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

29results about How to "Avoid complex calculations" patented technology

Rapid matching method for nonlinear state of aircraft

The invention discloses a non-linear state rapid fitting method for an aircraft, and belongs to the field of aircraft control. The implementation method comprises the following steps: constructing a two-loop attitude pilot and a three-loop attitude pilot, and discretizing to obtain a guidance instruction with a time-delay effect; according to coordinate conversion, forward deriving each aerodynamic parameter of the aircraft and an aircraft overload instruction equation; the method comprises the following steps: calculating all pneumatic data according to part of pneumatic data obtained by a blowing experiment of an aircraft, and fitting a guidance instruction with a balance attack angle, a sideslip angle and a rudder deflection angle of the aircraft to obtain a corresponding interpolation table; all aerodynamic parameters in the flight process of the aircraft are obtained according to an aircraft guidance instruction and an interpolation table in the actual situation, namely, nonlinear state rapid fitting of the aircraft is achieved, and simulation reproduction of the aircraft as a mass point in the whole guidance process is achieved according to the nonlinear state rapid fitting result. And the precision and efficiency of aircraft guidance control are improved.
Owner:BEIJING INST OF TECH +1

Clock gating circuit conversion method and device and related equipment

The embodiment of the invention provides a clock gating circuit conversion method and device and related equipment, and the method comprises the steps: obtaining target circuit design data of a clock gating circuit before conversion, the target circuit design data being part of data in the circuit design data of the clock gating circuit before conversion; predicting the power consumption income of the clock gating circuit before conversion based on the target circuit design data by using a pre-established power consumption income prediction model to obtain a power consumption income prediction result; wherein the power consumption income prediction model is used for predicting a power consumption change trend between the clock gating circuit before conversion and the clock gating circuit after conversion so as to form a power consumption income prediction result; if it is determined that the power consumption income prediction result is the forward power consumption income, the clock gating circuit before conversion is converted into the clock gating circuit after conversion. According to the technical scheme provided by the embodiment of the invention, the efficiency of determining the switching effectiveness of the clock gating circuit can be improved.
Owner:HYGON INFORMATION TECH CO LTD

Static control method of continuum robot

A statics control method for a continuum robot comprises the steps that a target node of the continuum robot is set, and node position coordinates of each section of mechanical arm of the continuum robot are set according to the environment or the pose required by work; motion statics modeling is conducted, a statics equilibrium equation of the mechanical arm of the continuum robot is constructed, the rotation angle of each joint is solved according to the pull force of the driving rope, and therefore the pose of the whole mechanical arm is obtained; and inverse statics control: adjusting the pulling force of the driving rope according to the rigidity to approach the target pose in a search mode. The accuracy of continuum robot form estimation, the simplicity of kinematic statics calculation and the high efficiency of inverse statics control can be improved.
Owner:XI AN JIAOTONG UNIV

Similar surgery picture retrieval method, system and equipment for minimally invasive surgery based on deep learning and medium

The invention discloses a similar surgery picture retrieval method, system and equipment for minimally invasive surgery based on deep learning and a medium, and relates to the technical field of image processing. Respectively extracting original image features in the preprocessed video stream and original text features in the preprocessed text content; performing interactive fusion on the original image features and the original text features by adopting a feature fusion module; using a feature codebook module to map the fusion feature into a codebook vector; a mapping feature decoding module is adopted to decompose the codebook vector into compressed image features and compressed text features, finally, the compressed image features are decoded into similar images, and the compressed text features are decoded into text descriptions corresponding to the similar images; and the operation picture can be quickly and accurately retrieved.
Owner:CHENGDU WITHAI INNOVATION TECH CO LTD

