90 results about "Weight factor" patented technology

The invention discloses an underground pipeline intelligent detection and mapping method based on image recognition, and the method comprises the following steps: 1, obtaining continuous video images, associating feature matching pairs of adjacent key frames, and forming a pose parameter set; 2, inputting the key frame into an improved YOLO-World detection network, and outputting a detection result set; 3, obtaining a geometric consistency matching set according to the detection result set; 4, performing multi-view triangularization on the geometric consistent matching set to form a weight factor; 5, introducing a weight factor, and executing incremental beam adjustment optimization on the pose parameter set and the three-dimensional sparse point set to obtain a sparse semantic point cloud; and step 6, outputting an underground pipe network topology map. According to the invention, high-precision and high-robustness intelligent identification and topological mapping in a complex underground pipeline environment are realized.

The invention provides a high-resolution DOA (direction of arrival) estimation method and system, and the method comprises the steps: updating a model covariance matrix based on a to-be-corrected space power spectrum and noise information of the iteration of this round, thereby obtaining a direction dependence weight factor, and carrying out the estimation of the direction dependence weight factor. And according to the direction dependence weight factor of the current round of iteration, the to-be-corrected spatial power spectrum, the model covariance matrix and the sample covariance matrix, predicting the to-be-corrected spatial power spectrum and noise information of the next round of iteration, and finally obtaining the spatial power spectrum. According to the method, on the premise that the number of prior information sources is not needed, the problem of spectrum peak merging of a traditional sparse method under the condition of adjacent information sources is solved, stable separation of near-angle incoming waves is achieved, and the high-resolution performance of DOA estimation is remarkably improved.

The invention provides a landslide mass recognition method and device, equipment, a storage medium and a program product, and can be applied to the field of landslide mass recognition. The method comprises the following steps: based on a landslide mass identification model, respectively carrying out feature extraction on images from a plurality of modalities to obtain extraction features corresponding to the images; converting the extracted features into corresponding frequency domains and carrying out frequency domain compression to obtain frequency domain features corresponding to the image; converting the frequency domain features into weight factors, and obtaining weighted features corresponding to the images according to the weight factors and extraction features corresponding to the same image; splicing the weighted features of the images to obtain fusion features; processing the fused features through a multilayer dense network, and carrying out multiple interpolations on the processed features by using a bilinear interpolation method; and obtaining the category of each pixel in the features after multiple interpolations by using a maximum parameter value decision method, and determining the landslide mass.

The invention discloses a unified identity generation method. The method comprises the following steps: acquiring a plurality of advertisement request events, wherein each advertisement request event comprises at least two mutually associated feature identifiers; according to the plurality of advertisement request events, determining a plurality of feature identifiers and association relationships among the plurality of feature identifiers, each association relationship having a corresponding event time; a connected subgraph is generated by taking a group of feature identifiers with the incidence relation in the plurality of feature identifiers as nodes and taking the incidence relation between the feature identifiers as edges, each edge of the connected subgraph has a corresponding weight factor, and the weight factor is attenuated along with the event time of the corresponding incidence relation; and generating a corresponding unified identity label based on the connected sub-graph.

The invention belongs to the technical field of electric valves, and provides a valve health state monitoring system and method.The method comprises the steps that a data processing module collects and preprocesses multi-dimensional parameters of an electric valve sealing piece, a gear and a carbon brush in real time by constructing a fusion sensor array, and a key component comprehensive monitoring data set is formed; the key component life module constructs a residual life prediction model of the carbon brush, the gear and the sealing element based on an accumulative damage theory and the data set; the similarity analysis module calculates an initial weight factor of a historical failure case, and calculates the similarity in combination with a residual life prediction result; the similar sample module screens similar samples to form a sample set so as to obtain an advanced weight factor set; a fitting weight factor screening module screens out a fitting weight factor based on the residual life similarity; the comprehensive prediction model construction module constructs an electric valve comprehensive prediction model by using the fitting weight factors; and the maintenance module performs prediction based on the model and gives maintenance suggestions.

