Information acquisition method and system

Abstract

The application provides an information acquisition method and system, which can be applied to the payment security field, and the method comprises the following steps: pre-training a convolutional neural network by using a first training sample to obtain an image recognition model; optimizing and training the image recognition model by using a second training sample to obtain a target image recognition model; performing face verification on received identity verification information uploaded by a user terminal and performing position verification on the identity verification information based on the target image recognition model; and in the case that the face verification and the position verification are both passed, sending data information corresponding to an information acquisition request sent by the user terminal to the user terminal. The system is used for executing the above method. Through the double identity verification of the face verification and the position verification, the application can realize the double security guarantee of the user identity and the user environment, and avoid the property loss of the user caused by the identity verification of some illegal user terminals based on the image processing means.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to an information acquisition method and system. Background Technology

[0002] Current facial recognition technology primarily relies on simply acquiring a user's facial features and then matching them with features in a feature database to achieve identity verification. This method can only determine the user's identity and cannot address the security of the user's surrounding environment. This allows unauthorized users to bypass identity verification through image processing, potentially leading to financial losses for the user. Therefore, eliminating security issues in the consumption or payment environment has become a pressing technical problem that needs to be solved. Summary of the Invention

[0003] The information acquisition method and system provided by this invention are used to solve the problems existing in the prior art. Through dual identity verification of face verification and location verification, dual security protection of user identity and user environment can be achieved, avoiding the loss of user property caused by some illegal user terminals based on image processing methods to verify user identity.

[0004] The present invention provides an information acquisition method, comprising:

[0005] The convolutional neural network is pre-trained using the first training samples to obtain an image recognition model;

[0006] The image recognition model is optimized and trained using a second training sample to obtain the target image recognition model;

[0007] The system performs face verification on the received identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model.

[0008] If both face verification and location verification are successful, the data information corresponding to the information acquisition request sent by the user terminal will be sent to the user terminal.

[0009] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0010] The second training sample is determined based on the target image obtained by overlaying a face image with an environmental image from the first training sample;

[0011] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0012] According to an information acquisition method provided by the present invention, the step of pre-training a convolutional neural network using a first training sample to obtain an image recognition model includes:

[0013] The first training sample is input into the convolutional neural network for pre-training, and the hyperparameters of the convolutional neural network are adjusted according to the comparison result between the second position information of each environmental image output by the convolutional neural network and the first position information.

[0014] The image recognition model is determined based on the adjusted convolutional neural network.

[0015] According to an information acquisition method provided by the present invention, the step of optimizing and training the image recognition model using a second training sample to obtain a target image recognition model includes:

[0016] The second training sample is input into the image recognition model for optimization training. Based on the comparison result between the third position information of the target image output by the image recognition model and the first position information, the image recognition model is optimized using the backpropagation algorithm and the stochastic gradient algorithm to obtain the target image recognition model.

[0017] According to an information acquisition method provided by the present invention, the location of the authentication information uploaded by the user terminal is determined in the following manner:

[0018] Upon receiving the information acquisition request sent by the user terminal, an authentication information collection message is sent to the user terminal so that the user terminal can collect the authentication information based on the received authentication information collection message.

[0019] According to an information acquisition method provided by the present invention, the step of performing face verification on the received identity verification information uploaded by the user terminal and performing location verification on the identity verification information based on the target image recognition model includes:

[0020] Extract the first facial features from the environmental image including the user's facial image;

[0021] The first facial feature and the second facial feature from the user's registration in the identity verification information are used to calculate the feature vector to obtain the distance between the first facial feature and the second facial feature;

[0022] Based on the distance, complete the facial verification of the identity verification information;

[0023] If the face verification is successful, the location of the identity verification information is verified based on the target image recognition model.

[0024] According to an information acquisition method provided by the present invention, the step of performing location verification on the authentication information based on the target image recognition model includes:

[0025] The environmental image, including the user's face image, is input into the target image recognition model. Based on the comparison result between the fourth location information output by the target image recognition model and the user's location information, the location verification of the identity verification information is completed.