Transient voltage instability identification method based on Koopman operator

The invention discloses a transient voltage instability identification method based on a Koopman operator, and belongs to the field of power system operation and maintenance. The method comprises the following steps: firstly, on the basis of a Koopman operator theory, extracting a leading Koopman operator in voltage response after large disturbance through a Hankel matrix combined with an extended dynamic mode decomposition (Hankel-EDMD) method; secondly, a dominant Koopman operator is adopted to carry out continuation on a voltage response dominant component, and an enough voltage dominant mode time sequence is obtained; on the basis, a transient voltage stability discrimination model of a Koopman operator coupled with a Lyapunov exponent is provided, due to the dimension expansion effect of a Hankel matrix on measured data, the timeliness of the method is good, and therefore the method has high practical application value.
Owner:HARBIN UNIV OF SCI & TECH +1

Key following transmission system and method based on dynamic window encryption

The invention discloses a secret key following transmission system and method based on dynamic window encryption, and the system comprises a transmitting end which is configured to obtain a chaotic initial value and an original signal to be transmitted; processing the chaotic initial value through a public key encryption module and a first constellation mapping module to obtain encryption key information; the original signal is processed by a bit stream encryption module, a second constellation mapping module and a symbol encryption module to obtain encrypted information, the bit stream encryption module realizes bit stream encryption by using a disturbance sequence generated by a chaotic initial value, and the symbol encryption module realizes symbol-level scrambling by using a'dynamic window structure '; superposing the encrypted information and the encrypted key information by using a power division multiplexing module to obtain to-be-transmitted composite information; the composite information is converted into a time domain signal through fast inverse Fourier transform (IFFT), and signal transmission is carried out through a channel; and dual improvement of communication safety and communication efficiency is realized.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Image distortion correction method, device and system and storage medium

The invention discloses an image distortion correction method, device and system and a storage medium, which are used for improving the aliasing elimination effect of a display screen image. The method comprises the following steps: partitioning a display screen image to be corrected to generate a plurality of image sub-block sets; inputting the plurality of image sub-blocks into a scale-invariant distortion correction model for distortion correction, and generating a plurality of transformation matrixes which are transformation coefficient sets of pixel point coordinates before and after correction; constructing an adaptive convolution filter according to the plurality of transformation matrixes; inputting the plurality of image sub-blocks after distortion correction into the adaptive convolution filter for anti-aliasing convolution and interpolation calculation, and outputting the plurality of image sub-blocks after pixel point optimization correction; performing multi-scale anti-mixing correction on the edge areas of the plurality of corrected image sub-blocks; and splicing the plurality of image sub-blocks to generate a complete target correction image.
Owner:SHENZHEN SEICHITECH TECHN CO LTD

Artificial intelligence decision support method and system for high-frequency transaction

The invention relates to the technical field of information, in particular to an artificial intelligence decision support method and system for high-frequency transactions. The method comprises the steps of collecting order book data, and obtaining a fluctuation rate and a trading price difference based on the order book data; the window at the current moment is adjusted based on the volatility to obtain a window at the next moment, and window detection is completed through the hash value; counting the order quantity difference of the key prices at the current moment and the adjacent moment and the difference between the buying and selling price difference at the current moment and the maximum buying and selling price difference for the window with the data change, and obtaining a dynamic compression ratio based on the two differences; the DPCM algorithm and the dictionary compression algorithm are adjusted based on the dynamic compression rate, and then compression is carried out; and generating a decision signal based on the compressed data to complete decision support. The compression speed is increased, and the accuracy and integrity of the data are improved.
Owner:CHINALIN SECURITIES CO LTD

Method and system for realizing differentiated adaptation of interface control positions on screens with different sizes

