10 results about "False rejection rate" patented technology

This invention discloses a method and system for suppressing false rejection behavior and selectively forgetting harmful semantics in large language models across vertical domains based on feature subspace decoupling, belonging to the field of fine-tuning and alignment technology for large artificial intelligence models. The method includes steps for target definition and data construction, feature subspace localization, key level optimization, orthogonal decoupling weight correction, constrained norm renormalization, selective fine-tuning, false rejection calibration, and closed-loop verification monitoring and document output. The system includes modules for concept discovery and data construction, representation subspace modeling, false rejection localization and calibration, and verifiable evaluation and continuous monitoring. This invention can significantly reduce the false rejection rate and maintain a safety baseline while preserving the model's generalizability, meeting the compliance requirements of generative artificial intelligence services.

The invention discloses an anti-electric-shock capacitive-resistive screen fused with pressure induction, and relates to the technical field of touch screens, the capacitive-resistive screen comprises a capacitive touch layer and a resistive pressure induction layer, the capacitive touch layer is used for detecting coordinate information of a touch position, the resistive pressure induction layer is used for detecting a pressure signal applied to the screen, and the capacitive touch layer is used for detecting the coordinate information of the touch position. The touch screen further comprises a processing unit, and the processing unit is electrically connected with the capacitance touch layer and the resistance pressure sensing layer and used for executing the following operation. According to the pressure-sensing-fused mistaken-electric-shock-preventing capacitive-resistive screen, accurate analysis of a touch intention is achieved by constructing a dynamic pressure fingerprint discrimination and self-adaptive threshold model. According to the scheme, a multi-level signal processing and decision-making mechanism is adopted, the dynamic click pressure and the static background pressure can be effectively distinguished, the problem that a traditional single pressure threshold criterion is high in misjudgment rate in a composite pressure scene is solved, and therefore the accuracy and reliability of touch operation are improved.

The application relates to the technical field of radar body detectors, and particularly discloses a radar body detector gesture mode switching method and system, wherein the method comprises the following steps: acquiring a radar echo signal, and extracting motion parameter information of a user according to the radar echo signal; generating a motion state index sequence according to the motion parameter information; analyzing the motion state index sequence, detecting a signal segment with a radar feature mode similar to a preset gesture and greater than a first preset threshold, and marking the signal segment as a potential gesture signal; and based on context intention judgment, analyzing the potential gesture signal to obtain an intention judgment score, and judging whether the potential gesture signal is a mode switching instruction; the method effectively distinguishes between a conscious mode switching instruction of a user and an unconscious background motion, and is adapted to gesture variation caused by changes in the position and posture of the user, so that the false rejection rate is significantly reduced, and the gesture interaction accuracy and reliability are improved.

The invention relates to a quick identity authentication method and device based on physical unclonable features, equipment and a medium, and the method comprises the steps: taking a query feature descriptor as a retrieval object, and carrying out approximate nearest neighbor matching retrieval in a local feature descriptor set of a global feature library, after screening, determining one or more candidate physical unclonable tag identities through voting; for candidate physical unclonable tag identities, corresponding registered key point space coordinates are called from a geometric feature library, and a re-projection error threshold is combined through a random sampling consistency algorithm; checking whether the space coordinate of the query key point and the space coordinate of the registered key point of the candidate physical unclonable tag meet a preset geometric transformation model or not, and calculating a geometric consistency score according to the preset geometric transformation model; and if it is detected that the geometric consistency score is greater than or equal to a preset score threshold, outputting an identity authentication success result. According to the invention, the identity authentication efficiency is greatly improved, and the false rejection rate of identity authentication is remarkably reduced.

This invention discloses a dynamic role-based access control method based on dual-source trust fusion to address the high risk of unauthorized access caused by static role authorization in dynamic network environments. The method first receives user access requests and extracts contextual risk features. Then, it extracts historical user interaction indicators and calculates dynamic behavior trust scores based on time decay. External feedback scores are obtained, outlier scores are removed, and weighted aggregation yields robust feedback trust scores. Then, based on data consistency and divergence, adaptive weighting is applied to derive a comprehensive trust score. Finally, the comprehensive trust score is coupled with the contextual risk value to determine the trust gap, and based on this, full authorization, partial authorization downgrade based on sensitivity truncation, or access denial are performed. This invention abandons static fixed weights, enhancing the robustness of trust assessment in extreme scenarios; and it pioneers a partial authorization pruning mechanism, effectively reducing the false rejection rate of legitimate users while ensuring security, achieving a balance between system availability and the principle of least privilege.

