39results about How to "High screening accuracy" patented technology

The invention relates to a digital modeling cooperation management method and system based on a block chain, and belongs to the technical field of cooperation management, and the method comprises the steps: building an interoperation framework of digital modeling cooperation based on an alliance chain; the participant BPMS passes the authentication of the CA identity certificate; a task node issues a collaboration task request and corresponding excitation of a new block, and a Hyperledger block chain performs information interaction by calling an intelligent contract deployed on an alliance chain to realize modeling collaboration design; digital modeling of a target task is completed by executing all cooperation task requests, and a model obtained through final consensus is determined as a modeling cooperation result to be published. According to the method, sharing and collaborative development of a digital model are realized by establishing an interoperation framework based on the block chain, modeling verification and participant reputation evaluation are realized through a consensus mechanism and reputation evaluation, and the collaborative efficiency is improved.

The invention relates to a small molecule virtual screening method and system based on a graph convolutional neural network, and the method comprises the steps: firstly obtaining the data of an active compound and a bait compound of a target spot, carrying out the preprocessing of the obtained data, constructing a graph convolutional neural network model, carrying out the training and evaluation of the model through a preprocessed data set, and obtaining a small molecule virtual screening result. And then scoring the small molecule compound data obtained in the compound database by using the trained graph convolutional neural network model, retaining the small molecule compound with high prediction score, and finally obtaining the known drug molecule data of the target spot. And performing compound similarity search on the small molecule compounds with high prediction scores and known drug molecules to obtain the small molecule compounds with similarity with the known drug molecules. Compared with the prior art, the method has the advantages that virtual screening is utilized, the drug research and development process is accelerated, the experiment cost is reduced, compound similarity search is combined on the basis, the screening accuracy is further improved, and the screening result range is narrowed.

The invention provides a phase identification method and system for a single-phase electric energy meter access measurement switch, and relates to the technical field of electric power phase identification. The method comprises the steps of data acquisition and arrangement, voltage fluctuation value calculation, difference value calculation and absolute value processing, effective characteristic voltage data screening and phase judgment, the A phase, the B phase and the C phase of the intelligent measurement switch are taken as reference, and the voltage effective value of a user electric energy meter and the voltage effective value of the measurement switch are acquired for one round per minute through an RS-485 bus. And after data of two adjacent moments in the measurement time period are cached, two adjacent voltage fluctuation quantities delta v of the two adjacent moments are calculated and compared, a phase with an obvious characteristic delta v is screened out, corresponding phase results are accumulated, and after time accumulation, the phase with the maximum accumulated value is screened out and serves as the phase where the electric energy meter is located. According to the invention, a plurality of data processing means are used, and the accuracy and reliability of phase identification are improved.

The invention discloses a depression screening method, device and equipment based on multi-modal data, and the method comprises the steps: extracting video features corresponding to video data through a video branch, extracting audio features corresponding to audio data through an audio branch, and extracting text features corresponding to the text data through the text branches, then fusing video features, audio features and the text features through a cross attention mechanism in the fusion module to obtain fused features, and finally determining depression scale scores of the to-be-screened data according to the fused features through the prediction module. In this way, the video features, the audio features and the text features are fused through a cross attention mechanism, knowledge information carried by the fused features can be increased, redundant features in the video features, the audio features and the text features can be paid attention to, and therefore the screening accuracy of the depression screening model can be improved, and the screening accuracy of the depression screening model can be improved. Therefore, the efficiency and accuracy of multi-mode automatic depression screening can be improved.

The invention belongs to the technical field of medical treatment and health information, and provides a CKD high-risk factor screening system based on big data, CKD medical record information of a plurality of CKD patients in a historical period is extracted from a hospital system through an ETL technology and is analyzed to obtain high-frequency factors, analysis is carried out based on the high-frequency factors to obtain a primary screening high-risk factor table, and the primary screening high-risk factor table is used for screening the CKD high-risk factors. Performing analysis processing on the primary screening high-risk factor tables in the plurality of continuous historical periods, analyzing ranking changes of the high-frequency factors in the plurality of primary screening high-risk factor tables and occurrence frequencies of the high-frequency factors in the plurality of continuous historical periods, and further screening the high-frequency factors to obtain sensitive factors; and the sensitive factors are summarized to obtain a sensitive high-risk factor table, so that CKD patient factors are screened layer by layer, high-risk screening conditions are determined, tracking and comparison of patients in the whole hospital can be realized according to medical record information of the patients in the hospital, and the statistical efficiency of the CKD patients is improved.

