Data processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a data processing method and device, equipment and a storage medium. The data processing method and device are used for recognizing abnormal groups in a game. Comprising the following steps: acquiring eye behavior features and iris features of a target object; the eye behavior features are input into a judgment model for suspicious judgment so as to obtain a prediction probability value, and the judgment model is obtained through training according to the eye sample data and the corresponding labeling information; comparing the iris feature with a registered iris feature corresponding to the current account to obtain a verification result; and determining an identification result of the target object according to the prediction probability value and the verification result. The technical scheme provided by the invention can be applied to the fields of artificial intelligence, computers, cloud technologies, games and the like.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a data processing method, device, equipment and storage medium. Background Art

[0002] With the popularization and development of the Internet, online games are becoming more and more popular among netizens, enriching people's leisure and entertainment life. However, in recent years, cheating behaviors have continued to emerge in various team combat gameplays. Cheating users use plug-in programs to lead weaker players through game levels to obtain game benefits. This cheating behavior is extremely unfair to normal players and seriously damages the game play ecology.

[0003] Therefore, there is an urgent need for a method to identify illegal gaming activities and ensure the normal operation of the game. Summary of the invention

[0004] Embodiments of the present application provide a data processing method, apparatus, device, and storage medium for identifying abnormal groups in a game.

[0005] In view of this, on the one hand, the present application provides a data processing method, including: obtaining eye behavior characteristics and iris characteristics of a target object; calling a judgment model to make a suspicious judgment on the eye behavior characteristics to obtain a predicted probability value, wherein the judgment model is trained based on eye sample data and corresponding annotation information; comparing the iris characteristics with the registered iris characteristics corresponding to the current account to obtain a verification result; and determining the recognition result of the target object based on the predicted probability value and the verification result.

[0006] On the other hand, the present application provides a data processing device, including: an acquisition module, for acquiring eye behavior characteristics and iris characteristics of a target object;

[0007] A processing module is used to call a judgment model to make a suspicious judgment on the eye behavior feature to obtain a predicted probability value, wherein the judgment model is trained based on the eye sample data and the corresponding annotation information; and compare the iris feature with the registered iris feature corresponding to the current account to obtain a verification result;

[0008] The recognition module is used to determine the recognition result of the target object according to the predicted probability value and the verification result.

[0009] In one possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is specifically used to acquire the corneal reflection point, pupil center point, eye rotation information and pupil zoom information of the target object;

[0010] Calculating the gaze coordinate point of the target object according to the eye corneal reflection point and the pupil center point;

[0011] The gaze coordinate point, the eyeball rotation information and the pupil zoom information are used as eye behavior features of the target object.

[0012] In a possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is specifically used to acquire an iris image of the target object;

[0013] Performing image segmentation processing on the iris image to obtain an iris region in the iris image belonging to the target object;

[0014] Feature extraction is performed on the iris region to obtain a feature vector corresponding to the iris region, and the feature vector is used as the iris feature.

[0015] In one possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is specifically used to perform image enhancement processing on the iris image to obtain an intermediate image, and the clarity of the intermediate image is higher than that of the iris image;

[0016] The intermediate image is subjected to image segmentation processing to obtain an iris region in the iris image.

[0017] In a possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is specifically configured to perform image enhancement processing on the iris image to obtain an intermediate image, including:

[0018] Performing denoising on the iris image to obtain the intermediate image;

[0019] or,

[0020] Performing contrast enhancement processing on the iris image to obtain the intermediate image;

[0021] or,

[0022] The iris image is subjected to denoising and contrast enhancement processing to obtain the intermediate image.

[0023] In one possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is specifically used to perform edge detection processing on the intermediate image to obtain an iris area in the iris image;

[0024] or,

[0025] Performing shape fitting processing on the intermediate image to obtain an iris region in the iris image;

[0026] or,

[0027] The intermediate image is subjected to edge detection and shape fitting processing to obtain the iris region in the iris image.

[0028] In one possible design, in another implementation of another aspect of the embodiment of the present application, the processing module is specifically used to extract features from the iris region using a Gabor filter to obtain a feature vector corresponding to the iris region;

[0029] or,

[0030] A Laplacian of Gaussian filter is used to extract features from the iris region to obtain a feature vector corresponding to the iris region.

[0031] In one possible design, in another implementation of another aspect of the embodiment of the present application, the processing module is used to determine the similarity between the iris feature and the registered iris feature;

[0032] When the similarity is greater than a first threshold, the verification result is used to indicate that the target object is a registered user of the current account;

[0033] When the similarity is less than or equal to the first threshold, the verification result is used to indicate that the target object is an abnormal object.

[0034] In one possible design, in another implementation of another aspect of an embodiment of the present application, the recognition result is used to determine that the target object is an abnormal object when the predicted probability value is greater than a second threshold and / or the verification result indicates that the target object is an abnormal object.

[0035] In one possible design, in another implementation of another aspect of the embodiment of the present application, the acquisition module is used to acquire a training sample pair and an initial determination model, the training sample pair including the eye sample data and annotation information of the eye sample data, the annotation information being used to indicate whether an object corresponding to the eye sample data is a normal object or an abnormal object;

[0036] The processing module is used to call the initial determination model to process the eye movement sample data to obtain a predicted training probability value of the eye movement sample data;

[0037] Processing the predicted training probability value and the labeled information to obtain a loss value;

[0038] The device also includes a training module, which is used to train the initial determination model according to the loss value to obtain the determination model.

[0039] In one possible design, in another implementation of another aspect of the embodiment of the present application, the training module is used to update and train the determination model based on the recognition result and the eye behavior characteristics.

[0040] In one possible design, in another implementation of another aspect of the embodiment of the present application, the processing module is used to trigger an alarm prompt when the recognition result indicates that the target object is an abnormal object.

[0041] Another aspect of the present application provides a computer device, including: a memory, a processor, and a bus system;

[0042] Wherein, the memory is used to store programs;

[0043] The processor is used to execute the program in the memory, and the processor is used to execute the above-mentioned methods according to the instructions in the program code;

[0044] The bus system is used to connect the memory and the processor so that the memory and the processor can communicate with each other.

[0045] Another aspect of the present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer is enabled to execute the above-mentioned methods.

[0046] Another aspect of the present application provides a computer program product or a computer program, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided by the above aspects.

