732 results about "Fingerprint recognition" patented technology

A modular system designed for privacy-preserving content recognition and supplemental content delivery across web and mobile environments. The system employs lightweight character sampling and vision-based recognition to generate unique content fingerprints without storing or replicating original data. It features a hybrid processing architecture, using local computing resources for intensive tasks while optimizing performance on resource-constrained devices. Core functionalities include multi-method content fingerprinting, real-time monitoring with adaptive sampling, and secure supplemental content association. Operating entirely on the client-side, it complies with website terms of service and privacy regulations. Advanced features include AI-driven content recognition, blockchain-based verification, and granular content targeting through resizable selection interfaces. This technology enables seamless delivery of supplemental content while preserving privacy, reducing resource usage, and ensuring scalability across browsers, mobile applications, and edge devices. It is particularly applicable in industries such as education, retail, and secure data sharing.

The invention designs a cross-Tor version domain small sample website fingerprint identification method based on comparative learning. The method comprises three parts of a pre-training strategy based on comparative learning, a fine tuning strategy based on double-branch confidence alignment and a flow classification strategy driven by a prototype. The method comprises the following steps: firstly, constructing a discriminative representation space through a trunk convolution feature extractor and a traffic attention module based on a pre-training strategy of comparative learning, and introducing supervised comparative learning to obtain feature representation with a cross-domain migration capability; secondly, a double-branch confidence alignment fine tuning strategy is adopted, the stability of a model structure is kept in combination with a partial freezing mechanism, and rapid adaptation to a target domain is achieved through joint optimization of cross entropy loss and weighted comparison loss; and finally, introducing a prototype-driven classification strategy, and on the basis of a semantic structure formed in a fine tuning stage, realizing accurate identification of Tor traffic in closed world and open world scenes by using a category prototype, so that the cross-domain generalization ability of small sample website fingerprint identification is remarkably improved.

The invention relates to the technical field of dynamic modeling and digital twinning, and discloses a digital twinning dynamic modeling method for new material research and development, which comprises the following steps: constructing a low-order linear reference model, calculating a residual signal flow, and extracting residual non-statistical topological characteristics by using a sliding window to retrieve a system matrix correction increment; constructing a parallel shadow verification model to execute virtual deduction, and screening and executing parameter hopping according to a convergence divergence ratio; according to the method, through a closed-loop mechanism of residual form fingerprint identification and shadow deduction verification, the problem of capturing discontinuous physical phase change under low computing power is solved, and real-time high-fidelity synchronization of the model on complex microscopic evolution is realized while environmental noise interference is suppressed.

The systems and methods disclosed herein orchestrate task execution among autonomous (or semi-autonomous) AI agentic models (“agents”) responsive to a received query by using a hierarchical semantic fingerprinting framework to generate semantic-aware fingerprints for the query and agents. Queries and descriptions of agent capabilities are processed by a series of hierarchical levels using locality-sensitive hash (LSH) functions, where subsequent layers encode more complex semantic information and generate longer hash values. The hash values are aggregated into a semantic fingerprint. A bloom filter cascade uses a series of increasingly accurate hierarchical bloom filters to reject agent fingerprints that differ from the query fingerprint. The remaining agent fingerprints are compared bitwise to the query fingerprint, and those closest to the query fingerprint are selected to generate a routing path for the query. Responses from the selected agents are aggregated into an output that is responsive to the input.

The invention relates to the field of network security and the deep learning field, in particular to a satellite internet-oriented Tor website fingerprint identification method, which is implemented by constructing a self-supervised contrast learning framework and is implemented by generating a multi-view sample; extracting a feature matrix of the time sequence granularity; generating a synthesized negative sample based on linear insertion, and constructing a contrast with the positive sample; and track representation is extracted, and joint optimization is carried out in combination with cross entropy loss and mask reconstruction loss. Compared with a traditional website fingerprint identification method, the robustness of the model to satellite inherent noise caused by the Doppler effect can be enhanced. According to the method, multi-scale semantic features are provided for the weak enhancement view and the strong enhancement view, the inter-class distinction degree is improved by synthesizing negative samples, and the misjudgment rate is reduced; the joint loss optimization framework enables the model to give consideration to global statistical characteristics and local burst characteristics, and under the conditions of strong dynamic topology and limited labeling of satellite internet constellations, the accuracy and adaptability of website fingerprint recognition are remarkably improved.

