44results about How to "Achieve accurate identification" patented technology

The invention relates to the technical field of chromatogram analysis, in particular to a chromatographic image recognition method and system based on characteristic peaks. The method comprises the following steps: acquiring a chromatogram of a target sample, and preprocessing the chromatogram to obtain an initial atlas; obtaining a plurality of target areas in the initial map; dividing all the target areas to obtain a first area and a second area; calculating a first overlapping probability of each first region, and taking the corresponding first region when the first overlapping probability is greater than a first threshold value as an overlapping peak region; calculating a second overlapping probability of each second region, and taking the corresponding second region when the second overlapping probability is greater than a second threshold value as an overlapping peak region; and performing Gaussian fitting on all overlapped peak regions to obtain a curve of a plurality of peaks. According to the scheme provided by the invention, the overlapping peaks can be accurately identified.

The invention discloses a data processing system and method for three-dimensional real estate surveying and mapping, and relates to the technical field of intelligent surveying and mapping, and the system comprises a multi-source data fusion module, a model generation module, a spatial relationship analysis module, an efficient rendering module and a data security module. The multi-source data fusion module converts the original surveying and mapping data in different formats into a unified three-dimensional point cloud data set; the model generation module generates a parameterized three-dimensional building model based on the point cloud data; the spatial relation analysis module constructs a relation graph of the building model and generates a surveying and mapping index report; the efficient rendering module processes large-scale three-dimensional data and generates an interactive three-dimensional scene; and the data security module controls the data access authority and generates an operation log. According to the method, the processing efficiency and precision of the three-dimensional real estate surveying and mapping data are improved, efficient analysis and visualization of large-scale three-dimensional data are realized, the security of sensitive data is ensured, and advanced technical support is provided for modern city planning, real estate management and real estate development.

The invention relates to the technical field of industrial working condition recognition, and discloses a blast furnace working condition recognition method and system fusing a process variable and a video image, and the method comprises the steps: carrying out the interpolation processing of the process variable, carrying out the averaging of a video image frame, and aligning the multi-source heterogeneous information to the same time step; thus, multi-source heterogeneous information with inconsistent sampling frequencies is aligned, a deep neural network model jointly driven by process variables and video images is constructed, representative working condition features in the multi-source heterogeneous information are extracted, the problem that working condition information is not completely utilized when only a single information source is used is solved, and the method is suitable for the multi-source heterogeneous information. A double-layer residual error connection module and a model stability evaluation index are designed, and accurate recognition of the working condition of the blast furnace is achieved.

The invention relates to the technical field of concrete crack detection, in particular to a concrete internal crack detection method based on image-impact echoes, which comprises the following steps: acquiring and marking a concrete crack data set, and preprocessing through a data enhancement technology; capturing multi-scale features of the crack by using an RFB network module, and training a target detection model; the trained model is applied to detect target concrete, the crack degree and coordinates are obtained, and a two-dimensional crack graph is drawn to divide crack areas; then, based on a crack area layout monitoring point, recording an echo signal of the concrete by using an impact echo technology, extracting crack characteristics and inputting the crack characteristics into the machine learning model, and obtaining a trained model to analyze an internal crack of the target concrete; and expanding the two-dimensional crack graph into a three-dimensional crack graph to obtain an actual crack degree. According to the method, the detection efficiency is improved, a visual effect is provided, and an effective technical means is provided for concrete structure crack monitoring.

The embodiment of the invention belongs to the field of voice processing, and relates to a voice recognition method and device, computer equipment and a storage medium, and the method comprises the following steps: obtaining multi-language voice signal information, and carrying out the preprocessing of the multi-language voice signal information, and obtaining standard voice signal information; performing feature extraction on the standard voice signal information to obtain an acoustic feature vector sequence; training a voiceprint embedding model based on the acoustic feature vector sequence; acquiring multi-language voice data, and inputting the multi-language voice data into the voiceprint embedding model to obtain a voiceprint feature vector; constructing a language voiceprint database based on the voiceprint feature vectors; performing feature extraction on the to-be-recognized voice information based on the voiceprint embedding model to obtain a to-be-recognized voiceprint feature vector; and comparing and matching the to-be-recognized voiceprint feature vector with a language voiceprint database to obtain a voice recognition result. According to the invention, the voice object of the to-be-recognized voice information can be accurately recognized.

The invention provides a bumpy road section recognition method, electronic equipment and a vehicle, and relates to the technical field of vehicle data processing, and the method comprises the steps: obtaining a current wheel speed, a plurality of historical wheel speeds and a plurality of historical longitudinal accelerations of the vehicle; and determining a mean wheel speed according to the current wheel speed, the plurality of historical wheel speeds and the plurality of historical longitudinal accelerations. Whether the current road section is the bumpy road section or not can be accurately determined through the difference between the current wheel speed and the average wheel speed, and the recognition accuracy of the bumpy road section is ensured. The preset jolting condition represents a relation condition which needs to be met by the current wheel speed and the average wheel speed under a jolting road section. If it is determined that the current wheel speed and the average wheel speed meet the preset bumping condition, it can be determined that the wheels enter the bumping road section. Through the bumpy road section identification method, accurate identification of the bumpy road section can be realized.