The invention discloses a method and a system for realizing differentiated adaptation of interface control positions on screens with different sizes, an embedded splicing component is constructed in a unity engine, splicing parameters and screen resolution of a target model are input through the embedded splicing component, adaptation parameters of a control under an original size are automatically converted, and the interface control positions are matched with the screen resolution of the target model. Compared with the prior art, the method has the advantages that the adaptive parameters are quickly set, complex calculation in the splicing process, particularly more complex adaptive calculation under the nested state of multiple adaptive rules is avoided, after the adaptive parameters are calculated and set, the adaptive parameters are applied to the adaptive process of screens of various sizes in a parameter fixing mode, the controls appear at expected positions, and the adaptive parameters can be quickly set. The flexible adaptation of the control in the screens with different proportions or different characteristics is realized, and the flexible setting of the position of the control in the long and short screen state becomes possible.
Owner:SHENZHEN THUNDER DIGITAL ENTERTAINMENT CO LTD

A dual-arm collaborative operation planning method, device, equipment and medium

The present invention provides a dual-arm collaborative operation planning method, device, equipment and medium, which relates to the technical field of robot motion planning. The method includes: performing hydrodynamic analysis on a UVDMS three-dimensional model to generate hydrodynamic constraints; obtaining the starting position and target position of a first robot arm and the starting position and target position of a second robot arm according to a D-H parameter method; performing path planning on the first robot arm and the second robot arm respectively to generate a first planning path and a second planning path; discretizing the first planning path and the second planning path to generate at least one discrete path point interval; simplifying the UVDMS three-dimensional model using a bounding box to generate a dual-arm simplified model; extracting the minimum distance between the first robot arm and the second robot arm; determining the collision situation according to the minimum distance and a preset minimum threshold, and generating a target planning path according to the collision situation, the first planning path and the second planning path. The present invention can improve the efficiency of motion planning.
Owner:HARBIN ENGINEERING UNIVERSITY SANYA NANHAI INNOVATION & DEVELOPMENT BASE +1

Temperature error compensation method for CNC machine tools based on fractional-order model synchronization

The present invention discloses a method for compensating temperature errors of numerically controlled machines based on fractional-order model synchronization, comprising: a first step: establishing a fractional-order model of temperature errors of numerically controlled machines and identifying the parameters of the fractional-order model according to the temperature error and the deviation of the model output; a second step: designing an equivalent circuit according to the established fractional-order model of temperature errors; the output of the equivalent circuit is consistent with the temperature error of the numerically controlled machine, and error compensation is performed; the circuit includes a real-time temperature detection unit, which is the same temperature detection unit used for fractional-order modeling; the model equivalent circuit receives a temperature signal and generates an error signal according to the temperature signal. The present invention avoids complex calculations and enables real-time compensation of temperature errors, thereby improving the machining accuracy of numerically controlled machines. It avoids temperature error modeling based on complex mechanisms and can approximate the actual temperature error model of numerically controlled machines with arbitrary accuracy.
Owner:HUBEI QIXING JINGCHUANG INTELLIGENT EQUIP CO LTD

A rapid cross-path scheduling method for customized public transit system among urban areas

The application discloses a kind of quick cross path scheduling methods of inter-city area customized public transport system, the shortest distance method between regions is used to build start point area end point set and end point area start point set, to generate start point area travel sequence Yo by insertion method, to generate end point area travel sequence Yd by insertion method, then the Yo and Yd are optimized by quick exchange method, finally the minimum value of start point × Yo × Yd is solved, which is the final inter-city area customized public transport system target path, with the shortest bus travel distance as the target;The method does not use probability distribution, effectively avoids the fluctuation of the final path result, according to the characteristics that the distance between nodes in different regions is much larger than the distance between nodes in the same region, the inter-regional traffic node set is established, and it is used as the end point of the start point region and the start point of the end point region, respectively, to maximize the range of optimal solution, effectively reducing the overall calculation scale.
Owner:NANJING COMM INST OF TECH +1

A method for obtaining gas-water relative permeability curve of tight sandstone based on DAE-DNN model