The application discloses a finger vein recognition method and system based on dynamic balance of false recognition rate and false rejection rate, and the method comprises the following steps: obtaining a to-be-recognized finger vein image, and performing image preprocessing and ROI extraction processing to obtain an ROI region of the finger vein image; a finger vein recognition model is constructed, three-stage hybrid training is performed in combination with the ROI region of the finger vein image, and a trained finger vein recognition model is obtained; a balanced error rate evaluation index is constructed to evaluate the trained finger vein recognition model, and an evaluated finger vein recognition model is obtained; and finger vein recognition is performed on the to-be-recognized finger vein image based on the evaluated finger vein recognition model, and a finger vein recognition result is obtained. The application can meet the finger vein recognition requirements in multiple scenes and improve the finger vein recognition accuracy. The application can be widely applied to the technical field of finger vein recognition as a finger vein recognition method and system based on dynamic balance of false recognition rate and false rejection rate.

The application discloses an instruction tamper-proofing device for a traffic information board system, relates to the field of traffic information security, and solves the three technical problems of key clonable risk, high algorithm dependence and poor environmental adaptability existing in traditional encryption schemes. A tamper-proofing system is constructed through a triple synergy mechanism: unique unclonable physical characteristics are extracted based on a physically unclonable circuit, efficient integrity verification is realized through a segmented cascading parity check circuit, and time stamps are accurately compared in combination with a temperature compensation clock; and multi-dimensional features are fused and integrated, tamper identification is performed through feature comparison, irreversible hardware failure is formed to trigger tamper identification, and ultimate protection is formed. The device achieves a pure hardware millisecond-level response, completely eliminates software dependence, maintains a zero false rejection rate in extreme environments, ensures the safety of the whole life cycle of the instruction through physical-level protection, and provides uncopyable security protection for the information board system.

The invention discloses a children voiceprint self-adaptive correction method and a children voiceprint self-adaptive correction system. The method comprises the steps of obtaining a target child voice signal; multi-dimensional voiceprint features are extracted from the target child voice signal, normalization processing is carried out, a high-dimensional voiceprint feature vector is constructed, and the multi-dimensional voiceprint features comprise MFCC, fundamental frequency and formant; the Euclidean distance between the high-dimensional voiceprint feature vector and the reference high-dimensional voiceprint feature vector is calculated, and a judgment threshold value is combined to carry out matching judgment, so that the final child voiceprint is determined; wherein the judgment threshold is dynamically adjusted by using historical matching data to adapt to sound changes, and the reference high-dimensional voiceprint feature vector is a voiceprint template obtained by combining a screened sample with confidence meeting requirements with a moving average method to progressively update. By implementing the method provided by the invention, the template and the threshold can be dynamically adjusted in combination with a self-adaptive correction mechanism, the error rejection rate is reduced on the premise of ensuring the safety, and the robustness and accuracy of the system when facing the child sounding behavior mode change are improved.

The utility model discloses an ampoule bottle breaking and falling detection device, relates to the technical field of medicine packaging equipment, and aims to solve the problems that a visual system is high in cost and easy to be interfered by ambient light, a photoelectric sensor is sensitive to transparency of a bottle body, the false detection rate is high, the manual detection efficiency is low, and the detection cost is high in the conventional detection mode. According to the key points of the technical scheme, the device comprises a supporting base, a holding seat is fixedly installed in the middle of the upper surface of the supporting base, a material moving groove is formed in the middle of the holding seat, an adjustable support is fixedly installed on the upper surface of the supporting base, and the adjustable support is fixedly installed on the upper surface of the supporting base. A microswitch is fixedly installed on the installation position of the adjustable support, a touch control strip is arranged on the microswitch, and one end of the touch control strip is arranged above the material moving groove of the holding base and attached to the side surface of the ampoule bottle moving in the material moving groove. The effects of reducing the false detection rate, reducing the cost and improving the detection efficiency are achieved.

The application provides a weld quality detection method and a training method. The weld quality detection method comprises the following steps: obtaining a first gray-scale image, wherein the first gray-scale image is obtained by sequentially irradiating a detected object by at least two light sources, the number of the first gray-scale image corresponds to the number of the light sources, and the light sources output parallel light. A first normal angle image of the detected object is obtained based on the first gray-scale image. The first normal angle image is divided into a marked area. And the first normal angle image and the division result of the marked area are output and / or displayed to obtain a weld quality detection result. More information is obtained based on the first normal angle image, and the information itself is more accurate, which can improve the detection accuracy of the weld quality detection, thereby solving the problem of high false rejection rate and high false acceptance rate in the prior art when the weld quality of a measured object with high surface reflectivity is detected.