24results about How to "Implement mining" patented technology

The invention belongs to the technical field of biological feature recognition, and relates to a Transform-based gene data mining method, which comprises the following steps of: loading gene expression data from a file, and preprocessing; inputting the data into a designed model for training and evaluation; the designed model comprises a CNN (Convolutional Neural Network) and an improved Transform model; the improved Transform model comprises an encoder and a classifier; the encoder adopts a multi-head self-attention mechanism, a convolutional self-attention mechanism and a feedforward neural network; processing the data by using the trained model, and storing the fusion attention weight obtained by the coding layer in the data processing process; and finally, averaging the fusion attention weights of all batches, calculating the comprehensive attention weight of each gene at different time points, and identifying the most important gene by calculating and analyzing the attention score of each gene. According to the method, the problems of scarcity and imbalance of gene data can be solved, the risk of overfitting is reduced, and the precision of gene data analysis is improved.

The invention belongs to the technical field of energy storage, and relates to a lithium battery energy storage system nonlinear capacity recession trajectory prediction method, which comprises the following steps: collecting discharge data of a first cycle period and an mth cycle period of a lithium battery, and extracting a voltage-capacity curve of the mth cycle period from the discharge data; the method comprises the following steps: extracting a voltage-capacity curve of an mth cycle period, extracting a capacity increment curve and a capacity difference curve of the mth cycle period on the basis of the voltage-capacity curve, respectively constructing GASF (Gramian Angle Summation Field) graphs on the basis of the voltage-capacity curve, the capacity increment curve and the capacity difference curve, and combining to form a multi-channel format as the input of a prediction model. The method comprises the following steps: firstly, acquiring a degradation track, outputting a degradation track key node on the basis of a prediction model, then integrating the predicted degradation track key node with battery state of health (SOH) information of an mth cycle period, realizing the reconstruction of a capacity degradation track through a three-time Hermite Interpolation Polynomial (PCHIP), realizing data information mining through the collection of early data, and finally realizing the reconstruction of the capacity degradation track. Therefore, the model obtains sufficient degradation information, precise trajectory prediction is realized, the degradation process information of the lithium battery is mastered in the early stage, and time margin is provided for operation and maintenance of an energy storage system.

The present invention discloses a system and method for collecting and importing data of a special disease database based on a dynamic form, comprising a data collection and organization module, a subject database data set creation module, a dynamic form design and management module, a special disease database data configuration management module, a special disease database data retrieval module, and a data visualization module. The data collection and organization module is used to collect user input data, the subject database data set creation module is used to create different subject data sets, the dynamic form design and management module is used for form design and visualization management, the special disease database data configuration management module is used for configuring data and mining analysis, the special disease database data retrieval module is used for data retrieval, and the data display and analysis module is used for visualization display. The present invention discloses a system and method for collecting and importing data of a special disease database based on a dynamic form, proposes a dynamic form design algorithm based on a probability model to design a dynamic form, and proposes a special disease database data mining algorithm based on a neural network to perform data mining analysis.

The present application relates to the field of biological identification, and provides a multi-modal impression identification method based on causality, which comprises obtaining first multi-modal data of a speaker and second multi-modal data of a listener; performing causality identification on the first multi-modal data and the second multi-modal data through a preset causality model to obtain first features; performing feature extraction on the second multi-modal data through a preset first BLSTM network to obtain second features; performing cross-domain fusion on the first features and the second features through a preset attention network to obtain first fusion features; and performing impression identification on the first fusion features through a preset full connection network to obtain a first impression identification result. The preset causality model is set to capture the causality between the speaker and the listener. The preset attention network is set to realize cross-domain fusion of the related information between the two, improve the accuracy of impression identification, and improve the performance of identifying impressions from a single aspect.

