21 results about "Target population" patented technology

The invention relates to a partial discharge fault diagnosis method and device, equipment, a medium and a product. The method comprises the following steps: performing feature extraction on sample partial discharge data of sample gas insulated switchgear under different fault types to obtain sample partial discharge features; constructing an initialized population; population individuals in the initialized population correspond to parameter combinations of to-be-trained parameters; updating individual positions of population individuals in the initialized population according to the sample partial discharge features to optimize the initialized population and obtain a target population; according to a target parameter combination in the target population, initializing model parameters of the extreme learning machine model; and performing model training on the initialized extreme learning machine model according to the sample partial discharge characteristics to obtain a fault diagnosis model which is used for diagnosing the fault type of the partial discharge signal. By adopting the method, the fault type of partial discharge can be accurately diagnosed.

The invention provides a Joint-Calling acceleration method and device for high-performance sequencing data, electronic equipment and a storage medium, and the method comprises the following steps: determining a division mode of genome variation data according to group information of a plurality of samples, and dividing each piece of genome variation data according to the division mode, obtaining a plurality of variation data fragments corresponding to each piece of genome variation data; merging variation data fragments with the same sequence in the genome variation data to obtain merged variation data; and respectively performing group variation detection on each piece of combined variation data to obtain group genome variation data of each piece of combined variation data, and combining each piece of group genome variation data to obtain target group genome variation data of a plurality of samples. Therefore, in the population variation detection process, the efficiency of obtaining complete population genome variation data can be improved by performing population anomaly detection on the multiple pieces of local merged data and merging the detection results.

The invention provides a causal inference method and device based on genetic variation, electronic equipment and a medium. The causal inference method comprises the following steps: acquiring whole genome SNP data and proteome data of a detection sample of a target population from a detection platform; performing whole genome association analysis on the whole genome SNP data to obtain outcome SNP data associated with the target phenotype; performing protein quantitative trait site analysis based on the whole genome SNP data and the proteome data to obtain exposure SNP data associated with the target exposure factor; and performing data preprocessing on the outcome SNP data and the exposed SNP data, and performing Mendel randomization analysis on the preprocessed outcome SNP data and exposed SNP data to obtain a causal relationship between the target exposure factor and the target phenotype. According to the method, the accuracy and reliability of Mendel stochastic analysis results are improved.

The invention discloses a population prediction method and device, electronic equipment and a storage medium. Comprising the following steps: acquiring satellite image data, night light image data and base station communication data of a target area; determining plane area data, floor number and building type of the building in the target area based on the satellite image data; for any building, determining the population density of the building based on the plane area data, the floor number and the building type of the building, and determining an initial population prediction result based on the plane area data, the floor number and the population density of the building; and determining a population calibration coefficient of the target area based on at least one of the night light image data, the base station communication data and the initial population prediction result of each building, so as to calibrate the initial population prediction result corresponding to each building, and obtain a corresponding target population data prediction result. Dynamic calibration of the population prediction data is realized, and the accuracy of the population prediction result is improved.

The invention provides a method and system for predicting the individual exposure level of air pollutants, and the method comprises the steps: S1, collecting the original sample data information of a subject population to form an original data set, and dividing the original data set into a training subset and a test subset; s2, constructing an air pollutant crowd exposure level initial model; s3, training the initial model by using the training subset, and optimizing the initial model based on the combination of a regularization method of Lasso regression, an SHAP value weighting method and a recursive feature elimination algorithm; step S4-S5, obtaining model prediction data and evaluating prediction accuracy; and step S6, collecting input characteristic variables of a target population different from the subject population, and substituting the input characteristic variables of the target population into the prediction model subjected to accuracy evaluation to realize prediction of the air pollutant individual exposure level of the target population. The prediction model is better in fitting performance and high in accuracy.