The present invention relates to microbial screening technology, and discloses a method for high-throughput screening of microbial strains by electrospraying a single emulsion and its application. The method comprises: establishing a microbial mutant library, obtaining a culture solution of the microbial mutant library; mixing the culture solution with a solution containing a gelling agent to obtain a dispersion, electrospraying the dispersion to form monodisperse droplets; contacting the monodisperse droplets with a collection solution containing a crosslinking agent to solidify to form microspheres, and subjecting the microspheres to microfluidic sorting after culturing; wherein the gelling agent and the crosslinking agent are in contact to generate a crosslinking and curing reaction. The method does not require the use of an oil phase to generate single-encapsulated droplets, and the fluorescent staining and screening process are simpler, effectively improving the effectiveness and accuracy of strain screening.

The application relates to a work item data processing method, device, equipment, medium and product. In the method, in response to a processing request, work item data corresponding to a plurality of work items is acquired; the work item data comprises assigned user information, closed user information and output submission information; for any work item, the output submission information corresponding to the work item and the output submission information corresponding to a plurality of other work items are compared to determine a duplication result; according to the assigned user information and the closed user information corresponding to the work item and the attendance information corresponding to the assigned user information, a replacement completion result is determined; when the duplication result or the replacement completion result meets a reality condition, the work item is determined as a target work item, and a problem type corresponding to the target work item is determined; according to the task man-hours corresponding to the target work item and the problem type corresponding to the target work item, deduction man-hours corresponding to the assigned user information are determined to perform deduction processing. The screening accuracy of the target work item is improved.

The present invention provides a satellite data processing and intelligent labeling method for precision agriculture, which relates to the field of computer model technology. The method comprises: obtaining a first agricultural satellite image with artificial edge labeling information and a second agricultural satellite image without artificial edge labeling information; correcting the artificial edge labeling information and training an edge detection model; processing the second agricultural satellite image through the edge detection model to obtain initial edge labeling information, and determining its edge detection effect score, if the score is lower than a preset threshold, continuing training through the second agricultural satellite image, otherwise determining the remaining edge information in the second agricultural satellite image through the edge detection model. According to the present invention, the artificial edge labeling information can be corrected, the error of artificial labeling can be reduced, the accuracy of the edge detection model can be improved, and the edge detection model can be evaluated and corrected, reducing the workload and error of artificial labeling.

The utility model discloses a crucible screening device for evaporation in the field of conductive metal film production, which comprises a conveyor belt and a detection box, the conveyor belt penetrates in from one side of the detection box and penetrates out from the other opposite side of the detection box, and one side of the detection box is provided with a crucible inlet for a crucible to pass through. A qualified crucible outlet for qualified crucibles to pass through and a defective crucible outlet for unqualified crucibles to pass through are formed in the other side of the detection box, and the crucible inlet and the qualified crucible outlet are at least partially overlapped; a detection mechanism is arranged in the detection box, the detection mechanism comprises a detection assembly and an inferior-quality product screening assembly, the conveying belt conveys the crucible into the detection box, the detection assembly detects the crucible in the detection box, and if the detection assembly detects an unqualified crucible, the inferior-quality product screening assembly aligns the crucible to an inferior-quality product crucible outlet. The crucible crack screening device solves the problems that an existing crucible crack screening device is low in efficiency and poor in accuracy, the screening efficiency can be improved, and the screening accuracy is high.

