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

173results about How to "Improve data utilization" patented technology

Intelligent risk control method, device and equipment for multi-source data fusion and storage medium

The invention relates to an intelligent risk control method and device for multi-source data fusion, equipment and a storage medium. The method comprises the following steps: collecting to-be-processed multi-source heterogeneous data based on a big data platform, and carrying out preprocessing and high-dimensional tensor conversion to obtain a target high-dimensional tensor; performing reconstruction to obtain a fusion reconstruction tensor; performing multi-dimensional decomposition and feature extraction to obtain a risk propagation network, and performing clustering analysis and feature mapping to obtain a risk feature mapping set; risk level prediction is carried out based on a cost-sensitive deep neural network integration model, and probability distribution of multi-class risk levels is obtained; and setting an early warning threshold according to the probability distribution of the multi-category risk levels, and performing similarity matching and decision reasoning in combination with a historical case database to obtain a digital intelligent risk control decision suggestion. According to the method, big data and artificial intelligence technologies can be fully utilized to realize omnibearing and multi-dimensional analysis and early warning, so that the data application capability and the risk decision-making efficiency are improved.
Owner:SHENZHEN YOURONG INFORMATION TECH CO LTD

Cloud computer end-to-end fault root cause analysis method and system

The invention discloses a cloud computer end-to-end fault root cause analysis method and system, and relates to the technical field of operation and maintenance data analysis, and the method comprises the steps: deploying data collectors on a virtual resource pool, a multi-stage cloud management platform and a cloud computer terminal, and monitoring and collecting various operation and maintenance data in real time; a unified operation and maintenance management center is introduced to complete the following work: providing management and configuration services of the data collector; receiving and summarizing operation and maintenance data; various AI models are accessed, operation and maintenance data from different sources are distributed based on the types of the AI models, the AI models perform deep analysis and diagnosis on the operation and maintenance data, and potential fault modes or abnormal behaviors are identified; customizing an alarm strategy, an alarm processing flow and an alarm notification mode; and introducing an AIOps service to generate an alarm and fault analysis report according to the analysis and diagnosis results of the AI model. According to the method, the service quality of the end-to-end full link of the cloud computer is monitored in real time, so that faults can be quickly positioned, early warning can be performed in advance, and the operation and maintenance cost and the fault risk are reduced.
Owner:INSPUR COMM TECH CO LTD

Monitoring point and data classification management method based on intelligent monitoring platform

The invention provides a monitoring point and data classification management method based on an intelligent monitoring platform, and belongs to the technical field of data processing, and the method comprises the steps: 1, importing a preset BIM model into a preset intelligent monitoring platform, and carrying out the analysis of the preset BIM model; 2, creating a monitoring project in a preset intelligent monitoring platform based on a model analysis result, and configuring monitoring project information; step 3, acquiring a monitoring demand matched with the monitoring project, determining the type of a monitoring point, analyzing the information of the monitoring project, and creating a plurality of monitoring points; 4, the monitoring equipment based on the monitoring points collects monitoring data in real time, uploads the monitoring data to a preset intelligent monitoring platform through a network, and automatically associates the uploaded real-time data with the corresponding monitoring points; and 5, analyzing the real-time data, and optimizing the deployment of the monitoring points and the data of the monitoring points. And an efficient and intelligent solution is provided for application scenes such as engineering monitoring and environment monitoring.
Owner:POWERCHINA RAILWAY CONSTR

Medical insurance business index data storage and query method and system

The invention provides a medical insurance business index data storage and query method and system, and the method comprises the steps: obtaining a definition index classification, a definition index modifier and a definition index attribute, and building an index model based on the obtained information; based on a dimension modeling theory, constructing an index storage model by using a star model; obtaining an index calculation parameter corresponding to the index model, calculating and generating index data through a matching calculation rule, and updating the index data into the fact table; according to the indexes and the index data, correlation among the indexes is calculated through a correlation analysis algorithm, a correlation analysis result among the indexes is generated, and an index system is formed; and in response to a medical insurance service information query instruction, extracting data related to the content of the query instruction and corresponding data in the related dimension table from the fact table according to the index model and the index system. According to the invention, the number of data tables and the data volume of a single table can be increased in a controllable range, and clear data storage logic is ensured.
Owner:DAREWAY SOFTWARE