The invention relates to the technical field of gear box state evaluation, and discloses a vehicle gear box state evaluation method, which comprises the following steps: S1, collecting physical and chemical performance data of oil in a gear box; s2, preprocessing the collected data through an independent component analysis (ICA) method, and screening out a data set which can be used as model input; dividing the model input data set into a test data set and a training data set; s3, improving a RBMO (Red Blue Mark Optimization) algorithm, including initializing an RBMO population through a Latin hypercube sampling method to improve the population initialization uniformity; a spiral search strategy is introduced in the RBMO foraging stage, so that the red-mouth blue-streak search efficiency is improved; in the RBMO attack stage, a weight factor is introduced to optimize the position update of the red-beaked blue-streak, and an improved red-beaked blue-streak optimization algorithm IRBMO and the like are obtained; according to the method, the defect of blindness of parameter selection in the training process is overcome, and the prediction precision of the regression prediction model is improved.

The invention discloses a popularity evaluation method and device, equipment and a storage medium, and relates to the technical field of big data, and the method comprises the steps: obtaining current operation data of a current service, and constructing a current item set according to index items exceeding a corresponding index range in the current operation data; matching the current item set with the frequent item set, and determining at least one target association rule corresponding to the current item set in the strong association rules according to the matched target frequent item set; determining a popularity index of the current service according to the exceeding degree of each index item in the current item set and the rule attribute and the weight factor of each target association rule; and determining the current popularity level of the current service according to the popularity index and the index interval corresponding to each popularity level. According to the technical scheme, the popularity level of the service is determined according to the popularity index of the service, accurate judgment of the popularity level of the service is achieved, an accurate data basis is provided for operation and maintenance of a service system according to the popularity level, and the operation and maintenance effect is improved.

The invention relates to the technical field of big data, particularly provides a target trajectory and behavior analysis method and device based on a clustering algorithm, and a medium, and aims to solve the technical problem that the accuracy of abnormal behavior prediction of a target person by an existing method is relatively low. In order to achieve the purpose, the target trajectory and behavior analysis method based on the clustering algorithm comprises the steps that historical trajectory information of a target object is acquired; performing feature extraction on the historical track information of the target object to obtain a feature matrix; determining a weight factor corresponding to the historical track information; clustering the feature matrix based on the weight factor to obtain a clustering result; and predicting the abnormal behavior of the target object based on the clustering result. By adding the weight to the historical data from the space-time dimension, the defect of the historical data is effectively made up, the accuracy of the clustering result is improved, and thus the abnormal behavior of the user can be accurately predicted.

The invention discloses a binocular vision naked eye 3D image processing method, device and system, and particularly relates to the technical field of naked eye 3D. According to the method, the foreground and background areas are defined, a parameter extraction and merit figure quantification calculation system covering parallax, scenes and splicing dimensions is constructed, and the multi-scene preset threshold and the weight factor are combined, so that comprehensive and accurate evaluation of the naked eye 3D image quality is realized, the problem of one-sided evaluation of a traditional single index is solved, and the evaluation efficiency is improved. And the core crux influencing the three-dimensional effect is accurately positioned.

The invention relates to the technical field of measurement, in particular to a float-type water level gauge dynamic compensation detection method which comprises the following steps: collecting float angle sequence data; synchronously acquiring environment disturbance parameters; calculating the floater angle sequence data to obtain a preliminary water level value; constructing a dynamic compensation model, and outputting an inertia force correction term, a fluid damping correction term and a mechanical hysteresis correction term; the inertia force correction term, the fluid damping correction term and the mechanical hysteresis correction term are multiplied by corresponding weight factors respectively, then algebraic sum is solved, a total compensation amount is obtained, and the weight factors are dynamically adjusted and normalized according to the current wave high energy spectral density, the wind speed gradient change rate and the water temperature viscosity correction coefficient; and deducting the total compensation amount from the initial water level value, and outputting a final compensated water level value. According to the method, the problems of poor multi-physical field sensing capability and poor online parameter identification capability of a compensation method in the prior art are solved.

The invention discloses an electric vehicle charging load prediction method in a low data quality scene, and relates to the technical field of electric vehicles, and the method comprises the steps: obtaining a first feature; setting a dynamic space-time weight factor according to the first feature; according to the dynamic space-time weight factors, vacancy values in the space-time associated charging power matrix are complemented, and complete target charging power matrix data are obtained; constructing a three-dimensional input tensor according to the complete target charging power matrix data; inputting the three-dimensional input tensor into a first model to obtain a charging load predicted value; performing trend verification on the charging load prediction value and historical charging load data to obtain a prediction trend; and if the difference value between the prediction trend and the historical trend exceeds a preset threshold value, correcting the charging load prediction value based on the change rate of the historical trend to obtain a target electric vehicle charging load prediction result. According to the method, high-precision load prediction can be realized, and powerful support is provided for power grid demand response.