The present invention discloses a method for obtaining a gas-water relative permeability curve of tight sandstone based on a DAE-DNN model. The relative permeability curve is obtained by a Brooks-Corey model, and combined with fracture parameters, construction parameters, and seepage characteristic parameters, production data is obtained through numerical simulation of gas reservoirs, including water production, gas production, and pressure. The production data, fracture parameters, construction parameters, and seepage characteristic parameters are subjected to dimensionality reduction processing using DAE, and the dimensionality reduction data is used as input, and the parameters related to the relative permeability curve are used as output. The parameters related to the relative permeability curve are imported into DNN to predict, and finally the relative permeability curve is determined by normalizing 10 groups of relative permeability curves predicted by the prediction simulation set. The present invention can quickly and accurately calculate the gas-water relative permeability curve, better reflect the actual gas-water flow capacity, and can provide strong support and guidance for gas field development and production.
Owner:SOUTHWEST PETROLEUM UNIV

Express delivery path planning method based on shortest loop

InactiveCN119558757AImprove efficiencyavoid complex calculationsForecastingOther databases indexingPathPingShort loop
The invention provides an express delivery path planning method based on a shortest loop, and aims to optimize the delivery path of a courier and improve the delivery efficiency. Firstly, express stations are determined as a starting point and an ending point, and longitudes and latitudes of all delivery places are recorded; then, whether the places are dispersed or not is detected through a distribution place dispersion judgment formula; and for the scattered places, constructing an outermost convex polygon path planning loop, and recursively constructing convex polygon loops for the remaining places until the number of the remaining places is not more than three. A path is systematically planned through a hierarchical convex polygon loop and a corresponding set of vertexes. Then, a migration site and a judgment site are determined, an FMP is inserted into the outermost loop in the clockwise direction, and path planning is updated; finally, when all places are included in a single convex polygon loop, an optimal path planning result is obtained. According to the method, the efficiency and accuracy of path planning are remarkably improved, and the method is suitable for various logistics distribution scenes.
Owner:DONGGUAN POLYTECHNIC +2

A low-power pulse wave signal arrhythmia classification method and system

The low-power pulse wave signal arrhythmia classification method and system of the application comprises the following steps: using a large convolution kernel to extract the bottom local features of the original signal, and reducing the sequence length by half through pooling; adopting a leaky integral-discharge neuron activation to make the data pulsed; using a large convolution kernel and a hollow convolution to expand the receptive field and capture longer-range local timing features; dimensionally reducing the output features, cooperating with batch normalization, leaky integral-discharge neurons and maximum pooling, and aggregating the local features; calculating self-attention in each subsequence, combining a linear mapping layer, focusing the model on the feature correlation in the local subsequence through the aggregation of the sub-attention map, and extracting the waveform dependence in the short time window of the pulse wave signal; calculating QKV interaction on the whole sequence, combining a linear layer and a pulse neuron, capturing long-distance global feature correlation, and mining the waveform dependence in different time periods of the pulse wave signal. The application can achieve a classification performance equivalent to that of a deep artificial neural network.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

LLC resonant converter feedforward control method based on state trajectory analysis

PendingCN119324634AOptimize transient control performanceavoid complex calculationsEfficient power electronics conversionDc-dc conversionTransient stateResonant converter
The invention discloses an LLC resonant converter feedforward control method based on state trajectory analysis. The LLC resonant converter feedforward control method comprises the following steps: S1, establishing a differential equation of an LLC resonant converter in a phase shift modulation typical working mode; s2, drawing a state trajectory equation of the LLC resonant converter in a positive half period under phase shift modulation, and drawing a phase plane curve graph; s3, combining and reasonably simplifying the state trajectory and geometric calculation, and estimating a phase shift angle; s4, the phase shift angle is fed forward to PI control output, and a pulse is generated and sent to the LLC resonant converter, the complex calculation process of solving a transcendental equation is avoided, state track jumping from heavy load to light load is achieved, and the transient control performance of the LLC resonant converter is optimized.
Owner:IANGSU COLLEGE OF ENG & TECH

A method for analyzing the online cycle of the sector guide roller of a continuous casting machine based on finite element analysis

