17 results about "Identity correlation" patented technology

The application discloses a kind of distributed data encryption sharing methods based on block chain, and using block chain realizes the traceable management of search and authorization process.The scheme is first by multi-authorization center to carry out distributed management to attribute domain, and generates attribute key associated with identity for user;In access verification link, construct parameter masking mechanism based on bilinear pairing, so that user attribute private key is not directly exposed in block chain verification and query process.Secondly, data owner carries out layered encryption to shared data and session key, and constructs the improved multi-key search structure, index and ciphertext positioning information are recorded to block chain, to support fast positioning target ciphertext.In addition, the application uses linear secret sharing to set access structure, and designs subset determination mechanism of general attribute name set, binds the download permission of ciphertext with the attribute condition that user can satisfy, to prevent overreach download behavior.Finally, with the help of cloud, outsourcing decryption is executed to generate intermediate result, and terminal only needs to complete light recovery and decryption.The application can give consideration to fine-grained control, high-performance search access and terminal side low load, and is suitable for secure data encryption sharing in resource-limited scene.

The embodiment of the application discloses a kind of staff visit training voice interaction method and system, method includes: the voice data and voiceprint feature information of staff are collected by voice interaction terminal;The real-time position of staff is obtained by positioning base station;According to voice data, voiceprint feature information and real-time position, staff identity association information is generated, and is given training interactive equipment simultaneously, staff identity association information includes the terminal number, staff state information, staff position information and staff question information associated with staff identity mark one-to-one, staff identity mark is associated with voiceprint feature information;According to staff identity association information, execute position boundary-crossing warning operation and multi-concurrent audio processing operation.The application can solve the problem that new staff position boundary-crossing risk is difficult to early warning and multi-person concurrent question when guiding response is chaotic in the scene of staff pre-service visit training, improve the intelligence and safety of staff pre-service visit training.

The application discloses a kind of golf leading type follow control system based on multi-modal monitoring, including multi-modal acquisition module, data pre-processing and confidence estimation module, target identity correlation module, scene semantic identification module, leading type target point generation and path planning module, behavior state machine control module, dynamic safety zone generation module, abnormal degradation and recovery module, display and interaction module and data closed loop optimization mechanism.The beneficial effects of the present application are: compared with prior art, through the multi-modal fusion of vision+wireless+trajectory consistency test, the robustness of following is greatly improved, and the complex scene is adapted.Combined with hole sequence semantics, leading type guidance is realized, and the efficiency of sports and venue is improved.Meanwhile, the site rules are integrated to ensure compliance, the dynamic safety zone is generated according to the user state to strengthen the swing safety, the explainable abnormal degradation mechanism is equipped to improve the practicability, and the scene adaptability of the equipment can be continuously enhanced through the use of feedback closed loop optimization model.

This application provides a method, apparatus, electronic device, and storage medium for silent login across system pages, relating to the field of system authentication technology. The method includes: receiving an access request from a third-party platform and verifying the access request; if the verification passes, generating user access credentials based on the access request and performing internal identity association based on the user access credentials; verifying a page access request from the third-party platform, the page access request including user access credentials and a target page identifier from the third-party platform; if the verification passes, performing a login operation based on an internal authentication engine and generating a system token; constructing a dynamic authentication address based on the system token, the target page identifier, and tenant information, and sending the dynamic authentication address to the third-party platform for automatic authentication login. This application, through a multi-level token conversion mechanism, enables embedded pages to fully reuse the original authentication system, achieving silent login when embedding pages across systems.

Systems and methods for digital ID sharing are disclosed. One disclosed method includes receiving a first digital ID comprising a verified credential of a first user; receiving a second digital ID comprising a verified credential of a second user, verifying a relationship between the first user and the second user, linking the first digital ID to the second digital ID; and outputting a verification message associated with the first digital ID and the second digital ID.

