, shape, and position of the ears; and feature extraction of the eyebrows can obtain details such as the density and shape of the eyebrows, which can be achieved through a facial key point detection algorithm. These key points can accurately depict the outline and position of the facial features.

[0063] It is worth mentioning that global facial features are extracted from face images to obtain overall facial feature information, including: by recognizing the face shape, it can be determined whether the user's face is round, square or other shapes; the analysis of skin texture can reflect the user's skin condition, etc. The extraction of overall facial feature information depends on more complex image processing technologies, such as feature descriptors, texture analysis and color space conversion.

[0064] Step S202, performing skull morphology simulation based on the facial features information and the overall facial feature information to obtain skull growth information.

[0065] It should be noted that skull morphology simulation refers to the use of computer vision and graphics technology to construct a skull simulation model, and then obtain the user's skull growth information based on the skull simulation model, including key data such as skull size, shape and growth trend. This embodiment does not impose specific restrictions on this.

[0066] It is understandable that the growth rate and shape of the skull gradually change with age, so the user's age can be determined more accurately based on the skull growth information.

[0067] In a feasible implementation, step S202 may include: performing skull morphology simulation according to the facial features information and the overall facial feature information to obtain an initial skull simulation model; aligning the initial skull simulation model according to a reference skull simulation model to obtain a target skull simulation model; extracting skull features according to the target skull simulation model to obtain skull shape information and skull size information; and determining skull growth information according to the skull shape information and skull size information.

[0068] It should be noted that the skull morphology simulation based on the facial features and overall facial characteristics mainly depends on the mapping relationship between facial features and skull features. Since there is a certain correspondence between the face and the skull in morphology, the general shape of the skull can be inferred by analyzing the facial features and overall facial features to obtain a 3D skull model, that is, an initial skull simulation model.

[0069] It is understandable that after obtaining the initial skull simulation model, in order to further improve its accuracy, it can be registered with the reference skull simulation model. The reference skull simulation model can be an average or standard skull model obtained through training with a large amount of sample data, which is used to calibrate and correct the initial skull simulation model. Through the registration process, it can be ensured that the initial skull simulation model and the reference skull simulation model maintain consistency in shape and size, thereby obtaining a more accurate target skull simulation model.

[0070] In the specific implementation, weighted sampling and feature extraction are performed on the initial skull simulation model to obtain a feature point set P={p i | p i ∈R 3 ,i=1, 2,...,s,s<N}; extract features from the reference skull simulation model to obtain a feature point set Q{q j | q j ∈R 3 ,j=1, 2,...,s,s<N}, for each point in set P, search for all points in set Q that have similar curvature to P, that is, points that satisfy the principal curvature, as follows:

[0071] Among them, k1 and k2 are the principal curvatures, p i are the feature points i, q in the initial skull simulation model j is the feature point j in the reference skull simulation model, , Represents two tunable parameters.

[0072] The feature vectors of the initial skull simulation model point cloud and the reference skull simulation model point cloud can be expressed as [K, H, , k1, k2], where K is the Gaussian curvature, H is the mean curvature, k1 and k2 are the principal curvatures, is the normal vector angle.

[0073] Let the feature vector of the matching point be X=[K, H, , k1, k2], then X pi and X qj They represent the registration points p i and the corresponding point q j The eigenvector of the registration point p i and the corresponding point q j The similarity between them is as follows:

[0074] Among them, S ij is the distance function, representing the registration point p i and the corresponding point q j The similarity between i is the feature point i in the initial skull simulation model, i.e., the registration point, q j is the feature point j in the reference skull simulation model, i.e. the corresponding point, .

[0075] The registration points and corresponding points whose maximum similarity is less than the similarity threshold are regarded as mismatched point pairs, and the registration points and corresponding points whose maximum similarity is greater than or equal to the similarity threshold are regarded as valid matching point pairs, and the initial matching point pair set is obtained. The mismatched point pairs are eliminated by the k-means algorithm to obtain the final matching point pair set, and then the registration vector is calculated according to the final matching point pair set. Finally, the initial skull simulation model is accurately aligned by the registration vector to obtain the target skull simulation model, as shown in Figure 3 As shown, Figure 3 Schematic diagram of the registration process.

[0076] Step S203, locating feature points according to the facial features information and the overall facial feature information to obtain a facial wrinkle index.