Multi-modal power knowledge base construction method and retrieval method based on AI large language model

The invention belongs to the technical field of power system informatization, and provides a multi-modal power knowledge base construction method and retrieval method based on an AI large language model.The method comprises the following steps that S1, classification and named entity extraction are conducted on an original database, and a data set and an entity set are obtained; s2, aligning the data set and the entity set based on an AI large language model; s3, extracting and complementing entity relationships, and constructing an electric power diagram database; s4, performing joint embedding on the entities and the associated data, mapping the entities and the associated data to the same vector space, constructing a multi-modal power knowledge base, and generating a data index; and performing retrieval by using the constructed multi-modal power knowledge base, and performing source file backtracking through a data index. According to the method, multi-modal data are fused, the constructed multi-modal electric power knowledge base is rich and accurate, and source file backtracking can be carried out.
Owner:STONE TECH CO LTD

Multi-modal fusion-based drug-protein interaction prediction model construction method

The invention belongs to the technical field of deep learning, and discloses a drug and protein interaction prediction model construction method based on multi-modal fusion. Due to the lack of protein three-dimensional data, the three-dimensional data of the protein is subjected to high-accuracy complementation by using a prediction model AlphaFold 2, and for the modal fusion problem, the drug molecules are fused at the atomic level with finer granularity, so that the multi-modal fusion effect is further enhanced, and the multi-modal fusion effect is improved. Protein 1D data and protein 3D data are processed by using Cross-Attention, the processed protein 1D data and protein 3D data are subsequently fused by using Cross-Attention, multi-modal fusion is performed by using Cross-Attention, so that the interaction relationship between modals can be carefully captured, and in a word, the DTI task effect is improved by designing a multi-modal fusion mode.
Owner:NORTHWEST UNIV

Robot arm control method based on video diffusion model and related equipment

The invention provides a robotic arm control method based on a video diffusion model and related equipment, and the method comprises the steps: extracting a plurality of sample historical image track features and sample target image track features from a robotic arm motion video, and carrying out noise diffusion to obtain sample track noise diffusion features; based on the sample historical image track features and the sample track noise diffusion features, taking noise diffusion features associated with the sample target image as a training target, and training a preset model; inputting the current image track feature of the robotic arm into a trained target video diffusion model to obtain a plurality of predicted noise diffusion features obtained by diffusion, and performing feature fusion based on the plurality of predicted noise diffusion features through a multi-layer cascaded action adapter contained in the target video diffusion model to obtain a plurality of predicted action features, the robot arm is controlled on the basis of the action control signals corresponding to the multiple predicted action characteristics, and therefore the accuracy of mechanical arm action prediction and control is improved.
Owner:PENG CHENG LAB

Quadruped robot fault-tolerant control method based on explicit predictive feedback

The invention provides a quadruped robot fault-tolerant control method based on explicit predictive feedback, and aims to solve the problem that a transferable robot fault-tolerant control model cannot be obtained due to the fact that an explainable and transferable representation containing robot motion model information cannot be obtained in an existing method. The state of the next moment is explicitly predicted by using historical observation information and the current action, and a prediction error is obtained by using an observation true value at the next moment. Prediction errors containing robot motion model information are introduced into input of a motion strategy, a feedback structure is formed, the perceptual ability for the motion model and the environment is provided for a motion network, and a brand-new high-performance fault-tolerant control model which does not need explicit damage judgment and has mobility and interpretability is obtained.
Owner:ZHEJIANG UNIV