The invention discloses a knowledge base document blocking method and device based on layout analysis and a medium, and relates to the technical field of artificial intelligence, and the method comprises the following steps: carrying out document image preprocessing on a to-be-stored document to obtain a document standard image; performing layout structure analysis on the document standard image to determine a layout structure layout; based on the layout structure layout, obtaining a structural logic relationship of layout elements through layout structure analysis; according to the structural logic relationship, performing layout partitioning on the layout of the to-be-stored document, and determining a first layout partition; block quality evaluation is carried out on the first layout blocks to determine the block quality of the first layout blocks, and block optimization is carried out on the blocks with the block quality lower than a preset threshold value to obtain second layout blocks. By means of the method, the technical problem that intelligent partitioning cannot be achieved in knowledge base document partitioning through layout analysis in the prior art is solved.

The invention relates to the technical field of medicine supplier monitoring, in particular to a medicine supplier holographic monitoring method and system based on risk assessment, and the method comprises the steps: carrying out the data preprocessing of collected target medicine supplier risk control data, and generating target medicine supplier risk control feature data; performing data search processing on the established medicine supplier risk type feature data to generate target medicine supplier risk type data, and searching matched weight data from the established medicine supplier risk type weight data set, the method comprises the steps of obtaining target medicine supplier risk type weight data, calculating a target medicine supplier risk assessment value, performing numerical comparison on the target medicine supplier risk assessment value and a set risk threshold value, generating target medicine supplier risk level data according to a numerical comparison result, and finally constructing target medicine supplier monitoring data. And the information is pushed to a medical supplier holographic monitoring platform, so that holographic monitoring and risk assessment of the medical suppliers are scientifically realized.

The invention relates to the technical field of cynomorium songaricum identification, in particular to a method for rapidly identifying cynomorium songaricum of different processing modes and host plants based on an electronic nose technology. The method comprises the following steps: filling 1.0 g of a sample into a 10mL silica gel cap penicillin bottle, balancing in a water bath at 60 DEG C for 25 minutes, and detecting by using an electronic nose; and statistical analysis. According to the method, the electronic nose technology is adopted, the cynomorium songaricum which is processed in different modes and comes from different host plants is detected and analyzed, the influence of the different host plants and the processing modes on the flavor of the cynomorium songaricum is known, and then a powerful theoretical basis is provided for rapid quality identification and characteristic flavor evaluation of the cynomorium songaricum. In the aspect of data analysis, a Gaussian Naive Bayes (GNB) classification model statistical method is adopted, qualitative judgment is performed on the characteristic smell of the cynomorium songaricum through a retention value of an electronic nose, a judgment model is constructed, and a solid theoretical foundation is laid for future qualitative prediction.

The invention provides a selenium peptide de novo sequencing method based on a full convolution attention mechanism neural network, and belongs to the field of selenium-containing natural polypeptide identification and detection.Specific seleno-amino acid corresponding to each characteristic fragment in all selenium peptides is used as initial amino acid, then the next symbol in the N / C end direction is sequentially predicted, and the sequence of the next symbol in the N / C end direction is determined; taking the symbol with the highest probability as the symbol at the corresponding position; learning selenium peptide N and C terminal amino acid features in a known selenium peptide sequence by using a full convolution attention mechanism neural network, then carrying out feature fusion, and standardizing to 0-1; taking all identified selenium peptide sequences as an input layer, performing data feature separation by using an activation function of a neural network hidden layer, calculating each separation feature, obtaining the probability that the corresponding selenium peptide sequence is a natural selenium peptide, removing unmatched selenium peptide sequences, and outputting the identified natural selenium peptide sequence by an output layer; and optimizing the weight and bias of the model, inputting all identified selenium peptide sequences into the optimization model, obtaining a sequencing model when the error between the selenium peptide sequences and a real sequence does not change any more, and inputting the selenium peptide sequences correspondingly identified by all selenium peptides of a to-be-detected sample into the sequencing model to obtain the natural selenium peptide sequence identified by the to-be-detected sample.

