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

357results about How to "Accuracy" patented technology

Extreme rainstorm waterlogging disaster risk dynamic assessment method for disaster prevention and reduction

The invention discloses an extreme rainstorm waterlogging disaster risk dynamic assessment method for disaster prevention and reduction, which comprises the following steps of: investigating urban system data and disaster prevention and reduction data, performing refined risk unit division on disaster-bearing bodies on urban building and road network scales by utilizing a GIS (Geographic Information System) technology, and determining disaster-bearing body space distribution; simulating the disaster influence of the dynamic change process of the flood ponding depth on the disaster-bearing body based on the extreme rainstorm waterlogging scene; carrying out waterlogging risk refined dynamic evaluation by combining two methods of waterlogging process simulation and an index system; calculating traffic capacity and emergency service accessibility of a road network system by utilizing a space complex network and shortest path planning; on the basis, reasonable distribution of disaster prevention emergency drainage and emergency rescue service to a high-risk area is comprehensively considered, a waterlogging risk dynamic assessment technology fusing disaster evolution and a disaster prevention response process is provided, and dynamic assessment of the waterlogging risk of each disaster-bearing unit in a waterlogging disaster evolution process is finally realized.
Owner:NORTHWEST ENGINEERING CORPORATION LIMITED

Intelligent control method of industrial production system based on time sequence prediction

The invention relates to the technical field of time sequence prediction, in particular to an intelligent control method of an industrial production system based on time sequence prediction, and the method comprises the steps: collecting historical time sequence data to improve the data quality; taking the preprocessed data as a training set, constructing a time sequence prediction model, and adjusting model parameters by using an algorithm so as to accurately capture time sequence features; predicting a controlled variable of a future time point through a time sequence prediction model, and making an optimal control strategy; weighting operation is carried out based on prediction results of different controlled variables, and a process variable is introduced to correct and adjust a reference value of a manipulated variable, so that multi-variable coordination control is realized; an actual value of a controlled variable is obtained in real time, error analysis is carried out on a predicted value of the controlled variable at a future time point in combination with the model, and dynamic adjustment is carried out. The method is used for solving the technical problems that in an existing scheme, data prediction of an industrial production system is inaccurate, and a control strategy is not optimized.
Owner:BEIJING NANTIAN ZHILIAN INFORMATION TECH CO LTD

Automatic task allocation method and system for elevator emergency rescue platform

The invention provides an automatic task allocation method and system for an elevator emergency rescue platform, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining elevator operation state data and environment information data, constructing an emergency task model, and obtaining classified emergency tasks; inputting the classified emergency tasks into a deep reinforcement learning model to generate a task allocation scheme; the deep reinforcement learning model is formed by combining a deep Q network structure with a priority scanning algorithm, and a priority experience playback mechanism is introduced; and constructing a multi-objective optimization module comprising a time constraint, a space constraint and a resource constraint, and optimizing the task allocation scheme by the multi-objective optimization module based on an improved particle swarm algorithm to obtain an optimal task allocation scheme.
Owner:NINGBO SPECIAL EQUIP INSPECTION & RES INST +1

Partial discharge positioning method, system and equipment based on acoustic-electric combined signal

The invention discloses a partial discharge positioning method, system and device based on an acoustic-electric combined signal, and relates to the technical field of electrical device detection, and the method comprises the steps: deploying a plurality of sensor nodes based on a target electrical device, and collecting an electromagnetic signal and a sound wave signal generated by partial discharge at the same time; calculating a preliminary positioning result of the partial discharge source based on the collected acoustic-electric combined signal; environment parameter data, historical operation data and electrical equipment structure information in the electrical equipment are collected and input into a preset error correction model, and a corresponding error correction interval is obtained; when a certain preliminary positioning result exceeds the corresponding error correction interval, obtaining a timestamp corresponding to the preliminary positioning result; performing multi-source information fusion positioning based on the environmental parameter data, the historical operation data, the electrical equipment structure information and the corresponding timestamps, and analyzing and determining final positioning coordinates of the partial discharge source; the accuracy of partial discharge signal positioning is improved, and the positioning efficiency is improved.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO

Industrial safety risk assessment and management system and method based on cognitive computing