Modbus communication method and communication system based on DCS controller

According to the Modbus communication method and communication system based on the DCS controller, after a Modbus master station sends a data reading instruction to the DCS controller through a Modbus slave station gateway, the DCS controller interrupts receiving of Modbus communication data after receiving the data reading instruction and inquires whether Modbus address table data is updated or not at present, and if yes, the Modbus communication data is updated. The Modbus address table is a slave station data area established in a controller memory by the DCS controller through Modbus slave station data configuration; if the DCS controller currently updates the Modbus address table data, the data reading instruction is cached, and the data reading instruction is called until updating is completed; if the DCS controller does not update the Modbus address table data at present, corresponding slave station data are acquired from the Modbus address table data according to the data reading instruction, packaged and fed back to the Modbus slave station gateway, so that a Modbus master station can receive all data in a DCS control process, and the data transmission efficiency and flexibility are improved.
Owner:HANGZHOU KANGJISEN AUTOMATION TECH CO LTD

Maintenance data intelligent storage method for medical equipment

The invention provides a maintenance data intelligent storage method for medical equipment, and the method comprises the steps: collecting the operation data of the medical equipment through a sensor, and deploying a microprocessor or embedded computing equipment at an edge node of each piece of medical equipment; segmenting the data according to a time window, constructing a physical model of the medical equipment to obtain a predicted value, identifying an abnormal condition, and setting a fault threshold value of each characteristic value; constructing a fault knowledge graph of the medical equipment; constructing intelligent semantic retrieval based on a knowledge graph, and obtaining required maintenance records and equipment operation data; automatically generating a maintenance plan according to the fault prediction data of the physical model and the fault knowledge graph of the medical equipment; and carrying out privacy protection on the data of the central storage system. According to the method, the data utilization rate and retrieval efficiency are improved, the equipment fault prediction capability is enhanced, the maintenance cost is reduced, the data security and privacy protection are ensured, and the maintenance efficiency and reliability of the medical equipment are improved.
Owner:HUAKANG HENGYE SMART MEDICAL TECH (HUBEI) CO LTD

Federal learning model training method

The invention belongs to the technical field of distributed intelligent computing, and aims to provide a federal learning model training method. In the implementation process, a semi-asynchronous federated learning aggregation scheme with a fixed time period is constructed by setting a period aggregation duration and adopting a semi-asynchronous federated learning model training mode, so that the bottleneck node delay influence of a synchronous federated aggregation strategy in an equipment heterogeneous environment can be solved, and the reliability of the system is improved. Meanwhile, deflection of a global model due to the fact that part of equipment frequently uploads the local model in the complete asynchronous federation aggregation strategy is prevented; besides, under the environment that the computing power of the federated learning system is unbalanced, data in all local clients can participate in model training in a semi-asynchronous aggregation mode under the condition that global training time is fixed, so that the data utilization rate of the local clients participating in training in the federated learning system is effectively improved, and the training efficiency of the federated learning system is improved. And the convergence precision of model training is improved.
Owner:SHENZHEN JINGTIE COMPUTING SYSTEM TECHNOLOGY CO LTD

Digital integrated system of LNG receiving station

The invention discloses a digital integrated system of an LNG receiving station. Wherein the data fusion module comprises a multi-source heterogeneous data fusion engine and is used for collecting, storing and preprocessing data of an LNG receiving station; the model building module comprises a self-adaptive digital twinning modeling framework and is used for building digital twinning models of the LNG receiving station, and the models comprise a physical model, a machine learning model and a 3D visual model; the service module comprises an intelligent scene engine and a decision support subsystem driven by a knowledge graph; and the application module comprises an application development framework of a micro-service architecture and is used for developing an application oriented to a terminal user. Thus, efficient fusion and processing of multi-source heterogeneous data are realized through fusion of a multi-layer module architecture design and an advanced technology, and the data utilization rate and the real-time performance are greatly improved. And meanwhile, the intelligent decision-making capability of the system is remarkably enhanced, and various complex operation scenes and emergency situations can be effectively handled.
Owner:CHINA NAT PETROLEUM CORP +1

Underwater scene three-dimensional reconstruction method based on two-dimensional sonar image gray level inversion height