The present invention relates to a method for analyzing the online cycle of a continuous casting machine sector guide roller based on finite element analysis, which comprises the following steps: establishing a finite element mathematical model for a group of down rollers of the continuous casting machine sector guide roller, collecting relevant data of the down rollers of the continuous casting machine sector, simulating the dynamic behavior of the material during high temperature deformation by using bilinear materials, and generating material constitutive curves; using augmented Lagrangian to perform theoretical analysis on the nonlinear contact between the roller surface and the slab surface, and by artificially introducing the penetration amount and the initial contact stiffness coefficient, performing iterative calculations, completing the estimation of the external fatigue cycle of the down roller, generating a life cloud map and a damage cloud map, and finding the lowest life point for estimation. Sub-model calculations are used to further verify the results. The method is simple and reliable, and the estimation of the external fatigue cycle of the down roller is completed within the finite element software, which is fast and efficient. The present invention can be widely used in the estimation and analysis of the online cycle of the sector guide roller of the continuous casting machine.
Owner:CHINA THIRD METALLURGICAL GRP

Display mode determination method and vehicle

PendingCN122275593Aavoid complex calculationsImprove the efficiency of usage preference assessmentVehicle controlReliability engineering
This application discloses a method for determining a display mode and a vehicle, relating to the field of vehicle control technology. The method includes: determining the first importance of a vehicle function to be displayed to the occupants based on their attribute information; determining the second importance of the vehicle function to the current driving process based on the vehicle's current driving scenario; determining the vehicle's usage preference for the vehicle function based on its historical usage information; and fusing the first importance, second importance, and usage preference levels to determine the target display mode corresponding to the vehicle function based on the fusion processing result. The technical solution of this application embodiment can make the target display mode more closely match the actual driving conditions of the vehicle and the actual needs of the occupants, thereby improving the convenience and experience of occupants using vehicle functions.
Owner:GREAT WALL MOTOR CO LTD

Control method for network construction type modular energy storage system and grid-connected improvement of network construction type modular energy storage system

The invention relates to a control method for a network construction type modularized energy storage system and grid connection improvement thereof, and the energy storage system comprises a modularized multi-level power converter, a converter DC side capacitor, an energy storage unit, an AC side inductor, a voltage sensor, a current sensor, an AD sampling module, a DSP main control board, a sub-module FPGA control board, and an IGBT drive board. The modularized multi-level power converter comprises a plurality of sub-modules, and each sub-module comprises an IGBT half-bridge sub-module and a sub-module capacitor. The control method is used for controlling the energy storage system and comprises the steps of signal acquisition and processing, signal modulation, PWM signal generation and module control. Compared with the prior art, the method has the advantages of high energy utilization rate, simple signal modulation process and the like.
Owner:SHANGHAI UNIVERSITY OF ELECTRIC POWER +1

A Machine Learning-Based Method and System for Predicting Gas-Water Two-Phase Production in Tight Sandstone

This invention discloses a machine learning-based method and system for predicting the production capacity of gas-water two-phase gas in tight sandstone. The method includes: constructing production capacity prediction models for different well types using an artificial neural network; inputting data such as critical flow saturation, water saturation, water phase relative permeability curve index, starting pressure gradient, permeability, reservoir thickness, fracture conductivity, fracture length, cluster number, and stress sensitivity coefficient as input variables into the production capacity prediction model, and using cumulative gas and water production as output variables. The input variables are then imported into the corresponding production capacity prediction model for different well types to obtain the cumulative gas and water production for each well type. This method uses an artificial neural network to construct a production capacity prediction model to predict the cumulative gas and water production in tight sandstone, achieving rapid and accurate prediction of the production capacity of the gas-water two-phase gas in tight sandstone, avoiding complex calculation processes, and reducing computation time and production costs.
Owner:PETROCHINA CO LTD