The invention provides a pollution control facility discrimination method and system based on multi-source data, and electronic equipment. The method comprises the following steps: collecting enterprise power consumption data, working condition parameters and CEMS online monitoring data; processing the data, including data cleaning, conversion and feature extraction; training and testing are carried out according to data of historical operation states, a CatBoost model is optimized by utilizing grid search and cross validation, and parameter characteristics are acquired by utilizing an optimal hyper-parameter training test model; and finally, calculating a factor contribution value by using an SHAP model, and determining an abnormal factor for early warning. According to the invention, through multi-source data fusion and an advanced model, the discrimination accuracy and interpretability of pollution control facilities are improved, and powerful support is provided for air pollution control.

The invention provides a key value caching method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a plurality of text segments corresponding to a current text and a segment attention score corresponding to each text segment; based on the fragment attention score, screening at least one target text fragment from the plurality of text fragments; performing attention analysis on the plurality of candidate lexical elements in the at least one target text fragment to obtain first attention scores corresponding to the plurality of candidate lexical elements; based on the first attention score, screening out at least one target lexical element from the plurality of candidate lexical elements; and updating the original cache based on the key value cache corresponding to the at least one target lexical element. By utilizing the embodiment of the invention, the recall of the key value cache of the target lexical element can be realized, the information loss caused by relatively far lexical element information is avoided, the reasoning of relatively long context can be supported, and the problem of precision loss caused by information loss in a rarefaction process is alleviated.

The embodiment of the present application relates to a kind of method and device for predicting early Alzheimer disease in combination with cognitive characteristics, the method comprises: the deep learning model of early Alzheimer disease three classification prediction based on pathological cognitive multi-modal feature is constructed to obtain the first prediction model;By collecting and analyzing the pathological cognitive multi-modal information of three kinds of crowd to construct the first data set;First prediction model is trained based on the first data set;After training, the pathological cognitive multi-modal information of any individual input by user is received as multi-modal feature input first prediction model and is processed to obtain corresponding prediction vector, and the classification type corresponding to the maximum prediction probability in vector is regarded as the prediction result of current individual and is fed back to current user.The present application can improve screening accuracy, reduce the misdiagnosis rate of cognitive resilience individual.

The invention relates to a molecular marker related to hypoxia adaptability of Tibetan chicken and application of the molecular marker. By analyzing the genetic structure and gene exchange of the Tibetan chicken under different altitude gradients and combining heart transcriptome data, the PARK7 gene shows a stable expression level in the Tibetan chicken and is not influenced by the plateau environment. Therefore, the breeding method for improving the survival rate and adaptability of the Tibetan chicken in the plateau low-oxygen environment is screened out. The method not only enriches the understanding of the hypoxia adaptation mechanism of the Tibetan chicken, but also provides technical support for breed conservation and breeding of the Tibetan chicken.

This invention discloses a cable production identification and monitoring system and method based on cable images, belonging to the field of image recognition technology. The system includes: acquiring a sequence of cable surface depth images to construct a grayscale surface map along the cable surface depth direction; using the central ridge of the grayscale surface map as a dynamic axis of symmetry, detecting candidate pixels through multi-scale morphological top-hat transformation to form a symmetrical residual distribution map; combining the eight-neighbor gradient direction field and Hessian matrix curvature to remove false defect points, obtaining an effective image, and inputting it into a pre-trained multi-task neural network to simultaneously output a defect segmentation mask and category label; generating a three-dimensional mesh model with dimensional accuracy through Poisson surface reconstruction; and finally, using the physical coordinates of the defect center to drive a laser marking machine to mark a QR code containing key information, which is then associated and stored in a blockchain database. This application improves the accuracy and efficiency of defect identification, realizing the quantitative characterization and full lifecycle management of defects.

This invention relates to the field of drug sorting and screening technology, and discloses a drug storage device and intelligent drug sorting method based on AI deep learning. The device includes a drug storage unit, a data acquisition and display unit, a decision management unit, a storage environment control unit, a drug screening unit, and a drug output and recycling unit. The data acquisition and display unit is used for user input of stored drug information, high-definition photography of the drugs, and the use of AI recognition technology to achieve visual recognition and measurement of the drug's appearance and dimensions. Continuous deep learning improves the accuracy of drug appearance recognition, facilitating the drug screening unit's selection of drug quantities. The drug screening unit automatically sorts and selects the required quantity of drugs for patients at specific times, based on different drug dosage regimens. This invention effectively solves the problem of low patient medication adherence, is highly practical, reliable, has low implementation costs, and targets a large beneficiary group.