The invention relates to an underwater scene three-dimensional reconstruction method based on two-dimensional sonar image gray level inversion height, and belongs to the field of sonar technology and acoustic image processing. Comprising the following steps: acquiring a sonar two-dimensional image, and dividing the sonar two-dimensional image into a plurality of areas according to direction angles; an inversion model is constructed according to a Lambertian reflection model; performing inversion calculation on each divided region based on an inversion model to obtain height information, and performing splicing and normalization processing on results of each region to obtain a normalized height information matrix of a detection region corresponding to the sonar image; adding the normalized height information matrix into the geometric dimension constraint of the sonar detection area, and estimating the real height information in the detection area; and the estimated real height information in the sonar image detection area is converted into a three-dimensional point cloud. The method solves the problem that a two-dimensional sonar image lacks three-dimensional information, provides three-dimensional information of a sound irradiation area for underwater scene detection, and has a good application prospect.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Method and system for evaluating flight route operation safety

The invention discloses an airline operation safety assessment method and system. The method comprises the following steps: constructing a route operation safety detection element library and a detection key point library according to a route operation safety detection theme, and forming a route operation safety detection plan through structural design; performing route operation safety detection based on the route operation safety detection plan, and cleaning and classifying the collected route operation safety detection data; and designing an evaluation index, and associating the threat information and the error information with a plurality of preset features to form an evaluation index system so as to provide a decision basis for subsequent flight safety management. According to the method, the flight route operation safety detection plan is disassembled into the detection elements and the detection key points, the safety evaluation indexes are designed, and multiple core competency of the pilot is evaluated through the representative evaluation indexes, so that the effectiveness of flight route operation safety detection is ensured, and the utilization rate of flight route operation safety data is also improved.
Owner:BEIJING RUISKE ENTERPRISE MANAGEMENT CONSULTING CO LTD

Nuclear power in-service inspection report generation method based on document labeling and tagging technology

The invention relates to the technical field of nuclear power in-service inspection report generation and provides a nuclear power in-service inspection report generation method based on document labeling and tagging technologies, aiming at solving the problems that the manual compiling cost of a nuclear power in-service inspection report is high, the data accuracy and consistency cannot be guaranteed, data updating is difficult and the utilization rate is low. Comprising the following steps: analyzing collected related data of the in-service inspection field to obtain text content, and carrying out structured storage; establishing a professional vocabulary recognition model, and performing text word segmentation; performing field proper noun recognition on a text word segmentation result; according to a predefined rule and guide, adjusting and labeling the words through an NLTK part-of-speech tagging device; converting the labeled text data set into a word vector, and calculating a position vector; analyzing and processing in-service inspection record content; according to the invention, the cost is saved, the data utilization rate is improved, and a more intelligent report generation service is provided for nuclear power in-service inspectors.
Owner:CHINA NUCLEAR POWER OPERATION TECH CORP

Language model optimizing and processing method and device, medium and program product

The embodiment of the invention provides a language model optimizing and processing method and device, a medium and a program product. The method comprises the steps that path data of a calling tool corresponding to a language model is obtained, a preference data set is constructed based on the path data, and the path data comprises a successful path and a failed path; obtaining input data based on the preference data set, inputting the input data into the language model, and obtaining a corresponding output result; determining a loss function based on the output result and a reward model; and adjusting parameters of the language model based on the loss function to obtain an optimized language model. The method can enrich the preference data set by introducing the failure decision information, improves the data utilization rate, optimizes the language model, and improves the accuracy of the language model.
Owner:ALIBABA CLOUD COMPUTING CO LTD

Method for constructing digital twin flight system of unmanned aerial vehicle cluster

The invention provides a digital twin flight system construction method of an unmanned aerial vehicle cluster, and belongs to the technical field of digital twin. The method comprises the following steps: constructing a system model of an unmanned aerial vehicle cluster flight system, wherein the system model comprises a plurality of unmanned aerial vehicle geometric models, an unmanned aerial vehicle cluster geometric model and a flight environment geometric model; constructing a digital twin system, loading the system model into the digital twin system, and completing recording, simulation, retrieval and control of all real unmanned aerial vehicles in the digital twin system to obtain a digital twin flight system; a digital twin flight system is utilized to construct a parameter optimization scheme of a system model, and the parameter optimization scheme is dynamically adjusted according to real-time data and historical data. The flight efficiency of the unmanned aerial vehicle cluster can be improved, and the flight path and maneuverability of the unmanned aerial vehicle cluster can be optimized.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Method and device for determining phase center deviation of GNSS antenna and medium