[0047] It can be seen from the above technical scheme that the embodiments of the present application have the following advantages: capturing the eye behavior characteristics and iris characteristics of the object, and then using the eye behavior characteristics and iris recognition as the judgment conditions for abnormal behavior, thereby combining the eye monitoring and iris recognition technologies, and at the same time adding a model obtained by deep learning to judge the eye behavior characteristics, so that the judgment of abnormal groups can be more intelligent, thereby improving the accuracy of identifying abnormal groups. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of the architecture of a data processing system in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of a network architecture of a determination model in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of a flow chart of a data processing method in an embodiment of the present application;

[0051] Figure 4This is a schematic diagram of an embodiment of a data processing method in an embodiment of the present application;

[0052] Figure 4a A schematic diagram of a process for acquiring eye behavior features in an embodiment of the present application;

[0053] Figure 4b A schematic diagram of a flow chart of eye behavior feature determination in an embodiment of the present application;

[0054] Figure 4c A schematic diagram of a process of iris recognition in an embodiment of the present application;

[0055] Figure 4d This is a schematic diagram of an overall flow chart of the data processing method in the embodiment of the present application;

[0056] Figure 5 This is a schematic diagram of an embodiment of a data processing device in an embodiment of the present application;

[0057] Figure 5a This is another schematic diagram of an embodiment of a data processing device in an embodiment of the present application;

[0058] Figure 6 This is another schematic diagram of an embodiment of a data processing device in an embodiment of the present application;

[0059] Figure 7 FIG. 1 is a schematic diagram of another embodiment of a data processing device in an embodiment of the present application. DETAILED DESCRIPTION

[0060] Embodiments of the present application provide a data processing method, apparatus, device, and storage medium for identifying abnormal groups in a game.

[0061] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "corresponding to" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0062] With the popularization and development of the Internet, online games are becoming more and more popular among netizens, enriching people's leisure and entertainment life. However, in recent years, cheating behaviors have continued to emerge in various team combat gameplays. Cheating users use plug-in programs to lead weaker players through game levels to obtain game benefits. This cheating behavior is extremely unfair to normal players and seriously damages the game's gameplay ecology. Therefore, there is an urgent need for a method to identify game black production and ensure the normal operation of the game.

[0063] In order to solve the above technical problems, the present application provides the following technical solutions: obtaining the eye behavior characteristics and iris characteristics of the target object; calling the judgment model to make suspicious judgments on the eye behavior characteristics to obtain a predicted probability value, and the judgment model is trained based on the eye sample data and the corresponding annotation information; comparing the iris characteristics with the registered iris characteristics corresponding to the current account to obtain a verification result; determining the recognition result of the target object based on the predicted probability value and the verification result. In this way, by capturing the eye behavior characteristics and iris characteristics of the object, and then using the eye behavior characteristics and iris recognition as the judgment conditions for abnormal behavior, the eye monitoring and iris recognition technologies are combined, and at the same time, the model obtained by deep learning is added to judge the eye behavior characteristics, so that it can have a higher intelligence when judging abnormal groups, thereby improving the accuracy of identifying abnormal groups.

[0064] For ease of understanding, some of the professional terms involved in this application are explained below:

[0065] Virtual Reality (VR) technology is a computer simulation system that can create and experience a virtual world. It uses computers to generate a simulated environment. It is a system simulation of interactive three-dimensional dynamic vision and entity behavior that integrates multi-source information, allowing users to immerse themselves in the environment. At present, VR technology is mainly used in VR games. It can simulate characters based on VR scenes, so that players can use hand models to control characters in VR scenes, so that virtual characters can represent players for experience. Characters and virtual props can also be displayed in VR scenes. These virtual props can be dynamically adjusted according to the operations in the VR scenes. Through the experience and operation of VR, players are given a lot of freedom, and there is an incomparable strong sense of immersion compared to ordinary games.

[0066] Iris recognition technology: It is based on the iris in the eye for identity recognition and is a type of human biometric recognition technology. The structure of the human eye is composed of sclera, iris, pupil, lens, retina and other parts. The iris is a circular part located between the black pupil and the white sclera, which contains many interlaced spots, filaments, crowns, stripes, crypts and other detailed features. Moreover, after the iris is formed during the fetal development stage, it will remain unchanged throughout the life course. These features determine the uniqueness of the iris features and also determine the uniqueness of identity recognition. Therefore, the iris features of the eye can be used as the object of identity recognition for each person. Iris recognition technology can identify the wearer's identity and can realize security applications such as device locks, network account logins, financial payments, and VR game account logins for head-mounted display devices.

[0067] Eye movement and sight line monitoring: A type of machine vision technology that uses an image sensor to capture an image of the eyeball, identifies features in the eyeball based on image processing, and uses these features to calculate the user's gaze point in real time. In this application, eye movement and sight line monitoring technology involves the process of capturing and analyzing the user's eye activities in real time, including sight line direction, pupil size changes, and eyeball movements, and can accurately monitor the user's sight line and eye activities during the game.

[0068] Judgment model: The judgment model in this application is a deep learning-based model used to analyze the user's eye movement, pupil dilation, and iris changes in the game. By learning the eye behavior characteristics of a large number of users during the game, the model can determine whether the user's behavior in the game meets expectations, thereby identifying abnormal groups. For example, in a shooting game, it can determine whether the user's eye behavior characteristics in the four stages of finding the target, aiming at the target, shooting, and ending meet expectations, thereby effectively identifying abnormal groups.

[0069] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that the machines have the functions of perception, reasoning and decision-making. In this application, the judgment model involves AI, wherein the judgment model is obtained by deep learning. Therefore, the architecture of the judgment model can be based on various network architectures of neural networks, which are not specifically limited here.

[0070] Deep learning: Deep learning is a machine learning method based on neural networks that can learn and abstract complex data features. In this application, deep learning is used to build a judgment model. By analyzing the eye behavior characteristics of a large number of users during the game, the user's line of sight movement patterns, pupil changes and eye changes in the game are learned, thereby effectively identifying abnormal groups. The concept of deep learning originated from the study of artificial neural networks. A multilayer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. The motivation for studying deep learning is to establish a neural network that simulates the human brain for analysis and learning. It imitates the mechanism of the human brain to interpret data, such as images, sounds, and text.

[0071] Neural Network: Artificial Neural Networks (ANN) are composed of a large number of neurons connected by adjustable connection weights. They have the characteristics of large-scale parallel processing, distributed information storage, and good self-organization and self-learning capabilities. There are many variants of neural networks involved in deep learning, such as error back propagation (BP) neural network, probabilistic neural network, convolutional neural network (CNN), time recursive neural network (LSTM), etc. However, the simplest and most original neural network is the Multi-Layer Perception (MLP).

[0072] Multilayer Perceptron (MLP): is a feed-forward artificial neural network model that maps multiple input data sets to a single output data set.

[0073] Convolutional Neural Network (CNN) is a feedforward neural network. A convolutional neural network includes at least two neural network layers, each of which contains a number of neurons. The neurons are arranged in layers. Neurons in the same layer are not connected to each other, and information between layers is transmitted in only one direction.