The invention discloses an unmanned factory monitoring system based on the Internet of Things, and relates to the technical field of factory supervision, and the system comprises a visual module, a smoke detection module, and a supervision device. The visual module comprises a plurality of cameras I and a camera II, the cameras I respectively monitor one or more pre-divided monitoring areas, and the monitoring area of the camera II covers the monitoring areas of the plurality of cameras I; the monitoring device comprises a front-end AI unit and a supervision background connected with the front-end AI unit, and the front-end AI unit is integrated in production equipment with a visual function in an unmanned factory. The method and the device have the effect of reducing the interference of structural facilities in the unmanned chemical plant on safety monitoring.

The application provides a complex trait gene mining method and system based on a large language model and multi-modal data, and belongs to the technical field of gene data analysis. The method comprises the following steps: obtaining a statistical data set containing multi-modal data of different legume populations; annotating all genes in the statistical data set based on a reference genome to obtain a whole genome semantic graph; if the large language model receives a site of a target significant trait, calculating the comprehensive scores of each gene at the site based on the whole genome semantic graph and the site by using the large language model, and determining a complex trait gene based on the comprehensive scores of each gene; if the large language model does not receive the site of the target significant trait, determining candidate genes based on the target significant trait by using the large language model, and determining the complex trait gene from each candidate gene by using the large language model based on the whole genome semantic graph. The application can locate the most essential gene affecting the target significant trait.

The invention belongs to the technical field of autism screening, and discloses a rapid interactive screening test method for infant autism, which is suitable for Chinese environment infants of 18-36 months old. The method comprises the following steps: determining an adaptive test object, preparing a test, executing an interactive test and scoring according to a sequence that the first three items are fixed and the other items are flexible, adding scores of the nine items, and judging the risk according to the total score. The method can be completed within 5-10 minutes and is adaptive to Chinese culture, equipment is simple, operation is standardized, and the problems that an existing tool is poor in adaptation and low in efficiency are solved; the method is high in accuracy, is suitable for multiple scenes such as communities, can quickly recognize autism risks, and provides support for early intervention of child autism.

The invention discloses a collection data processing method and device, a storage medium and electronic equipment. Relates to the technical field of data analysis. The method comprises the steps that collection strategy data is acquired from a target page, the target page is used for configuring the collection strategy data, the collection strategy data comprises a screening rule for screening user information of a to-be-collected user, a plurality of preset fields and a plurality of condition fields are arranged in the target page, and the condition fields are used for setting screening conditions of the screening rule; converting the collection strategy data into structured data to obtain target strategy data; the target strategy data are converted into scripts to obtain initial scripts, the initial scripts are compiled to obtain target scripts, and the target scripts are used for screening user information of the to-be-collected users. According to the invention, the technical problem of poor screening effect of the to-be-collected customer group caused by high error rate of configuration of the collection strategy for screening the to-be-collected user in the related technology is solved.

The invention relates to the technical field of electric power operation and maintenance data processing, provides a photovoltaic power generation effective data screening optimization method and system, and aims to solve the problem that the screening accuracy of photovoltaic power generation effective data of a new energy power plant in an extreme natural environment is reduced. And in combination with comparison of real-time plant natural environment data and theoretical natural environment information and a natural environment simulation model, accurate screening of the data is realized. And meanwhile, the screened operation data of the photovoltaic power station are optimized by using a genetic algorithm, so that the photovoltaic power station of the new energy power plant can efficiently and stably operate under the natural environment change. According to the invention, the accuracy of photovoltaic power generation effective data screening is improved, and powerful support is provided for intelligent operation and maintenance of a photovoltaic power station.

