17 results about "High sensitive" patented technology

The invention discloses a trusted digital space-oriented dynamic data sharing security method and system, and relates to the technical field of dynamic data sharing. The isomorphic design enables dynamic attributes such as aging scores and the like to be directly embedded into an access strategy to form a mathematical basis of a dynamic strategy, and when the data aging state changes, a promise value updated by a dynamic credible data label design module automatically triggers strategy re-evaluation of a CP-ABE data sharing module to realize cross-module penetration of the dynamic attributes; in a medical data sharing scene, data timeliness is confirmed to reach the standard and to be compliant with the identity of a visitor through single interaction, so that redundant overhead caused by multiple times of verification in a traditional scheme is avoided; according to the invention, the cross cooperation realizes the attribute-strategy-verification integrated control in the dynamic data circulation process, and when the data aging state changes, the smart contract automatically coordinates the label update and strategy re-evaluation, constructs a dynamic response closed loop on the cryptographic level, and provides a provable and safe mathematical base for the high-sensitivity data sharing.

This invention discloses a blockchain-based hierarchical sharing method for medical data. This method encrypts files with monotonic access structures according to different levels of sensitivity. The secret value is passed upwards through a secret value sharing mechanism, transferring the secret value of the low-sensitivity ciphertext to the high-sensitivity ciphertext. During the data decryption stage, a rapid comparison is performed to find the file with the highest sensitivity that the user can satisfy, and a pre-decryption is performed. This makes it easier to decrypt sensitive files in the file set, improving access control and effectively reducing the number of decryption steps in the medical data sharing process. This truly achieves multi-level attribute data sharing while ensuring privacy and security.

This invention provides a localized differential privacy protection method for medical data. It employs a perturbation algorithm to perturb the data, with the privacy budget set as follows: sensitivity levels are applied to the relevant disease types; based on the sensitivity level, a corresponding privacy budget is set for each disease, where higher sensitivity levels correspond to smaller privacy budget values. This invention assesses disease sensitivity from multiple dimensions, including genetic risk, social discrimination, and treatment costs, achieving differentiated dynamic privacy budget allocation. Smaller values ​​are allocated to highly sensitive diseases to enhance privacy protection, while larger privacy budget values ​​are allocated to less sensitive diseases to reduce data distortion. This solves the problem of insufficient targeted protection caused by fixed privacy budgets in existing methods. Furthermore, the accuracy against background knowledge attacks is significantly lower than 1.2 times that of random guessing, and the privacy protection effect meets the stringent requirements of the formal definition of localized differential privacy.

The present invention relates to the technical field of image recognition. Provided are a cancer detection method and apparatus based on a medical image, and a device, a medium and a product. The method comprises: inputting a medical image into an image classification model, so as to obtain an image classification result that is output by the image classification model, wherein the image classification result is used for representing a recognition result of performing cancer identification on the medical image; inputting the medical image into a semantic segmentation model, so as to obtain a semantic segmentation result that is output by the semantic segmentation model, wherein the semantic segmentation result is used for indicating whether there is a lesion region in the medical image; on the basis of the semantic segmentation result and the image classification result, determining whether it is necessary to perform detection on a corresponding organ part in the medical image; and when it is necessary to perform detection on the corresponding organ part in the medical image, outputting detection prompt information. The present invention can realize high-efficiency, high-sensitivity, and high-accuracy cancer detection.

The invention relates to the technical field of differential pressure sensors, and discloses a side line differential pressure sensor and an underwater device.The side line differential pressure sensor comprises a sensing unit, a cilium structure, a sensor bonding substrate and a packaging shell, the interior of the packaging shell is hollow to form a containing space, and two coaxially-arranged flow guide holes are formed in the side wall of the packaging shell; the sensor bonding substrate is positioned in the accommodating space and is fixedly connected with the bottom of the packaging shell; the sensing unit is arranged on the sensor bonding substrate and is electrically connected with the sensor bonding substrate; the cilium structure is arranged on the sensing unit, and the cilium structure and the two flow guide holes are coaxially arranged; the flow guide holes are used for guiding fluid to form a pressure difference on the two sides of the cilia structure, so that the cilia structure receives a pressure difference signal of the fluid. According to the invention, high-sensitivity detection of weak fluid pressure difference can be realized.