The present application relates to the technical field of power distribution network planning, and more particularly to a power distribution network multi-resource integrated planning method and system based on a graph neural network. The method comprises the following steps: collecting the operation and geographic data of the distribution transformers, feeder switches, 10kV feeders and each load access point in the target planning area to form a basic planning data set; constructing a power distribution network topology graph and using a graph neural network to identify overloaded feeder sections, low-voltage end sections and overloaded transformer nodes; then, according to the spatial position and power supply correlation of each problem area, determining the distribution transformer capacity expansion layout, tie switch addition and line extension reconstruction path; and finally, optimizing and outputting the target area planning scheme through power flow checking. The present application identifies the weak links of the power distribution network through a graph neural network and cooperatively optimizes the capacity expansion layout, tie transfer and line extension path, thereby achieving the precision, collaboration and economy of power distribution network planning and significantly improving the power supply capacity and overall operation reliability.

The utility model belongs to the technical field of rotary excavating equipment for foundation pits, and particularly relates to a two-wheel type electric T-shaped square pile drill bit. According to the specific technical scheme, the device comprises a box body, rotatable excavating parts are coaxially arranged on the two sides of the box body, an expanding excavating part matched with a T-shaped square pile hole excavating protruding part is arranged on the periphery of an excavating wheel body of one excavating part, and the expanding excavating part and the excavating parts rotate synchronously; the expanding excavating part comprises a supporting and fixing part connected with the excavating part, and an expanding excavating element is arranged on the side, away from the excavating part, of the supporting and fixing part.

The present invention proposes a charging demand prediction system for new energy vehicle charging stations based on big data, which relates to the technical field of charging demand prediction. The specific implementation steps include: first, collecting vehicle images and identifying them through high-definition cameras to obtain vehicle flow data, and at the same time obtaining charging pile distribution, geographical distribution, historical charging data and meteorological data; second, cleaning and processing the acquired data, and constructing a charging station spatial relationship diagram; then, by analyzing the similarity of historical data sequences, determining time series key data; finally, based on the charging station spatial relationship diagram and time series key data, constructing a charging quantity prediction model, thereby predicting future charging quantity and determining whether to update the model. The system not only improves the accuracy of charging demand prediction, but also optimizes the resource configuration of charging stations. It can monitor and dynamically adjust the charging strategy of charging stations in real time, thereby improving the utilization efficiency of charging facilities.

The invention relates to the technical field of feed water heater operation performance analysis, and provides a nuclear power feed water heater operation performance analysis method which comprises the following steps: calculating a pipe side state according to pipe side measuring point data of a feed water heater, calculating states of a feed water heater shell side and a drain outlet pipeline, and calculating heat exchange performance of a condensation zone. Comprising condensation zone heat transfer efficiency and condensation heat transfer coefficient. The operation performance and the interface thermodynamic state of the nuclear power plant feed water heater can be efficiently and accurately analyzed.

The invention relates to a signal modulation identification method based on mixed mode comparison and fusion, and the method comprises the steps: mining the feature representation of a modulation signal through employing an image mode represented by a time-frequency spectrogram and a sequence mode represented by an A / P sequence; a feature extractor comprising an image encoder and a sequence encoder is obtained through label-free bimodal comparison self-supervision pre-training, and then a trained signal modulation recognition model is obtained after supervision fine tuning is conducted through modal-level feature fusion; and carrying out modulation identification on the received signal by adopting the model to obtain a modulation classification result. According to the method, the hidden features of the signals can be extracted, high model performance can be obtained under the conditions of complex multi-path scenes and small samples, and an accurate recognition result is obtained.

The present invention discloses a water affairs safety operation status inspection management system and method based on big data, belonging to the field of big data technology. The present invention obtains the water affairs operation lines corresponding to the target area through the GIS system, and collects real-time water affairs data for each line; performs interference removal and analysis processing on the retrieved water affairs operation lines in the target area, performs node marking on the simplified operation lines after processing, obtains the sections between the associated nodes, and marks the comprehensive water affairs data of the sections; retrieves the historical safe operation water affairs data of each section in the target area, builds a reference analysis model based on the current data of each section, and performs safety assessment on the current water affairs operation section in the target area; feeds back the assessment data of the sections of the water affairs lines in the target area in real time, and gives abnormal prompts for abnormal sections.