The invention discloses an industrial safety risk assessment and management system and method based on cognitive computing, and the method comprises the following steps: S1, collecting operation data from industrial equipment, including equipment states, performance parameters and environmental factors, and carrying out the preprocessing of the collected data; s2, performing feature learning on the preprocessed data by using a convolutional neural network, and identifying a spatial pattern and relevance in the data; s3, taking the output of the convolutional neural network as the input of a long-short term memory network, and analyzing the time sequence features of the data; s4, performing mode identification and fault prediction based on the output of the long and short term memory network in the step S3, and identifying a potential fault mode and an abnormal signal; and S5, generating a risk assessment report and a fault early warning according to the information identified in the step S4, and providing the risk assessment report and the fault early warning to an operator and a manager as decision support. According to the invention, a deep learning technology is fully utilized, and a system for industrial safety risk assessment and management is described.
Owner:JIJI SAFETY & ENVIRONMENTAL PROTECTION TECHNOLOGY (CHANGZHOU) CO LTD

Wide-frequency-range resonance detection method for power system

The invention relates to the technical field of resonance detection, and discloses a power system wide frequency range resonance detection method, which is based on broadband signal detection, and comprises the following steps: in an early-stage preparation stage, selecting proper sensors and equipment to collect signals, and ensuring that the collected signals have broadband characteristics; meanwhile, the collected signals are filtered, high-frequency noise is removed, and continuous signals are converted into discrete data; according to the force system wide frequency range resonance detection method, a discrete instantaneous sampling value derivation metering formula is utilized to calculate instantaneous power, and a new metering algorithm is formed through wavelet packet frequency band decomposition, harmonic power metering, harmonic distortion rate calculation, resonance harmonic amplitude analysis and amplitude comparative analysis, so that precise metering of each harmonic is realized; a Hilbert transformation algorithm is introduced in the instantaneous power calculation and resonance harmonic amplitude analysis process; discrete electric energy metering based on an integral theory and resonance harmonic analysis based on a broadband quantity measurement method form a system broadband resonance detection technical process, corresponding harmonic waves can be extracted, and parameter characteristics and resonance information can be obtained.
Owner:YUXI POWER SUPPLY BUREAU OF YUNNAN POWER GRID

Manufacturing industry supply chain optimization method, system and equipment based on large model and medium

The invention discloses a manufacturing industry supply chain optimization method, system and equipment based on a large model, and a medium, belongs to the technical field of large model and supply chain management, and aims to solve the technical problem of how to monitor, predict and optimize a supply chain in real time, improve the efficiency of the supply chain and improve the efficiency of the supply chain. According to the technical scheme, the method comprises the following steps: data acquisition and preprocessing: comprehensively acquiring manufacturing industry supply chain data, and carrying out cleaning, duplicate removal, missing value processing, abnormal value detection and data normalization processing on the acquired manufacturing industry supply chain data to obtain preprocessed manufacturing industry supply chain data; building a large supply chain model: building the large supply chain model by utilizing the preprocessed manufacturing industry supply chain data, and training, optimizing and deploying the supply chain model; real-time monitoring and prediction: monitoring the inventory level and each index of the generation progress in the manufacturing industry supply chain in real time through the trained large model; optimizing the decision; and updating and iterating the model.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Industrial defect real-time detection and positioning method, system and device and medium

The invention provides an industrial defect real-time detection and positioning method, system and device and a medium, and the method comprises the steps: collecting an industrial defect data image, and carrying out the preprocessing of the industrial defect data image; marking the industrial defect data image to generate an industrial defect detection data set; fusing the convolutional neural network and the recurrent neural network to generate a deep neural network hybrid model; performing self-supervised pre-training and transfer learning according to the deep neural network hybrid model and the industrial defect detection data set; introducing an attention mechanism for the deep neural network hybrid model, and outputting coordinate information of a defect area in combination with frame regression and a key point estimation algorithm; optimizing the model by adopting a model lightweight technology and a hardware acceleration technology; and packaging the model and a corresponding algorithm into a preset industrial detection system, and carrying out real-time detection and positioning of industrial defects through linkage with production line equipment. According to the invention, defects of industrial products can be efficiently and accurately detected and positioned.
Owner:INSPUR YUNZHOU (SHANDONG) IND INTERNET CO LTD

