20results about How to "Eliminate differences" patented technology

The application discloses a brain function state evaluation and psychological disease auxiliary analysis system based on a brain fluctuation map, comprising: a multi-modal electroencephalogram signal acquisition and preprocessing module; a brain fluctuation map feature extraction module; an individualized baseline modeling module; and an adaptive weighting evaluation module based on an attention mechanism, which constructs an individualized deviation vector and adaptively weights the current features and deviation features based on an attention network, and outputs a disease risk probability and a channel contribution weight map. Compared with traditional population norms or simple arithmetic means, the method can more truly reflect the stable ground state of the subject itself, effectively eliminate individual differences and measurement noise, and provide accurate dynamic reference system for subsequent abnormal deviation judgment. Meanwhile, the fluctuation threshold calculation unit sets an adaptive threshold based on a statistical confidence interval, and introduces an abnormal deviation index and a multi-dimensional joint determination, further reducing the false positive risk.

The invention discloses a carbon dioxide inter-section displacement pre-fracturing process and a design method and related equipment thereof, and belongs to the technical field of oil and gas production, the design method comprises the following steps: establishing an integrated fractured horizontal well numerical simulation model according to seismic data of a target well, logging interpretation data and an engineering parameter range given by an oil production scheme; the integrated fractured horizontal well numerical simulation model is used for simulating single well yields under different section intervals and different single-section carbon dioxide injection amounts by adopting a section-separated gas injection method; drawing a parameter optimization chart based on the single well yield and the carbon dioxide injection section number obtained under different section distances and different single-section carbon dioxide injection amounts; and according to the parameter optimization plate, determining the final segment spacing and the single-segment carbon dioxide injection amount. While the recovery efficiency is improved, the construction efficiency is improved, and the fracturing cost is saved.

The application relates to the field of artificial intelligence and power equipment operation and maintenance data processing technology, and particularly discloses a power energy storage operation and maintenance health evaluation method based on deep learning, which comprises the following steps: a pre-processing unit first performs caliber unification according to a historical caliber change set and extracts single data in real time, eliminates equipment differences, makes the algorithm identify only one set of caliber, and reduces special cases and error sources; an edge gateway performs clock consistency test, aligns the time axis, and avoids wrong time misjudgment; if the test fails, the data is improved and data reliability is output, and the caliber change set is rewritten and corrected; then, the data and the reliability are sent to a model to perform health evaluation and physical consistency verification, and the correlation is improved to be explainable physical reliability; finally, the evaluation result is mapped to a standardized operation and maintenance disposal suggestion, and the operation and maintenance plan is synchronized to a platform; the standardized action and plan are synchronized to realize a closed loop of diagnosis, disposal and recovery, and the whole process is auditable and reproducible.

This application discloses a gamma curve calibration method, a gamma curve calibration device, and a computer storage medium. The gamma curve calibration method includes: acquiring first image data from a reference device and second image data from a test device under identical conditions; acquiring the data difference between the first and second image data; using the data difference and the first image data from the reference device to obtain a difference curve between the reference device and the test device; and determining the gamma curve of the test device based on the difference curve and the gamma curve of the reference device. Through this method, the gamma curve calibration method of this application can automatically calibrate the gamma curve and effectively eliminate device variability issues, improving the dynamic range brightness consistency of the device.

The invention discloses a thoracolumbar vertebra fracture detection method and system based on sequence modeling and a prior graph, and the method comprises the steps: obtaining thoracolumbar vertebra CT volume data and fracture type truth value label data, carrying out the preprocessing, and constructing a training set and a test set; and constructing a fracture detection multi-branch classification network model, training and testing the constructed fracture detection multi-branch classification network model by using the training set and the test set, preprocessing thoracolumbar vertebra CT body data of a to-be-detected patient, inputting the preprocessed thoracolumbar vertebra CT body data into the trained fracture detection multi-branch classification network model, and outputting a fracture type classification prediction result. By designing an end-to-end framework of an image feature branch, a label relation branch and a branch fusion module, the problems that in the prior art, continuity of a vertebral body structure is deficient, long-range dependence is insufficient, feature fusion is insufficient and the like are solved, and accurate detection and refined classification of thoracolumbar vertebral fractures are achieved.