[0026] The present invention also provides an information acquisition system, comprising: a first training module, a second training module, an identity verification module, and an information acquisition module;

[0027] The first training module is used to pre-train a convolutional neural network using the first training samples to obtain an image recognition model;

[0028] The second training module is used to optimize and train the image recognition model using the second training samples to obtain the target image recognition model;

[0029] The identity verification module is used to perform face verification on the identity verification information uploaded by the received user terminal and to perform location verification on the identity verification information based on the target image recognition model.

[0030] The information acquisition module is used to send the data information corresponding to the information acquisition request sent by the user terminal to the user terminal when both face verification and location verification are passed.

[0031] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0032] The second training sample is determined based on the target image obtained by overlaying a face image with an environmental image from the first training sample;

[0033] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0034] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the information acquisition method as described above.

[0035] The present invention also provides a processor-readable storage medium storing a computer program for causing the processor to execute, as described in any of the above-described information acquisition methods.

[0036] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the information acquisition method as described above.

[0037] The information acquisition method and system provided by this invention can achieve dual security protection for user identity and user environment through dual identity verification of face verification and location verification, thus preventing some illegal user terminals from causing financial losses to users by using image processing methods to verify user identity. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the information acquisition method provided by the present invention;

[0040] Figure 2 This is one of the structural schematic diagrams of the convolutional neural network provided by the present invention;

[0041] Figure 3 This is the second schematic diagram of the structure of the convolutional neural network provided by the present invention;

[0042] Figure 4 This is a schematic diagram of the Inception module in the convolutional neural network provided by the present invention;

[0043] Figure 5 This is a schematic diagram of the information acquisition system provided by the present invention;

[0044] Figure 6 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0046] When users first access an internet application, they need to fill in personal information and bind their mobile phone number (by sending an SMS verification code) to register an account. During normal use, if sensitive operations such as payments or password retrieval are involved, existing internet applications typically use SMS verification codes and facial recognition to identify the user and confirm that the operation is performed by the account holder. This user authentication method often fails to ensure the security of the user's payment environment. Based on this, the present invention provides an information acquisition method that incorporates multiple verification matching of environmental information, location information, and facial expressions during user identity verification, thereby achieving identity verification. The specific implementation is as follows:

[0047] Figure 1 This is a flowchart illustrating the information acquisition method provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0048] Step 100: Pre-train the convolutional neural network using the first training samples to obtain an image recognition model;

[0049] Step 200: Optimize and train the image recognition model using the second training sample to obtain the target image recognition model;

[0050] Step 300: Perform face verification and location verification on the identity verification information uploaded by the received user terminal based on the target image recognition model;

[0051] Step 400: If both face verification and location verification are successful, send the data information corresponding to the information retrieval request sent by the user terminal to the user terminal.

[0052] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0053] The second training sample is determined by superimposing the face image with the environmental image in the first training sample into a target image;

[0054] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0055] It should be noted that the above method can be implemented by computer equipment.

[0056] Optionally, the present invention pre-labels each environmental image with location information corresponding to each environmental image in the majority of collected environmental images as location labels to obtain a first training sample, and inputs the first training sample into a convolutional neural network for training and learning to obtain an image recognition model.

[0057] Environmental images refer to pictures that include objects in natural scenes, specifically including pictures of buildings, street scenes, interior views of buildings, etc. When acquiring environmental images, the corresponding acquisition location information (i.e., first location information) is also acquired. The environmental images are then labeled using this first location information to obtain the first training sample; for example, the label could be "**city**, **street**, **road**".

[0058] Based on the image recognition model, the relationship between environmental images and location information is explored; then, the face image and the environmental image in the first training sample are randomly superimposed and combined and input into the image recognition model to obtain the location information corresponding to the face image and the environmental image. The location information is compared with the location label corresponding to the environmental image to optimize the image recognition model and obtain the target image recognition model.

[0059] The random overlay of the face image and the environment image in the second training sample refers to the free combination of the face image and the environment image, with the environment image as the background image and the face image as the foreground image, and then layering them.

[0060] During identity verification, the system performs face recognition on the identity verification information uploaded by the user terminal (including environmental images captured in real time by the user, including the user's face image, and the user's location information). Based on the face recognition results, it completes the face verification of the identity verification information uploaded by the user terminal and performs location verification on the identity verification information based on the trained target image recognition model.