The utility model belongs to the technical field of drilling equipment, and particularly relates to a telescopic hydraulic square pile drill bit. According to the specific technical scheme, the device comprises a top plate, a bottom plate, an adjusting assembly and an excavating assembly; the top plate and the bottom plate are connected through a telescopic assembly; the adjusting assembly comprises first connecting arms and second connecting arms, one ends of the two first connecting arms are symmetrically hinged to the lower end of the top plate, and the excavating assembly is arranged at the other ends of the first connecting arms. One ends of the two groups of second connecting arms are respectively hinged with the two groups of first connecting arms, and the other ends of the two groups of second connecting arms are hinged with the bottom plate; the telescopic assembly stretches up and down to adjust the distance between the top plate and the bottom plate so as to adjust the wheel track between the two excavating assemblies.

The embodiment of the present application discloses a process mining method, device, electronic device and medium based on a graph database. The method includes: obtaining an event log in a business process system, extracting a case identifier and case information for any event log, and storing them in a log layer corresponding to the case identifier in a first graph database; for a log layer corresponding to any case identifier, storing the activities in the case information stored in the log layer in chronological order to the activity layer corresponding to the case identifier in the first graph database; mining the process edge information contained in the log layer based on the case information in the log layer, and storing the process edge information in the edge layer corresponding to the case identifier in the first graph database. This mining and storage method is compatible with process edge information, the storage method of the graph database, and has lower expression complexity and higher visibility.

The application provides a data processing system based on a stream computing engine, comprising a data acquisition module: after acquiring original data from a terminal, a coding and decoding protocol of a sending end and a receiving end is compiled and sent synchronously, corresponding table information is matched from a non-bound data stream, and acquisition of information events is completed; a pre-filtering module: information screened by acquisition is provided with lightweight data filtering by a Bloom filter, and massive data filtering provided by K-V storage is synchronously utilized; a data preprocessing module: the stream computing engine provides unified stream processing of streams and batches, avoids resource waste caused by two sets of business development of offline and real-time, and provides SQL support to abstract data flow; a data blood relationship module: SQL abstract processing provided by the stream computing engine is adopted, a script is written by using SQL language to describe the flow of data, and then the script is submitted to a platform to parse and start a job. The application realizes mining of data value and processing and analysis of unstructured data.

This invention provides a photovoltaic (PV) operation status management and control method and system, comprising: constructing and training a PV ecological monitoring model including a physical coupling field submodule and a PV ecological agent submodule; performing risk assessment on a real-time PV operation dataset based on the PV ecological monitoring model to generate risk assessment results; performing strategy exploration and counterfactual reasoning based on the risk assessment results to generate corresponding optimal control strategies; executing the optimal control strategies; and performing feedback optimization based on the feedback data corresponding to the optimal control strategies, thereby achieving efficient and accurate management and control of PV operation status.

The present invention relates to a chemical process slow-changing fault detection method based on weighted probability typical variable dissimilarity analysis, the steps of which are: standardizing the training data and constructing a historical data matrix and a future data matrix, establishing a CVDA model and extracting the CVDA features of the training data, and calculating the corresponding training WD features, and further calculating the statistics T corresponding to the training WD features. 2 , statistics Q and statistics D and determine the corresponding control limits; collect test data, construct historical data vectors and future data vectors of test data, use the established CVDA model to extract the corresponding online CVDA features, calculate the online WD features, further calculate the online weighted WD features, and calculate the statistic T based on the online weighted WD features 2 , statistics Q and statistics D, and monitor using control limits. The fault detection method of the present invention introduces Wasserstein distance and online weighting strategy, which improves the detection performance of slowly varying faults in chemical process data.