The application discloses a civil aircraft wing-body docking contact gap virtual measurement method and system based on manifold space alignment, constructs a "physical manifold guide-micro texture compensation" collaborative architecture, analyzes the nonlinear mapping reference of macro load and average gap, defines the physical manifold boundary conforming to energy conservation and deformation coordination, and designs a deep space-time network to adaptively extract micro texture residual features caused by surface roughness from a dynamic strain sequence, and then introduces a latent space manifold alignment mechanism, uses a physical reference track to forcibly constrain a data feature track in a low-dimensional manifold space, realizes deep fusion of mechanism priori and data features, effectively solves the problems of physical consistency loss and non-physical oscillation of a pure data-driven model under sparse samples, performs high-precision and strong-robustness cross-scale quantitative state reconstruction on a non-uniform contact gap field, and provides a technical path with mechanical interpretability for digital precise assembly of an aviation structural part.

The application provides a test case automatic generation system based on mutation, which analyzes initial test cases, obtains corresponding component structures and field type information according to case subnode data obtained through analysis, and generates new test cases by applying mutation operations with correct semantics according to the type of corresponding subnode data, thus solving the problem that mutation operations damage the format of test cases and cannot generate effective test cases. Meanwhile, the application uses randomization and semantic-based mutation, adopts corresponding semantic mutation strategies according to the type of data, enhances the pertinence and effectiveness of generated test cases, enhances the difference and richness of generated test cases through randomization mutation strategies, and adopts a plurality of mutation strategies designed according to the characteristics of XML and JSON formats, so as to eliminate the difference of XML and JSON format test case generation tasks from different sources to the greatest extent and enhance the universality of the test case generation method.

This invention provides a method and apparatus for evaluating software bill of materials (SBOM) generation tools, relating to the field of computer technology. The method includes: inputting a pre-selected target software project into a SBOM generation tool to be tested, obtaining an original SBOM file output by the tool; performing standardized parsing on the original SBOM file to obtain a corresponding standard SBOM file; performing multi-dimensional evaluation on the standard SBOM file to obtain an evaluation score; the evaluation score includes a field compliance score, a package-level consistency score, and a field-level consistency score; and obtaining an evaluation result for the SBOM generation tool based on the evaluation score. The software bill of materials (SBOM) generation tool evaluation method provided by this invention, by integrating multi-dimensional scores to generate a final evaluation result, achieves an accurate and reliable evaluation of the SBOM generation tool.

The invention provides an intelligent data quality evaluation system and method based on a large model, and relates to the technical field of data processing.The method comprises the steps that data fields of basic data are divided into a plurality of hierarchies, a hierarchy description vector is constructed for each data field, the number of co-occurrence times of value sequences of all the data fields in the same hierarchy is counted, and the number of co-occurrence times of value sequences of all the data fields in the same hierarchy is calculated; performing multilayer back propagation updating on semantics of each data field through a large model, adjusting a field embedding weight, calculating a coordination degree of each data field in the same hierarchy to obtain a hierarchy harmonic factor, calculating a stability degree of a semantic relationship of each data field in the hierarchy under a disturbance condition to obtain a semantic drift factor, and constructing a fusion matrix; and carrying out weight distribution and principal component space extraction on each level of data field in the fusion matrix, and calculating the deviation rate of each data field in the fusion matrix under the principal component space to obtain a data quality evaluation result. According to the invention, accurate evaluation of data quality is realized through a large model.