A system and method for determining and managing reputation of an entity or industry includes determining a sample size of the population that provides at least a pre-defined percent confidence interval, and which has the predefined level of familiarity (unique group); determining a measure of likelihood that the targeted population will perform a positive action on behalf of an entity (behavioral connection score), wherein determining the measure of the likelihood that the targeted population will perform a positive action on behalf of an entity comprises: receiving survey ratings from behavioral connection survey questions where each survey rating is provided by a party within the unique group; weighting the received survey ratings to accommodate for at least one of the group consisting of cultural bias and missed demographic quotas; and aggregating the ratings within each individual question to provide a single aggregated behavioral connection score for each behavioral connection survey question.

The system according to the embodiment aims to efficiently collect and analyze reviews from personas tailored to a target demographic. [Solution] A system according to an embodiment includes a reception unit, a generation unit, a collection unit, an analysis unit, and a provision unit. The reception unit inputs attributes of a target demographic. The generation unit generates a persona based on the attributes input by the reception unit. The collection unit collects reviews based on the persona generated by the generation unit. The analysis unit analyzes the reviews collected by the collection unit. The provision unit provides the analysis results obtained by the analysis unit.

The invention provides a parameter identification method and device of a permanent magnet synchronous motor, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed parameter of the permanent magnet synchronous motor, the to-be-processed parameter being used for representing an initial population individual in a genetic algorithm; identifying a permanent magnet synchronous motor working condition corresponding to the initial population individuals, and determining a pre-calibration weight coefficient corresponding to the preset target function through the working condition; determining fitness values of the initial population individuals through a preset objective function; target population individuals are screened out through the fitness values, and iterative operation is carried out on the target population individuals; for each iterative operation, determining an update vector corresponding to the target population individuals; adjusting the to-be-processed parameters corresponding to the target population individuals through the update vectors to obtain adjustment parameters corresponding to the target population individuals; and identifying the target parameter of the permanent magnet synchronous motor through the adjustment parameter corresponding to the target population individual under the condition that the preset iteration termination condition is satisfied, thereby improving the accuracy of the identification result.

We provide the system. [Solution] The primary means of receiving data input from users, A second means for obtaining related information from information storage based on the data input, A third means that uses the acquired information to generate the optimal question using artificial intelligence, A fourth means for formatting the generated questions and creating an electronic questionnaire, A fifth method for distributing the questionnaire to the target persons, A sixth method involves collecting and analyzing responses from the target individuals after distribution. A system that includes this.

This invention provides a genome-wide selection breeding method based on pooled simplified genome sequencing, relating to the field of breeding. The method includes obtaining the minor allele ratios and genotype data of SNP loci, mixing them according to the target group size, statistically analyzing the probability density distribution of allele frequencies corresponding to each possible outcome of genotype mixing, and obtaining the parameters α and β of the β distribution. After mixing the genotype and phenotypic data of the target species according to the target group size, the minor allele ratios simulating real pooled sequencing are obtained by sampling using the fitted β distribution, which serves as the genotype. A regression model is then selected to estimate the marker effect value, and the breeding value of each individual in the target population is estimated. Using this method avoids the problem of single-sample data uniformity and improves the accuracy of breeding value prediction with a reference population establishment cost of one-fifth or even one-tenth, thus better enabling breeding of species such as Litopenaeus vannamei and dairy cows.

The invention relates to a physiological data fused comprehensive assessment method and system for the exercise ability of old people. The method comprises the following steps: acquiring physiological health information of a target population in a specific region, and dividing exercise health risk levels through a preset machine learning classification algorithm to obtain a preliminary sample set; integrating the data with regional climate indexes and regional high-incidence disease related indexes to form a comprehensive input data set, constructing an evaluation framework based on SPPB to perform hierarchical evaluation to obtain a preliminary risk hierarchical result, and determining a final risk group through a clustering algorithm; inputting the final risk group into a preset classification model adaptive to the region and health characteristics to generate a risk level tag, and generating a final intervention scheme according to the risk level tag; and allocating the scheme to a target population, dynamically evaluating and calculating a deviation value based on a preset health target and a risk threshold, and if the deviation exceeds the threshold, generating a personalized participation report in combination with the real-time health state. According to the method, the accuracy and the region adaptability can be improved, the reduction of the exercise ability is assisted and delayed, and the risk of bad health events is reduced.