The application provides a virtual resource pushing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining a current geographical text message initiated by a user of a virtual resource to be pushed; obtaining a target geographical text information set matched with the current geographical text message based on query keyword information and current position information issued by the user for describing the virtual resource contained in the current geographical text message; updating the target geographical text information set by using the message; obtaining a virtual resource set matched with the updated target geographical text information set; and pushing the virtual resource contained in the virtual resource set to a target user issuing information in the target geographical text information set. The method can consider regional influencing factors, improve the timeliness of virtual resource pushing, and mine potential users.

A Lipu taro harvesting and sowing all-in-one machine comprises a movably-arranged rack, a harvesting mechanism and a conveying mechanism matched with the harvesting mechanism are arranged at the end of the rack, and a cleaning mechanism matched with the harvesting mechanism is arranged on the harvesting mechanism; a storage mechanism matched with the conveying mechanism is arranged on the rack, a seeding mechanism and an excavating mechanism are arranged below the storage mechanism, a soil covering mechanism is arranged at the tail end of the rack, and an irrigation mechanism is further arranged on the rack; compared with the prior art, harvesting and sowing of the Lipu taros are integrated, so that the harvesting and sowing efficiency of the Lipu taros is improved, a harvester and a sowing machine do not need to be purchased independently, the cost is reduced, and meanwhile, the maintenance work of equipment is also facilitated.

The invention belongs to the technical field of biological medicine, and relates to a gastric cancer biomarker mining method and system. The method comprises the following steps: acquiring data; preprocessing the data; generating a gene interaction network; performing data difference analysis; performing function enrichment analysis; analyzing a survival prognosis model gene; carrying out GSEA enrichment analysis; carrying out progression-free lifetime analysis; a Nomogram model is constructed; analyzing the causal relationship between the gastric cancer biomarker and the gastric cancer; analyzing the causal relationship between protease and gastric cancer; and analyzing the causal relationship between the gastric cancer biomarker and the protease. According to the invention, the gastric cancer mechanism is explored by combining a bioinformatics method and a Mendel randomization method, and the gastric cancer biomarker indirectly affects the occurrence of gastric cancer through mediated protease, so that the mining of the gastric cancer biomarker is realized.

The invention relates to the field of tunnel construction engineering, in particular to a variable-diameter full-section cutting cutterhead and a using method thereof. Comprising a fixing ring which can be fixed at the front end of the shield tunneling machine; one ends of the cutter spokes are connected to the outer side of the fixing ring, and the included angles between the adjacent cutter spokes are equal; the plurality of hobs are rotatably arranged on the cutter spokes and the fixing ring; each cutter spoke is provided with one cutting tool bit, and the cutting tool bits can move in the axial direction of the cutter spokes; the driving mechanism is arranged on the cutter spokes, connected with the cutting tool bits and used for driving the cutting tool bits to move; the plurality of arc-shaped inner-layer ring beams are connected between the adjacent cutter spokes, and the plurality of inner-layer ring beams enclose to form a circular ring; and the control system is in control connection with the driving mechanism. The variable-cross-section tunnel excavation device has the beneficial effects that the movable cutting tool bits are arranged on the cutter spokes, the moving speed, the moving direction and the moving stroke of the cutting tool bits are controlled through the driving mechanism, the cutting range of the cutting tool bits is changed, and therefore excavation of a variable-cross-section tunnel is achieved.

The present invention discloses an intelligent focusing device and method for laser induced breakdown spectroscopy. The device is arranged in conjunction with a spectrometer, including a laser and its control box, an autofocus module, and an optical path module. The equipment except the laser control box is integrated into a cubic box. At the same time, in order to simplify the sample preprocessing operation and improve the accuracy of laser focusing, an autofocus integration algorithm is written based on the focusing method and control technology of image processing, which is used to predict the focus moving distance, and the autofocus module is used for automatic focusing according to the moving distance. Compared with the traditional manual focusing method, the present invention makes full use of the image learning ability of deep learning, mines the information characteristics of the sample image and the ablation pit left by the LIBS laser hitting the sample, and establishes a multimodal information fusion regression model algorithm, which reduces the human error in manual focusing and effectively improves the collection efficiency of LIBS samples.