[0061] During user authentication, the system collects environmental images including the user's face image and user location information. The environmental image including the user's face image is input into the target image recognition model to obtain predicted location information. Then, the predicted location information is matched with the collected user location information to complete the user's location verification. Combined with the face verification result, the system ultimately achieves both location verification and face verification for the user.

[0062] For example, facial features of an environmental image including the user's face can be matched with the user's facial features in a pre-existing feature library to complete the user's facial verification.

[0063] If both face verification and location verification are successful, the data information corresponding to the information retrieval request sent by the user terminal will be sent back to the user terminal.

[0064] The information acquisition method provided by this invention can achieve dual security protection for user identity and user environment through dual identity verification of face verification and location verification, thus preventing some illegal user terminals from causing financial losses to users by using image processing methods to bypass user identity verification.

[0065] Furthermore, in one embodiment, step 100 may specifically include:

[0066] Step 1001: Input the first training sample into the convolutional neural network for pre-training, and adjust the hyperparameters of the convolutional neural network according to the comparison results of the second position information and the first position information of each environmental image output by the convolutional neural network.

[0067] Step 1002: Determine the image recognition model based on the adjusted convolutional neural network.

[0068] Optionally, in step 1001, the obtained first training sample can be input into, for example... Figure 2 The convolutional neural network shown is pre-trained. The convolutional neural network has a multi-layered network structure and is also a multi-layered non-fully connected neural network.

[0069] Functionally, convolutional and pooling layers are mainly used for image feature extraction, mapping image features from low to high dimensions, while fully connected layers transform high-dimensional features into image categories.

[0070] Optionally, this invention uses Recog-Net, a deep convolutional network based on GoogleNet, as the convolutional neural network, with the following structure: Figure 3 , Figure 4 As shown:

[0071] in, Figure 3 This describes the overall structure of a convolutional neural network. Figure 4 for Figure 3 A structural diagram of the Inception module. Figure 3 In this process, the input to the convolutional neural network is an RGB three-channel environmental image of size 229*229*3. Then, three stages of convolution operations C1, C2, and C3 are performed, followed by p1 pooling dimensionality reduction and convolutions C4 and C5 to extract more abstract high-level features.

[0072] like Figure 4 As shown, the core of the convolutional neural network is the Inception module, which consists of three convolutional kernels of different scales: 1x1, 3x3, and 5x5. These are stacked together with pooling operations (3x3 kernels) (the convolutional and pooling layers have the same size, and the channels are added together). This increases both the width of the convolutional neural network and its scale fit. A ReLU operation is performed after each convolutional layer. The ReLU function, as a non-linear activation function, can effectively fit the training state of the convolutional neural network.

[0073] During the pre-training phase, the prediction results of the convolutional neural network are compared with the first position information labeled on the corresponding first training sample. Then, the convolutional neural network is optimized based on the comparison results. Specifically, the hyperparameters of the convolutional neural network can be optimized and adjusted to determine the adjusted hyperparameters. Based on the adjusted convolutional neural network, an image recognition model is obtained.

[0074] The information acquisition method provided by this invention uses a first training sample to train a convolutional neural network to obtain an image recognition model, which lays the foundation for subsequent acquisition of a target recognition model based on the image recognition network and ultimately realizes user location verification.

[0075] Furthermore, in one embodiment, step 200 may specifically include:

[0076] Step 2001: Input the second training sample into the image recognition model for optimization training, and optimize the image recognition model by using the backpropagation algorithm and the stochastic gradient algorithm based on the comparison results between the third position information and the first position information of the target image output by the image recognition model, so as to obtain the target image recognition model.

[0077] Optionally, the second training sample is input into the image recognition model pre-trained in step 100. The position data predicted by the image recognition model (i.e., the third position information) is compared with the position information of the environment image labeled in the second training sample (which is consistent with the first position information). Based on the comparison result, the image recognition model is optimized by using a continuous backpropagation algorithm combined with a stochastic gradient descent algorithm with dynamically changing learning rate to obtain the optimized image recognition model. The optimized image recognition model is then used as the target image recognition model.

[0078] For example, the location recognition of environmental images in this invention can be for the location recognition of building images. In order to make the trained target image recognition model more accurate, this invention uses the original building image as the first training sample for pre-training of a convolutional neural network, so that the trained image recognition model can accurately determine the location of the building. Then, the face image and the building image are randomly superimposed, and the resulting randomly superimposed image is used as the second training sample to perform secondary optimization training on the pre-trained image recognition model. This allows the target image recognition model obtained after two training sessions to accurately predict the location of building images, including face images, based on the memory of the pre-trained image recognition model.

