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

12results about How to "Ease complexity" patented technology

Multivariable inversion method for buried hill reservoir neutron porosity measurement

The invention discloses a multivariable inversion method for measuring the neutron porosity of a buried hill reservoir, and belongs to the technical field of nuclear logging. The multivariable inversion method specifically comprises the following steps: constructing a neutron logging instrument array detector, measuring the buried hill reservoir, calculating a counting ratio R, and defining R1 and R2; constructing a multivariable inversion model, and performing inversion to obtain Por, Por1, Por2, cal and OFFSET; and the relative eccentricity OFFSETRE is defined, iteration inversion is conducted on the OFFSETRE through a dichotomy method, and the well diameter, the relative eccentricity and the porosity are output to serve as inversion results. The method can effectively reduce the negative influence of dual environment effects generated by well diameter fluctuation and instrument eccentric distance change on a logging result, remarkably alleviates the complexity and difficulty of environment correction, greatly improves the accuracy and reliability of neutron porosity measurement of the buried hill reservoir, and has a great significance in improving the oil-gas exploration and development efficiency. And the reservoir evaluation precision is optimized, and the method has extremely important practical significance and application value.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Time sequence causal-driven meteorological disaster prediction method

The invention discloses a sequential causal-driven meteorological disaster prediction method, and belongs to the field of causal relationship discovery and meteorological disaster prediction. According to the specific scheme, the method comprises the following steps: preprocessing time series data of meteorological disasters to obtain an optimal lag window and an optimal data length; dividing the meteorological data into a plurality of meteorological data segments with the same length according to the optimal lagging window and the optimal data length; respectively applying a time sequence causal relationship discovery method to the divided meteorological data segments to obtain window causal structure diagrams; and fusing the causal structure diagrams in the plurality of data fragments in an ensemble learning mode to obtain a globally consistent time sequence causal structure diagram. In meteorological disaster prediction, the time sequence causal relationship between disaster risk levels and key meteorological factors in meteorological data can be mined, the accuracy of meteorological disaster prediction by a meteorological institution is improved, and effective prevention of meteorological disasters is realized.
Owner:SHANXI UNIV

Remote sensing image target detection method, system and device based on deep learning

The invention belongs to the technical field of remote sensing image processing, and particularly relates to a remote sensing image target detection method, system and device based on deep learning, and the method comprises the steps: carrying out the depth separable convolution of a plurality of convolution kernels with different scales on to-be-processed remote sensing image data, so as to capture the information with different scales, and effectively enlarging the receptive field; a strip-shaped convolution attention mechanism is adopted, and a strip-shaped convolution combination not only can help to understand context information, but also can enhance the sensitivity to a strip-shaped object; the obtained features effectively alleviate the problems of target scale difference and complex background information existing in a target detection task, and not only realizes high detection precision, but also maintains high reasoning speed.
Owner:YANTAI UNIV

Class-level relation constraint and structured graph enhancement method and system, medium and terminal

ActiveCN119068272AEnhance representation learning abilityease complexityInstrumentsPattern recognitionEffective solution
The invention belongs to the technical field of image classification, and particularly relates to a class-level relation constraint and structured graph enhancement method and system, a medium and a terminal. Constructing visual representation distribution of data set images by utilizing clustering, and constructing a hierarchical structured relationship based on distribution information; expanding a typical batch construction process under the guidance of the relationship, hierarchically aggregating associated knowledge through a graph smoothing operation, and enhancing the representation learning ability of the model in a manner of guiding the knowledge; a sampling strategy based on visual distribution is designed, intra-class and inter-class constraints are constructed, and visual representation is further explicitly enhanced in combination with curriculum construction and class-level distribution regularization operation. Finally, the enhanced visual representation is used for the classification task, thereby improving the visual classification effect. According to the innovative method, an effective solution is provided for a visual classification problem through deep mining and utilization of distribution information of visual representation.
Owner:SHANDONG RES INST OF IND TECH +1

Three-level DCDC parallel positive and negative electrode current sharing control method and device and storage medium