The application discloses a marker for screening aggressive social harmful behavior, a screening method and device and a storage medium, and relates to the technical field of aggressive social behavior screening. The reagent comprises a reagent for detecting relative abundance data of a microbial combination at the genus level. When the 13 kinds of bacteria are used for screening aggressive social harmful behavior, the screening accuracy is extremely high, and the screening method is non-invasive and objective. When the 13 kinds of bacteria are combined with social demographic information as screening factors of aggressive harmful social behavior, the screening accuracy is also extremely high. The application provides a new way for screening and intervention of aggressive social harmful behavior.

A signal weak feature extraction method and system mainly includes the following steps: obtaining original vibration signals of a non-circular gear housing in an electromechanical device under normal and fault states and the like, decomposing the original vibration signals according to an improved empirical wavelet transform, and extracting a frequency band instantaneous envelope line of the decomposed signal components combined with an improved sequential statistical filter; then, combining preset constraint criteria such as a multi-scale correlation criterion, an entropy criterion and a fault feature frequency matching criterion, a weak feature signal modal component in the original vibration signal is screened out. The method can effectively improve the extraction effect of the non-circular gear signal weak feature, reduce the influence of noise and interference signals, improve the screening accuracy of the weak feature signal component, and help improve the accuracy of fault diagnosis and analysis.

The invention relates to a work item data processing method and device, equipment, a medium and a product. The method comprises the following steps: in response to a processing request, obtaining work item data corresponding to a plurality of work items; the work item data comprises assigned user information, closed user information and product submission information; for any work item, comparing the output submission information corresponding to the work item with output submission information corresponding to a plurality of other work items, and determining a repetition result; according to the assigned user information and the closed user information corresponding to the work item and the attendance information corresponding to the assigned user information, determining an on-behalf completion result; when the repetition result or the completion result meets the authenticity condition, determining the work item as a target work item, and determining a problem type corresponding to the target work item; and according to the task man-hour corresponding to the target work item and the problem type corresponding to the target work item, determining the deduction man-hour corresponding to the assigned user information so as to carry out deduction processing. And the screening accuracy of the target work item is improved.

The present invention relates to the field of data processing technology, and discloses a method and system for deploying vehicle type recognition equipment, the method comprising: determining a set of identification quantity parameters for each type of vehicle type recognition equipment among multiple types of vehicle type recognition equipment; calculating an index set for each type of vehicle type recognition equipment according to the set of identification quantity parameters for all vehicle type recognition equipment; screening out target vehicle type recognition equipment that meets preset rating conditions from all vehicle type recognition equipment according to the index set for all vehicle type recognition equipment; determining at least one deployment point of the target vehicle type recognition equipment from the target lane area to be deployed according to the target identification quantity parameter set for the target vehicle type recognition equipment. It can be seen that the implementation of the present invention can improve the deployment accuracy of vehicle type recognition equipment, thereby facilitating the reduction of vehicle missed recognition / misrecognition based on accurately deployed vehicle type recognition equipment, and further facilitating the reduction of the loss of lane tolls.

The invention relates to the technical field of material performance analysis, and discloses a method for improving the performance of an antibacterial nano-material in a kitchen knife, which comprises the following steps: detecting environmental resident bacterial strains and bacterial flora density of the kitchen knife in a storage environment, and determining the antibacterial nano-material corresponding to the kitchen knife; performing synthesis treatment on the cutter base material and the antibacterial nano material to obtain a synthetic material, analyzing the chemical stability corresponding to the synthetic material, and analyzing the physical stability corresponding to the synthetic material; evaluating the efficiency attenuation of the synthetic material in the storage environment; calculating the sterilization efficiency gradient of the antibacterial nano material; the optimal antibacterial material in the antibacterial nano materials is screened out, a performance improvement scheme corresponding to the kitchen knife is generated, performance improvement processing on the kitchen knife is executed, and an improvement result is obtained. The invention mainly aims to solve the problem of low performance improvement efficiency of the antibacterial nano material in the kitchen knife.