The invention provides a fingerprint signal processing method and device and electronic equipment, and can be applied to the technical field of fingerprint identification. Based on the method, before specific implementation, fingerprint pixel units in a fingerprint pixel unit array circuit can be connected with a preset gain amplifier with adjustable gain, and an improved fingerprint pixel unit array circuit is obtained. In specific implementation, when a fingerprint related signal is received, a matched target convolution kernel is determined in the fingerprint pixel unit array circuit; wherein the range of the target convolution kernel comprises a plurality of fingerprint pixel units; and traversing the fingerprint pixel unit array circuit by using a target convolution kernel, and processing the fingerprint related signal to obtain a target fingerprint signal. Therefore, the fingerprint pixel units in the fingerprint pixel unit array circuit can be fully utilized, the received fingerprint related signals are processed by constructing and using the corresponding target convolution kernels, the signal-to-noise ratio of the signals is effectively improved, and target fingerprint signals with high quality are obtained.

The invention discloses a robust radio frequency fingerprint identification method based on Barlow Twins domain adaptation. Aiming at the problems of training and deployment environment distribution offset and cross-domain identification performance reduction caused by wireless channel multipath and time-varying characteristics in the prior art, the invention provides a domain adaptation framework combined with feature decoupling. The method comprises the following steps: firstly, converting a received time domain signal into a short-time Fourier transform spectrogram to reserve a time-frequency structure; then, a double-end convolutional encoder is constructed, bottom layer features are extracted through a shared backbone network, and device fingerprints and channel features are obtained in an identity branch and a channel branch respectively; in order to realize thorough decoupling of the two types of features, Barlow Twins-based independence regularization is introduced, and the identity features and the channel features are statistically orthogonal by minimizing a cross-correlation matrix of the identity features and the channel features, so that purer fingerprint features are obtained, channel interference is effectively eliminated, and generalization and recognition precision of the model under an unknown channel are remarkably improved.

The invention discloses an unmanned aerial vehicle radio frequency fingerprint identification method and device, a medium and equipment, and relates to the technical field of computers. According to a time-frequency graph corresponding to a radio frequency signal, time domain convolution is carried out by sliding along a time axis of the time-frequency graph, time domain features of the time-frequency graph are extracted, frequency domain convolution is carried out by sliding along a frequency axis of the time-frequency graph, frequency domain features of the time-frequency graph are extracted, and heterogeneous combined convolution kernels with different sizes are adopted in the time domain convolution and the frequency domain convolution, so that the time-frequency graph is more accurate. Therefore, time-frequency anisotropic convolution is realized, and short-time dynamic evolution and local energy distribution characteristics are respectively captured. According to the method, the uniform operation defect of traditional isotropic convolution is avoided, parameter redundancy is reduced and feature discrimination is enhanced through physically interpretable dimension decoupling, and the accuracy of radio frequency fingerprint identification of the unmanned aerial vehicle is improved.

The invention discloses a multi-label website fingerprint identification method and system based on attribution analysis, and the method comprises the steps: firstly carrying out the model attribution analysis of a training sample, and constructing an average discrimination template of each website category; high contribution areas of all categories are extracted according to the average discrimination template, and a structured mask template used for guiding identification is formed; in the identification stage, sliding window matching is carried out on input hybrid network traffic, the position of a potential pseudo sub-stream is judged according to the similarity between a mask template and a window sub-sequence, and single-label identification is carried out on the extracted pseudo sub-stream, so that effective analysis of multi-label traffic is realized. The method has the advantages of being high in structure perception, high in template generalization and good in mixed flow adaptability, the website recognition capacity in a complex network environment can be remarkably improved, and the method is suitable for scenes such as encrypted communication monitoring and anonymous channel flow analysis.

The invention discloses a honeypot automatic coping strategy generation method based on a large model. The method comprises the steps of S1, performing semantic analysis on dynamic attack behaviors; s2, performing context-aware threat reasoning; s3, adaptive strategy generation and semantic verification are carried out; s4, strategy executable compiling is carried out; s5, enhancing the efficiency of the closed-loop strategy; according to the method, the authority / service logic contradiction is thoroughly eliminated through a semantic consistency verification mechanism, so that the false alarm rate of the honeypot in the APT attack is reduced; an anti-recognition perturbation code injected by the low-entropy strategy compiling technology breaks through a traditional honeypot periodic response mode, and the fingerprint recognition success rate of an attacker is reduced; a resource penalty function of the Pareto optimal strategy sequence enables a trapping intensity mean value under limited resources to be improved; a double-channel updating mechanism promotes coevolution of a knowledge base and a constraint set, and the response generation speed for an unknown attack mode is shortened.