ActiveCN119030286APlays the role of fine-tuning auxiliary controlSimple control methodDc-dc conversionElectric variable regulationControl engineeringInductor
The invention discloses a three-level DCDC parallel positive and negative electrode current sharing control method and device and a storage medium, and the method comprises the steps: enabling a current sampling value of a first electrode inductor of each DCDC to track a current average value of the first electrode inductor, obtaining a current sharing compensation value of the first electrode inductor, superposing the current sharing compensation value to a given value of a current inner ring, and obtaining a current sharing compensation value of the first electrode inductor; generating a first driving signal based on the output value of the current inner loop; a current error compensation value between the two-pole inductors is obtained by tracking the current sampling value of the first-pole inductor with the current sampling value of the second-pole inductor, the current error compensation value and the output value of the current inner loop are superposed, and a second driving signal is generated based on the superposition result; therefore, the DCDC driving signal is generated by taking the current inner loop control of the first-pole inductive current as a leading function and the current sharing loop control of the second-pole inductive current as an auxiliary function, the problem of non-current sharing of the positive electrode and the negative electrode in the operation process of multiple DCDCs is solved, and meanwhile, the oscillation caused by out-of-control or control function conflict due to multi-current loop control is avoided.
Owner:SHENZHEN SINEXCEL ELECTRIC

Method for generating synthetic traffic sign data

The invention relates to a method for generating synthetic traffic sign data. The computer-implemented method (100) for generating synthetic traffic sign data for training a traffic sign detection model comprises: extracting (S106) a front face of a detected traffic sign from a sample image depicting a vehicle surroundings comprising the detected traffic sign using information indicative of a position of the detected traffic sign; forming (S108) a 3D model of the traffic sign, the 3D model having a front face of the extracted detected traffic sign; and generating (S110) synthetic traffic sign data by placing the 3D model of the traffic sign in the one or more background images, wherein the 3D model is placed in the one or more background images based on a placement distribution of the real-world traffic sign in the dataset of the real-world image.
Owner:ZENSEACT AB

A dispatching method for a connected vehicle system

The present invention discloses a scheduling method for a networked vehicle system, which belongs to the field of intelligent transportation. Specifically, the method comprises the following steps: first, for the current moment, obtaining in real time the number of service providers and service objects in a to-be-scheduled area and adjacent areas as supply and demand information; then, inputting the supply and demand information into a trained neural network, and outputting the value estimation of all pricing factors in each area; and using an ε-greedy strategy, selecting a unique pricing factor for each area; finally, inputting the number of service objects and the unique pricing factor in each area into an adjustment function, calculating the number of service objects that accept pricing in each area, and randomly selecting an equal number of service providers to provide services; at the same time, inputting the remaining service providers in each area that have not accepted pricing into a learned network flow scheduling model, and outputting and executing the scheduling strategy for each service provider; the present invention takes into account constraints in multiple aspects, such as scheduling cost, idle time, spatiotemporal pricing, and supply and demand balance, to maximize the benefits of the service provider.
Owner:BEIJING UNIV OF POSTS & TELECOMM

A lightweight encrypted traffic analysis method and system based on distillation characterization model

The present invention relates to a lightweight encrypted traffic analysis method and system based on a distillation representation model, comprising: obtaining an original data set of encrypted network traffic, performing unified processing on the data in the original data set and then dividing it according to a set ratio to generate various sample data sets; inputting pre-trained samples into a BERT model based on representation learning for pre-training to obtain a pre-trained model, inputting fine-tuning samples into the pre-training model for detailed task training to obtain a traffic classification teacher model; using a knowledge distillation method of multi-layer jump fusion learning to extract teacher information of the traffic classification teacher model, and inputting fine-tuning samples into a lightweight traffic analysis model for training; inputting test samples into the lightweight traffic analysis model to realize end-to-end target network encrypted traffic classification tasks; while ensuring classification accuracy, reducing analysis resource requirements, and facilitating the realization of online low-consumption encrypted traffic classification functions in delay-sensitive resource-constrained network scenario nodes.
Owner:湖北省楚天云有限公司 +2

Complex signal field recovery system and recovery method based on native optical carrier