[0077] It should be noted that the facial wrinkle index is one of the important indicators to describe the degree of facial skin aging, which is related to the age of the individual. Through the comprehensive analysis of facial features and overall feature information, the facial feature points can be extracted and the facial wrinkle index can be calculated.

[0078] In a feasible implementation, step S203 may include: determining a wrinkle area based on the facial features information and the overall facial feature information; locating feature points of the wrinkle area to obtain a plurality of wrinkle location points; calculating wrinkle curvature based on the wrinkle location points; and determining a facial wrinkle index based on the wrinkle curvature.

[0079] It should be noted that feature fusion is performed based on the facial features information and the overall facial feature information to obtain fused features, and the facial image is restored based on the fused features to obtain a restored facial image to enhance the image detail information, and then the wrinkle area is determined based on the restored facial image.

[0080] It is understandable that wrinkle areas are usually located on the forehead, corners of the eyes, corners of the mouth, etc., which are the most obvious parts of skin aging. In order to more accurately determine the wrinkle areas, deep learning-based image segmentation technology can be used to automatically identify and locate wrinkle areas by training a segmentation model. Once the wrinkle areas are determined, detailed feature point positioning can be performed on these areas.

[0081] When locating wrinkle feature points, a shape context or local feature descriptor-based approach is used to find areas in the image that match the known feature point pattern, thereby locating the specific location of the wrinkle.

[0082] In the specific implementation, the facial wrinkle positioning point is set to δ(x i ,y i ,z i ), i=0,1,2,…,n are arranged from small to large in x-coordinates, and the line vectors of the positioning points are introduced as follows:

[0083] in, is the line vector between wrinkle positioning points i and i-1, and are the coordinates of wrinkle positioning points i and i-1, respectively, and x, y, z are the coordinates of the positioning points in the x, y, and z directions, respectively.

[0084] The curvature of the curve between three adjacent positioning points, that is, the wrinkle curvature, is as follows:

[0085] in, is the average curvature, is the line vector between wrinkle positioning points i and i-1, It is the line vector connecting wrinkle positioning points i+1 and i.

[0086] In the specific implementation, the user's facial wrinkle index can be determined by a comprehensive evaluation based on wrinkle curvature, wrinkle depth, wrinkle length and distribution density. By comparing the grayscale value difference between the wrinkle area and the surrounding normal skin, the depth of the wrinkle can be preliminarily estimated. Usually, the grayscale value of the wrinkle area is lower than that of the normal skin area, indicating that the skin in the wrinkle area is more sunken, that is, the wrinkles are deeper. According to the coordinate information of the wrinkle positioning points, the distance between adjacent positioning points can be calculated to obtain the approximate length of each wrinkle. By counting and weighting the lengths of all wrinkles, an indicator reflecting the total length of wrinkles can be obtained. The wrinkle distribution density refers to the number of wrinkles per unit area. By calculating the ratio of the number of wrinkle positioning points in the wrinkle area to the area of ​​the wrinkle area, the wrinkle distribution density can be obtained. This indicator can reflect the density of wrinkles on the face.

[0087] In this embodiment, by simulating the skull morphology and locating feature points based on the facial features and overall facial feature information identified in the face image, the user's skull growth information and facial wrinkle index can be obtained quickly and accurately, thereby improving the accuracy of user age recognition.

[0088] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the user identification method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0089] This application also provides a user identification device, please refer to Figure 4 , the user identification device comprises: The acquisition module 10 is used to acquire the user's facial image when the user's login information on the network platform is detected.

[0090] The recognition module 20 is used to perform facial information recognition based on the face image to obtain skull growth information and facial wrinkle index.

[0091] The prediction module 30 is used to predict the user's age information based on the skull growth information and the facial wrinkle index.

[0092] The control module 40 is used to identify the user's identity according to the age information, and control the user's use time of the network platform according to the user's identity.

[0093] The present embodiment provides a user identification device. The present embodiment first collects a facial image of the user when the user's login information on the network platform is detected; performs facial information recognition based on the facial image to obtain skull growth information and a facial wrinkle index, thereby accurately identifying the user's facial features; predicts the user's age information based on the skull growth information and the facial wrinkle index, thereby accurately predicting the user's age; identifies the user's identity based on the age information, and controls the user's use time of the network platform based on the user's identity, thereby accurately identifying the user's identity and supervising the network usage time of underage users.