The invention discloses a tight oil and gas reservoir horizontal well volume fracturing fracture network wave and volume prediction method, which comprises the following steps of: based on geological engineering parameters of a fractured horizontal well and microseism monitoring fracture volume data, calculating weight factors of each geological and engineering parameter by establishing a multi-factor evaluation model; aiming at a to-be-predicted fracturing section, combining the solved weight factor and the geological parameters of the perforation positions of the fracturing clusters in the fracturing section, and calculating a fracturing crack-making efficiency coefficient representing the distribution uniformity of fracturing fluid; multiplying the original micro-seismic monitoring fracture volume of the fractured section by the calculated fracture forming efficiency coefficient to obtain a corrected effective fracture network wave and volume; according to the method, the fracture forming efficiency coefficient is introduced to correct the original microseismic monitoring volume, the problem that prediction results of an existing method are generally large is solved, accurate quantitative prediction of the effective fracture network waves and the volume is achieved, and a scientific basis is provided for fracturing effect evaluation and scheme optimization.

The invention discloses a two-parameter temperature control method for a quantum computing measurement and control system, which comprises the following steps of: firstly, determining a difference value between a current temperature and a target temperature, namely a current instantaneous temperature difference as a first parameter, calculating a change rate of the temperature difference in unit time in real time as a second parameter, and calculating to obtain a fan rotating speed compensation value through a formula =; k is a dynamic adjustment coefficient and is a weight factor of the change rate of the temperature difference in unit time. The invention further discloses a two-parameter temperature control system for the quantum computing measurement and control system. According to the method, a two-parameter coupling formula is provided, a proper fan rotating speed compensation value is calculated, self-adaptive accurate temperature control is achieved, the method is suitable for fan rotating speed adjustment under different environment temperature conditions, and the method has wide applicability.

The invention provides a student behavior prediction method based on multi-modal data fusion, and the method comprises the steps: predicting a missing value through a data entropy calculation formula if a reliability and integrity score is lower than a preset threshold value, and complementing a heterogeneous feature set through information uncertainty quantification, thereby obtaining a complemented feature set; extracting a feature mode through the complemented feature set, calculating the contribution degree of each data source type by adopting a weight distribution basis, and generating an integrated feature vector by dynamically adjusting a threshold value; if the contribution degree distribution does not meet the uniformity standard, adjusting the weight proportion according to the importance of the data source type, and generating an adjustment weight vector through entropy normalization processing and algorithm iterative loop; and if the confidence fusion rule displays a deviation mode, optimizing a scene adaptation index through weight factor updating and real-time state feedback, and determining the reliability of an evaluation result.

The invention discloses an offshore wind turbine generator stochastic dynamics analysis method capable of processing high-dimensional stochastic factors, which comprises the following steps of: establishing a self-adaptive weight factor-based uniform subdivision technology, and obtaining a high-dimensional stochastic input variable of a structure in a complex environment; deriving a probability density integral equation of the offshore wind turbine generator with high-dimensional random factors, and depicting a structural uncertainty propagation process; solving the probability density integral equation by adopting a direct probability integral method based on a uniform subdivision technology to obtain a probability density function of the structural response of the wind turbine generator; and in combination with equivalent extreme value mapping, a direct probability integral method based on a uniform subdivision technology is further used for solving the fatigue reliability of the wind turbine generator. According to the self-adaptive uniform subdivision technology based on the weight factors, the weight factor solving process and the representative point selecting process are decoupled, the representative points of the high-dimensional probability space can be generated in a self-adaptive mode, the assignment probability of the representative points is calculated based on the weight factors, and the random factors of the structure in the complex environment are obtained.