ActiveCN118337284BEnhanced phase recovery capabilityDecreased extinction ratio indexRadio-over-fibreElectromagnetic receiversConvertersDigital signal processing
The present invention discloses a complex signal field recovery system based on native optical carrier, including a transmitting end digital signal processing module, a digital-to-analog converter, an electro-optical modulator, an optical fiber link, an optical coupler, a dispersion element, a photodetector, an analog-to-digital converter and a receiving end digital signal processing module; the transmitting end digital signal processing module performs nonlinear pre-compensation and DC bias correction of the electro-optical modulator; the electro-optical modulator converts the electrical signal from the digital-to-analog converter into an optical signal carrying target information, and generates a native optical carrier at the same time; the dispersion element performs dispersion on the optical signal passing through; and the receiving end digital signal processing module performs signal recovery operations. The present invention also discloses a complex signal field recovery method, including the following steps: electro-optically modulating an optical carrier signal using an electro-optical modulator with a finite extinction ratio; receiving an optical signal using a phase recovery receiver; and performing signal field recovery based on an improved Gerchberg‑Saxton algorithm in the receiving end digital signal processing module.
Owner:XIANGTAN UNIV

Class-level relationship constraint and structured graph enhancement method, system, medium and terminal

ActiveCN119068272Bease complexityEnhance visual representationInstruments
The present invention belongs to the field of image classification technology, and specifically relates to a class-level relationship constraint and structured graph enhancement method, system, medium and terminal. Clustering is used to construct the visual representation distribution of the data set image, and a hierarchical structured relationship is constructed based on the distribution information; the typical batch construction process is extended under the guidance of the relationship, and the associated knowledge is hierarchically aggregated through graph smoothing operations to enhance the representation learning ability of the model in a guided knowledge manner; a sampling strategy based on visual distribution is designed to construct intra-class and inter-class constraints, and at the same time, the course construction and class-level distribution regularization operations are combined to further explicitly enhance the visual representation. Finally, the enhanced visual representation is used for classification tasks, thereby improving the visual classification effect. This innovative method provides an effective solution to the visual classification problem by deeply mining and utilizing the distribution information of the visual representation.
Owner:SHANDONG RES INST OF IND TECH +1

Time division multiplexing based forward transmission type distributed optical fiber vibration sensor

PendingCN122282081ANo coherent fadingmaintain coherent fadingPhotovoltaic detectorsPhotodetector
This invention discloses a forward-transmission distributed optical fiber vibration sensor based on time-division multiplexing, belonging to the field of distributed optical fiber vibration sensor technology. It includes: a laser, a first optical coupler, an optical modulator, a first circulator, a second optical coupler, a time-division multiplexing structure, and a photodetector. The output of the laser is connected to the input of the first optical coupler. The output of the first optical coupler is connected to the inputs of both the optical modulator and the second optical coupler. The output of the optical modulator is connected to one end of the optical fiber under test via the first circulator. The other end of the optical fiber under test is connected to the time-division multiplexing structure. One end of the optical fiber under test is also connected to the input of the second optical coupler via the first circulator. The output of the second optical coupler is connected to the photodetector. This invention alleviates the technical problems of high system complexity and high implementation cost in existing technologies.
Owner:UNIV OF SCI & TECH BEIJING

Elevator power failure emergency rescue device, method, elevator

ActiveCN120622264BImplementing power outage emergency rescue methodsreduce complexity
The application discloses an elevator power-off emergency rescue device, method and elevator. The device comprises a control module, a storage battery, a voltage boosting module, an auxiliary source module and a relay module. The auxiliary source module is connected with commercial power and connected with the control module through the relay module. The control module is used for adjusting the state of the relay in the relay module according to the state of the commercial power, and determining whether to connect the commercial power to the elevator control cabinet or connect the storage battery and the voltage boosting module to the elevator control cabinet. The storage battery is connected with a frequency converter of the elevator control cabinet through the relay module. The storage battery is connected with the voltage boosting module. The voltage boosting module is connected with an integrated power source of the elevator control cabinet through the relay module. The application is beneficial to reducing the complexity of the emergency rescue equipment and improving the working reliability. The application can be widely applied in the elevator control technical field.
Owner:GUANGZHOU CHUOLI TECH CO LTD