The invention discloses a surface defect detection method based on a line-scan digital camera, and relates to the technical field of image data processing and image analysis. A space-time fusion module, a dynamic up-sampling module and a multi-scale feature pyramid network are introduced into an image sequence formed by continuous scanning of the line-scan digital camera; the characterization capability on the defects of the micro solder balls under the condition of high-speed acquisition is integrally enhanced; time attention and space attention are jointly modeled, multi-frame information is referred to at the same space position, weights are adaptively distributed according to inter-frame similarity and time intervals, transient defect signals such as cracks and bridging occurring in a short time are amplified, stable background constraints are provided by long-distance frames, and the accuracy and the reliability of the system are improved. Therefore, high sensitivity and discrimination capability to real defects are still kept when motion blur and noise exist.

The invention discloses an anti-single particle risk system for a spacecraft, and the system is characterized in that a filtering module is connected to a power module, and is used for filtering noises and peaks with different frequencies in the power module; and the latch-up effect caused by the influence of transient voltage fluctuation on the CMOS in the chip is prevented. The signal limiting module is connected to the signal line and used for limiting the trigger current of the signal. And latch-up caused by CMOS well current abrupt change in the chip due to large current generated by the single event effect is prevented. And the level conversion module is connected to the high-sensitivity device and is used for ensuring the stability and the reliability of the power supply. And the surge protection module is connected to the power loop and is used for absorbing transient voltage, so that overvoltage protection is realized, and false triggering or latching of a subsequent circuit is prevented. And all power supply lines adopt a double-point double-line design, so that single-point failure caused by breakdown of a certain power distribution switch by a single particle is prevented. The control unit adopts a hot and cold dual redundancy measure of a host and a standby, and the management power supply module carries out hot backup, so that the normal work of the management power supply module is ensured.

The invention discloses a deformation monitoring system and method for an energy storage earth surface of an aquifer, and relates to the field of deformation monitoring regulation and control. According to the deformation monitoring system and method, the current earth surface is subjected to partition processing based on a model, geological environment parameters are synchronously collected, and the deformation sensitivity level of each partition is accurately output through a constructed associated condition set; the comprehensiveness and the accuracy of risk identification are obviously improved; the maintenance frequency, the inspection frequency and the sensor parameters are automatically configured when the proportion of the medium-high sensitive area exceeds the threshold value, maintenance is implemented, and time consumption and cost are recorded until the proportion of the medium-high sensitive area is reduced to be below the threshold value, so that resource waste is effectively avoided, and the timeliness of maintenance is ensured; when the current maintenance time consumption or cost is monitored to exceed a threshold value, a microcosmic adjustment mechanism is triggered, sensor parameters, maintenance frequency and inspection frequency are iteratively optimized, adjusted data are input into a model for evaluation again, and partition is performed again when conditions are not met, so that the maintenance efficiency and economy are remarkably improved.

Systems and methods are provided for detecting defects on a demagnification mask. One system is configured to generate different stacked difference images for a plurality of instances of a first patterned region in different rows on a wafer based on images generated for the first patterned region in the different rows. The system is also configured to perform double detection based on the different stacked difference images. The system then identifies defects on the demagnification mask based on defects detected by the double detection. As described further herein, the systems and methods detect defects from multiple demagnification mask rows printed on a wafer, which can reduce noise and enable detection of substantially small reticle defects. Embodiments are particularly useful for extreme ultraviolet (EUV) demagnification mask and multi-die demagnification mask (MDR) high sensitivity reticle defect detection.

The present application provides a kind of trace thiabendazole detection method and system of terahertz metamaterial resonance enhancement, the method comprises: based on the characteristic peak frequency of single period structure and thiabendazole, the parameter information of the metamaterial sensor is constructed, and modeling simulation is carried out according to parameter information, to obtain the terahertz metamaterial with L type composite double-peak structure;Preparation thiabendazole sample, and utilize terahertz metamaterial to carry out spectrum collection to thiabendazole sample, to obtain corresponding spectral data;Support vector regression model is constructed, and the optimization algorithm of weighted vector average is integrated, and global optimization of hyperparameter is carried out, to construct corresponding optimization model;According to spectral data and optimization model, corresponding detection model is constructed, and nondestructive testing of trace thiabendazole is realized using detection model.The present application not only realizes high sensitive quantitative analysis to trace thiabendazole residue, also verifies the feasibility and superiority of INFO optimization algorithm in the field of spectral detection.