[0074] Back propagation: Forward propagation refers to the feedforward processing of the model, while back propagation is the opposite of forward propagation, which refers to updating the weight parameters of each layer of the model according to the output of the model. For example, if the model includes input layer, hidden layer and output layer, then forward propagation refers to processing in the order of input layer-hidden layer-output layer, and back propagation refers to updating the weight parameters of each layer in the order of output layer-hidden layer-input layer.

[0075] Eye behavior characteristics: behavior sequence data generated by changes in the eyeball, sight line and pupil of the target object when the target object is operated through a VR head display in a VR application. In an exemplary scheme, the behavior sequence data can be obtained by reading the identification number of the application corresponding to the virtual environment and the name of the eye behavior characteristic. For example, in game A, the behavior sequence data of user A can be "20133245|1,2,1,1,1,2,2,4,5,6,1,2,3,2", where "20133245" is the identification number of user A, and "1,2,1,1,1,2,2,4,5,6,1,2,3,2" are different behavior identification numbers of eye behavior characteristics. Assume that the identification of eye movement is 1 to 4, where "1" is used to indicate left movement, "2" is used to indicate right movement, "3" is used to indicate upward movement, and "4" is used to indicate downward movement. The mark of pupil zoom is 5 to 6, where "5" is used to indicate pupil constriction and "6" is used to indicate pupil dilation.

[0076] The data processing method, device, equipment and storage medium provided in the embodiments of the present application can improve the recognition effect of abnormal groups of gamers. The following describes an exemplary application of the electronic device provided in the embodiments of the present application. The electronic device provided in the embodiments of the present application can be implemented as various types of user terminals or as a server.

[0077] By running the data processing solution provided in the embodiment of the present application, the electronic device can improve the recognition effect of abnormal game groups. That is, the electronic device itself can improve the recognition effect of abnormal game objects, which is applicable to a variety of game applications. For example, first-person shooter games, action role-playing games, fighting games, etc.

[0078] See also Figure 1 , Figure 1It is an optional architecture diagram under an application scenario of the data processing solution provided by the embodiment of the present application. In order to realize and support a data processing solution, the terminal device 100 is connected to the server 300 through the network 200, and the server 300 is connected to the database 400. The network 200 can be a wide area network or a local area network, or a combination of the two. The client for implementing the data processing solution is deployed on the terminal device 100, wherein the client can be run on the terminal device 100 in the form of a browser, or can be run on the terminal device 100 in the form of an independent application (application, APP), etc. The specific presentation form of the client is not limited here. The server 300 involved in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal device 100 can be a smart phone, a tablet computer, a laptop, a PDA, a personal computer, a smart TV, a smart watch, a vehicle-mounted device, a wearable device, etc., but is not limited thereto. The terminal device 100 and the server 300 can be directly or indirectly connected through the network 200 by wired or wireless communication, and this application does not limit this. The number of servers 300 and terminal devices 100 is also not limited. The solution provided in this application can be completed independently by the terminal device 100, or by the server 300, or by the terminal device 100 and the server 300 in cooperation, and this application does not make specific limitations. Among them, the database 400, in short, can be regarded as an electronic filing cabinet-a place for storing electronic files, and users can add, query, update, delete, and other operations on the data in the file. The so-called "database" is a collection of data that is stored together in a certain way, can be shared with multiple users, has as little redundancy as possible, and is independent of the application program. A database management system (DBMS) is a computer software system designed for managing databases, generally with basic functions such as storage, interception, security, and backup.Database management systems can be classified according to the database models they support, such as relational, Extensible Markup Language (XML); or according to the types of computers they support, such as server clusters, mobile phones; or according to the query language used, such as Structured Query Language (SQL), XQuery; or according to performance impulse focus, such as maximum scale, maximum operating speed; or other classification methods. Regardless of the classification method used, some DBMSs can cross categories, for example, supporting multiple query languages ​​at the same time. In the present application, database 400 can be used to store eye behavior features and iris features. Of course, the storage location of eye behavior features and iris features is not limited to the database, for example, it can also be stored in the terminal device 100, blockchain or distributed file system of server 300.

[0079] In some embodiments, the server 300 and the terminal device 100 can both execute the data processing method provided in the embodiment of the present application and the training method of the determination model in the data processing method, or the server 300 and the terminal device 100 can execute the data processing method provided in the embodiment of the present application and the training method of the determination model in the data processing method. In this embodiment, in an exemplary scheme, the determination model may include a multi-layer neural network, wherein the determination model may include Figure 2 The input layer, embedding layer, multi-head self-attention mechanism layer and multiple fully connected layers are shown. The input layer and the embedding layer are used to encode the eye behavior feature to generate an eye behavior vector. The multi-head self-attention mechanism layer and the multiple fully connected layers are used to deeply learn the semantic representation of the eye behavior feature, and predict the prediction probability value corresponding to the eye behavior feature based on the semantic representation.

[0080] It is understandable that the above Figure 2 This is only an exemplary network architecture of the determination model, and may also be other network structures, such as CNN structure or LSTM structure, which is not specifically limited here.

[0081] In this embodiment, the training process of the judgment model can be as follows: obtain training sample pairs from the terminal device 100 and / or the database 400 and establish an initial judgment model; predict the training sample pairs through the initial judgment model to obtain training prediction probability values, and determine the loss value corresponding to the training prediction probability value and the true label based on the loss function including the pre-designed loss factor, and then adjust the parameters of the judgment model by backpropagation based on the loss value, so as to achieve the training of the initial judgment model to obtain the judgment model.

[0082] In this embodiment, when training the judgment model, the server 300 may use a cross entropy loss function to calculate the loss value. In an exemplary solution, the expression of the cross entropy loss function may be as shown in Formula 1, where Formula 1 is as follows: Among them, M is used to indicate the number of classification categories of the fully connected classification layer of the judgment model, N is used to indicate the number of input samples, and y ic It is used to indicate the real annotation corresponding to the eye sample data. ic Used to indicate the training prediction probability value.

[0083] It should be understood that the user can also set multiple categories for the annotation information in the training sample pair, such as abnormal objects under the first type of cheating behavior, abnormal objects under the second type of cheating behavior, abnormal objects under the third type of cheating behavior, etc. At this time, the number of classification categories will be adjusted accordingly, and the number of probability values ​​in the predicted probability vector output by the judgment model will also be adjusted accordingly.