The invention discloses a cerebrovascular disease risk assessment method, and relates to the technical field of risk prediction, and the method comprises the steps: determining a target population, and collecting first multi-dimensional data including demographic information, biochemical index information, lifestyle information and target risk type exclusive data; preprocessing the second multi-dimensional data to obtain second multi-dimensional data, and screening key feature variables by adopting a category-type feature improvement algorithm; constructing a machine learning model matched with the target risk, and outputting a risk assessment result or analyzing a variable risk association relationship after training; combining crowd characteristics or variable dependency relationship optimization model output, and verifying efficiency through decision curve analysis, an ROC curve and a confusion matrix; and finally integrating results to generate an evaluation report containing risk levels and key influence factors. According to the invention, through multi-dimensional data acquisition, scenarized model construction and two-dimensional verification, the assessment is more suitable for clinical requirements, and effective guidance can be provided for cerebrovascular disease risk prevention and control.

A multi-stratified sampling system using a machine learning algorithm, according to one embodiment of the present invention, comprises: a sample size calculation unit for calculating a sample size on the basis of the size of a target population; a multi-stratified sampling unit for performing multi-stratified sampling on the target population on the basis of the calculated sample size; and a multi-stratified sample group calculation unit for calculating a multi-stratified sample group from the target population on the basis of the performed multi-stratified sampling.

The invention relates to a model-assisted calibration estimation method and device, electronic equipment and a medium, and belongs to the technical field of data processing.The method comprises the steps that non-probability samples are extracted from a target population, and a multiple linear regression model between research variables and covariables of the non-probability samples is established; model parameters in the multiple linear regression model are estimated, and estimation of the research variables is obtained based on the estimated model parameters; obtaining a diagonal matrix corresponding to an original weight of a sample unit in the non-probability sample; obtaining a KL distance between the diagonal matrix and a preset calibration weight; constructing a calibration constraint condition of a target calibration weight based on the estimation of the research variable; the calibration weight is calibrated with the minimum KL distance under the calibration constraint condition to obtain a target calibration weight; and determining an estimation result of a total mean value of the target calibration weights based on the target calibration weights. According to the invention, the calibration estimation effect of the non-probability sample is improved.

According to the air conditioner and the adjusting method of the air conditioner, human body data, obtained by a sensor, in a target area where the air conditioner is located are input into a target crowd classification model to obtain a target crowd classification result, and the age ranges of different types of crowds are different; the target crowd classification result, the environment data obtained by the sensor and the operation data of the air conditioner are input into a target room load prediction model, a target load prediction result of the target area is obtained, and the target load prediction result comprises cooling capacity or heat needed by the target area; and the initial operation parameters of the air conditioner are adjusted according to the target load prediction result. The real-time change of the room load is predicted in combination with the crowd classification result, the accuracy of load prediction is effectively improved, the air conditioner operation parameters can be automatically adjusted more accurately and individually according to the load prediction result, the air conditioner energy consumption is reduced to the maximum extent while the comfort requirements of different crowds are met, and the user experience is improved. And the intelligent level of the air conditioner is effectively improved.

The invention relates to the technical field of intelligent recognition, in particular to a community aging-suitable service recognition method, device and equipment based on double portraits, and the method comprises the steps: obtaining the personal data and family data of a target group; obtaining an individual ability evaluation result and a family ability evaluation result based on the individual data and the family data of the target population, constructing an individual ability portrait based on the individual ability evaluation result, and constructing a family ability portrait based on the family ability evaluation result; and obtaining a service demand list of the target crowd based on the personal ability portrait of the target crowd and the family ability portrait of the target crowd according to a preset double portrait fusion analysis method, and obtaining a community service combination based on a pre-constructed community aged service resource library and the service demand list of the target crowd. According to the invention, the problem that the matching degree of the community age-suitable service and the demand is low in the related technology is solved, and the identification accuracy of the community age-suitable service is improved.

