Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

8results about How to "Small time complexity" patented technology

Load prediction method based on fusion of attention mechanism and spatio-temporal characteristics

The invention discloses a load prediction method for fusing an attention mechanism with spatio-temporal characteristics, and the method comprises the steps: obtaining a power load data set, and dividing the data set into a training set and a test set; collecting weather data, sorting according to importance by using a random forest algorithm, and selecting the first three significant features of the weather data as model input; vMD is applied to decompose the power load data into a plurality of local components, each component corresponds to a vibration mode in a frequency range, an RIME algorithm is utilized to iteratively optimize parameters in the VMD, and a subsequence component with the minimum complexity is obtained; and according to each decomposed sub-sequence component, combining the selected first three meteorological features as model input, constructing an energy consumption prediction model with an attention mechanism fused with spatio-temporal features, applying a parallel mechanism of a BiTCN model and a BiGRU model, processing time sequence data at the same time, and performing feature enhancement through a cross attention layer to obtain a prediction result.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO +1

Log matching method, device, equipment, storage medium and product

The present application provides a log matching method, device, equipment, storage medium and product. The method includes: obtaining a key text log and a target text log corresponding to a target object; determining a first digital number corresponding to each word in the key text log and a second digital number corresponding to each word in the target text log; using the first digital number and the second digital number to filter the key text log to filter out the key text log to be matched; matching the key text log to be matched with the target text log to obtain a target text log that matches the key text log to be matched. By filtering the key text log, the matching efficiency can be improved; by numbering each word in the log and filtering the key text log according to the first digital number and the second digital number, the efficiency of filtering the key text log can be improved, thereby improving the matching efficiency.
Owner:ALIBABA (CHINA) CO LTD

A sub-circuit matching method for analog integrated circuits

The present invention proposes a subcircuit matching method for analog integrated circuits, including: reading a circuit netlist file, defining node labels for component nodes in the circuit to distinguish; topologically analyzing the components respectively, generating a directed circuit topology diagram; sorting the node search order of the subcircuit, and dynamically selecting several nodes of the analog integrated circuit accordingly, thereby forming multiple node pairs and organizing them into a search tree, wherein a tree node of the search tree represents a subgraph state; adding the node pair to the tree node to form a new subgraph state, and when adding node pairs composed of nodes of the same subcircuit and nodes of different analog integrated circuits, the search tree forms different branches; pruning invalid branches in the search tree, thereby quickly matching the subcircuit and the nodes of the analog integrated circuit. The present invention has the effect of being able to achieve circuit matching with high accuracy and low computational complexity.
Owner:XIAMEN UNIV

A method for predicting the remaining life of rolling bearings

The present invention discloses a method for predicting the remaining life of a rolling bearing, comprising the following steps: S1, constructing fuzzy entropy as a rolling bearing performance degradation feature for the original vibration acceleration data of the rolling bearing in the source domain and the target domain; S2, inputting the training fuzzy entropy sample sets of multiple different source domains and the training fuzzy entropy sample sets of the target domain into the AAET-Crossformer model for training the parameters of the AAET-Crossformer model at the same time; S3, using the trained AAET-Crossformer model to hierarchically decode and predict the performance degradation characteristic trend of the rolling bearing in the target domain in the future; S4, establishing a three-parameter Weibull distribution reliability model to predict the failure threshold time point and RUL of the rolling bearing in the target domain. The prediction method of the present invention can achieve higher RUL prediction accuracy, better generalization performance and higher computational efficiency.
Owner:SICHUAN UNIV +1

Load forecasting method based on attention mechanism and spatiotemporal features

A load forecasting method using an attention mechanism to fuse spatiotemporal features, wherein an electric load data set is obtained and divided into a training set and a test set; weather data is collected and sorted by importance using a random forest algorithm, and the top three significant features of the weather data are selected as model inputs; VMD is applied to decompose the electric load data into multiple local components, each component corresponds to a vibration mode within a frequency range, and the parameters in VMD are iteratively optimized using a RIME algorithm to obtain a subsequence component with the least complexity; an energy consumption forecasting model using an attention mechanism to fuse spatiotemporal features is constructed based on the decomposed subsequence components and the top three selected meteorological features as model inputs, and a BiTCN model and a BiGRU model are used in parallel to simultaneously process time series data, and feature enhancement is performed after passing through a cross-attention layer to obtain a forecasting result.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO +1

Method, device, equipment and readable storage medium for simplifying triangular mesh model

The present invention discloses a method, device, equipment and readable storage medium for simplifying a triangular mesh model. The method comprises: in the process of simplifying a first triangular mesh model into a second triangular mesh model, simplifying the to-be-folded edge in the first triangular mesh model into a folding point in the second triangular mesh model; calculating the face error distance of each triangular face in a one-ring neighborhood of two vertices of the to-be-folded edge according to the face error distance of each triangular face in a one-ring neighborhood of the folding point; calculating the model error distance of the second triangular mesh model relative to the initial triangular mesh model according to the face error distance of all triangular faces in a one-ring neighborhood of the folding point; judging whether the model error distance is greater than a preset error threshold, if so, stopping the simplification operation on the second triangular mesh model, if not, continuing the simplification operation on the second triangular mesh model; the BIM model can be simplified efficiently and quickly.
Owner:GLODON CO LTD

A data storage method and apparatus

ActiveCN116028497Bsmall time complexitysave storage spaceDatabase indexing
This disclosure provides a data storage method and apparatus. The method includes: acquiring target data to be stored; reading a bitmap structure from a database based on a target identifier in the target data; and determining the mode of the bitmap structure. When the bitmap structure is determined to be in a variable-length mode, writing a target time from the target data into a newly added time unit in the data portion of the bitmap structure, wherein the data portion of the variable-length bitmap structure contains at least one time unit. When the bitmap structure is determined to be in a fixed-length mode, setting corresponding data bits in the data portion of the bitmap structure based on the target time in the target data, wherein the storage location of each data bit in the data portion of the fixed-length bitmap structure corresponds to a time point. This method can reduce the space occupied by data storage, thereby reducing storage costs, and improve the efficiency of data retrieval, thereby reducing query latency.
Owner:ZHEJIANG ZEEKR INTELLIGENT TECH CO LTD +1

Method and device for analyzing and early warning electricity consumption behavior of intelligent electric energy meter

PendingCN119624019ARealize the function of early warningsimple methodData processing applicationsStatistical analysisElectric consumption
The invention discloses an intelligent electric energy meter power consumption behavior analysis early warning method and device, and the method comprises the steps: generating a daily power consumption sequence of a user in the first seven days at a time interval of 0.5 h, and further generating a power consumption summary sequence in the first seven days; generating a comprehensive electricity consumption valley interval and a comprehensive electricity consumption peak interval according to the electricity consumption summary sequence of the first seven days, and calculating the average electricity consumption in the comprehensive electricity consumption valley interval and the average electricity consumption in the comprehensive electricity consumption peak interval; generating a real-time electricity consumption sequence of the ith day of the user by taking 0.5 hour as a time interval; delimiting a real-time electricity consumption trough interval and a real-time electricity consumption peak interval for a real-time electricity consumption sequence according to the comprehensive electricity consumption trough interval and the comprehensive electricity consumption peak interval; and according to the delimited real-time electricity consumption valley interval and the delimited real-time electricity consumption peak interval, judging an electricity consumption abnormal condition, and sending early warning information to the intelligent terminal of the user. According to the method, the electricity consumption behavior is subjected to statistical analysis, electricity consumption abnormity early warning is achieved, and the space-time complexity is small.
Owner:S P ELECTRIC