[0084] In this embodiment, the operation of acquiring the eye behavior feature can collect the eye behavior data of the user in the game through a camera, and intercept the target eye behavior data from the eye behavior data according to a preset time length. For example, for a certain game, the eye behavior data of the target object is obtained, and the eye behavior data of the target object is converted into a sequence form of behavior numbers in chronological order. For example, the eye behavior data here includes eye movements, pupil changes, and line of sight changes, and the eye movements, pupil changes, and line of sight changes are sequentially formed into a sequence data in chronological order.

[0085] In this embodiment, when the initial model is trained according to the loss value, an optimizer can be used to reversely adjust the parameters of the initial model according to the loss value. It is understandable that the optimizer can select the ADAM optimizer, which calculates the adaptive learning rate of each parameter of the neural network based on momentum, and only requires a small amount of parameter adjustment, thereby speeding up the model training efficiency.

[0086] After the judgment model is trained, the server 300 can save the judgment model locally, thereby providing the terminal device 100 with a remote abnormal game object recognition function. For example, the server 300 can receive the eye behavior features and iris features sent by the terminal device 100, call the judgment model to make a suspicious judgment on the eye behavior features to obtain a predicted probability value, and the judgment model is obtained by deep learning based on the eye sample data and the corresponding annotation information; the iris feature is compared with the registered iris feature corresponding to the current account to obtain a verification result; the recognition result of the target object is determined based on the predicted probability value and the verification result, and the recognition result is sent to the game service provider, so that the service provider can perform corresponding operations on the target object or game. For example, prompt information such as account blocking or profit penalty is displayed in the terminal device 100 used by the target object, or the game design is optimized.

[0087] The server 300 can also send (deploy) the trained judgment model to the terminal device 100, so as to realize the recognition of abnormal game objects locally on the terminal device 100. For example, the terminal device 100 can obtain eye behavior features and iris features in real time, call the judgment model to make suspicious judgments on the eye behavior features to obtain a predicted probability value, and the judgment model is obtained by deep learning based on the eye sample data and the corresponding annotation information; the iris feature is compared with the registered iris feature corresponding to the current account to obtain a verification result; the recognition result of the target object is determined based on the predicted probability value and the verification result, and the recognition result is sent to the game service provider, so that the service provider can perform corresponding operations on the target object or game. For example, prompt information such as account blocking or profit penalty is displayed in the terminal device 100 used by the target object, or the game design is optimized.

[0088] Based on the above system, please refer to Figure 3 As shown, an execution flow of the data processing method in this application can be as follows:

[0089] 1. Obtain the target object’s eye behavior characteristics and iris features.

[0090] 2. Determine a predicted probability value of the target object based on the eye behavior characteristics. The predicted probability value is used to indicate the probability value of the target object being an abnormal object. It can also be a probability value indicating that the target object is a normal object. As long as the classification category of the target object can be predicted, no specific limitation is made here.

[0091] 3. Authenticate the target object based on the iris feature to obtain a verification result.

[0092] 4. Determine the recognition result of the target object based on the verification result and the predicted probability value.

[0093] It is understandable that in the specific implementation of the present application, data related to eye behavior characteristics and iris characteristics are involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0094] In combination with the above introduction, the data processing device method in this application will be introduced below with the server as the execution subject, please refer to Figure 4 , an embodiment of the data processing device method in the embodiment of the present application includes:

[0095] 401. Obtain eye behavior characteristics and iris characteristics of the target object.

[0096] In this embodiment, the server receives the eye image and the iris image taken by the camera of the head display device or the camera of other terminal devices, and then performs corresponding image processing on the eye image and the iris image to obtain the eye behavior characteristics and the iris characteristics.

[0097] Optionally, after receiving the eye image, the server obtains the target object's corneal reflection point, pupil center point, eye rotation information and pupil zoom information based on the eye image; calculates the target object's gaze coordinate point based on the eye corneal reflection point and the pupil center point; and uses the gaze coordinate point, the eye rotation information and the pupil zoom information as the target object's eye behavior characteristics.

[0098] In an exemplary solution, taking a head mounted device running a VR game as an example, the process of acquiring the eye behavior features is described:

[0099] like Figure 4a As shown, the specific process can be as follows:

[0100] 1. The target object wears the VR device and starts the game.

[0101] 2. The infrared light source of the VR device is irradiated on the eyeball of the target object, and the eyeball of the target object is photographed using the camera of the VR device.

[0102] 3. The camera captures the eye image of the target object.

[0103] 4. Based on the eye image, use an image processing algorithm to calculate the gaze point coordinates of the target object, and simultaneously obtain the eye movement information and pupil zoom information of the target object.

[0104] 5. The VR device sends the gaze point coordinates, the eye movement information, and the pupil zoom information to the background server, and the background server records and analyzes the gaze point coordinates, the eye movement information, and the pupil zoom information.

[0105] It is understandable that the above steps 1 to 5 can all be performed on the VR device, and the specific details are not limited here.

[0106] It is understandable that when the gaze point coordinates, the eye movement information, and the pupil zoom information are sent to the backend server, the sending frequency and the sending load can be adjusted according to the specific conditions of the network. For example, when the network quality is good, the sending frequency and the amount of data carried by each data packet sent can be increased. When the network quality is poor, the sending frequency and the amount of data carried by each data packet sent can be reduced.

[0107] At the same time, after receiving the iris image, the server performs image enhancement processing on the iris image to obtain an intermediate image, the clarity of which is higher than that of the iris image; performs image segmentation processing on the intermediate image to obtain the iris area in the iris image; performs feature extraction on the iris area to obtain a feature vector corresponding to the iris area, and uses the feature vector as the iris feature. It is understandable that when performing image enhancement processing on the iris image, the image enhancement processing method includes but is not limited to denoising, contrast enhancement and other methods. At the same time, when performing image segmentation on the iris image, the image segmentation method includes but is not limited to edge detection and shape fitting and other methods. When performing feature extraction on the iris area, the feature extraction method includes but is not limited to Gabar filter and Gaussian Laplacian filter.

[0108] 402. Calling a judgment model to make a suspicious judgment on the eye behavior feature to obtain a predicted probability value, wherein the judgment model is obtained by deep learning based on the eye sample data and corresponding annotation information.

[0109] In this embodiment, the server inputs the eye behavior feature into the determination model for suspicious prediction to obtain the prediction probability value. The determination model can be trained using the training process described above, which will not be described in detail here.