[0079] The information acquisition method provided by this invention uses a second training sample to train an image recognition model, which lays the foundation for subsequent determination of the target recognition model based on the trained image recognition network and ultimately realizes user location verification.

[0080] Furthermore, in one embodiment, the location of the authentication information uploaded by the user terminal in step 300 is determined in the following way:

[0081] Upon receiving an information retrieval request from a user terminal, the system sends authentication information collection information to the user terminal, enabling the user terminal to collect authentication information based on the authentication information.

[0082] Optionally, in many internet applications, such as WeChat, Alipay, Meituan, and Didi, and especially in mobile 5G messaging functions, user authentication is involved in implementing 5G messaging-related application functions. Currently, authentication is mainly achieved through facial recognition, fingerprint recognition, and other methods.

[0083] This invention proposes a novel authentication method that combines location-based authentication with environmental images. When using internet applications, users retrieve target page information, such as personal center pages or password payment pages, from the server by sending information retrieval requests. These requests include the address data of the requested information and the user's identity information (such as user terminal identifier, user account, or phone number).

[0084] Based on the user identity information included in the information acquisition request, the server sends authentication information collection information to the user terminal.

[0085] After receiving the authentication information collection information, the user terminal uses the collection device to capture an environmental image including the user's face and the user's location information, which is then uploaded to the server as authentication information. The server receives the authentication information and obtains the environmental image; at the same time, the authentication information includes the user's identity information, such as the user's mobile phone number.

[0086] The data acquisition device can be specifically designed to use a built-in camera to capture environmental images, including the user's facial image, and the user's location information. Alternatively, it can use an external camera connected to the user terminal to capture these environmental images and location information. For example, the user terminal can connect to the image acquisition device via a cable or network. The image acquisition device uses its camera to capture environmental images, including the user's facial image, and the user's location information, and then transmits these images and information to the user terminal. The camera can be a monocular camera, a binocular camera, a depth camera, a 3D (3D) camera, etc. The user terminal can capture images of live individuals in a real-world scene, or it can capture existing images containing faces in a real-world scene, such as scanned copies of ID cards.

[0087] The user terminal can be, but is not limited to, various smartphones, tablets, laptops, desktop computers, portable wearable devices, smart speakers, etc. The server can specifically be a server, which can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0088] The information acquisition method provided by this invention improves the security of verification by using environmental images including the user's face image and the user's location information captured in real time in the identity verification information uploaded by the user terminal.

[0089] Furthermore, in one embodiment, step 400 may specifically include:

[0090] Step 4001: Extract the first facial features from the environmental image including the user's facial image;

[0091] Step 4002: Calculate the feature vectors of the first face feature and the second face feature from the user registration information in the identity verification information to obtain the distance between the first face feature and the second face feature;

[0092] Step 4003: Based on the distance, complete the facial verification of the identity information;

[0093] Step 4004: If the face verification is successful, perform location verification on the identity verification information based on the target image recognition model.

[0094] Optionally, based on the environmental image including the user's face image in the authentication information uploaded by the user terminal, the server extracts the facial features, i.e., the first facial features, from the environmental image through the image processing module.

[0095] By using the user's identity information in the authentication information, the facial features obtained during user registration are retrieved from the facial feature database, i.e., the second facial features.

[0096] Facial features are the inherent physiological characteristics of the human face, such as the shape of the iris, the positional relationship between facial organs (eyes, nose, mouth, ears, etc.), the structure of facial organs (shape, size, etc.), skin texture, etc.

[0097] The first facial feature extracted from the environmental image including the user's face image in the authentication information uploaded by the user terminal is compared with the second facial feature obtained from the facial feature database to calculate the feature vector. For example, the distance between the first facial feature and the second facial feature can be obtained through Mahalanobis distance. This completes the facial verification of the environmental image including the user's face image in the authentication information. If the calculated distance is zero, the facial verification is successful.

[0098] If facial recognition passes, the location information of the user in the identity verification information is verified based on the target image recognition model.