The present application relates to nursing device technical field, disclose a kind of invisible stoma vibration underwear reminding monitoring system, including one distributed resistance network and microcontroller being arranged in underwear;Microcontroller is compared difference by establishing reference voltage division ratio between network nodes, and continuously monitors current voltage division ratio with the reference, when difference exceeds mutation threshold, drive reminding device.The present application shifts monitoring focus from tracking complex physiological parameters to guarding the electrical integrity of a stable physical system by using the relative stability of voltage division ratio, which can suppress global interference such as body temperature or deformation in structure, while showing high sensitivity to leakage-specific local electrical mutations, thereby achieving high-reliability early warning of leakage risk at very low power consumption.

The invention discloses an efficient federal learning method and system. According to the method, firstly, through model privacy measurement and sensitivity analysis, privacy risk assessment and grading are carried out on model parameters, homomorphic encryption is only carried out on high-sensitivity parameters, light disturbance is applied to medium-sensitivity parameters, and plaintext transmission is kept on low-sensitivity parameters, so that a'key encryption and non-key plaintext 'hybrid protection mechanism is realized. A server generates a global encryption mask according to sensitivity information uploaded by a client, and performs security aggregation in a ciphertext domain and a plaintext domain respectively. And the client carries out decryption and adaptive updating after receiving the global model, dynamically adjusts an encryption strategy, and realizes continuous balance between privacy protection strength and model precision. According to the invention, the communication and calculation overhead is effectively reduced, the security and training efficiency of the federal learning system are improved, and the method is suitable for privacy collaborative learning of multiple scenes such as medical treatment, industry and Internet of Things.

The invention provides an entropy production region sampling system and method, electronic equipment and a computer readable storage medium, and aims to directly calculate a weight based on a physical parameter change rate and realize a millisecond-level response speed. The feature weight is automatically adjusted through working condition recognition, and high detection precision can still be kept in a variable working condition scene. The real-time identification of the high-entropy production area is realized, the sampling density is improved, and the resource consumption of the low-value area is reduced. Under the transient working condition, the system rapidly captures feature changes by dynamically adjusting weight parameters, and missing detection of key events is effectively avoided. The hierarchical sampling strategy enables computing resources to act on a high-sensitivity area in a concentrated mode, and the overall energy consumption is remarkably reduced while the monitoring precision is guaranteed.

Embodiments of the present application provide a kind of processing method, system and equipment of merchant registration information, the method comprises: receiving the registration information of multiple types uploaded by merchant;According to the type of the registration information, dynamically determine the comprehensive sensitivity of each type registration information;According to the comprehensive sensitivity of each type registration information, determine the privacy level of each type registration information;According to the privacy level of each type registration information, the differential encryption processing is carried out to each type registration information, and encrypted registration information is obtained;The compliance verification is carried out to the encrypted registration information, and verification result is obtained;The verification result is fed back to the merchant.The present application can dynamically divide privacy level according to registration information type, implement differential encryption, both intensify security protection to high sensitive information, reduce the risk of leakage and tampering, avoid ordinary information excessive processing, reduce system overhead.

The invention provides a mechanical arm obstacle avoidance detection method and system, is applied to the technical field of mechanical arm control, and avoids the excessive response of a mechanical arm to a non-entity phenomenon by distinguishing the non-entity phenomenon from an entity obstacle, so that unnecessary obstacle avoidance actions are remarkably reduced, and the working efficiency and reliability of the mechanical arm are improved. And meanwhile, for a real entity obstacle, the system can still keep high sensitivity and take proper obstacle avoidance measures, so that the operation safety of the mechanical arm in a complex environment is ensured. Therefore, on the premise that the safety is guaranteed, the working efficiency and the intelligent level of the mechanical arm in the polluted environment are greatly improved.

The invention discloses an engineering video monitoring safety management method and system, and the method comprises the steps: constructing an engineering video monitoring data grading system, and configuring an operation authority baseline of each grade of data; acquiring an operation log of the engineering video monitoring system in real time and storing the operation log in the block chain; constructing a multi-dimensional behavior feature model based on the operation authority base line and the historical operation data; comparing the collected operation log with the multi-dimensional behavior feature model, identifying an abnormal operation behavior according to an abnormal early warning rule, and generating an abnormal early warning; and executing hierarchical response on the generated abnormal early warning. According to the method, videos of different risk levels are distinguished through a sensitive grading system in combination with manual presetting and AI dynamic marking; then role permission baselines are matched, operation is limited from an access source, low-permission users are prevented from making contact with high-sensitivity videos in an unauthorized mode, the risk of important data leakage can be effectively reduced, obvious violations such as unauthorized conditions can be recognized through a multi-dimensional model, and a small number of hidden operations can be early warned in advance.