[0110] In this embodiment, the predicted probability value can be one value or multiple values. When the predicted probability value is multiple, the number of predicted probabilities included in the predicted probability value is the number of classification categories set in the determination model, and the value of each predicted probability in the predicted probability value can be set according to the actual classification category, that is, the sum of the various predicted probabilities is 1 or the various predicted probabilities do not affect each other. When the predicted probability value includes multiple predicted probabilities, the server compares each predicted probability in the predicted probability value with a preset threshold value, and when the predicted probability corresponding to the kth classification category in the predicted probability value is greater than the preset threshold value, it is determined that the recognition result of the target object is the kth classification category, and k is an integer. In this embodiment, the number of predicted probabilities in the predicted probability value is the number of classification categories set in the recognition model, and the value of each predicted probability in the predicted probability value can be set according to the actual classification category, that is, the sum of the various predicted probabilities is 1 or the various predicted probabilities do not affect each other.

[0111] In an exemplary embodiment, if the predicted probability value includes two classification categories, and the classification categories are abnormal objects and normal objects, the sum of the two probability values ​​in the predicted probability value is 1, for example, the predicted probability value can be (0.4, 0.6). At this time, assuming that the preset threshold is 0.5, if the probability value indicating the abnormal object is 0.6, the recognition result of the target object is determined to be that the target object is an abnormal object.

[0112] In another exemplary embodiment, if the predicted probability value includes three classification categories, and the classification categories are the first type of cheating behavior abnormal object, the second type of cheating behavior abnormal object, and the third type of cheating behavior abnormal object, the three probability values ​​in the predicted probability value may not affect each other, for example, the predicted probability value may be (0.7, 0.8, 0.2). At this time, assuming that the preset threshold is 0.6, if the probability value indicating the first type of cheating behavior abnormal object is 0.7, and the probability value indicating the second type of cheating behavior abnormal object is 0.8, then the identification result of the target object is determined to be the first type of cheating behavior abnormal object and the second type of cheating behavior abnormal object.

[0113] In an exemplary solution, taking a head mounted device running a VR game as an example, the eye behavior feature determination process is described:

[0114] like Figure 4b As shown, the specific process can be as follows:

[0115] 1. Collect historical user data, that is, collect the eye behavior characteristics of normal objects and the eye behavior characteristics of abnormal objects.

[0116] 2. Analyze the historical user data, that is, label each eye behavior feature to obtain training sample pairs.

[0117] 3. Train the initial judgment model based on the training samples to obtain the judgment model.

[0118] 4. Deploy the judgment model on the background server corresponding to the VR game.

[0119] 5. The target object wears the VR device and starts the game.

[0120] 6. The infrared light source of the VR device is irradiated on the eyeball of the target object, and the camera of the VR device is used to photograph the eyeball of the target object.

[0121] 7. The camera captures an eye image of the target object.

[0122] 8. Based on the eye image, use an image processing algorithm to calculate the gaze point coordinates of the target object, and simultaneously obtain the eye movement information and pupil zoom information of the target object.

[0123] 9. The VR device sends the gaze point coordinates, the eye movement information, and the pupil zoom information to a background server, and the background server records and analyzes the gaze point coordinates, the eye movement information, and the pupil zoom information.

[0124] 10. The backend server inputs the gaze point coordinates, the eye movement information, and the pupil zoom information into the determination model to perform suspicious determination and obtain the predicted probability value.

[0125] 11. Determine whether the target object is an abnormal object based on the predicted probability value. If so, execute 12; if not, execute 13.

[0126] 12. Send an alarm prompt.

[0127] 13. Run the game normally.

[0128] 14. Update the parameters of the determination model according to the predicted probability value and the eye behavior characteristics.

[0129] It is understandable that the above steps 1 to 14 can all be performed on the VR device, and the specific details are not limited here.

[0130] 403. Compare the iris feature with the registered iris feature corresponding to the current account to obtain a verification result.

[0131] The server compares the iris feature with the registered iris feature corresponding to the current account to obtain the similarity between the two.

[0132] In an exemplary solution, the iris determination process is described by taking a head mounted device running a VR game as an example:

[0133] like Figure 4c As shown, the specific process can be as follows:

[0134] 1. The target object wears the VR device and starts the game.

[0135] 2. The infrared light source of the VR device is irradiated on the eyeball of the target object, and the eyeball of the target object is photographed using the camera of the VR device.

[0136] 3. The camera captures the eye image of the target object.

[0137] 4. Perform image enhancement processing on the eye image to obtain an eye image with better image clarity. It is understood that the image enhancement processing method includes but is not limited to denoising, contrast enhancement and other processing methods.

[0138] 5. Perform image segmentation on the processed eye image to obtain an image that only includes the iris area. It is understood that the image segmentation method includes but is not limited to edge detection and shape fitting algorithms.

[0139] Among them, edge detection: is a fundamental problem in image processing and computer vision. The purpose of edge detection is to identify points in digital images where brightness changes significantly. Significant changes in image attributes usually reflect important events and changes in attributes. These include (i) discontinuities in depth, (ii) discontinuities in surface orientation, (iii) changes in material properties, and (iv) changes in scene lighting. Edge detection is a research area in image processing and computer vision, especially in feature extraction. Image edge detection greatly reduces the amount of data, eliminates information that can be considered irrelevant, and retains important structural properties of the image.

[0140] Shape fitting is a common image processing technology that can fit a set of discrete points into a polygon to better describe and analyze the shape and structure in the image. Shape fitting is widely used in computer vision, robotics, automatic control and other fields. The basic idea of ​​shape fitting is to regard a set of discrete points as the vertices of a polygon, and then determine the boundary and vertex positions of the polygon through a certain algorithm. Common shape fitting algorithms include least squares method, convex hull algorithm, etc.

[0141] 6. The VR device performs feature extraction on the segmented iris region to obtain a feature vector of the iris region, and uses the feature vector as the iris feature. In this embodiment, the feature extraction method includes but is not limited to a Gabor filter and a Laplacian of Gaussian filter.

[0142] Among them, the Gabor filter: is a linear filter used for texture analysis, which essentially refers to analyzing whether there is a specific frequency content in a specific direction in the image in the local area around the analysis point or analysis area. The frequency and direction representation of the Gabor filter is considered by many contemporary visual scientists to be similar to the frequency and direction representation of the human visual system. Therefore, the Gabor filter is particularly suitable for texture representation and discrimination. In the spatial domain, the two-dimensional Gabor filter is a Gaussian kernel function modulated by a sinusoidal plane wave (see Gabor transform). The Gabor transform is a short-time windowed Fourier transform (simply understood as a Fourier transform within a specific time window), which is a special case when the window function in the short-time Fourier transform is a Gaussian function. Therefore, the Gabor filter can extract relevant features at different scales and directions in the frequency domain.

[0143] Laplacian of Gaussian (LOG) filter: It is an operator that extracts edges by using the Laplacian operator based on the Gaussian function. The Laplacian operator is a two-dimensional isotropic measure of the second-order spatial derivative of an image. The Laplacian operator can highlight areas in an image where the intensity changes rapidly, so it is often used in edge detection tasks. Before performing the Laplacian operation, it is usually necessary to smooth the image with a Gaussian smoothing filter to reduce the sensitivity of the Laplacian operation to noise. This operation usually inputs a grayscale image and outputs a grayscale image after processing.