Modeling method of discontinuous conduction mode DC / DC converter based on signal flow graph method

The present invention belongs to the field of power electronics technology, and discloses a modeling method of a discontinuous conduction mode DC / DC converter based on a signal flow graph method, and analyzes three modes of the discontinuous conduction mode DC / DC converter in steady state to obtain voltage and current waveforms at both ends of the energy storage inductor. When the DC / DC converter is a non-isolated converter, the corresponding energy storage inductor is a pure inductor type, which can be equivalent to a control current source with a duty cycle disturbance as the control variable and an internal resistance in parallel; when the DC / DC converter is an isolated converter and the transformer has energy storage, the corresponding transformer is a coupled inductor type, and is connected in parallel with an ideal transformer on the basis of the pure inductor. In the derivation process of the model, the present invention has a clear physical meaning starting from the essence of the small signal model; the Mersenne formula is directly used in the model calculation, which avoids the complex calculations in the traditional modeling method, and can effectively reduce the difficulty of modeling the discontinuous conduction mode DC / DC converter.
Owner:XI'AN PETROLEUM UNIVERSITY

A method and system for analyzing continuous motion process of freight ropeway load

The present invention provides a method for analyzing the continuous motion process of a freight ropeway load, comprising: obtaining the parameters of the load-bearing cable nodes and the load nodes of the freight ropeway; bringing the parameters of the load-bearing cable nodes and the load nodes of the freight ropeway into the pre-established load-bearing cable node and load node motion equations, increasing the time step according to the set time increment step, solving the node motion equations, calculating the position vector and the combined force of the load-bearing cable nodes and the load nodes in the next time step, until the preset time period ends, obtaining the position vector and the combined force of the load-bearing cable nodes and the load nodes in each time step; verifying the maximum load-bearing capacity of the freight ropeway based on the maximum force value that the freight ropeway can bear and the position vector and the combined force of the load-bearing cable nodes and the load nodes in each time step. The technical solution provided by the present invention inserts the load node into the load-bearing cable unit for calculation, and can obtain accurate calculation results when the number of units is small, reducing the calculation complexity and improving the calculation efficiency.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2

Relational query method and system based on relational database

The invention discloses an association query method and system based on a relational database. The method comprises the following steps: acquiring a query request of a requester; determining a base point in the query request; executing initial query of the root table or the service table to obtain an initial current query result; then determining an associated query base point; then executing an associated query; judging whether the query result of the associated query meets the query requirement of the requester or not: if the query result of the associated query can meet the query requirement of the requester, extracting root table target information required by the requester from the root table, or extracting service target information required by the requester from the service table; if the query result of the associated query cannot meet the query requirement of the requester, repeatedly executing the associated query until the query result can meet the query requirement of the requester; and finally returning the root table target information or the service target information required by the requester to the requester. According to the method, the data association query in the relational database can be efficiently realized.
Owner:CHINA UNITED NETWORK COMM GRP CO LTD

Lightning simulation method and device in virtual scene, terminal, and readable storage medium

The present application provides a method and device, terminal, and readable storage medium for simulating lightning in a virtual scene. The method includes: when lightning needs to be simulated in a virtual scene, obtaining multiple preset lightning texture images and quadrilateral patches; randomly selecting a lightning texture image to be rendered from the multiple lightning texture images, and pasting the lightning texture image to be rendered to the surface of the quadrilateral patch to obtain a preliminary rendering result corresponding to the lightning texture image to be rendered; determining the presentation position of the preliminary rendering result in the virtual scene based on the current observation angle of the virtual scene; rendering the preliminary rendering result to the presentation position to present simulated lightning corresponding to the lightning shape in the lightning texture image to be rendered in the virtual scene. The method realizes efficient simulation of lightning in a game scene.
Owner:BEIJING PIXEL SOFTWARE TECH

