7 results about "Weight value" patented technology

The invention provides a legal clause recommendation method, electronic equipment and a program product. The legal clause recommendation method comprises the steps that a collected legal text is analyzed based on a large legal language model in the vertical field, a legal knowledge dynamic graph is generated, and the legal knowledge dynamic graph comprises the logic relation, the conflict relation and the dynamic revision relation between legal clauses; nodes in the legal knowledge dynamic graph are labeled with timeliness tags and regional tags; performing judicial logic reasoning on the received case description according to the law big language model and the law knowledge dynamic graph, and determining a target law clause matched with the case description; based on a weight adjustment factor, a weight value corresponding to the target legal clause is determined, and the weight adjustment factor is used for describing the association degree between the target legal clause and the case description; and generating a legal clause recommendation report according to the weight value corresponding to the target legal clause.

The present invention discloses a scoring card modeling method and device based on five-fold cross validation, which defines a target variable; obtains original variable data to form a sample data set; performs binning on the original variable data, calculates the evidence weight value of each box variable, and the information value corresponding to the variable; uses the Pearson correlation coefficient to calculate the correlation between variables, and screens collinear variables; constructs a five-fold cross validation label based on the original variable data and the target variable; uses the five-fold cross validation label to randomly divide the sample data set into five parts, and uses the LightGBm algorithm to train the five-fold data respectively to obtain a scoring card model. The present invention can be well applied to the current credit scenario, fully mining the deep features in the massive third-party data to improve the distinguishing effect of the scoring card for different users.

The invention relates to the technical field of intelligent diagnosis, and provides a machine tool bearing diagnosis method and system based on improved SMOTE. According to the method, for the problem of data imbalance caused by scarcity of fault samples in bearing vibration signals, the vibration signals are obtained and processed into a feature sample set; identifying minority class fault samples, calculating weight values according to sample distribution of the minority class fault samples in the feature space, adaptively determining a generation area for each sample based on the weight values, and synthesizing new samples to balance data; and finally using the balanced sample set to train a fault diagnosis model for classification. According to the bearing fault diagnosis method, through weight-driven adaptive region adjustment, the classification boundary is effectively protected while the sample diversity is enhanced, the accuracy of bearing fault diagnosis is improved, and the missing report rate of minority class faults is effectively reduced.

The present invention provides a method for evaluating and controlling the comprehensive risk of oil and gas pipelines. The evaluation method includes: for each major factor affecting pipeline risk, determining n-level basic indicators respectively, where n≥2; determining the score of each basic indicator and the weight value corresponding to each basic indicator; for a single major factor, determining the score of each level of negative indicator and the score of each level of positive indicator step by step in ascending order; according to the score P Ni of the first-level negative indicator and the score P Si of the first-level positive indicator of a single major factor, determining the failure probability indicator P x of the single major factor; establishing a coupling action matrix of failure factors, and determining the correction value P' of the coupling action of different types of negative factors on the failure probability; determining the pipeline risk indicator score R. The evaluation method of the present invention fully considers the mutual relationship between risk influencing factors, can objectively evaluate the comprehensive risk of the pipeline, and reflects the true risk situation of the pipeline.

The application discloses a power infrastructure project risk assessment method based on a multi-factor dynamic weighting algorithm, and belongs to the technical field of project management. The steps include: filtering noise from original business flow data, normalizing and compressing the filtered data fields to obtain a standardized data set; stripping factors from the standardized data set to obtain an original risk factor spectrum; assigning weights to the original risk factor spectrum to obtain an initial weighted factor set; calling a weight correction coefficient matrix in a preset benchmark project database, and dynamically and iteratively calibrating the initial weight values to obtain a stage weight vector; weighting and reconstructing the initial weighted factor set to obtain a risk feature vector; matching the risk feature vector with a fuzzy membership degree to obtain an assessment conclusion; and standardizing and packaging the assessment conclusion, the risk feature vector and the stage weight vector to obtain a risk assessment data message. The application can improve the accuracy and efficiency of power infrastructure project risk assessment.

The invention discloses a flood early warning comprehensive dynamic index determination method, which comprises the following steps: collecting target index data, and normalizing each index value; calculating a subjective weight value and an objective weight value of each index data according to a subjective and objective combined weight method; the subjective weight value and the objective weight value are combined to calculate the consistency coefficient of subjective and objective weights, a long-term low-correlation index replacement mechanism is established, and then the weights are dynamically adjusted; determining a comprehensive dynamic index in combination with the corresponding index normalization data; risk grades are divided according to the numerical range of the comprehensive dynamic indexes, and a judgment basis is provided for decision makers. According to the method, various flood related factors are comprehensively considered, index weight values at different moments are calculated, a systematic early warning index determination method is constructed, the limitation of a traditional method is effectively overcome, flexible adaptation can be achieved according to real-time data and flood scenes, more accurate and more adaptive technical means are provided for flood early warning, and disaster prevention and reduction work is assisted.

The application provides a bridge construction risk assessment method, system, electronic equipment and storage medium, and belongs to the technical field of bridge construction safety; the method comprises the following steps: confirming a risk analysis total target of a target bridge; decomposing the risk analysis total target to construct a risk evaluation model of a layered structure; determining weight values corresponding to an evaluation set by using an analytic hierarchy process, and determining a risk evaluation grade based on the evaluation set and the weight values; scoring each evaluation factor in the risk evaluation grade to establish a membership matrix; performing operation on the membership matrix by using a comprehensive weighting method to obtain a fuzzy evaluation matrix; calculating a judgment matrix corresponding to the evaluation set according to the fuzzy evaluation matrix, and obtaining the risk grade of the evaluation set based on the maximum membership degree principle. The application determines the evaluation set composed of risk factors and the corresponding weight by using a hierarchical decomposition and analysis method, and quantifies the risk factors by using a fuzzy comprehensive evaluation method of mathematics, so that the comprehensiveness and accuracy of the evaluation result are improved.