[0144] 7. Compare the iris features with the iris features of the registered users stored in the iris feature database, calculate the similarity, and then verify whether the target object is an abnormal object based on the similarity. For example, if the similarity exceeds the first threshold, the target object is determined to be a registered user of the current account, that is, the identity authentication of the target object is successful, and the target object is determined to be a normal object; if the similarity does not exceed the first threshold, the target object is determined to be a proxy player, and the target object is determined to be an abnormal object.

[0145] 404. Determine a recognition result of the target object according to the predicted probability value and the verification result.

[0146] After the server obtains the predicted probability value and the verification result, the recognition result of the target object is determined according to the two determination dimensions, that is, as long as there is a determination result in the two determination dimensions indicating that the target object is an abnormal object, the recognition result of the target object is determined to be that the target object is an abnormal object.

[0147] In this embodiment, after the server identifies the target object as an abnormal object, the server can perform corresponding operations on the target object. Specifically, the processing of the target object includes sending a warning prompt to the target object, forcibly intercepting the game operation of the target object, or forcibly exiting the game running by the target object.

[0148] The data processing method of the present application is described below with an overall flow chart. Figure 4d As shown:

[0149] The data processing system includes three modules, namely, eye behavior feature acquisition module, iris recognition module and eye behavior feature determination module. The specific process is as follows:

[0150] The eye behavior feature acquisition module acquires the user's eye data, and then determines the eye movement information and pupil zoom information (also known as eye movement monitoring); at the same time, the user's gaze point coordinates are determined based on the eye data (also known as line of sight direction analysis). Then the eye behavior feature acquisition module transmits the above information to the eye behavior feature determination module, and performs deep learning through the above data to obtain a determination model; and uses the determination model to determine whether the eye behavior features acquired in real time by the eye behavior feature acquisition module are abnormal, and then determines whether the user is an abnormal user. After acquiring the user's iris image, the iris recognition module preprocesses the iris image, and then performs feature extraction to obtain iris features; then identity authentication is performed based on the iris features and the registered iris in the iris feature library. When the identity authentication fails, the user is determined to be abnormal. When the user is determined to be an abnormal user in any of the above two methods, an alarm prompt is sent to the game service provider.

[0151] The data processing device in this application is described in detail below. Figure 5 , Figure 5 This is a schematic diagram of an embodiment of a data processing device in an embodiment of the present application. The data processing device 20 includes:

[0152] An acquisition module 201 is used to acquire eye behavior characteristics and iris characteristics of a target object;

[0153] The processing module 202 is used to call the judgment model to make a suspicious judgment on the eye behavior feature to obtain a predicted probability value, wherein the judgment model is obtained by deep learning based on the eye sample data and the corresponding annotation information; the iris feature is compared with the registered iris feature corresponding to the current account to obtain a verification result;

[0154] The recognition module 203 is used to determine the recognition result of the target object according to the predicted probability value and the verification result.

[0155] In the embodiment of the present application, a data processing device is provided. The above device is used to capture the eye behavior characteristics and iris characteristics of the object, and then the eye behavior characteristics and iris recognition are used as the judgment conditions of abnormal behavior, so that the eye monitoring and iris recognition technologies are combined, and the model obtained by deep learning is added to judge the eye behavior characteristics, so that the judgment of abnormal groups can be more intelligent, thereby improving the accuracy of identifying abnormal groups.

[0156] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0157] The acquisition module 201 is specifically used to acquire the corneal reflection point, pupil center point, eye rotation information and pupil zoom information of the target object;

[0158] Calculating the gaze coordinate point of the target object according to the eye corneal reflection point and the pupil center point;

[0159] The gaze coordinate point, the eyeball rotation information and the pupil zoom information are used as eye behavior features of the target object.

[0160] In an embodiment of the present application, a data processing device is provided. By using the above device, eye movement monitoring and sight line monitoring technology are combined to simultaneously obtain eye behavior characteristics, pupil zoom characteristics, and sight line change characteristics, thereby obtaining rich eye behavior characteristics and improving the accuracy of identifying abnormal groups.

[0161] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application, the acquisition module 201 is specifically used to acquire the iris image of the target object;

[0162] Performing image segmentation processing on the iris image to obtain an iris region in the iris image belonging to the target object;

[0163] Feature extraction is performed on the iris region to obtain a feature vector corresponding to the iris region, and the feature vector is used as the iris feature.

[0164] In an embodiment of the present application, a data processing device is provided. The above device is used to capture an eye image, segment the eye image, and finally extract features to obtain the iris feature, thereby finely processing the iris feature, removing the influencing factors in the image, increasing the accuracy of the iris feature, and thus improving the accuracy of identifying abnormal groups.

[0165] Optionally, in the above Figure 5On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0166] The acquisition module 201 is specifically used to perform image enhancement processing on the iris image to obtain an intermediate image, and the clarity of the intermediate image is higher than that of the iris image;

[0167] The intermediate image is subjected to image segmentation processing to obtain an iris region in the iris image.

[0168] In an embodiment of the present application, a data processing device is provided. By using the above device, the clarity of the iris image is further improved through image enhancement processing, thereby enriching the features of the iris, ensuring the accuracy of the iris features, and further improving the accuracy of identifying abnormal groups.

[0169] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0170] The acquisition module 201 is specifically used to perform image enhancement processing on the iris image to obtain an intermediate image, including:

[0171] Performing denoising on the iris image to obtain the intermediate image;

[0172] or,

[0173] Performing contrast enhancement processing on the iris image to obtain the intermediate image;

[0174] or,

[0175] The iris image is subjected to denoising and contrast enhancement processing to obtain the intermediate image.

[0176] In the embodiment of the present application, a data processing device is provided. By using the above device, a variety of image enhancement schemes are provided, thereby increasing the feasibility of the schemes. At the same time, the clarity of the iris image is further improved through image enhancement processing, thereby enriching the features of the iris, ensuring the accuracy of the iris features, and further improving the accuracy of identifying abnormal groups.

[0177] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application, the acquisition module 201 is specifically used to perform edge detection processing on the intermediate image to obtain the iris area in the iris image;

[0178] or,

[0179] Performing shape fitting processing on the intermediate image to obtain an iris region in the iris image;

[0180] or,

[0181] The intermediate image is subjected to edge detection and shape fitting processing to obtain the iris region in the iris image.

[0182] In an embodiment of the present application, a data processing device is provided. The device is used to segment eye images using a variety of image segmentation schemes, thereby increasing the feasibility of the schemes.