The invention discloses a multi-interface fingerprint identification card type USB flash disk, which belongs to the technical field of USB flash disks, and comprises a hardware core module, a software interaction module and a software-hardware combination module, the hardware core module is a physical basis of the USB flash disk, and is responsible for interface adaptation, fingerprint acquisition, data storage and state indication; the hardware core module comprises a multi-interface protocol module, a dual-master control cooperation module, a multi-specification plug-in card adaptation module and a fingerprint identification module; and the software interaction module is used for realizing fingerprint management, authority configuration and log recording functions through a four-layer architecture. In the use process, the plug-in type USB flash disk with the multi-interface fingerprint identification function is compatible with Lightning, TYPE-C and USB-A interfaces, adapts to multiple devices such as a computer, a mobile phone, a tablet computer and an industrial controller, does not need an additional adapter, is plug-and-play, improves the convenience of a use scene, is matched with a high-speed protocol of USB3.2 and above, gives consideration to the transmission efficiency and the device compatibility, has multiple permissions, and is convenient to use. And efficient protection of the information is realized through three-level permission classification.

The invention relates to a radio frequency fingerprint identification method based on knowledge and data hybrid driving, which comprises the following steps of: on one hand, learning channel characteristics of an input signal by using a SupportNet model, and carrying out equalization processing on the signal so as to remove the influence of Doppler frequency offset on the signal and obtain a signal irrelevant to a channel; on the other hand, radio frequency fingerprint features are extracted in parallel through the knowledge graph and the one-dimensional convolutional network, the radio frequency fingerprint features extracted in parallel through the knowledge graph and the one-dimensional convolutional network are spliced, feature recombination is achieved through the attention module, enhancement of effective features and weakening of irrelevant features are achieved, and finally classification is conducted through the classifier. Therefore, the radio frequency fingerprint identification performance in a high-speed moving scene is improved. According to the method, the signal is subjected to equalization processing by using a SupportNet model, radio frequency fingerprint identification is realized by combining a convolutional neural network and a knowledge graph, and the method is suitable for a high-speed mobile channel.

A system and method may be provided for real-time RF fingerprinting, that includes obtaining residual data from each transmission via residual data preprocessing, processing at least a portion of the residual data using a photonic hardware-compatible continuous-time recurrent neural network (CTRNN) model to correlate temporal information and generate informative features, classifying the residual data based on the informative features using a convolutional neural network (CNN) model, and outputting a prediction of which of the plurality of devices at least one of the plurality of adjacent data units was transmitted from. The CNN model may be configured to convolute the generated informative features using at least one convolution-1D layer, for each of which it may select a maximum value for every two consecutive sequential points output from the convolution-1D layer using a max-pooling layer, and flatten and fully connect the output from a last max-pooling layer using a fully-connected layer.

A system and method for file type identification involving extraction of a file-print of a file, the file-print being a unique or practically-unique representation of statistical characteristics associated with the distribution of bits in the binary contents of the file, similar to a fingerprint. The file-print is then passed to a machine learning algorithm that has been trained to recognize file types from their file-prints. The machine learning algorithm returns a predicted file type and, in some cases, a probability of correctness of the prediction. The file may then be encoded using an encoding algorithm chosen based on the predicted file type.

The invention discloses a power distribution network fault positioning method and system based on multi-source sensing fusion, and relates to the technical field of intelligent power distribution, and the method comprises the following steps: collecting high-frequency fluctuation signals corresponding to a plurality of sensing points around the transient high-frequency disturbance generated at the initial stage of a power distribution network fault, expanding each high-frequency fluctuation signal under a unified time reference, and obtaining a plurality of high-frequency fluctuation signals; and extracting starting and ending moments of protruding segments in the high-frequency fluctuation signal, and forming a local amplification fingerprint set based on the protruding segments. According to the invention, by introducing local amplification fingerprint identification and propagation consistency constraint, the pseudo propagation influence is eliminated, so that the fault trace is more consistent with the real propagation law, and the positioning accuracy and stability are improved; and meanwhile, through bandwidth convergence type peak clipping and energy boundary retention, in combination with time and space anchoring of a main fault trace, accurate locking and dynamic isolation are realized, and the fault response speed and the system reliability are improved.