[0099] The information acquisition method provided by this invention predicts the location information corresponding to the environmental image, compares the predicted location information with the location information collected by the user, realizes environmental image verification based on location information, and improves the security of verification.

[0100] Furthermore, in one embodiment, step 4004 may specifically include:

[0101] Step 40041: Input the environmental image including the user's face image into the target image recognition model, and complete the location verification of the identity verification information based on the comparison result between the fourth location information output by the target image recognition model and the user's location information.

[0102] Optionally, an environmental image including the user's face image is input into the target image recognition model, and the location information (i.e., fourth location information) of the environmental image including the face features output by the target image recognition model is compared to complete the location verification of the user's location information.

[0103] For example, location comparison can specifically involve collecting the user's location information G. j With the predicted fourth position information G i Compare the collected user location information G j Information G located at the fourth predicted position i Within the planned geographical area, location verification can be performed. In addition to simple geographical area planning, other technologies are used to ensure the authenticity of the user's location information during the collection process.

[0104] For example, by comparing the real-time location of users on map software, WeChat, etc., with the location information of users in the identity verification information uploaded by user terminals, the authenticity of the collected user location information can be guaranteed.

[0105] For example, blockchain technology can be introduced, with the server acting as a blockchain node in the blockchain network. This involves storing environmental images, including real-time user facial images, and user location information on the blockchain, and retrieving the user's location information from the blockchain's data blocks to ensure consistency between the user's location information uploaded to the user's terminal and the information stored in the blockchain. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0106]

[0107] Where Q=1 indicates that the location verification is passed, and Q=-1 indicates that the location verification is not passed.

[0108] Upon successful face verification and location verification, a message is sent to retrieve the corresponding data information, specifically:

[0109] If facial recognition passes but location verification fails, identity verification will not be successful.

[0110] If face verification fails, location verification will not be performed, which can save verification processing time.

[0111] Once face verification and location verification are successful, the system will authenticate the user and send the received information from the user terminal to obtain the corresponding data information.

[0112] In actual user authentication, the location information of the user in the authentication information uploaded by the user terminal can be verified first. If the location verification fails, face verification will not be performed to save verification processing time.

[0113] The information acquisition method provided by this invention can achieve dual security protection for user identity and user environment through dual identity verification of face verification and location verification. It can ensure that users can perform payment and other operations in a safe environment, and prevent some illegal user terminals from causing financial losses to users by using image processing methods to bypass user identity verification.

[0114] The information acquisition system provided by the present invention is described below. The information acquisition system described below and the information acquisition method described above can be referred to in correspondence.

[0115] Figure 5This is a schematic diagram of the information acquisition system provided by the present invention, such as... Figure 5 As shown, it includes:

[0116] The first training module 510, the second training module 511, the identity verification module 512, and the information acquisition module 513;

[0117] The first training module 510 is used to pre-train the convolutional neural network using the first training samples to obtain an image recognition model.

[0118] The second training module 511 is used to optimize and train the image recognition model using the second training samples in order to obtain the target image recognition model.

[0119] The identity verification module 512 is used to perform face verification on the identity verification information uploaded by the user terminal and to perform location verification on the identity verification information based on the target image recognition model.

[0120] The information acquisition module 513 is used to send the data information corresponding to the information acquisition request sent by the user terminal to the user terminal when both face verification and location verification are passed.

[0121] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0122] The second training sample is determined by superimposing the face image with the environmental image in the first training sample into a target image;

[0123] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0124] The information acquisition system provided by this invention can achieve dual security protection for user identity and user environment through dual identity verification of face and location, thus preventing some illegal user terminals from causing financial losses to users by using image processing methods to bypass user identity verification.

[0125] Furthermore, in one embodiment, the first training module 510 may also be specifically used for:

[0126] The first training sample is input into the convolutional neural network for pre-training, and the hyperparameters of the convolutional neural network are adjusted according to the comparison results of the second position information and the first position information of each environmental image output by the convolutional neural network.

[0127] Based on the adjusted convolutional neural network, the image recognition model is determined.

[0128] The information acquisition system provided by this invention uses a first training sample to train a convolutional neural network to obtain an image recognition model, which lays the foundation for subsequent acquisition of a target recognition model based on the image recognition network and ultimately realizes user location verification.