The application relates to the technical field of construction safety management, and discloses a power engineering construction safety management system, which comprises a real-time risk assessment scheduling unit, a forward-looking human factor risk perception unit and a risk simulation mapping unit. The real-time risk assessment scheduling unit is used for generating a safety state characteristic map based on heterogeneous safety data of a construction site, identifying a risk event of the construction site through the safety state characteristic map, and generating an intervention instruction and a resource scheduling scheme to optimize the construction site. The application can comprehensively capture multi-dimensional information of the construction site by collecting personnel biological characteristics, equipment operation logs, environmental indexes and work video streams and other heterogeneous safety data through a multi-modal perception unit, breaks the limitation of single and one-sided data collection in the traditional management mode, and enables management personnel to obtain more rich and comprehensive on-site safety information, so that the overall safety condition of the construction site can be more clearly understood.

The application relates to a low-cost three-dimensional mapping method, system, electronic equipment and storage medium based on a smart handheld mobile terminal, which collects data by using the smart mobile terminal, a civil equipment, and realizes alignment of each track in the Z-axis direction by constructing an elevation map based on the data, and finally performs three-dimensional reconstruction by using the aligned data. The smart mobile terminal, a handheld equipment, can be used to collect data on the ground in a good GPS signal and realize low-cost fast mapping.

The application discloses a pulmonary arterial hypertension recognition device and method based on multiple ECG and PCG signals, and relates to the technical field of biomedicine. The device comprises the following steps: limiting the landing points of the aortic valve closing candidate peak and the pulmonary valve closing candidate peak in the main peak anchor point time boundary and the ECG segment key turning point time interval of the double-anchored split segment set, performing adjacent beat backtracking replacement and multi-channel consistent voting reservation on the candidate peak of the cross-beat jump, and generating a physiological consistency split segment set; according to the physiological consistency split segment set, gathering the split sequence of the multiple PCGs, and performing beat-level splicing and window-in-consistency closure on the right heart load related morphological items of the multiple ECGs, and generating a pulmonary arterial hypertension recognition diagnosis set. The application realizes high-precision synchronization of multiple ECG and PCG signals, eliminates device differences and noise interference, guarantees the reliability of feature extraction, and improves the stability of pulmonary arterial hypertension recognition.

The invention relates to the technical field of image recognition, and discloses a multi-modal AI image recognition method and system applied to arrival goods acceptance of power equipment, and the method comprises the steps: obtaining multi-modal data of target equipment, and carrying out the standardization of the multi-modal data, and obtaining the standardized data; according to a preset acceptance standard, abnormal contours and thermal anomaly features in the data are extracted; performing cross-modal correlation analysis on the two features to obtain composite defect features; the composite defect feature confidence is evaluated, and a high-confidence evaluation report is generated; and combining acceptance standard matching report compliance to form a structured acceptance report. According to the scheme, the acceptance accuracy and compliance are improved, and the safety risk is reduced. According to the scheme, the problems of incomplete single-mode detection, unassociated multi-mode data, no confidence evaluation of results, difficulty in compliance matching of reports, easiness in missing judgment and existence of potential safety hazards in existing acceptance check are solved.

The invention provides a scene self-adaption-oriented evaluation index generation method, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the semantic analysis of an evaluation index demand description text corresponding to a target scene, and obtaining a global feature vector corresponding to the evaluation index demand description text; predicting a target formula template and a target atomic index set corresponding to the evaluation index demand description text based on the global feature vector; complementing the target formula template based on the target atomic index set to obtain a complemented formula; determining an executable code corresponding to the completion formula; and based on the verification result of the executable code, determining an evaluation index generation code corresponding to the evaluation index demand description text. According to the method, the evaluation index demand description text is intelligently deconstructed through semantic analysis, the difference of different scenes is eliminated, the evaluation index code is automatically generated, and the compatibility of different scenes and the code generation efficiency are improved.