Flight space orientation training auxiliary system and method

The invention discloses a flight space directional training auxiliary system and method, and the system comprises a flight task simulation module; the meteorological environment simulation module is used for simulating a meteorological scene corresponding to a flight task, and simulating the meteorological scene by establishing a multi-dimensional meteorological model and combining meteorological parameters; the meteorological environment parameter control module comprises a time step length control module which adopts a preset time step length to input meteorological parameter observation data collected in real time to the meteorological parameter setting module; the specific meteorological event control module is used for transmitting meteorological parameters of a specific meteorological event area to the meteorological parameter setting module when the airplane triggers a specific meteorological event; and the training scheme generation module is used for generating a proper training scheme according to the historical training information of the flight personnel. According to the system and the method, a real and personalized simulation training environment can be provided for the flight personnel, and the professional skills and the capability of coping with various flight conditions of the flight personnel are effectively improved.
Owner:AIR FORCE MEDICAL CENT PLA

Vegetation resistance and resilience evaluation system and method under drought stress

The invention discloses a vegetation resistance and resilience evaluation system and method under drought stress, and belongs to the field of global change ecology research. Comprising the following steps: collecting related data of vegetation resistance and restoring force by using a data collection module, and inputting the related data of vegetation resistance and restoring force into a data storage module for storage, a vegetation physiological index processing sub-module, a vegetation structure index processing sub-module and a vegetation function index processing sub-module in the data processing module are called to process the collected and stored data; and calling a lag accumulation correlation coefficient calculation sub-module, a vegetation resistance index and restoring force index evaluation model sub-module and a vegetation resistance and restoring force grade division sub-module in the analysis and evaluation module, and finally outputting vegetation resistance and restoring force evaluation grades. According to the method, comprehensive, systematic and accurate evaluation and grading can be carried out on the resistance and the restoring force of the vegetation under drought stress, the vegetation which is difficult to resist drought or is restored after drought stress in the evaluation area is effectively identified, and the method is simple to operate and easy to realize.
Owner:SHENYANG INST OF APPL ECOLOGY CHINESE ACAD OF SCI

Diabetic retinopathy image recognition method based on federal learning and differential privacy

PendingCN119128979ASolving privacy challengesmaintain statistical propertiesDigital data protectionMachine learningDiabetes retinopathyData set
The invention provides a diabetic retinopathy image recognition method based on federated learning and differential privacy, and belongs to the field of federated learning. The method comprises the following steps: carrying out preprocessing and Poisson sampling on a diabetic retinopathy image data set to initialize a global model located in a central server; the local client obtains parameters of the global model from the central server and constructs a local model; the local client performs training and differential privacy processing on a local model by using local data; the central server receives the parameters uploaded by the clients for secure aggregation, and updates the global model by using the parameters after secure aggregation; if the number of training iterations does not reach the threshold value specified by the user, a result is transmitted to the local model to continue the training process; and when the number of training iterations reaches a threshold value specified by the user, terminating a further iteration process to obtain a trained model. And the problems of gradient leakage and data loss possibly existing in privacy protection by introducing differential privacy in federated learning are balanced.
Owner:DALIAN MARITIME UNIVERSITY

Self-adaptive cruise target selection method and device, computer equipment and medium

The invention provides a self-adaptive cruise target selection method and device, computer equipment and a medium, and relates to a self-adaptive cruise technology, and the method comprises the steps: obtaining historical tracks of a plurality of targets under a self-vehicle coordinate system; determining a predicted driving track of the vehicle; for each target, calculating a deviation average value EAvg and a deviation maximum value EMax of a target historical track and a self-vehicle prediction track at each point; traversing each target, judging whether the own vehicle follows the historical track of the target or not, and determining the target of which the own vehicle follows the historical track; and determining a self-vehicle following target in the targets of the self-vehicle following historical track. The method is suitable for high-speed or low-speed lane changing; target historical trajectories are introduced to be fused with self-vehicle predicted driving trajectories, and target selection is more stable; according to the target selection method, the target selection track is adopted only for the current target which is the lane changing scene that the vehicle follows the target vehicle and is judged to be recently followed by the vehicle, and the target selection tracks of other targets are not influenced, so that the flexibility of target selection is improved.
Owner:WUHAN JIMU INTELLIGENT TECH CO LTD

Automatic measurement method for net water intake rate of acute ischemic stroke based on CTP infarct core