[0129] Furthermore, in one embodiment, the second training module 511 may also be specifically used for:

[0130] The second training sample is input into the image recognition model for optimization training. Based on the comparison between the third position information and the first position information of the target image output by the image recognition model, the backpropagation algorithm and the stochastic gradient algorithm are used to optimize the image recognition model to obtain the target image recognition model.

[0131] The information acquisition system provided by this invention uses a second training sample to train an image recognition model, laying the foundation for subsequent determination of a target recognition model based on the trained image recognition network and ultimately realizing user location verification.

[0132] Furthermore, in one embodiment, the authentication module 512 may also be specifically used for:

[0133] Upon receiving an information retrieval request from a user terminal, the system sends authentication information collection information to the user terminal, enabling the user terminal to collect authentication information based on the authentication information collection information.

[0134] The information acquisition system provided by this invention improves the security of verification by using environmental images including the user's face image and the user's location information captured in real time in the identity verification information uploaded by the user terminal to achieve dual identity verification of the user's face and location.

[0135] Furthermore, in one embodiment, the authentication module 512 may also be specifically used for:

[0136] Extract the first facial features from the environmental image, including the user's facial image;

[0137] The first facial feature and the second facial feature from the user's registration information are used to calculate the feature vector to obtain the distance between the first facial feature and the second facial feature.

[0138] Based on the distance, complete the facial verification of identity information;

[0139] If facial verification is successful, location verification is performed on the identity verification information based on the target image recognition model.

[0140] The information acquisition system provided by this invention predicts the location information corresponding to the environmental image, compares the predicted location information with the location information collected by the user, realizes environmental image verification based on location information, and improves the security of verification.

[0141] Furthermore, in one embodiment, the authentication module 512 may also be specifically used for:

[0142] The environmental image, including the user's face image, is input into the target image recognition model. Based on the comparison between the fourth location information output by the target image recognition model and the user's location information, the location verification of the authentication information is completed.

[0143] The information acquisition system provided by this invention can achieve dual security protection for user identity and user environment through dual identity verification of face verification and location verification. It can ensure that users can perform payment and other operations in a safe environment, and prevent some illegal user terminals from causing financial losses to users by using image processing methods to bypass user identity verification.

[0144] Figure 6 This is a schematic diagram of the physical structure of an electronic device provided by the present invention, such as... Figure 6 As shown, the electronic device may include a processor 610, a communication interface 611, a memory 612, and a bus 613. The processor 610, communication interface 611, and memory 612 communicate with each other via the bus 613. The processor 610 can call logical instructions from the memory 612 to execute the following methods:

[0145] The convolutional neural network is pre-trained using the first training samples to obtain an image recognition model;

[0146] The image recognition model is optimized and trained using a second training sample to obtain the target image recognition model;

[0147] The system performs facial verification on the identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model.

[0148] If both face verification and location verification are successful, the data information corresponding to the information retrieval request sent by the user terminal will be sent back to the user terminal.

[0149] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0150] The second training sample is determined by superimposing the face image with the environmental image in the first training sample into a target image;

[0151] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0152] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer power supply (which may be a personal computer, server, or network power supply, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0153] Furthermore, this invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the information acquisition methods provided in the above-described method embodiments, such as including:

[0154] The convolutional neural network is pre-trained using the first training samples to obtain an image recognition model;

[0155] The image recognition model is optimized and trained using a second training sample to obtain the target image recognition model;

[0156] The system performs facial verification on the identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model.

[0157] If both face verification and location verification are successful, the data information corresponding to the information retrieval request sent by the user terminal will be sent back to the user terminal.

[0158] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0159] The second training sample is determined by superimposing the face image with the environmental image in the first training sample into a target image;

[0160] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0161] On the other hand, the present invention also provides a processor-readable storage medium storing a computer program for causing the processor to execute the methods provided in the above embodiments, such as including...

[0162] The convolutional neural network is pre-trained using the first training samples to obtain an image recognition model;

[0163] The image recognition model is optimized and trained using a second training sample to obtain the target image recognition model;

[0164] The system performs facial verification on the identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model.

[0165] If both face verification and location verification are successful, the data information corresponding to the information retrieval request sent by the user terminal will be sent back to the user terminal.

[0166] The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images.

[0167] The second training sample is determined by superimposing the face image with the environmental image in the first training sample into a target image;

[0168] The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information.