This application relates to the field of accelerometer calibration, and more particularly to an accelerometer calibration method, apparatus, and related equipment. The method includes: constructing a population comprising multiple individuals based on multiple parameters of the accelerometer to be calibrated; determining the current diversity value of the current population based on the current fitness value of each current individual in the current population during the current evolutionary process of the population's iterative evolution; determining the current evolutionary strategy of the current population based on the current diversity value; controlling the current population to evolve based on the current evolutionary strategy to obtain a target population; if the target population meets the termination condition of population evolution, determining the calibration values ​​of multiple parameters based on the candidate values ​​carried by the target individuals in the target population. This application can solve the technical problem that the accuracy of the determined mathematical mapping relationship of the accelerometer is low due to the problem that traditional genetic algorithms are prone to getting trapped in local optima.

The embodiment of the invention provides a spectrum model construction method. The method comprises the following steps: acquiring a host spectrum matrix and a slave spectrum matrix; respectively preprocessing the host spectrum matrix and the slave spectrum matrix; constructing a correction model according to the preprocessed host matrix and the preprocessed slave matrix, and calculating fitness corresponding to each sample according to the preprocessed host matrix and the preprocessed slave matrix through the correction model; according to the fitness corresponding to each sample, a plurality of samples are selected from the samples through a roulette algorithm to serve as parent populations; according to a preset crossover probability, performing data exchange on every two samples in the parent population to obtain a filial generation sample set; and randomly modifying the sample data in the offspring sample set, constructing a target migration model according to the target population sample data, and detecting component information through the constructed target migration model, so that the problem of constructing a spectrum model can be solved.

The embodiment of the invention provides a method for detecting the robustness of a multi-label classification model and related equipment, which are used for generating a test sample in a multi-label classification task and detecting and improving the robustness of the model. The method comprises the steps of obtaining an original image sample and generating an original population; obtaining an expected label value, a classification threshold value, a previous adversarial sample, a previous fitness and a plurality of disturbance individuals; performing variation processing on the plurality of disturbance individuals to obtain a current variation individual; obtaining individual fitness corresponding to the current variation individual by using a fitness function; selecting an individual with the minimum fitness as a disturbance individual; selecting target fitness to obtain a corresponding target disturbance individual, and performing environment change to obtain an optimized confrontation sample; population response updating is carried out, target disturbance individuals are removed, a target population is obtained, and one-time iteration is completed; and if the current number of iterations is not less than the maximum number of iterations, taking the optimized current adversarial sample as a target adversarial sample.

The present application relates to the technical field of detection experiment, and particularly relates to a pipeline experiment automatic scheduling method and system and related equipment, the method comprising: randomly generating a full permutation array as an initial population; taking the initial population as the parent generation, performing a crossover operation to determine a first offspring; pairing the individuals in the initial population two by two to determine paired individuals, and taking the paired individuals as the parent generation, performing a mutation operation to determine a second offspring; determining a target population based on the first offspring, the second offspring and the parent generation; detecting according to the detection order corresponding to each individual in the target population to determine a first total detection time corresponding to each individual; taking the individuals in each first total detection time that meet a first preset requirement as target individuals, and detecting each detection experiment according to the detection order corresponding to the target individuals. The present application uses a genetic algorithm to schedule and arrange tasks, thereby optimizing detection efficiency.

The application discloses a cerebrovascular disease risk assessment method, and relates to the technical field of risk prediction, which comprises the following steps: determining a target population, collecting first multi-dimensional data containing demographic information, biochemical index information, lifestyle information and target risk type exclusive data; preprocessing the first multi-dimensional data to obtain second multi-dimensional data, screening key characteristic variables by using a category type characteristic promotion algorithm; constructing a machine learning model matched with the target risk, outputting a risk assessment result or analyzing a variable risk correlation relationship after training; optimizing the model output by combining population characteristics or variable dependency relationships, verifying the efficiency by decision curve analysis, ROC curve and confusion matrix; and finally integrating the results to generate an assessment report containing risk levels and key influencing factors. The application makes the assessment more suitable for clinical needs through multi-dimensional data collection, scenario-based model construction and two-dimensional verification, and can provide effective guidance for cerebrovascular disease risk prevention and control.