The invention belongs to the field of aircraft landing, and particularly relates to an aircraft automatic landing flight quality evaluation method, which divides a landing process and analyzes the influence of different landing stages on arresting landing, determines evaluation indexes of each stage, a decision point and a touch plate point, and then establishes a comprehensive evaluation system of the landing process. The method comprises the following steps of: firstly, obtaining a weight factor of an evaluation index system by utilizing an expert scoring method, and introducing different membership functions to score an evaluation index; and finally, obtaining a comprehensive evaluation score of the automatic landing process of the aircraft by combining the evaluation score of the index in each stage and the weight factor of each level. By evaluating the automatic landing process and constructing a comprehensive evaluation system, the systematicness and logicality of the evaluation method are improved; a weight factor is obtained by utilizing an expert scoring method, so that the trueness of an evaluation result is improved; and engineering realization is easy.

The invention discloses a pressure control method and system for a marine ammonia fuel supply system based on model-free self-adaptive control, and the method employs a model-free self-adaptive control scheme based on tight format dynamic linearization, and carries out the real-time collection of system pressure and valve control quantity data. And dynamically estimating a pseudo partial derivative phi (k) on line to capture system characteristics, and designing an adaptive control law to calculate a valve opening instruction according to the system characteristics. A dual-robust mechanism is formed by introducing an estimation weight factor mu and a control weight factor lambda, and noise interference and controlled quantity mutation are effectively suppressed. The method can automatically adapt to system dynamic change and external disturbance, high-precision and strong-robustness stable control over the ammonia fuel supply pressure is achieved under the complex ship working condition, and the safety and reliability of the ammonia power ship are remarkably improved.

The present invention discloses a side milling cutter position planning method for weight adjustment of non-developable ruled surfaces. The method first completes the non-developable ruled surface construction based on the original control points; secondly, the original two-point offset algorithm is used to obtain the initial tool axis vector with equal parameters, and the maximum overcut position of the corresponding side milling area is solved; then the maximum overcut offset position and the initial tool vector are used to form two segmented vectors, and the weight factor is calculated; finally, the side milling cutter axis vector after weight adjustment is obtained. In addition, the method calculates different weight factors for different distortion positions, which can be better adapted to the side milling of non-developable ruled surfaces. The present invention focuses on the side milling processing errors of non-developable ruled surfaces, especially the overcut and individual positioning tool errors, and completes the purpose of outputting the tool axis vector by the weight optimization algorithm with the initial tool axis vector as the starting point, thereby improving the side milling processing accuracy and efficiency, and providing certain technical support for the field of modern mechanical manufacturing and processing.

The application discloses a kind of compact oil and gas reservoir horizontal well volume fracturing fracture network swept volume prediction method, including, based on the geology engineering parameter of implemented fracturing horizontal well and microseismic monitoring fracture volume data, the weight factor of each geology and engineering parameter is calculated by establishing multi-factor evaluation model;For the fracturing section to be predicted, the weight factor obtained is combined with the geology parameters of each fracturing cluster perforation position in the fracturing section, and the fracturing fracture efficiency coefficient for characterizing fracturing fluid distribution uniformity is calculated;The original microseismic monitoring fracture volume of the fracturing section is multiplied by the calculated fracturing fracture efficiency coefficient, and the corrected effective fracture network swept volume is obtained;The original microseismic monitoring volume is corrected by introducing the fracture efficiency coefficient in the application, the problem that the prediction result is generally large in the prior art is overcome, and accurate quantitative prediction of effective fracture network swept volume is realized, which provides a scientific basis for fracturing effect evaluation and scheme optimization.

The embodiment of the invention discloses a grease spraying amount adjusting method and system, electronic equipment and a storage medium, and relates to the technical field of food processing.The method comprises the steps that key factors influencing the product demolding difficulty are obtained through a single-factor test to serve as calculation variables, deriving a weight factor of the calculation variable and a calculation formula of a standard spraying amount based on data experience, calculating to obtain the standard spraying amount of the product according to formula data of the product and the calculation formula of the standard spraying amount, and setting corresponding spraying parameters according to the standard spraying amount. And grease spraying is conducted on a production line of the product according to the spraying parameters, and feedback adjustment is conducted on the spraying parameters according to the demolding effect of the product in actual production till the demolding effect meets the set requirement. The problems that in the prior art, process fluctuation cannot be responded in real time, repeated debugging depends on artificial experience, scientific calculation basis is lacked, and resource waste is serious are solved.