An intelligent scale removal system for geothermal wellbore

The present application relates to a kind of geothermal wellbore scale intelligent scale removal system, including wellhead monitoring module, downhole monitoring module, main control system, injection module;Main control system includes the analysis module, dosing scheme generation module, control module connected in sequence;Injection module includes the lifting unit connected, injection unit;Analysis module, for according to the wellhead geothermal fluid data, downhole geothermal fluid data and multiple-field multiphase multi-component non-isothermal phase transition flow model obtained by real-time monitoring, inversion obtains the real-time flashing face depth of geothermal fluid in wellbore, and the real-time scale rate of different depth positions;Dosing scheme generation module, according to the real-time flashing face depth, the real-time scale rate of different depth positions, real-time generates corresponding scale inhibitor dosing scheme, scale inhibitor dosing scheme includes scale inhibitor injection rate, scale inhibitor injection depth;Control module, for according to real-time scale inhibitor dosing scheme to lifting unit, injection unit is controlled.The present application can realize intelligent scale removal.
Owner:中核坤华能源发展有限公司

Speech processing method of early education robot and early education robot

The invention discloses a voice processing method of an early education robot and the early education robot, and relates to the technical field of voice processing, and the method comprises the steps: receiving a voice instruction inputted by a user for recognition, and when the voice instruction is recognized as a teaching instruction, displaying the teaching content in the teaching instruction to the user; after the teaching content is displayed, receiving feedback voice of a user and collecting a feedback image of the user; the feedback voice and the feedback image are subjected to content consistency verification, after the consistency verification is passed, whether the feedback voice and the feedback image conform to the teaching content is judged, an early education processing result is obtained and displayed to the user, and the early education processing result comprises feedback correctness or feedback error. The technical problems that in the prior art, an early education robot is large in voice recognition computing power consumption and poor in early education effect are solved.
Owner:DAZA ELECTRONICS CO

A method and system for calculating customer indicators in the Internet field based on rule engine

A method and system for calculating customer indicators in the Internet field based on a rule engine, relating to the field of data processing technology. The method solves the problem that the existing customer indicator calculation method uses machine learning technology for data processing, consumes a lot of computing resources, cannot respond to market changes and customer needs in a timely manner, and customer indicators usually involve multiple dimensions and complex features. High-dimensional data makes the feature selection process complicated and time-consuming. The method includes: obtaining customer data and product data information, and preprocessing the customer data and product data information; encrypting the preprocessed customer data and product data information to obtain encrypted data information; constructing a feature extraction model, and extracting features from the encrypted data information according to the feature extraction model; constructing rule trigger conditions, and using the rule trigger conditions to match the data after feature extraction to calculate customer indicators. It is applied to risk assessment and e-commerce fields.
Owner:JILIN SENYI INTELLIGENT TECH CO LTD

Reliability prediction method for complex simulation system

PendingCN119150660ARealism fastRealism gained quicklyDesign optimisation/simulationNeural architecturesAlgorithmEngineering
The invention relates to a fidelity prediction method for a complex simulation system, belongs to the technical field of simulation, and solves the problem of low fidelity calculation efficiency of the complex simulation system in the prior art. The method comprises the following steps: constructing a super network corresponding to each historical simulation moment of the complex simulation system; calculating the fidelity of a simulation system at each historical simulation moment based on the super network; extracting historical simulation time sequence data of the complex simulation system, and constructing a training sample set based on the time sequence data and the corresponding fidelity; constructing a time sequence prediction neural network model, and training the time sequence prediction neural network model based on the training sample set to obtain a fidelity prediction model; and obtaining to-be-predicted time sequence data of a to-be-predicted simulation system, inputting the to-be-predicted time sequence data into the fidelity prediction model, and predicting to obtain the fidelity of the complex simulation system. And objective and efficient evaluation of the whole-process network fidelity of the complex simulation system is realized.
Owner:3RD GENERAL DESIGN DEPT CHINA AEROSPACE SCI & IND CORP