The invention discloses a method for improving screening accuracy of specific primers of Shigella by using fluorescent loop-mediated isothermal amplification and a high-resolution melting curve, and belongs to the field of molecular biology. The method comprises the following steps: designing a primer group through an ipaH gene, extracting Shigella genome DNA, taking the Shigella genome DNA as a template, carrying out a fluorescent LAMP amplification reaction on the designed LAMP primer group, and carrying out HRM analysis on an amplification product; the positive amplification curve in the amplification curves is in a typical S shape, the negative control is not amplified, or the peak time of the amplification curve lags the positive peak time by more than 30 min is screened as a specific primer; in an HRM melting curve, a positive template is in a single sharp peak shape, and the positive Tm value is 90.0-91.0 DEG C; the negative control does not have a specific melting peak or has a wide and blunt non-specific peak, and the difference value between the negative control Tm and the positive Tm is greater than or equal to 2.0 DEG C. Through dual verification of fluorescent LAMP and HRM accurate analysis, the advantages and disadvantages of the primers are accurately evaluated, accurate and efficient screening of the optimal primer group is realized, and sensitive and specific primers are provided for subsequent LAMP detection tests.

The invention relates to a metagenome sequencing data screening method, device and equipment and a readable storage medium. The method comprises the steps that similar sequence comparison information jointly corresponding to a plurality of non-human genome similar sequences is obtained, and the non-human genome similar sequences are non-human genome sequences having a similar relation with a reference human genome sequence in all non-human genome segments; according to the similar sequence comparison information and the reference human genome sequence, detecting an original non-human genome similar sequence and an original non-human genome sequence in the original metagenome sequencing data; the detected original non-human genome similar sequence and the original non-human genome sequence are jointly used as a potential non-human genome sequence; and screening the original metagenome sequencing data according to a comparison relationship between the potential non-human genome sequence and the reference non-human genome sequence to obtain a data screening result. By adopting the method, the screening accuracy of the metagenome sequencing data is improved.

The invention discloses a storage battery container formation charging and matching method, and belongs to the technical field of storage battery production. According to the container formation charging and matching process method for the storage battery, through three times of discharge capacity detection, grading is carried out according to the discharge termination voltage value in the same range, and grading and matching are carried out in the specified floating charge voltage value range, so that the online discharge one-time qualified rate and the capacity online matching qualified rate of all the batteries can be ensured; the battery screening accuracy, stability and performance consistency are improved, and the cycle period and the service life of the battery are prolonged.

The embodiment of the present application provides a retired battery screening method and retired battery screening device. The method includes: obtaining a predetermined standard impedance for retired batteries; the standard impedance is obtained based on the impedance of retired batteries in different health states; obtaining the initial battery capacity of the battery to be tested, and determining the charging current of the battery to be tested based on the initial battery capacity; the initial battery capacity is the rated capacity of the battery to be tested before it is used; when the battery to be tested is charged to a fully charged state, determining the test impedance of the battery to be tested; wherein the fully charged state is a state where the charging current is charged to the charging cut-off voltage of the battery to be tested, and constant voltage charging is performed at the charging cut-off voltage until the current reaches the cut-off current; based on the test impedance and the standard impedance, the screening results of retired batteries are obtained. The method is used to achieve the effect of improving the accuracy of retired battery screening.

The present specification discloses an image processing method, device, storage medium and electronic device. The method obtains a set of remote sensing image slices to be screened, which includes a plurality of remote sensing image slices to be screened, and determines the slice image features of each remote sensing image slice to be screened according to a preset feature extraction method. The set of remote sensing image slices to be screened is screened according to the slice image features to obtain an initial screening result. According to the initial screening result, a quality assessment result is obtained by using a pre-trained image quality assessment model. Based on the quality assessment result, a target remote sensing image slice is determined in the set of remote sensing image slices to be screened. The features of the remote sensing image slices are extracted, and a primary screening is performed according to the features. Then, according to the primary screening result, the remote sensing image slices are secondary screened using the image quality assessment model to obtain high-quality target remote sensing image slices. This not only improves the screening efficiency, but also improves the screening accuracy.