The invention relates to an acute ischemic stroke net water intake rate automatic measurement method based on a CTP infarction core, and the method comprises the following steps: (1) registration of an NCCT image and a CTP image, (2) extraction of an RAPID-CTP core infarction region, (3) mapping of the infarction core region, (4) searching of a brain midline on the NCCT, and (5) mirroring of the core infarction region on the NCCT. (6) threshold operation; and (7) NWU value calculation. And calculating according to an NWU calculation formula so as to quantify the NWU of the AIS ischemic infarction focus. The technical scheme has the characteristics of automation, standardization, simplicity and convenience in operation and the like, and manual intervention is not needed.
Owner:JIANGSU PROVINCE HOSPITAL (THE FIRST AFFILIATED HOSPITAL OF NANJING MEDICAL UNIVERSITY)

Helicopter adaptive command filtering backstepping tracking control law design method

The invention belongs to the field of aircraft control, and particularly relates to a helicopter adaptive command filtering backstepping tracking control law design method, which comprises the following steps: firstly, decomposing a helicopter kinetic model into a plurality of strict feedback systems with uncertainty, and then designing a controller by using a backstepping method; a hybrid command filter is adopted to solve the problem of calculation explosion of backstepping, and a filtering compensation mechanism is introduced. In addition, an uncertain part in the model is approximated by adopting a neural network, and network parameters are updated online by adopting an adaptive law. And finally, designing a Lyapunov function to prove the effectiveness of the method.
Owner:CHINA HELICOPTER RES & DEV INST

Premature delivery prediction method and device, electronic equipment and readable storage medium

The invention provides a premature delivery prediction method and device, electronic equipment and a readable storage medium, and relates to the technical field of data analysis. The method comprises the following steps: based on a preset model, scoring acquired comprehensive information of a pregnant woman in an early pregnancy stage; wherein the comprehensive information comprises demographic information, clinical information and biochemical index information; and predicting the premature delivery risk of the pregnant woman according to the scoring result. According to the method, the comprehensive information of the pregnant women at the early pregnancy stage is scored through the preset model, the premature delivery risk of the pregnant women is predicted according to the scoring result, quantitative evaluation of premature delivery risk prediction of the pregnant women at the early pregnancy stage is achieved, and objectivity and certain accuracy are achieved; and the difficulty and the cost of obtaining the comprehensive information of the pregnant women in the early pregnancy are relatively low, the difficulty and the cost of predicting the premature delivery risk of the pregnant women in the early pregnancy are reduced, and medical resources are saved.
Owner:NINGBO UNIV

Data merging optimization method and device for incremental data migration, equipment and storage medium

The invention discloses a data merging optimization method and device for incremental data migration, equipment and a storage medium, and relates to the technical field of databases, and the method comprises the steps: carrying out the data collection of a source end database, and sequentially sending the collected data to a message queue; sequentially pulling the data from the message queue, merging the data, and converting the data into a data packet; performing execution sequence number distribution on the data packets; and based on the execution sequence number, sequentially playing back the data of the data packet to a target end database. According to the method, the effect of concurrent execution of the single-table data is achieved through data merging, the problem that the single-table incremental data cannot be executed in parallel due to the time sequence problem is solved, the method does not depend on the characteristics of the database, can be suitable for data migration synchronization of different database types, and is good in compatibility.
Owner:JINZHUAN INFORMATION TECHNOLOGY CO LTD

Method for quantitatively evaluating subsequent commutation failure immune level of alternating-current and direct-current hybrid system

The invention discloses a method for quantitatively evaluating the immune level of subsequent commutation failure of an AC-DC hybrid system, and the method comprises the steps: carrying out the analysis of the transient process of the system based on the transient reactive dynamic characteristics of the AC-DC hybrid system on the basis of achieving the cross-regional power transmission through a high-voltage DC power transmission technology; the essential relation among the electrical quantities in the transient process is obtained; and deducing an online evaluation index GCFII for reflecting the immune level of the subsequent commutation failure of the system in combination with known system parameters and electrical signals acquired by the PMU. According to the method, the influence of the direct current control mode is considered by obtaining the online evaluation index GCFII, and real-time updating can be carried out along with the change of system operation parameters, so that the requirements of real-time performance and accuracy can be met, a theoretical basis is provided for power grid construction and operation of operation personnel, and safe operation of a power grid is effectively ensured.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO

Method and system for monitoring regional biodiversity based on unmanned aerial vehicle technology

The embodiment of the invention relates to the technical field of information, in particular to a method and system for monitoring regional biodiversity based on an unmanned aerial vehicle technology. The method comprises the following steps: reading a plurality of aerial images; identifying a plant population in the area according to the visible light aerial image, and obtaining a predicted animal variety and a prediction scale according to the plant population; animal individuals appearing in the visible light aerial image and the infrared aerial image are recognized, and the appearing type and the appearing number of the animal individuals are obtained; obtaining each appearance type, likelihood scale and confidence coefficient according to the appearance type, the appearance number, the predicted animal type and the prediction scale thereof; establishing a regional ecological model according to the likelihood scale of all appearance types; correcting the likelihood scale of each appearance type according to the food chain relationship of the regional ecological model and the confidence coefficient of each appearance type; and obtaining a regional biodiversity monitoring result according to the plant population and the regional ecological model after the likelihood scale is corrected.
Owner:ZHEJIANG FORESTRY UNIVERSITY

Safety monitoring method and device for roof of fully mechanized coal mining face

PendingCN119435135AAccuracy
The invention provides a safety monitoring method and device for a fully mechanized coal mining face roof. The method comprises the steps that a first data set related to a hydraulic support of the fully mechanized coal mining face is obtained, wherein the first data set at least comprises the initial supporting force, the resistance increasing ratio, the weighting step pitch and the safety valve opening proportion of the hydraulic support; micro-seismic of the fully mechanized coal mining face is monitored, a second data set is obtained, and the second data set comprises daily micro-seismic event maximum energy, daily micro-seismic event total energy and daily micro-seismic event total energy increase; and according to the first data set and the second data set, carrying out disaster grade identification on the fully mechanized coal mining face roof so as to determine a target disaster grade of the fully mechanized coal mining face roof. Due to the fact that multiple evaluation indexes are adopted for evaluating and analyzing the roof disaster danger degree, and the adopted evaluation index reference values are all statistical data obtained based on the mining theory and mining practice, the analysis structure of the roof disaster danger degree is more scientific and accurate.
Owner:SHENHUA SHENDONG COAL GRP +1

Frequency conversion regulation and control system of dust removal fan set for recycling secondary metal

The invention discloses a dust removal fan set frequency conversion regulation and control system for secondary metal recovery, relates to the technical field of dust removal fan control, and solves the technical problem in the prior art that regulation and control requirements of a dust removal fan cannot be judged after efficiency evaluation is qualified during frequency modulation control of a dust removal fan set. The method specifically comprises the steps that after the efficiency of a dust removal fan is normal, the frequency modulation requirement of the dust removal fan is judged, the historical machining time period of a smelting site is collected, the operation time period of a dust removal fan unit in the historical machining time period is collected, and the smelting site is divided into a plurality of sub-areas according to the area where construction process equipment is located; and dividing into a main evaluation area and an auxiliary evaluation area according to sub-area analysis, acquiring a control time period parameter and a control mean value parameter, and performing frequency modulation demand judgment according to parameter analysis.
Owner:ANHUI HUACHUANG ENVIRONMENTAL TECHNOLOGY CO LTD

Application of copper-gold nano-cluster / carbon quantum dot ratiometric fluorescent probe in detection of aflatoxin

The invention discloses application of a copper-gold nano-cluster / carbon quantum dot ratiometric fluorescent probe in detection of aflatoxin, and belongs to the technical field of ratiometric fluorescent probes. According to the invention, the ratio fluorescent probe is constructed by using the copper-gold nano-cluster / carbon quantum dots, and an aflatoxin fluorescence detection system based on nano-cluster aggregation fluorescence quenching is established according to the structure and property characteristics of a target detection object aflatoxin, so that convenient and accurate detection of aflatoxin is realized. The copper-gold nano-cluster is prepared by adopting a chemical reduction method, the method is simple and easy to operate, and the process is simple and controllable; the ratio-type fluorescence probe is used for replacing a traditional switch-type fluorescence detection probe and does not depend on single signal change, so that background and environmental errors are greatly reduced. The copper-gold nano-cluster / carbon quantum dot ratiometric fluorescent probe disclosed by the invention lays a theoretical and experimental foundation for accurate and rapid detection of aflatoxin.
Owner:SICHUAN UNIV