The present disclosure provides a system and a method for performing real-time cloud-native fingerprinting and managing sensitive content within a cloud storage platform to prevent data leakage. The system comprises a cloud storage platform comprising a data leakage prevention (DLP) server. The DLP server configured for receiving and storing a sensitive document, receiving a sensitivity level of the sensitive document, fingerprinting the sensitive document based on the sensitivity level, indexing and storing the fingerprint, sharing the fingerprint to an endpoint security agent, receiving leak indication, performing leak analysis and notifying the leak to a document owner. The system and method further perform monitoring of the sensitive data that has been fingerprinted and stored under a security folder, for a predefined time and automatically moving the sensitive data from the security folder after the predefined time.

A radio frequency fingerprinting method and system based on a convolution-attention mechanism and multi-packet inference are disclosed, and belong to the technical field of communication networks and artificial intelligence. The radio frequency fingerprinting method based on the convolution-attention mechanism and multi-packet inference includes: step 1: capturing a device transmission signal, and preprocessing the transmission signal to obtain a spectrogram; step 2: constructing a radio frequency fingerprinting model, and inputting the obtained spectrogram into the radio frequency fingerprinting model for training, to obtain a trained radio frequency fingerprinting model; and step 3: performing prediction by employing the trained radio frequency fingerprinting model, to obtain a final prediction result.

A radio frequency fingerprint identification method based on an image transmission signal of an unmanned aerial vehicle comprises the following steps: firstly identifying the image transmission signal of the unmanned aerial vehicle, and then respectively carrying out short-time Fourier transform and cyclic spectrum analysis to respectively obtain a time-frequency diagram and a cyclic spectrum diagram; respectively inputting the time-frequency graph and the cyclic spectrum graph into a time-frequency feature extraction stream based on CNN and deformation convolution and a cyclic spectrum feature extraction stream based on Vision Transform, and extracting a local time-frequency feature and a global cyclic stationary feature of the signal; fusing the local time-frequency features and the global cyclostationary features through a multi-modal feature fusion module to obtain fused features; and inputting the fused features into a classification head, and outputting probability distribution of each unmanned aerial vehicle model. And the limitation of a traditional single feature recognition method is effectively overcome. According to the technology, the problem of low recognition rate of the low-altitude unmanned aerial vehicle in a complex electromagnetic environment and under the condition of low signal-to-noise ratio can be solved.

The invention discloses a cloud edge end collaborative computing power scheduling system supporting task dynamic migration, which relates to the technical field of intelligent computing power scheduling and comprises a path modeling module, a conflict identification module, a time sequence checking module, a rehearsal switching module and an interference suppression module, and constructing a routing convergence time sequence profile and a link playback spectrum, modeling an overlapping window of the old path and the new path and a life cycle of a control signal, and generating a path evolution baseline for subsequent conflict identification. By means of path modeling, fingerprint identification, causal check, shadow rehearsal, interference suppression and the like, time sequence consistency of a control instruction and a data stream, continuous path switching and real-time extinguishing of link interference are realized, and the stability and reliability of cloud edge collaborative scheduling are improved.

The invention provides an unmanned cargo automatic handover system based on multi-mode biological recognition. The unmanned cargo automatic handover system comprises a biological recognition device, an identity verification module, a cargo handover control device and a cloud management platform. The biological recognition device integrates a fingerprint recognition module, a face recognition module and an iris recognition module, and high-accuracy identity recognition is ensured by using advanced sensors and algorithms. The identity verification module guarantees the safety of the verification process through real-time comparison and multi-factor verification in combination with dynamic database management. The cargo handover control device automatically controls unlocking and locking of a cargo cabin door, and records, encrypts and stores all handover operation data at the same time. According to the technical scheme, high safety and high efficiency of cargo handover of the logistics vehicle are achieved, the method is suitable for being widely applied to the modern logistics field, the safety and accuracy of the logistics vehicle in the cargo handover process are improved, and automation and traceability of operation are achieved.