[0094] In summary, this embodiment identifies the user's facial information when detecting the user's login information on the network platform, obtains skull growth information and facial wrinkle index, thereby predicting the user's age information, and controls the user's network usage time based on the age information. This overcomes the current technical defect of being unable to accurately identify whether the user is a minor and thus being unable to accurately supervise their network usage time. This embodiment can accurately identify the user's identity and thus supervise the network usage time of underage users.

[0095] Optionally, the recognition module 20 is further used to perform facial information recognition based on the face image to obtain facial features information and overall facial feature information; perform skull morphology simulation based on the facial features information and the overall facial feature information to obtain skull growth information; perform feature point positioning based on the facial features information and the overall facial feature information to obtain a facial wrinkle index.

[0096] Optionally, the recognition module 20 is also used to simulate the skull morphology according to the facial features information and the overall facial feature information to obtain an initial skull simulation model; align the initial skull simulation model according to a reference skull simulation model to obtain a target skull simulation model; extract skull features according to the target skull simulation model to obtain skull shape information and skull size information; determine skull growth information according to the skull shape information and skull size information.

[0097] Optionally, the recognition module 20 is further used to determine the wrinkle area based on the facial features information and the overall facial feature information; locate feature points of the wrinkle area to obtain multiple wrinkle location points; calculate the wrinkle curvature based on the wrinkle location points; and determine the facial wrinkle index based on the wrinkle curvature.

[0098] Optionally, the prediction module 30 is also used to obtain skull growth information and facial wrinkle index and corresponding real age of users of multiple different age groups; generate a data set based on the skull growth information and facial wrinkle index and corresponding real age of users of multiple different age groups; train a deep learning neural network model through the data set to obtain an age prediction model; perform age prediction based on the skull growth information and the facial wrinkle index through the age prediction model to obtain the user's age information.

[0099] Optionally, the prediction module 30 is further used to divide the data set into a training set and a test set according to a preset ratio; train the deep learning neural network model according to the training set to obtain a trained deep learning neural network model; test the trained deep learning neural network model through the test set to obtain a loss value; when the loss value reaches a predicted loss threshold, use the trained deep learning neural network model as an age prediction model; when the loss value does not reach the predicted loss threshold, update the parameters and weights of the deep learning neural network model according to the loss value, and return to the step of training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model.

[0100] Optionally, the control module 40 is also used to compare the age information with a preset age threshold; when the age information is less than the preset age threshold, determine that the user is a minor user; obtain the time limit for the use of the network platform corresponding to the minor user; and when the user's use of the network platform reaches the time limit, restrict the user's network behavior.

[0101] The user identification device provided by the present application adopts the user identification method in the above embodiment, which can solve the technical problem of how to accurately identify the identity of the user, thereby supervising the network usage time of underage users. Compared with the prior art, the beneficial effects of the user identification device provided by the present application are the same as the beneficial effects of the user identification method provided by the above embodiment, and the other technical features in the user identification device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0102] The present application provides a user identification device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the user identification method in the above-mentioned embodiment 1.

[0103] Reference below Figure 5, which shows a schematic diagram of the structure of a user identification device suitable for implementing an embodiment of the present application. The user identification device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The user identification device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0104] like Figure 5 As shown, the user identification device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the user identification device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the user identification device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a user identification device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0105] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0106] The user identification device provided by the present application adopts the user identification method in the above embodiment, which can solve the technical problem of how to accurately identify the identity of the user, thereby supervising the network usage time of underage users. Compared with the prior art, the beneficial effects of the user identification device provided by the present application are the same as the beneficial effects of the user identification method provided by the above embodiment, and the other technical features in the user identification device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0107] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0109] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the user identification method in the above-mentioned embodiment.

[0110] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0111] The computer-readable storage medium may be included in the user identification device; or may exist independently without being assembled into the user identification device.

[0112] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the user identification device, the user identification device: when detecting the user's login information on the network platform, collects the user's facial image; performs facial information recognition based on the facial image to obtain skull growth information and facial wrinkle index; predicts the user's age information based on the skull growth information and the facial wrinkle index; identifies the user's identity based on the age information, and controls the user's use time of the network platform based on the user's identity.