The invention provides a GNSS antenna phase center deviation determination method and device and a storage medium, and relates to the technical field of satellite navigation and positioning. Comprising the steps of obtaining parameter information of a to-be-tested antenna and a reference antenna; based on the parameter information, establishing a phase center deviation observation model of the to-be-tested antenna based on rotation modulation; controlling GNSS receivers corresponding to the antenna to be measured and the reference antenna to perform synchronous static measurement on a target satellite based on the parameter information so as to obtain a measurement result; determining a target position corresponding to the target satellite in the observation time period; and determining a horizontal phase center deviation value e of the antenna to be measured according to the measurement result, the target position and the phase center deviation observation model. The method can achieve the purpose of simply and efficiently measuring the phase center deviation of the antenna.
Owner:WUHAN SEISMIC METROLOGY & MEASUREMENT ENG RES INST CO LTD

Method for rapidly evaluating residual life of high-temperature material for active service equipment

The invention provides a method for rapidly evaluating the residual life of a high-temperature material for active service equipment, and belongs to the field of life evaluation in the field of materials. The method comprises the following steps: firstly, obtaining high-temperature creep relaxation rates and high-temperature creep endurance life information of two or more samples at different temperatures, and determining main curve equations and corresponding parameters ZSRT of different time sequence tissue states; thirdly, main curve equations of different time sequence organization states and corresponding parameters Zc are obtained, and the incidence relation between the ZSRT and the Zc is established; 5, for the to-be-evaluated alloy, obtaining a high-temperature creep relaxation rate main curve equation and a corresponding parameter ZSRT of the to-be-evaluated alloy; and 6, calculating the parameter Zc of the to-be-evaluated alloy by using the incidence relation between the ZSRT and the Zc, and establishing a high-temperature creep endurance life main curve equation through the parameter Zc to realize life evaluation. The method has the advantages of short test time, less material loss, high data utilization rate and the like, and is particularly suitable for evaluating the endurance life caused by the change of the structure state.
Owner:DALIAN UNIV OF TECH

Component reliability evaluation method and device

The invention belongs to the technical field of electronic component reliability evaluation, and discloses a component reliability evaluation method and device, and the method comprises the steps: obtaining historical test data and production process parameters, and the reliability expectation value and production process parameters of a to-be-evaluated batch; statistical analysis is carried out on historical test data to establish a product reliability baseline and failure rate statistical model parameters; performing statistical estimation by using the baseline and the expected value to obtain a production sample scheme and a sampling scheme; performing statistical estimation and comparison by using the baseline after parameter association, the production process parameters of the batch to be evaluated, the model parameters after index association and an expected value, and determining a screening method and an inspection method; and evaluating the screening reliability by using a screening scheme composed of a production sample scheme and a screening method to obtain screening reliability data, and comparing the screening reliability data with a product reliability baseline to determine an inspection scheme. According to the method, the historical data is used for component reliability evaluation, the data utilization rate is improved, and the inspection time and expenditure are reduced.
Owner:NAT SPACE SCI CENT CAS

Load frequency control method applied to multi-region power system with hopping parameters

The invention relates to the technical field of electric power control systems, in particular to a load frequency control method applied to a multi-region electric power system with hopping parameters, which takes a multi-region Markov hopping power system model as an asynchronous Markov process, introduces a Markov superposition technology into the system model, and improves the load frequency control accuracy. Operation state switching caused by factors such as different load requirements, element faults, environment changes and complex external disturbance in practical application is described. This Markov overlay process has been attempted for the first time in a multi-zone interconnected power system. Therefore, according to the method, a traditional power system model is popularized, the proposed power system model better conforms to an actual application scene, and any initial strategy pair can be selected to initialize the proposed algorithm. The algorithm makes up for insufficient experience of operators and avoids certain potential safety hazards of an actual device. The problem that an existing load frequency control method is low in practicability is solved.
Owner:GUANGXI NORMAL UNIV