The application relates to the air conditioner technical field and discloses an air conditioner, which comprises a vibration damping structure, a storage structure, an amplitude monitoring structure and a control structure. The vibration damping structure wraps a structure to be damped, and comprises a shell and a liquid damping medium. The shell is provided with an injection port, and the liquid damping medium is arranged in the shell and used for damping the structure to be damped. The storage structure is connected with the injection port and used for adding the liquid damping medium to the vibration damping structure. The amplitude monitoring structure is used for detecting the amplitude of the structure to be damped. The control structure is connected with the amplitude monitoring structure and the vibration damping structure, and is used for connecting the vibration damping structure and the storage structure in the state that the amplitude exceeds a first set value, filling the liquid damping medium into the shell until the amplitude is lower than the first set value. The application can make the air conditioner operate in a full frequency band and improve the modularity and universality. The application further discloses a method and device for the air conditioner.

The invention discloses a network equipment double-flow throughput testing method, and relates to the technical field of network equipment testing, and the method comprises the steps: carrying out the multi-group double-flow testing of target network equipment under the condition that the CPU utilization rate of the target network equipment is within a first set range, and obtaining the throughput of the target network equipment through the multi-group double-flow testing; determining a linear fitting relational expression between the tunnel traffic and the Internet traffic; dividing the tunnel traffic into a plurality of traffic levels, performing a double-traffic test on the target network equipment for the traffic level of each tunnel traffic, and collecting effective double-traffic data pairs of which the change rate of the CPU utilization rate is within a second set range; for the traffic level of each tunnel traffic, substituting the normalized tunnel traffic and Internet traffic into a linear fitting relational expression to obtain a fitting error, if the fitting error does not exceed a set value, determining that the test is valid, otherwise, re-fitting the linear fitting relational expression; and outputting the related data obtained by the test corresponding to the traffic level of each tunnel traffic. According to the invention, cross-device multiplexing can be realized.

The present application relates to the technical field of detection of Dendrobium polysaccharide content, and discloses a system and method for rapid nondestructive detection of Dendrobium polysaccharide content, which comprises the following steps: collecting spectral reflection data in the 600 nm-1700 nm band by using a FLA6800 spectrometer, and performing data preprocessing, feature extraction, machine learning model training and prediction to rapidly and accurately predict the Dendrobium polysaccharide content, and finally generating a visual report and performing grading. The present application combines near-infrared spectroscopy technology with a machine learning model to realize efficient, accurate and nondestructive detection of the Dendrobium polysaccharide content, significantly improves the detection speed and accuracy, and provides real-time and reliable quality control basis.

The application relates to the technical field of construction safety management, and discloses a power engineering construction safety management system, which comprises a real-time risk assessment scheduling unit, a forward-looking human factor risk perception unit and a risk simulation mapping unit. The real-time risk assessment scheduling unit is used for generating a safety state characteristic map based on heterogeneous safety data of a construction site, identifying a risk event of the construction site through the safety state characteristic map, and generating an intervention instruction and a resource scheduling scheme to optimize the construction site. The application can comprehensively capture multi-dimensional information of the construction site by collecting personnel biological characteristics, equipment operation logs, environmental indexes and work video streams and other heterogeneous safety data through a multi-modal perception unit, breaks the limitation of single and one-sided data collection in the traditional management mode, and enables management personnel to obtain more rich and comprehensive on-site safety information, so that the overall safety condition of the construction site can be more clearly understood.

The invention discloses slicing equipment and a wire arranging method thereof. The wire arranging method of the slicing equipment comprises the following steps: obtaining a standard position parameter when a standard winding reel is mounted on a shaft rod, so that a wire arranging mechanism defines a preset wire arranging starting point and a preset wire arranging terminal point on the standard winding reel; a winding reel is installed on the shaft rod, and an actual position parameter of the winding reel is obtained; comparing the actual position parameter with the standard position parameter by a processing device to obtain a position compensation parameter, so that the winding displacement mechanism adjusts the preset winding displacement starting point and the preset winding displacement ending point to be an actual winding displacement starting point and an actual winding displacement ending point respectively; and winding a cutting wire on the winding reel from the actual winding starting point to the actual winding ending point by the winding mechanism. Therefore, a standardized winding displacement process is provided, so that the winding displacement operation time is effectively shortened, and poor winding displacement quality caused by continuous tolerance accumulation in the winding displacement process is avoided.