[0113] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0116] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned user identification method, and can solve the technical problem of how to accurately identify the identity of the user, thereby supervising the network usage time of underage users. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the user identification method provided by the above-mentioned embodiment, and will not be repeated here.

[0117] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned user identification method when executed by a processor.

[0118] The computer program product provided by this application can solve the technical problem of how to accurately identify the identity of a user, thereby supervising the network usage time of underage users. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the user identification method provided by the above embodiment, and will not be repeated here.

[0119] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A user identification method, characterized in that: The method comprises: When the user's login information on the network platform is detected, the user's facial image is collected; Perform facial information recognition based on the face image to obtain skull growth information and facial wrinkle index; Predicting the user's age information based on the skull growth information and the facial wrinkle index; The user identity is identified according to the age information, and the user's use time of the network platform is controlled according to the user identity.

2. The method according to claim 1, characterized in that The step of performing facial information recognition according to the face image to obtain skull growth information and facial wrinkle index includes: Perform facial information recognition based on the face image to obtain facial features information and overall facial feature information; Performing skull morphology simulation according to the facial features information and the overall facial feature information to obtain skull growth information; Feature points are located according to the facial features information and the overall facial feature information to obtain a facial wrinkle index.

3. The method according to claim 2, characterized in that The skull morphology simulation is performed according to the facial features information and the overall facial feature information to obtain the skull growth information, including: Performing skull morphology simulation according to the facial features information and the overall facial feature information to obtain an initial skull simulation model; Registering the initial skull simulation model according to the reference skull simulation model to obtain a target skull simulation model; Extract skull features according to the target skull simulation model to obtain skull shape information and skull size information; The skull growth information is determined according to the skull shape information and the skull size information.

4. The method according to claim 2, characterized in that The method of locating feature points according to the facial features information and the overall facial feature information to obtain a facial wrinkle index includes: Determine a wrinkle area according to the facial features information and the overall facial feature information; Positioning feature points of the wrinkle area to obtain a plurality of wrinkle positioning points; Calculating wrinkle curvature according to the wrinkle positioning points; A facial wrinkle index is determined based on the wrinkle curvature.

5. The method according to claim 1, characterized in that The predicting of the user's age information according to the skull growth information and the facial wrinkle index includes: Obtain the skull growth information and facial wrinkle index of multiple users of different age groups and their corresponding real ages; Generate a data set according to the skull growth information and facial wrinkle index of the users of the multiple different age groups and the corresponding real ages; The deep learning neural network model is trained by using the data set to obtain an age prediction model; The age prediction model is used to perform age prediction based on the skull growth information and the facial wrinkle index to obtain the user's age information.

6. The method according to claim 5, characterized in that The deep learning neural network model is trained by the data set to obtain an age prediction model, including: Dividing the data set into a training set and a test set according to a preset ratio; Training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model; Testing the trained deep learning neural network model using the test set to obtain a loss value; When the loss value reaches a predicted loss threshold, using the trained deep learning neural network model as an age prediction model; When the loss value does not reach the predicted loss threshold, the parameters and weights of the deep learning neural network model are updated according to the loss value, and the step of training the deep learning neural network model according to the training set to obtain a trained deep learning neural network model is returned.

7. The method according to claim 1, characterized in that The identifying of the user identity according to the age information and controlling the user's use time of the network platform according to the user identity includes: comparing the age information with a preset age threshold; When the age information is less than the preset age threshold, determining the user as a minor; Obtain the time limit for underage users to use the corresponding online platform; When the duration of use of the network platform by the user reaches the limit duration, the network behavior of the user is restricted.

8. A user identification device, characterized in that: The user identification device comprises: A collection module, used to collect the user's face image when detecting the user's login information on the network platform; A recognition module, used to perform facial information recognition based on the face image to obtain skull growth information and facial wrinkle index; A prediction module, used for predicting the user's age information according to the skull growth information and the facial wrinkle index; The control module is used to identify the user's identity according to the age information, and control the user's use time of the network platform according to the user's identity.

9. A user identification device, characterized in that: The user identification device comprises: a memory, a processor, and a user identification program stored in the memory and executable on the processor, wherein the user identification program is configured to implement the user identification method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a user identification program, and when the user identification program is executed by the processor, the user identification method according to any one of claims 1 to 7 is implemented.

Images