The application discloses a kind of safety state monitoring method and system of urban slow traffic, it is related to traffic space-time data processing technical field, including to the electronic data of urban slow traffic, constructs slow scene topology graph and generates time-varying visibility matrix.Slowness scene topology graph and time-varying visibility matrix are used to establish double memory state and generate candidate continuous trajectory.Based on candidate continuous trajectory, identity correlation score is calculated, identity corresponding relationship is determined, and subject level safety state value is output.The application constructs continuous data processing chain of synchronous modeling, double memory maintenance, associated output around urban slow traffic electronic data, realizes the unified organization and unified update of topological constraint, visibility constraint, negative evidence constraint and state value calculation.Compared with the distributed processing mode, the application can convert multi-source space-time objects into indexable, associated, accumulative digital data objects.

Embodiments of this application disclose a blockchain key-based data processing method and apparatus. The method includes obtaining communication channels respectively communicating with N clients, and respectively performing key shard negotiation with the N clients to obtain a local private key shard and a complete public key; receiving signature requests transmitted by M−1 clients in the N clients, and obtaining identity association information in the M−1 signature requests; if the identity association information in the M−1 signature requests is legitimate identity information, determining a client that is in the M−1 clients as a target client, and obtaining service execution data associated with the target client; and if the service execution data conforms to a risk management policy corresponding to identity association information of the target client, jointly participating in joint signature processing on the blockchain service with the M−1 clients.

The embodiment of the application discloses a kind of staff visit training voice interaction method and system, method includes: the voice data and voiceprint feature information of staff are collected by voice interaction terminal;The real-time position of staff is obtained by positioning base station;According to voice data, voiceprint feature information and real-time position, staff identity association information is generated, and is given training interactive equipment simultaneously, staff identity association information includes the terminal number, staff state information, staff position information and staff question information associated with staff identity mark one-to-one, staff identity mark is associated with voiceprint feature information;According to staff identity association information, execute position boundary-crossing warning operation and multi-concurrent audio processing operation.The application can solve the problem that new staff position boundary-crossing risk is difficult to early warning and multi-person concurrent question when guiding response is chaotic in the scene of staff pre-service visit training, improve the intelligence and safety of staff pre-service visit training.

The application provides a kind of wisdom campus non-motor vehicle management method and system based on Internet of Things, it is related to Internet of Things technical field, first, obtain the real-time position information of campus non-motor vehicle basic information and Internet of Things perception, identity association information set is generated in association, determine target mobile area based on campus area function, user use purpose and vehicle type, then combine target area, path traffic state and real-time position, generate path guide instruction and send to user terminal, after vehicle arrives, collection parking area occupancy state, combine vehicle size and allocate parking area and guide parking, when user applies for leaving school, generate leaving school check information according to identity association information, parking allocation and vehicle current state, after being verified by the verification equipment of campus entrance Internet of Things, generate leaving school state record and store in management database, thus realize all-around intelligent management of campus non-motor vehicle, improve management efficiency and campus safety level.

This invention provides a pedestrian re-identification method and apparatus, belonging to the field of computer vision technology. The method includes: extracting image viewpoint features, pedestrian pose features, and identity features from an original pedestrian image, and reconstructing the identity features into identity sequence features; inputting the image viewpoint features, pedestrian pose features, and identity sequence features into a diffusion model for diffusion generation to obtain a virtual pedestrian image with identity feature labels consistent with the original pedestrian image; adding the virtual pedestrian image to the original pedestrian dataset to form an expanded dataset for training to obtain a pedestrian re-identification model; and using it to identify the target pedestrian image to obtain the pedestrian re-identification result. This invention addresses the problems of insufficient modeling of long-distance identity associations during feature extraction in existing pedestrian re-identification methods, and identity recognition bias caused by scarce and unevenly distributed training data.