This application relates to the field of industrial operating condition identification technology, and discloses a method and system for identifying the operating conditions of industrial furnaces and kilns. This method designs an adaptive sliding window transfer entropy as the fitness function of the optimization algorithm to accurately quantify whether the current time delay sequence is optimal. Simultaneously, it utilizes the DDS-POGIC algorithm to effectively and quickly search for the target sequence even in high-dimensional environments with numerous time delay sequences. Addressing the problems of severe multi-field and multi-phase coupling, dynamic and variable operating conditions, and severe data imbalance in large industrial furnace and kiln systems, a DWTD-SDAE operating condition identification model is constructed. This model effectively mines information from both process variables and operating condition samples, enhancing the guiding role of the operating condition target in the identification process. It can accurately and quickly identify the current operating condition even with imbalanced samples, helping operators quickly grasp operating condition fluctuations and adjust on-site operations in a timely manner.

The utility model discloses a civil engineering foundation pit excavating device which comprises a movable seat. And the rotary supporting mechanism is installed on the movable base and comprises a servo motor fixedly connected to the top of the movable base, and a rotary support is fixedly connected to an output shaft of the servo motor. According to the foundation pit excavation device, the movable base is moved to a to-be-constructed area, then the excavation assembly is driven by the first electric cylinder to move downwards, meanwhile, the excavation motor is started, the excavation head can be driven to rotate, then excavation of a foundation pit can be achieved, and after excavation of the foundation pit is completed, the servo motor is started; a servo motor drives a discharging mechanism to move to a pit digging position through a rotating support, then a conveying assembly is driven by a second electric cylinder to move downwards, a barrel is made to go deep into a foundation pit, then a driving motor is started, and therefore excavated soil can be spirally conveyed through spiral conveying blades and discharged through a discharging pipe; and therefore, the convenience of the foundation pit is improved to a great extent.

The invention discloses a number identification method and device, equipment and a computer storage medium. The method comprises the steps of obtaining user communication data; extracting user attribute data, call behavior data, call object data and time sequence data corresponding to a communication number from the user communication data; determining communication key data corresponding to the communication number based on user attribute data, call behavior data, call object data and time sequence data corresponding to the communication number; and extracting behavior mode characteristics corresponding to the communication key data by using a number identification model, and carrying out investigation number identification on the behavior mode characteristics based on an investigation number behavior mode learned by the number identification model in advance. According to the embodiment of the invention, the identification of the investigation number can be realized.

The utility model relates to water plant construction, in particular to a buried pipe pay-off device for water plant construction, which comprises a fixed box body, a U-shaped conveying bin and a fixed plate are fixedly connected to one side in the fixed box body, and a U-shaped bin inclined shovel plate is fixedly connected to the bottom of the U-shaped conveying bin. The bottom of the fixing plate is fixedly connected with one side of the inclined face of the U-shaped bin inclined shovel plate, a round notch is formed in the bottom of the fixing plate, the U-shaped conveying bin and the U-shaped bin inclined shovel plate are buried in a pit, after the U-shaped conveying bin is started, soil is conveyed into the position between the U-shaped conveying bin and the fixing plate, and the U-shaped conveying bin and the U-shaped bin inclined shovel plate are fixed. Soil is conveyed out of the fixed box body through an output pipeline, a motor and conveying blades, excavation of the pipeline is achieved, a steering plate, an upper input cylinder and a lower input cylinder are pushed through a third pneumatic telescopic rod to steer, and after the high position of the upper input cylinder faces the ground, the input pipeline can be directly buried.