The invention discloses a weight factor design method based on data driving, and a model prediction control method and device. The model prediction control method comprises the following steps: acquiring a state variable of a T-type three-level energy storage converter at a k moment; establishing a discrete mathematical model of the T-type three-level energy storage converter in a two-phase static alpha-beta coordinate system, and obtaining a reference value of the power grid current at the k + 1 moment according to the Lagrange extrapolation theorem; optimizing a weight factor of a neutral-point voltage balance item on line; determining candidate voltage vectors based on a voltage vector conversion rule; calculating the cost function value of each candidate voltage vector through a cost function, and selecting the voltage vector corresponding to the minimum cost function value as the optimal voltage vector of the kth control period; and applying the gate driving signal corresponding to the optimal voltage vector and the action time of the optimal voltage vector to a power electronic semiconductor device of the T-type three-level energy storage converter. According to the method, the weight factors can be optimized online, and the design process of the weight factors is greatly simplified.

The present application relates to the technical field of measurement, and more particularly to a dynamic compensation detection method for a float type water level meter, which comprises: collecting float angle sequence data; synchronously collecting environmental disturbance parameters; performing calculation on the float angle sequence data to obtain a preliminary water level value; constructing a dynamic compensation model to output an inertial force correction term, a fluid damping correction term and a mechanical hysteresis correction term; multiplying the inertial force correction term, the fluid damping correction term and the mechanical hysteresis correction term by corresponding weight factors respectively, and then obtaining an algebraic sum of the three terms to obtain a total compensation amount, wherein the weight factors are dynamically adjusted according to the current wave height energy spectrum density, the wind speed gradient change rate and the water temperature viscosity correction coefficient, and are subjected to normalization processing; and deducting the total compensation amount from the preliminary water level value to output a final compensated water level value. The present application solves the problems of poor multi-physical field sensing ability and poor online parameter identification ability of the compensation method in the prior art.

The present application discloses an information detection method and apparatus for improving the accuracy of target recognition. The method includes: for each feature of the detection target, comparing the feature with the main feature vector in the feature database corresponding to the feature to obtain the comparison similarity of the main feature vector of the feature; and comparing the feature with the auxiliary feature vector in the feature database corresponding to the feature to obtain the comparison similarity of the auxiliary feature vector of the feature; for each feature, determining the weight factor and similarity corresponding to the feature based on the comparison similarity of the main feature vector of the feature, the comparison similarity of the auxiliary feature vector of the feature, the preset main feature weight factor, and the auxiliary feature weight factor; determining the normalized weight factor of the detection target by using the weight factor corresponding to each feature of the detection target; and determining the comprehensive similarity of the detection target by using the normalized weight factor of the detection target and the similarity corresponding to each feature of the detection target.

The invention provides a wheel wear detection method and system. The method comprises the following steps: calculating a measurement parameter value of wheel tread measurement data; determining a control point coordinate and a curve weight factor according to the measurement parameter value, and constructing a tread curve after wheel abrasion according to the control point coordinate and the curve weight factor; calculating a difference area of a difference region between the tread curve after wheel abrasion and the wheel tread measurement data, and performing iterative optimization on a curve weight factor according to the difference area to obtain a weight factor combination; and obtaining the operation mileage of the to-be-tested train wheel, and determining the wheel abrasion value according to the operation mileage and the weight factor combination. According to the embodiment of the invention, the quantitative mapping relation between the abrasion characteristic parameter and the wheel abrasion value is constructed by taking the weight factor combination as the abrasion characteristic parameter, so that the corresponding wheel abrasion value can be automatically calculated after the operation mileage of the train wheel to be measured is obtained, and the specific condition of wheel abrasion can be intuitively reflected.

The application discloses a novel traffic scene target detection evaluation method and system, and relates to the technical field of target detection model performance evaluation. The application obtains the prediction result of a target detection model, determines true positive TP or false positive FP based on the matching relationship between the prediction frame and the real label, and respectively calculates the position weight factor and the scale weight factor. Then, the application obtains PSTP / PSFP by weighting TP / FP, constructs a position-scale weighted PR curve, and integrates to obtain the position-scale weighted average precision PSAP. The application can significantly improve the evaluation sensitivity of edge regions and small-scale high-risk targets, support scene adaptation and security level linkage, and make the evaluation results more suitable for the actual safety needs of automatic driving.