[0183] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application, the processing module 202 is specifically used to extract features of the iris region using a Gabor filter to obtain a feature vector corresponding to the iris region;

[0184] or,

[0185] A Laplacian of Gaussian filter is used to extract features from the iris region to obtain a feature vector corresponding to the iris region.

[0186] In the embodiment of the present application, a data processing device is provided. By using the above device, multiple feature extraction schemes are provided to increase the feasibility of the schemes.

[0187] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0188] The processing module 202 is used to determine the similarity between the iris feature and the registered iris feature;

[0189] When the similarity is greater than a first threshold, the verification result is used to indicate that the target object is a registered user of the current account;

[0190] When the similarity is less than or equal to the first threshold, the verification result is used to indicate that the target object is an abnormal object.

[0191] In an embodiment of the present application, a data processing device is provided. Using the above device, by comparing the collected iris features with the iris features of registered users pre-stored in the iris feature library, when the similarity exceeds a first threshold, the target object is determined to be the current registered user, and when the similarity is less than or equal to the first threshold, the target object is determined to be an abnormal object.

[0192] Optionally, in the above Figure 5 On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0193] The recognition result is used to determine that the target object is an abnormal object when the predicted probability value is greater than a second threshold and / or the verification result indicates that the target object is an abnormal object.

[0194] In an embodiment of the present application, a data processing device is provided. The above device is used to combine the two results to determine whether the target object is an abnormal group, which increases the conditions for cheating determination, so that abnormal determination can be performed in multiple dimensions, thereby improving the accuracy of identifying abnormal groups.

[0195] Optionally, in the above Figure 5 Based on the corresponding embodiments, Figure 5a As shown, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0196] The acquisition module 201 is used to acquire a training sample pair and an initial determination model, wherein the training sample pair includes the eye sample data and annotation information of the eye sample data, wherein the annotation information is used to indicate whether the object corresponding to the eye sample data is a normal object or an abnormal object;

[0197] The processing module 202 is used to call the initial determination model to process the eye movement sample data to obtain a predicted training probability value of the eye movement sample data;

[0198] Processing the predicted training probability value and the labeled information to obtain a loss value;

[0199] The device also includes a training module 204, which is used to train the initial determination model according to the loss value to obtain the determination model.

[0200] In the embodiment of the present application, a data processing device is provided. The above device is used to train the judgment model using eye behavior characteristics, and eye movement monitoring and sight line monitoring technology are combined to simultaneously obtain eye behavior characteristics, pupil zoom characteristics, and sight line change characteristics, thereby obtaining rich eye behavior characteristics, thereby improving the accuracy of identifying abnormal groups.

[0201] Optionally, in the above Figure 5a On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0202] The training module 204 is used to update and train the determination model according to the recognition result and the eye behavior characteristics.

[0203] In an embodiment of the present application, a data processing device is provided. By using the above device, the determination model is updated and trained according to the real-time recognition results and eye behavior characteristics, so that the determination model has a certain degree of self-adaptation, thereby improving the application scope of the determination model and the recognition accuracy of eye behavior characteristics.

[0204] Optionally, in the above Figure 5a On the basis of the corresponding embodiment, in another embodiment of the data processing device 20 provided in the embodiment of the present application,

[0205] The processing module 202 is used to trigger an alarm prompt when the recognition result indicates that the target object is an abnormal object.

[0206] In an embodiment of the present application, a data processing device is provided. By using the above device, when an abnormal group is identified, an alarm prompt is issued, so that the game service provider can handle the abnormal group in time, thereby ensuring the fairness of the game environment.

[0207] The data processing device provided in this application can be used in a server, see Figure 6 , Figure 6 : is a schematic diagram of a server structure provided in an embodiment of the present application. The server 300 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 322 (for example, one or more processors) and memory 332, and one or more storage media 330 (for example, one or more mass storage devices) storing application programs 342 or data 344. Among them, the memory 332 and the storage medium 330 can be short-term storage or permanent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 322 can be configured to communicate with the storage medium 330 to execute a series of instruction operations in the storage medium 330 on the server 300.

[0208] The server 300 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input and output interfaces 358, and / or one or more operating systems 341, such as Windows Server 2000. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM etc.

[0209] The steps performed by the server in the above embodiment can be based on the Figure 6 The server structure shown.

[0210] The data processing device provided in this application can be used in terminal equipment. Figure 7 For the sake of convenience, only the parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. In the embodiments of the present application, the terminal device is a smart phone as an example for explanation:

[0211] Figure 7 The block diagram shows a partial structure of a smart phone related to the terminal device provided in the embodiment of the present application. Figure 7 The smart phone includes: a radio frequency (RF) circuit 410, a memory 420, an input unit 430, a display unit 440, a sensor 450, an audio circuit 460, a wireless fidelity (WiFi) module 470, a processor 480, and a power supply 490. Those skilled in the art will appreciate that Figure 7 The structure of the smartphone shown in the figure does not constitute a limitation of the smartphone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0212] Combine the following Figure 7 A detailed introduction to the various components of a smartphone:

[0213] The RF circuit 410 can be used for receiving and sending signals during the process of sending and receiving information or making calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 480 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 410 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 410 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the global system of mobile communication (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short messaging service (SMS), etc.

[0214] The memory 420 can be used to store software programs and modules. The processor 480 executes various functional applications and data processing of the smartphone by running the software programs and modules stored in the memory 420. The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the smartphone (such as audio data, a phone book, etc.), etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0215] The input unit 430 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the smart phone. Specifically, the input unit 430 may include a touch panel 431 and other input devices 432. The touch panel 431, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 431 or near the touch panel 431 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 431 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 480, and can receive and execute commands sent by the processor 480. In addition, the touch panel 431 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 431, the input unit 430 may also include other input devices 432. Specifically, other input devices 432 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc.

[0216] The display unit 440 can be used to display information input by the user or information provided to the user and various menus of the smartphone. The display unit 440 may include a display panel 441. Optionally, the display panel 441 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 431 may cover the display panel 441. When the touch panel 431 detects a touch operation on or near it, it is transmitted to the processor 480 to determine the type of touch event. Subsequently, the processor 480 provides a corresponding visual output on the display panel 441 according to the type of touch event. Although in Figure 7 In the embodiment, the touch panel 431 and the display panel 441 are used as two independent components to implement the input and output functions of the smartphone, but in some embodiments, the touch panel 431 and the display panel 441 can be integrated to implement the input and output functions of the smartphone.