Unconventional oil reservoir volume fracturing horizontal well yield prediction method and device and storage medium

The invention relates to an unconventional oil reservoir volume fractured horizontal well yield prediction method and device and a storage medium. The method comprises the steps that horizontal well parameters of a horizontal well to be predicted are obtained; obtaining the peripheral vertical well yield of the horizontal well to be predicted; constructing a horizontal well after-pressure yield prediction formula of the horizontal well to be predicted; determining an undetermined coefficient of the horizontal well after-pressure yield prediction formula; and calculating the yield of the horizontal well to be predicted. According to the method, the actual mine field data regression analysis method is adopted to calculate the horizontal well yield after volume fracturing, the influence of the oil and gas enrichment degree and the fracturing transformation degree on the yield increasing effect is considered, meanwhile, by introducing the peripheral vertical well yield, the difference of the yield increasing effects of different blocks and different parts is reduced, and the yield increasing efficiency is improved. Practice proves that the calculation method has certain accuracy; the method has high operability and is well applied to exploration and development practice of low-grade oil reservoirs.
Owner:PETROCHINA CO LTD

Method implemented by computer system and oocyte mass analysis system

The present disclosure relates generally to systems and methods for assessing oocyte viability. In some embodiments, a sequence of images associated with an oocyte sucked into a pressure tool is acquired. Based on the sequence of images and the pressure applied to the oocytes, morphological and mechanical features associated with the oocytes can be derived. At least some of the features may then be provided to a machine learning model to determine an indicator representative of oocyte quality, where a particular indicator may be representative of blastocyst formation. Optionally, the determined oocyte quality information may be presented to a user via an interactive user interface.
Owner:INTI TAIWAN INC

GOOSE protocol message anomaly detection method based on generative adversarial network model

The invention discloses a GOOSE protocol message anomaly detection method based on a generative adversarial network model, and the model training method comprises the following steps: S1, obtaining a large number of network data messages of an electric power industrial control system, and carrying out the preprocessing of the data, including denoising and data cleaning; s2, performing feature extraction on the GOOSE data, including a protocol field value, a source / destination address, a timestamp, a state number, a serial number, an AppID application identifier, a TAG identification value and a data length, so as to establish a proper feature set; and S3, training the GOOSE protocol data feature set through a generative adversarial network model. And continuously adjusting model parameters and training according to a training judgment result during detection, and analyzing and detecting an abnormal GOOSE protocol message. According to the method, effective anomaly detection can be carried out on the existing GOOSE protocol network attack, and safe operation guarantee is provided for an electric power industrial control network system.
Owner:ELECTRIC POWER SCI RES INST OF STATE GRID XINJIANG ELECTRIC POWER CO LTD

Method and system for automatically updating power grid equipment graph model based on data collected and recorded by unmanned aerial vehicle

The invention provides an automatic updating method and system for a power grid equipment graph model based on data collected and recorded by an unmanned aerial vehicle. The unmanned aerial vehicle is used for regularly patrolling a power grid line and collecting image data and position data of power grid equipment in real time; on the basis of a power grid GIS system and identified equipment information, topology key nodes of the power grid are automatically identified, and data collected by the unmanned aerial vehicle are compared and matched with an existing power grid topology structure through a data matching algorithm; providing a user interaction interface for a user to check a matching result, and performing confirmation or necessary adjustment; based on topological key node information, information of other devices on a line is automatically updated, newly collected data is integrated with an existing power grid device graph model, and corresponding power grid device graph model data is automatically updated. According to the method, the key topological nodes of the power grid can be automatically identified, the equipment information on the power grid line is automatically updated, the updating efficiency and accuracy of the power grid equipment graph model are improved, and real-time updating and sharing of data are realized.
Owner:NARI INFORMATION & COMM TECH

Risk assessment method and device, equipment, storage medium and computer program product