The application discloses a kind of monitoring video in motion target automatic tracking and trajectory generation method and system, belong to computer vision and video monitoring technical field.This method includes: obtaining monitoring video frame and detecting motion target;When there is target in current frame missing, based on its historical state construct probability distribution field diffusing with time, determine prediction candidate region in combination with scene occlusion constraint and actively enhance detection;The target and predicted candidate target detected in current frame are regarded as multi-agent, and identity correlation and state updating are carried out by introducing interactive game model;The trajectory attention weight obtained by self-supervised learning is used to guide and smooth the target trajectory, and the continuous trajectory data with identity identification is output.The application can maintain target identity stability and trajectory continuity under complex occlusion, dense interaction and weak detection scene, significantly reduce trajectory interruption and mismatch rate, and improve the reliability of motion target automatic tracking and trajectory generation in monitoring video.

The application discloses a kind of safety state monitoring method and system of urban slow traffic, it is related to traffic space-time data processing technical field, including to the electronic data of urban slow traffic, constructs slow scene topology graph and generates time-varying visibility matrix.Slowness scene topology graph and time-varying visibility matrix are used to establish double memory state and generate candidate continuous trajectory.Based on candidate continuous trajectory, identity correlation score is calculated, identity corresponding relationship is determined, and subject level safety state value is output.The application constructs continuous data processing chain of synchronous modeling, double memory maintenance, associated output around urban slow traffic electronic data, realizes the unified organization and unified update of topological constraint, visibility constraint, negative evidence constraint and state value calculation.Compared with the distributed processing mode, the application can convert multi-source space-time objects into indexable, associated, accumulative digital data objects.

The application relates to a face identity protection method and system for three-dimensional Gaussian point cloud scene editing. The method comprises the following steps: acquiring three-dimensional Gaussian point cloud scene data and camera internal and external parameters, generating a scene image through multi-view rendering; detecting a face to obtain a region mask, and projecting two-dimensional face pixels to a three-dimensional space to screen out target Gaussian points related to the identity of a person; performing text-driven image editing based on a diffusion editing model, extracting face features before and after editing to calculate identity consistency loss and visual feature difference loss; generating weights according to the identity leakage degree of each view angle, and obtaining a multi-view identity protection loss through weighted fusion, and the multi-view identity protection loss is combined with a three-dimensional scene editing loss to be optimized, and finally, scene parameters are updated. The method positions target Gaussian points through multi-view face back projection, and combines multi-view weighted identity protection loss to be optimized, so that the face identity protection capability and scene editing security in the Gaussian point cloud scene editing process are significantly improved.

This invention relates to the fields of computer vision and 3D graphics technology, specifically disclosing a target identity and trajectory localization method driven by multi-camera 3D reconstruction. The method involves acquiring video sequences through a synchronous camera network and constructing an implicit representation model containing only static background structures to establish a stable 3D coordinate system. Then, target detection is performed on the real-time video stream, and the 2D coordinates of the detection points are back-projected and the accurate 3D spatial coordinates are calculated by querying the static model. Finally, the target's motion state, appearance, and behavioral characteristics are fused to perform multi-target tracking and identity association, generating a 3D motion trajectory with a consistent identity identifier.

The application discloses a video-oriented interactive human pose labeling and cross-frame correction propagation method and belongs to the technical field of computer vision and intelligent labeling. The application adopts a double-layer correction propagation framework combining instance-level tracking and key point-level tracking, first completes multi-person bounding box and key point initialization of a current frame through a human-to-key point encoding and decoding network, and then realizes cross-frame identity association by fusing frame features, key point geometric relationship features and identity embedding. After correction by a labeler, a point tracker is used to propagate the result to subsequent frames, generate key point and bounding box reference points as geometric prior input decoders, and refine subsequent frame pose estimation. The method can convert sparse manual correction into time-continuous and identity-consistent multi-person pose trajectories, significantly reduces labeling cost of long videos and complex multi-person videos, improves labeling accuracy, time consistency and interactive efficiency, and is suitable for pose dataset construction, action recognition, virtual reality and human-computer interaction scenes.