The invention provides a water quality fingerprint identification and feed-forward addition control method and system, and the method comprises the steps: obtaining a UV254 absorption value and tyrosine-like and tryptophan-like fluorescence peak signal intensity, and carrying out data fusion preprocessing to generate inflow water quality characteristic fingerprint data; through a preset UV254-BOD / COD prediction model and a fluorescence characteristic ratio correction model, outputting a predicted BOD / COD ratio and an effective carbon content; calculating the theoretical carbon source quantity according to a denitrification theoretical model by combining the real-time water inlet flow and the total nitrogen concentration, deducting the effective carbon content to obtain the external carbon source demand quantity, and outputting a carbon source adding quantity predicted value after the time sequence is adjusted; the predicted value is used as a feedforward control signal, effluent total nitrogen monitoring data is used as a feedback control signal, a final control quantity is obtained through a compound control algorithm, and the final control quantity is converted into an operation instruction of the carbon source adding device and executed. According to the invention, the biodegradability is evaluated by rapidly detecting the water quality characteristics of inlet water, the carbon source demand is calculated, and the accurate addition of the carbon source is realized by adopting a feedforward-feedback composite control strategy.

The invention provides a desktop browser plug-in compatible adaptation method and system based on a credential terminal Web application, and relates to the technical field of credential terminal Web application, firstly, behavior data of a plug-in during operation of a credential terminal is captured, including calling a system interface, accessing local resources and outputting a data rendering record, and time sequence correlation analysis is performed on the data; the method comprises the following steps: establishing an interaction behavior fingerprint, identifying an abnormal interaction node, calling a mismatching pattern library to determine a mismatching reason and generate an adaptive adjustment instruction for the abnormal node, injecting the instruction into a plug-in running process, starting a behavior monitoring process, recording the adjusted interaction behavior fingerprint, and judging a plug-in function completion condition based on adjusted data. The effective adjusting parameters are extracted to construct the adaptation operation process, the final compatible adaptation scheme is generated, and the compatible adaptation efficiency and accuracy of the plug-in and the credential terminal can be improved.

The invention relates to the technical field of fingerprint identification, and particularly discloses a flexible bus crimping fingerprint identification quality tracing system. The system comprises a crimping process multi-mode sensing module, a crimping quality fingerprint feature extraction module, a quality tracing block chain evidence storage module and a self-adaptive environment compensation decision module, and a unique crimping quality fingerprint is generated through fusion by collecting multi-dimensional signals such as pressure, displacement, temperature and operation behaviors in real time. And non-tampering traceability evidence storage is realized based on the block chain, and the measurement data is dynamically corrected through an environment compensation mechanism, so that the detection precision and the system robustness are improved, and closed-loop quality control of the whole flexible bus crimping process is realized.

Disclosed are techniques for selective and scalable sensor fusion for autonomous emergency braking (AEB). In an aspect, an AEB system on a vehicle dynamically selects one or more vehicle sensors from a plurality of vehicle sensors and / or dynamically scales an output from each of the dynamically selected one or more vehicle sensors based on one or more factors, such as the condition of the vehicle, weather, road, or traffic, a location of the vehicle, a sensor capability, a required sensing accuracy, etc., or a change of any of the above. The AEB system monitors a forward path of travel of the vehicle for potential collisions, based on data comprising the output from the one or more vehicle sensors. If a potential collision is detected, the AEB system autonomously applies vehicle brakes to avoid the potential collision. The AEB system can use data and location fingerprinting to reduce false positives.

The application provides a fingerprint identification device with small thickness and low cost and an electronic terminal. The fingerprint identification device comprises an optical film and an image sensor arranged along a first direction and at a first distance. The optical film comprises a first area and a second area with different light transmittances, and the first area and the second area form a first pattern. When the optical film receives light reflected from a first object, the optical film converts the light into an optical image with the first pattern and transmits the optical image to the image sensor. The image sensor is configured to receive an optical signal in the optical image and convert the optical signal into an electrical signal, and the electrical signal is used to construct an image of a surface of the first object reflecting the light. In an embodiment of the application, an electronic terminal comprising the aforementioned fingerprint identification device is provided.

The application discloses a radio frequency fingerprint identification strategy suitable for a low signal-to-noise ratio environment for the purpose of protecting wireless network security. In an Internet of Things system, how to avoid attacks such as illegal monitoring, tampering and impersonation by intruders is a prerequisite for guaranteeing user security. Therefore, a radio frequency fingerprint identification technology without password authentication is proposed to guarantee the security of a wireless network. However, in a low signal-to-noise ratio environment, the existing radio frequency fingerprint identification technology may not have good performance, and therefore it is an urgent problem to be solved to improve the radio frequency fingerprint identification accuracy in a low signal-to-noise ratio environment. The application converts the denoising problem of a one-dimensional radio frequency signal into a denoising problem of a two-dimensional time-frequency graph, and denoises the Wigner-Ville time-frequency graph of the radio frequency signal through a Swin-Conv-UNet denoising network, so as to reduce the influence of noise on the radio frequency fingerprint and greatly improve the accuracy of device identification.