The invention discloses a risk assessment method, device and equipment, a storage medium and a computer program product, and is applied to the technical field of artificial intelligence. The multi-dimensional data at least comprises historical loan data of the to-be-evaluated enterprise, operation data of the to-be-evaluated enterprise and macroeconomic indicators; carrying out data processing on the multi-dimensional data through a target model, and generating a risk probability containing to-be-evaluated enterprise default; according to the risk probability and a risk probability range of a plurality of risk levels corresponding to the business to be handled, determining a risk level corresponding to the enterprise to be assessed under the business to be handled, the business to be handled being a business requested to be handled by the enterprise to be assessed; and determining whether to handle the to-be-handled business for the to-be-assessed enterprise according to the Therefore, the scheme provided by the invention can improve the accuracy of enterprise default risk assessment.
Owner:CHINA CONSTRUCTION BANK +1

Spatial surveying and mapping calibration method and system based on synchronous positioning drawing

The invention discloses a space surveying and mapping calibration method and system based on synchronous positioning drawing, and relates to the technical field of space surveying and mapping, the space surveying and mapping calibration method based on synchronous positioning drawing comprises the following steps: obtaining environment characteristic data; identifying a space environment and a key landmark; based on a stereoscopic vision technology, obtaining a space environment map according to the identified space environment and the key landmarks; adjusting the motion track of the detection equipment in the space environment by using an optimization algorithm; and calibrating the space environment map. The dynamic change in the space environment is monitored in real time, and the influence of the change on the map is evaluated, so that the environment change can be automatically judged and dealt with, the map is ensured to be always kept in the latest state, the space environment map can be automatically calibrated and updated, the need of manual intervention is reduced, and the working efficiency is improved. And the efficiency and timeliness of map maintenance are improved.
Owner:JIANGSU BURO INFORMATION TECH CO LTD

Method for correcting aging of nitrogen-oxygen sensor

The invention relates to an aging correction method for a nitrogen-oxygen sensor, which comprises the following steps of: measuring and calculating an aging correction coefficient, archiving the aging correction coefficient into an aging correction module, and extracting data in real time by using the aging correction module, so that the output value of the nitrogen-oxygen sensor is corrected, and after a probe is aged, the output value of the nitrogen-oxygen sensor is corrected. A relatively accurate numerical value can still be output, namely, aging of a probe is offset by using a correction part, an aging correction coefficient can be obtained by looking up a table in combination with accumulated working time, accumulated driving mileage and daily driving working conditions after the nitrogen-oxygen sensor is loaded and parameters such as NOx and O2 concentrations measured for a long time, and the value is multiplied by an output coefficient, so that the aging correction coefficient is obtained. And the output precision can be improved.
Owner:ZHEJIANG KERUIXIN ELECTRONIC TECH CO LTD

Detection method for targeted determination of branched chain amino acid and branched chain alpha-keto acid

The invention relates to the technical field of detection of endogenous substances in organisms, in particular to a detection method for targeted determination of branched chain amino acid and branched chain alpha-keto acid. According to the detection method, the branched chain amino acid and the branched chain alpha-keto acid are subjected to derivatization reaction, so that the detection targeting and the detection sensitivity of the branched chain amino acid and the branched chain alpha-keto acid are effectively improved; the UHPLC-MS / MS technology is adopted to improve the distinguishing capability of various isomers in branched chain amino acid and branched chain alpha-keto acid, and the detection targeting, detection sensitivity and detection precision of branched chain amino acid and branched chain alpha-keto acid are further improved.
Owner:SHENZHEN TRADITIONAL CHINESE MEDICINE HOSPITAL

Electric energy metering method and equipment for broadband characteristic of power system

The invention relates to an electric energy metering method for broadband characteristics of an electric power system. The electric energy metering method comprises the following steps: acquiring electric quantity data corresponding to current and voltage by using a filter built in a power grid system; preprocessing the electric quantity data to obtain effective electric quantity data; calculating the effective electric quantity data through a preset power formula to obtain average power of a sampling period; decomposing the electric quantity data of the electric power system to obtain a wavelet packet frequency band; carrying out adaptive harmonic extraction on the wavelet packet frequency band to obtain a sampling frequency spectrum; and obtaining an electric energy metering value of the power system according to the sampling frequency spectrum and time integration. In the technical scheme of the invention, the result shows that the amplitude and phase information of the waveform are well reserved by the extracted waveform, and electric energy metering can be carried out on each frequency component by direct integration; similarly, the method is used for processing other wavelet packet frequency bands, the same effect is remarkable, and the metering error can be controlled within 3%.
Owner:YUXI POWER SUPPLY BUREAU OF YUNNAN POWER GRID