[0169] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0170] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer power supply (which may be a personal computer, server, or network power supply, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An information acquisition method, characterized in that, include: The convolutional neural network is pre-trained using the first training samples to obtain an image recognition model; The image recognition model is optimized and trained using a second training sample to obtain the target image recognition model; The system performs face verification on the received identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model. If both face verification and location verification are successful, the data information corresponding to the information acquisition request sent by the user terminal will be sent to the user terminal. The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images. The second training sample is determined based on the target image obtained by randomly superimposing the face image and the environment image in the first training sample. Random superposition involves freely combining the face image and the environment image, using the environment image as the background image and the face image as the foreground image for layer superposition. The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information; The step of performing face verification on the received identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model includes: Extract the first facial features from the environmental image including the user's facial image; The first facial feature and the second facial feature from the user's registration in the identity verification information are used to calculate the feature vector, and the distance between the first facial feature and the second facial feature is obtained. Based on the distance, complete the facial verification of the identity verification information; If facial verification is successful, location verification is performed on the identity verification information based on the target image recognition model; The location verification of the authentication information based on the target image recognition model includes: The environmental image, including the user's face image, is input into the target image recognition model. Based on the comparison result between the fourth location information output by the target image recognition model and the user's location information, the location verification of the identity verification information is completed.

2. The information acquisition method according to claim 1, characterized in that, The step of pre-training the convolutional neural network using the first training samples to obtain an image recognition model includes: The first training sample is input into the convolutional neural network for pre-training, and the hyperparameters of the convolutional neural network are adjusted according to the comparison result between the second position information of each environmental image output by the convolutional neural network and the first position information. The image recognition model is determined based on the adjusted convolutional neural network.

3. The information acquisition method according to claim 1, characterized in that, The step of optimizing and training the image recognition model using the second training samples to obtain the target image recognition model includes: The second training sample is input into the image recognition model for optimization training. Based on the comparison result between the third position information of the target image output by the image recognition model and the first position information, the image recognition model is optimized using the backpropagation algorithm and the stochastic gradient algorithm to obtain the target image recognition model.

4. The information acquisition method according to claim 1, characterized in that, The location of the authentication information uploaded by the user terminal is determined in the following way: Upon receiving the information acquisition request sent by the user terminal, an authentication information collection message is sent to the user terminal so that the user terminal can collect the authentication information based on the received authentication information collection message.

5. An information acquisition system, characterized in that, include: The system comprises a first training module, a second training module, an identity verification module, and an information acquisition module. The first training module is used to pre-train a convolutional neural network using the first training samples to obtain an image recognition model; The second training module is used to optimize and train the image recognition model using the second training samples to obtain the target image recognition model; The identity verification module is used to perform face verification on the identity verification information uploaded by the received user terminal and to perform location verification on the identity verification information based on the target image recognition model. The information acquisition module is used to send the data information corresponding to the information acquisition request sent by the user terminal to the user terminal when both face verification and location verification are passed. The first training sample is obtained by annotating each environmental image based on the first location information corresponding to each environmental image in the majority of acquired environmental images. The second training sample is determined based on the target image obtained by randomly superimposing the face image and the environment image in the first training sample. Random superposition involves freely combining the face image and the environment image, using the environment image as the background image and the face image as the foreground image for layer superposition. The authentication information includes environmental images captured in real time by the user, including the user's facial image, and the user's location information; The step of performing face verification on the received identity verification information uploaded by the user terminal and location verification on the identity verification information based on the target image recognition model includes: Extract the first facial features from the environmental image including the user's facial image; The first facial feature and the second facial feature from the user's registration in the identity verification information are used to calculate the feature vector, and the distance between the first facial feature and the second facial feature is obtained. Based on the distance, complete the facial verification of the identity verification information; If facial verification is successful, location verification is performed on the identity verification information based on the target image recognition model; The location verification of the authentication information based on the target image recognition model includes: The environmental image, including the user's face image, is input into the target image recognition model. Based on the comparison result between the fourth location information output by the target image recognition model and the user's location information, the location verification of the identity verification information is completed.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the information acquisition method according to any one of claims 1 to 4.

7. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program that causes the processor to perform the information acquisition method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the information acquisition method as described in any one of claims 1 to 4.

Images