To provide a weighting factor determination device, a weighting factor determination method and a program, that can set a weighting factor of an evaluation function used for solving an optimization problem to a value suitable for the optimization problem.SOLUTION: A weighting factor determination device 200 comprises: calculating a calculated value di'_sim when a value of an evaluation function J is maximum or minimum for variables in an evaluation function that define an evaluation index ei' included in the evaluation function J by algorithm of a first optimization problem; calculating the value of a difference evaluation index |di'_sim-di'_opt| for evaluating the difference between the calculated value di'_sim of the variable in the evaluation function and a preset optimal value di'_opt of the variable in the evaluation function; and determining an optimal solution wi_opt for the weighting factor based on a calculated difference evaluation index value.SELECTED DRAWING: Figure 2

The present application provides a kind of geologic multi-source constraint adaptive full waveform inversion method and system, constructs multiple complementary constraint norms, organically fuses multiple modal prior information, forms unified multi-source constraint framework, compared with traditional single type prior constraint, the present application can more comprehensively utilize available prior information, guide inversion to the direction that both conforms to geophysical data and geological understanding converges;While introducing adaptive regularization parameter strategy based on Bayes theory, realize the adaptive update of weight factor, avoid the subjectivity and randomness caused by the dependence of regularization parameter on experience selection in traditional method, make the inversion result more stable, and do not need tedious manual parameter adjustment, can dynamically adjust the constraint strength according to the data noise level, enhance the guiding role of prior constraint in low signal-to-noise ratio, more rely on observation data in high signal-to-noise ratio;At the same time, through the combination of model compression and forward simulation calculation, the calculation efficiency is greatly improved.

The present invention discloses an item recommendation algorithm based on latent features and ratings, including: processing input data, extracting user rating data, and constructing a user-item rating matrix; introducing an activity penalty factor to calculate the similarity of a collaborative filtering algorithm; introducing a time factor and a penalty factor to penalize active users, and calculating the Pearson similarity based on time weight; based on an introduced item popularity weight factor, using an exponential function to replace the popularity difference between two items and integrating it into the Pearson similarity calculation; using the weighted sum of the two similarities as the final similarity, and sorting from large to small, obtaining the first k items that are most similar to the item to form a similar item set; introducing a time weight function, calculating the user's predicted interest in unrated items and sorting them, and recommending the first N items to the user. The present invention can realize personalized recommendations, improve the accuracy of recommendations and the user's experience.

The invention provides an analysis, early warning and release system based on a flood inundation condition, and relates to the technical field of flood early warning, the system comprises a constant flow special monitoring module, a probability forecast analysis module and a flood discharge risk analysis module, and the constant flow special monitoring module collects river data and rainfall data; judging whether flood analysis is started or not through risk index calculation; the probability forecast analysis module determines a weight factor based on historical data of each prediction model, obtains water level prediction data in combination with real-time water surface change data, and calculates a water area risk index to realize flood early warning; the flood discharge risk analysis module evaluates a flood discharge point use index according to historical flood discharge data, sets a monitoring point, calculates a flood discharge demand index by combining a water level, embankment stress and the like, and performs early warning on a risk flood discharge point, the system has multi-module cooperation and multi-dimensional analysis, flood risk early warning and flood discharge decision can be accurately realized, and the flood disaster prevention and control capability is effectively improved.

This invention relates to the field of image data processing technology, and more particularly to a method and system for processing store sales data. The method includes: acquiring reference samples and actual sales figures for each store, as well as samples to be predicted for which store sales figures need to be predicted; training a random forest algorithm and using the trained model for prediction; designating any prediction tree in the trained model as the target tree and determining the accuracy of the target tree; determining the weight factors for the samples to be predicted when using the target tree for prediction; and determining the final predicted sales figures for the samples to be predicted, thereby achieving store sales data processing. This invention dynamically allocates weight factors for each tree by comprehensively considering multiple dimensions such as the training sample coverage, prediction error of unselected samples, and sample path homogeneity of a single decision tree, avoiding interference from low-quality predictions on the final result and improving the accuracy and reliability of store sales prediction.