[0217] The smartphone may also include at least one sensor 450, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 441 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 441 and / or the backlight when the smartphone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the smartphone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in smartphones, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0218] The audio circuit 460, the speaker 461, and the microphone 462 can provide an audio interface between the user and the smartphone. The audio circuit 460 can transmit the received audio data to the speaker 461 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 462 converts the collected sound signal into an electrical signal, which is received by the audio circuit 460 and converted into audio data, and then the audio data is output to the processor 480 for processing, and then sent to another smartphone through the RF circuit 410, or the audio data is output to the memory 420 for further processing.

[0219] WiFi is a short-range wireless transmission technology. Smartphones can help users send and receive emails, browse web pages, and access streaming media through WiFi module 470, which provides users with wireless broadband Internet access. Figure 7 A WiFi module 470 is shown, but it is understandable that it is not an essential component of the smartphone and can be omitted as needed without changing the essence of the invention.

[0220] Processor 480 is the control center of the smartphone, which uses various interfaces and lines to connect various parts of the entire smartphone, and executes various functions of the smartphone and processes data by running or executing software programs and / or modules stored in memory 420, and calling data stored in memory 420, thereby monitoring the smartphone as a whole. Optionally, processor 480 may include one or more processing units; optionally, processor 480 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into processor 480.

[0221] The smart phone also includes a power source 490 (such as a battery) for supplying power to various components. Optionally, the power source can be logically connected to the processor 480 through a power management system, thereby managing functions such as charging, discharging, and power consumption management through the power management system.

[0222] Although not shown, the smartphone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0223] The steps performed by the terminal device in the above embodiment can be based on the Figure 7 The terminal device structure shown.

[0224] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the methods described in the aforementioned embodiments.

[0225] The present application also provides a computer program product including a program, which, when executed on a computer, enables the computer to execute the methods described in the aforementioned embodiments.

[0226] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0227] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0228] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0229] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0230] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0231] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data processing method, characterized in that: include: Obtain the target object's eye behavior characteristics and iris characteristics; Calling a judgment model to make a suspicious judgment on the eye behavior feature to obtain a predicted probability value, wherein the judgment model is obtained by deep learning based on the eye sample data and the corresponding annotation information; Comparing the iris feature with the registered iris feature corresponding to the current account to obtain a verification result; The recognition result of the target object is determined according to the predicted probability value and the verification result.

2. The method according to claim 1, characterized in that Obtaining the target object's eye behavior characteristics includes: Obtaining the target object's eye corneal reflection point, pupil center point, eye rotation information, and pupil zoom information; Calculating the gaze coordinate point of the target object according to the eye cornea reflection point and the pupil center point; The gaze coordinate point, the eyeball rotation information and the pupil zoom information are used as eye behavior features of the target object.

3. The method according to claim 1, characterized in that: Acquiring the iris feature of the target object includes: Acquire an iris image of the target object; Performing image segmentation processing on the iris image to obtain an iris region in the iris image belonging to the target object; Feature extraction is performed on the iris region to obtain a feature vector corresponding to the iris region, and the feature vector is used as the iris feature.

4. The method according to claim 3, characterized in that: Performing image segmentation processing on the iris image to obtain an iris region in the iris image includes: Performing image enhancement processing on the iris image to obtain an intermediate image, wherein the clarity of the intermediate image is higher than that of the iris image; Perform image segmentation processing on the intermediate image to obtain the iris area in the iris image.

5. The method according to claim 4, characterized in that Performing image enhancement processing on the iris image to obtain an intermediate image includes: Performing denoising processing on the iris image to obtain the intermediate image; or, Performing contrast enhancement processing on the iris image to obtain the intermediate image; or, The iris image is subjected to denoising and contrast enhancement processing to obtain the intermediate image.

6. The method according to claim 4, characterized in that Performing image segmentation processing on the intermediate image to obtain an iris region in the iris image includes: Performing edge detection processing on the intermediate image to obtain an iris region in the iris image; or, Performing shape fitting processing on the intermediate image to obtain an iris region in the iris image; or, The intermediate image is subjected to edge detection and shape fitting processing to obtain an iris region in the iris image.

7. The method according to claim 3, characterized in that The step of extracting features from the iris region to obtain a feature vector corresponding to the iris region includes: Performing feature extraction on the iris region using a Gabor filter to obtain a feature vector corresponding to the iris region; or, A Laplacian of Gaussian filter is used to extract features from the iris region to obtain a feature vector corresponding to the iris region.

8. The method according to any one of claims 1 to 7, characterized in that Comparing the iris feature with the registered iris feature corresponding to the current account to obtain a verification result includes: Determining the similarity between the iris feature and the registered iris feature; When the similarity is greater than a first threshold, the verification result is used to indicate that the target object is a registered user of the current account; When the similarity is less than or equal to the first threshold, the verification result is used to indicate that the target object is an abnormal object.

9. The method according to any one of claims 1 to 7, characterized in that Determining the recognition result of the target object according to the predicted probability value and the verification result includes: When the predicted probability value is greater than a second threshold and / or the verification result indicates that the target object is an abnormal object, it is determined that the target object is an abnormal object.

10. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Acquire a training sample pair and an initial determination model, wherein the training sample pair includes the eye sample data and annotation information of the eye sample data, wherein the annotation information is used to indicate whether an object corresponding to the eye sample data is a normal object or an abnormal object; Calling the initial determination model to process the eye movement sample data to obtain a predicted training probability value of the eye movement sample data; Processing the predicted training probability value and the labeled information to obtain a loss value; The initial determination model is trained according to the loss value to obtain the determination model.

11. The method according to any one of claims 1 to 7, characterized in that The method further comprises: The determination model is updated and trained according to the recognition result and the eye behavior characteristics.

12. The method according to any one of claims 1 to 7, characterized in that The method further comprises: When the recognition result indicates that the target object is an abnormal object, an alarm prompt is triggered.

13. A data processing device, characterized in that: include: An acquisition module, used to acquire eye behavior characteristics and iris characteristics of a target object; A processing module, configured to call a determination model to make a suspicious determination on the eye behavior feature to obtain a predicted probability value, wherein the determination model is obtained by deep learning based on the eye sample data and the corresponding annotation information; and compare the iris feature with the registered iris feature corresponding to the current account to obtain a verification result; An identification module is used to determine the identification result of the target object according to the predicted probability value and the verification result.

14. A computer device, characterized in that: include: Memory, processor, and bus system; Wherein, the memory is used to store programs; The processor is used to execute the program in the memory, and the processor is used to execute the method according to any one of claims 1 to 12 according to the instructions in the program code; The bus system is used to connect the memory and the processor so that the memory and the processor can communicate with each other.

15. A computer-readable storage medium comprising instructions, which, when executed on a computer, causes the computer to perform the method according to any one of claims 1 to 12.

Images