The application relates to the technical field of network security, in particular to a network fingerprint identification method and system based on feature hierarchical filtering and deep learning classification, which comprises receiving detection response data of a target network asset, obtaining multi-dimensional feature data through feature extraction, screening a preset fingerprint library through a hierarchical filtering mechanism to obtain a candidate fingerprint set, performing accurate identification based on the set and original response data by means of a preset deep learning classification model, generating a preliminary identification result and a corresponding confidence, comparing the confidence with a preset threshold, and verifying the consistency of the identification result and a preset classification boundary, and finally outputting the identification result only when the confidence is higher than the threshold and the result is far away from the classification boundary. The performance of asset identification under a large-scale network is realized, the problems that the existing technology cannot cope with large-scale network detection due to low processing efficiency and the high misjudgment rate of fuzzy samples and poor reliability due to the lack of a multiple verification mechanism are solved.

The utility model discloses a fingerprint identification device of a single-chip microcomputer, and the device comprises a fingerprint identification assembly which comprises a machine body; the fingerprint cleaning assembly comprises a clamping groove, a connecting block, a sponge pad, a nozzle, a water storage tank and a control button; the sponge mat is fixed to the top end of the connecting block; the nozzle is fixed to the top end in the clamping groove; the water storage tank is fixed above one side of the machine body; and the control button is fixed to one side of the machine body. Through the arrangement of the clamping groove, the connecting block, the sponge mat, the nozzle, the water storage tank and the control button, water in the water storage tank enters the nozzle, the nozzle sprays water to the sponge mat below, so that the sponge mat is wet, a finger identifying fingerprints is pressed on the sponge mat and then rubbed, the sponge mat cleans the fingerprints, and the fingerprint identification effect is good. And then the cleaned fingers can be placed on the recognizer for fingerprint recognition, so that the fingers do not need to be cleaned at other places, and the time of running back and forth is reduced.

The application discloses an OCT fingerprint recognition method based on a three-dimensional convolutional neural network, which comprises the following steps: obtaining OCT three-dimensional fingerprint data of a reference fingerprint and a fingerprint to be detected, and the OCT three-dimensional fingerprint data of the reference fingerprint and the fingerprint to be detected respectively contain one sweat gland and one sweat gland; the OCT fingerprint recognition method based on the three-dimensional convolutional neural network takes the three-dimensional data with the sweat gland as the center as the input of the recognition model, compared with the traditional two-dimensional epidermal pore recognition method, not only the feature information of the plane dimension is contained, but also the depth dimension information is increased, the three-dimensional morphological characteristics such as the spiral structure of the sweat gland are completely presented, these multi-dimensional three-dimensional data can provide more detailed and unique biological feature identification, and the distinguishing degree and the accuracy of the fingerprint recognition are effectively improved; meanwhile, the method can keep stable recognition performance under harsh conditions based on the three-dimensional data with the sweat gland as the center, and then the fingerprint anti-counterfeiting capability is significantly improved, and the false fingerprint attack can be effectively resisted.

The application provides a display screen, an electronic device and a preparation method of the display screen. The display screen comprises a cover plate, a touch panel and a liquid crystal layer, and the liquid crystal layer is arranged between the cover plate and the touch panel. The touch panel comprises a plurality of signal emitting lines and a plurality of signal receiving lines, and the plurality of signal emitting lines and the plurality of signal receiving lines are arranged in different layer structures respectively. The intersection position between the projection of the signal emitting line and the projection of the signal receiving line forms a fingerprint sensing point. The liquid crystal layer comprises a plurality of first regions and a second region between any two adjacent first regions. The plurality of first regions are arranged one by one corresponding to the plurality of fingerprint sensing points, and the projection of the first region on the touch panel covers the fingerprint sensing point arranged corresponding thereto. In addition, the relative dielectric constant of the first region is greater than that of the second region, so that the induced voltage signal at the fingerprint sensing point is increased, thereby being beneficial to realizing the fingerprint identification of the display screen.