Fire coal information data management method and system

The invention discloses a fire coal information data management method and system. The method comprises the following steps: S1, recording and storing fire coal management data for calling; s2, recording and storing fire coal transportation data for calling; s3, recording and storing coal sample data for calling; s4, selecting a coal source according to the blending combustion scheme; and calling fire coal management data, fire coal transportation data and coal sample data, automatically calling the fire coal plan, purchase plan data and as-fired coal source information data in the data analysis module according to the interval of the load value corresponding to each time period of the coal-fired unit in the actual fire coal machine account information, and automatically calling the fire coal plan, purchase plan data and as-fired coal source information data according to the blending combustion scheme matched with the power generation load of the unit. Forming a decision; s5, generating fire coal plan and purchase plan information data; and S6, confirming and issuing a fire coal plan and purchase information data. The system executes the method. The method has the advantages of being simple in principle, easy to implement, capable of improving working efficiency and operation management level and the like.
Owner:JINGDEZHEN POWER PLANT OF STATE POWER INVESTMENT GRP JIANGXI ELECTRIC POWER CO LTD

Power grid data analysis and prediction method and system

The invention belongs to the technical field of data analysis, and relates to a power grid data analysis and prediction method and system, and the method comprises the steps: obtaining original data, carrying out the analysis and processing of the original data, carrying out the data feature selection, constructing the data meeting the data features into a data set, and storing the data set; business scene building is carried out, and a data set is selected according to manual building or intelligent building; and constructing an interaction component, wherein the interaction component calls the selected data set to output interaction information. The method has the beneficial effects that a set of software with high flexibility and high operability is provided, the data utilization capability is improved, the operation efficiency and reliability of a power grid are optimized, and the response capability to emergencies is also improved, so that a power grid enterprise is supported to efficiently extract valuable information from mass data for scene planning, and the power grid enterprise is enabled to have a good development prospect. Strategic decision and daily operation management are assisted.
Owner:XIAN AOFANG ELECTRIC TECH CO LTD

Semiconductor device data acquisition methods and systems that support standardized communication upgrades

The present invention provides a semiconductor equipment data acquisition method and system that supports standardized communication transformation, realizes data acquisition and process control of different types of semiconductor equipment, formulates corresponding communication rules for equipment that already meets the communication standards, and the cluster system converts the equipment communication protocol to match the standard interface. For equipment that does not fully meet the standards but can achieve communication through programming, the cluster system will directly obtain the required data and convert it to meet the standard interface specifications. For equipment without communication capabilities, image recognition technology is used to collect data through the equipment interface, and data input and function operations are achieved by simulating keyboard and mouse operations. Finally, the cluster equipment control system completes the protocol conversion from data to the standard interface. And the equipment data is converted into a message data packet that meets the standard semiconductor equipment communication interface, thereby achieving docking with the semiconductor equipment data analysis and process control system, and improving the production efficiency and quality of semiconductor equipment.
Owner:BEIJING KEYANG TECH CO LTD

Drilling pump pressure prediction method based on artificial neural network

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.
Owner:CNOOC ENERGY TECHNOLOGY & SERVICES LTD

AS severity classification system based on lightweight model and semi-supervised learning

The invention discloses an AS severity classification system based on a lightweight model and semi-supervised learning, and belongs to the field of medical image processing. According to the method, the problems of waste of unlabeled data, poor interpretability of patient-level AS severity classification caused by lack of view classification and image-level AS severity classification, high calculation requirement caused by large model parameter quantity and the like in the existing method are solved. According to the method, a lightweight model LWM is designed based on structure re-parameterization, deep large kernel convolution and wavelet down-sampling, and the LWM is trained through semi-supervised learning. The semi-supervised learning uses targeted strong enhancement and selective total loss calculation, a model LWM can be trained by using label data and a large amount of label-free data, view classification and image-level AS severity classification are realized by the trained LWM, and a patient-level AS severity classification result is obtained by using an aggregation mechanism based on view correlation. The method can be applied to view classification and AS severity classification of echocardiograms.
Owner:NORTHEAST FORESTRY UNIV

Wheel-rail contact load decoupling prediction method, electronic equipment and storage medium

The invention provides a wheel-rail contact load decoupling prediction method, electronic equipment and a storage medium, and the prediction method comprises the steps: building a wheel-rail contact three-dimensional simulation model, and determining a strain collection radius and a collection point on a wheel; setting boundary conditions, running speed and traction torque of the wheel-rail contact three-dimensional simulation model; solving and calculating the wheel-rail contact three-dimensional simulation model to obtain a strain value and a contact force of each strain acquisition point of the wheel; inputting the obtained strain value and contact force of each strain acquisition point of the wheel into a neural network model for training, and establishing a wheel-rail contact neural network model of a strain-contact force relationship; unknown strain data are input into the wheel-rail contact neural network model of the strain-contact force relation, and wheel-rail contact force is obtained; according to the method, the wheel-rail contact force can be accurately identified and predicted.
Owner:HUNAN UNIV

Construction method of software reliability evaluation model

The invention relates to a method for constructing a software reliability evaluation model, which comprises the following steps of: A, acquiring multi-source data, and preprocessing the multi-source data; b, constructing a multivariate smooth spline regression model; c, updating parameters of the multivariate smooth spline regression model in real time according to the prior distribution and operation data through a Bayesian formula; d, parameters of the multivariate smooth spline regression model are updated in real time through the Kalman filtering technology, and model parameter prediction, prediction error covariance calculation, Kalman gain calculation, state updating and error covariance updating are sequentially carried out every time operation data arrives; and E, training and verifying the updated multivariate smooth spline regression model to obtain a final evaluation model. According to the method, the evaluation precision and robustness of the software reliability are improved, the calculation efficiency and the automation degree are improved, and the result interpretability and the data utilization efficiency are enhanced.
Owner:CHENGDU TIANHE TECH CO LTD

Question and answer knowledge base construction method and device, equipment and storage medium

The invention relates to a question and answer knowledge base construction method, which comprises the following steps: acquiring historical text data, simultaneously acquiring question examples, and identifying potential questions in the historical text data according to the question examples and a question model; and inputting the potential questions and the reference text into a question model to obtain question answers, and forming an original question-answer pair by the potential questions and the corresponding question answers. And screening out high-quality target question and answer pairs from the original question and answer pairs, and constructing a question and answer knowledge base according to the target question and answer pairs. The question and answer knowledge base is constructed by utilizing the large language model, so that the labor cost can be greatly reduced, the data utilization rate and the construction efficiency are improved, the expansibility and the consistency of the knowledge base can be enhanced, and the information requirement of rapid change is met.
Owner:PING AN TECH (SHENZHEN) CO LTD

WGS methylation level prediction method and tissue origin inference method

PendingCN118983003AOvercoming technical barriers to bisulfite conversionImprove data utilizationProteomicsGenomicsBio informaticsHuman specific
The invention relates to a WGS methylation level prediction method and a tissue origin inference method, and belongs to the technical field of gene detection. And performing whole genome sequencing (WGS) on the cfDNA by using a next-generation sequencing technology. The method comprises the following steps: extracting fragment characteristics of each cfDNA fragment through a bioinformatics means, marking CpG points covered by each fragment of WGS data as an unmethylated state and a methylated state by using a Gaussian mixture model, then constructing a non-uniform hidden Markov model, decoding the optimal methylated state of each CpG in each fragment, and finally obtaining the optimal methylated state of each CpG in each fragment. And summarizing the state of each CpG point on the reference genome, and calculating the continuous methylation level. In contrast to the disclosed human specific reference methylation profiles, methylation signals are deconvolved at the fragment level, estimating the relative abundance of cell types and tissues contributing to cfDNA. According to the method, the methylation level and the origin tissue state of the cfDNA can be directly deduced from WGS data.
Owner:GENESEEQ TECH INC +1