The application discloses a phosphoric acid modified protein or polypeptide, a preparation method thereof and application thereof in vaccines, and belongs to the field of protein phosphoric acid modification. The preparation method of the phosphoric acid modified protein or polypeptide is as follows: a compound containing an aldehyde group and a phosphate group is subjected to nucleophilic reaction with a protein or polypeptide to form a Schiff base; a reducing agent is used to reduce the Schiff base, and after post-treatment, the phosphoric acid modified protein or polypeptide is obtained. After the phosphoric acid modified protein product prepared by the method is prepared into a vaccine with an aluminum hydroxide adjuvant and mice are immunized, the antibody titer is significantly increased. This is of great significance for increasing the immune effect, reducing the inoculation dose, saving the antigen amount and improving the immune response of some people or in specific conditions.

The application discloses a method and device for identifying a seismic horizon and a storage medium, and belongs to the technical field of seismic interpretation. The method comprises the following steps: acquiring a seismic data body and a multi-target horizon identification sample set seismic data body, and using the multi-target horizon identification sample set seismic data body to generate a sample seismic profile W r The multi-target horizon identification sample set comprises artificial interpretation seismic horizons obtained after marking and processing the sample seismic profile W r , and at least four auxiliary seismic horizons related to the artificial interpretation seismic horizons; a convolutional neural network is trained according to the sample seismic profile W r and the multi-target horizon identification sample set, and a multi-target horizon identification network Net L is obtained; a to-be-identified seismic profile is substituted into the multi-target horizon identification network Net L , and a transition seismic horizon and at least four auxiliary seismic horizons related to the transition seismic horizon are obtained, and then a target seismic horizon is determined through fusion processing. The method can accurately identify the seismic horizon and improve the accuracy of seismic interpretation.

The present disclosure provides a transposon insertion marker specific to tropical japonica rice and its application. First, the insertion site of the transposon insertion marker specific to tropical japonica rice is located between the 20,300,698th and 20,300,699th nucleotides of chromosome 5 of the Nipponbare reference genome of version IRGSP-1.0; the variety of tropical japonica rice contains a 140 bp long transposon insertion at the insertion site, while the varieties of other rice groups do not contain the transposon insertion. Further, the above transposon insertion marker is provided for identifying tropical japonica rice. The transposon insertion marker specific to tropical japonica rice has important application value in precise identification of rice groups, classification of germplasm resources, screening of breeding materials, purity detection of hybrid rice germplasm, etc., and can significantly improve the efficiency of molecular marker assisted selection and shorten the breeding cycle.

This invention provides a method and system for automatically generating parking lot maps based on point cloud and semantic features, belonging to the field of parking lot map construction technology. The method includes: acquiring the original LiDAR point cloud of the parking lot and preprocessing it to obtain a ground point cloud; extracting parking space line point clouds based on the reflection intensity of each point from the obtained ground point cloud; clustering and segmenting the parking space line point clouds to obtain multiple independent parking space line point cloud clusters; performing straight line fitting on each parking space line point cloud cluster to obtain parking space boundary lines and parking space dividing lines; generating parking space boxes based on the intersections of the parking space boundary lines and parking space dividing lines, and outputting the parking lot map. This invention uses a reflection intensity threshold segmentation method to extract parking space line point clouds, overcoming the influence of illumination changes on parking space line extraction; by combining density clustering and a two-step straight line fitting strategy based on geometric constraints, it effectively solves the problems of ineffective differentiation of continuous parking space boundaries and insufficient fitting accuracy of dividing lines.

This invention discloses a primer-probe combination for detecting multiple types of Lactobacillus and its applications, belonging to the field of biotechnology. The primer-probe combination includes a primer-probe combination for detecting *Lactobacillus casei*, a primer-probe combination for detecting *Lactobacillus paracasei*, and a primer-probe combination for detecting *Lactobacillus rhamnosus*. The primer-probe combination of this invention can be used for both singleton and multiplex PCR detection, and can accurately detect *Lactobacillus casei*, *Lactobacillus paracasei*, and *Lactobacillus rhamnosus*, enabling the authentication of products containing Lactobacillus. This invention provides a more convenient method for detecting *Lactobacillus casei*, *Lactobacillus paracasei*, and *Lactobacillus rhamnosus*.

The present invention discloses a multi-dialect speech recognition method, system, device and medium, the method comprising: obtaining dialect data; extracting speech feature representation and dialect label feature representation of the dialect data; using the speech feature representation and dialect label feature representation as input of a multi-dialect speech recognition model, outputting dialect speech recognition text corresponding to each dialect; converting the dialect speech recognition text into Mandarin text. By using transformer-based speech recognition technology, combined with multi-dialect speech data sets for training and optimization, accurate recognition of multiple dialects is achieved, and recognition accuracy and robustness are improved.

The invention provides a method for allele matching of donor mesenchymal stem cells and a receptor. The method comprises the following steps: S10, separating mesenchymal stem cells from perinatal tissue of a donor; s20, extracting genome DNA (deoxyribonucleic acid) of the mesenchymal stem cells, and performing HLA (human leukocyte antigen) genetic typing; s30, performing HLA (human leukocyte antigen) genetic typing on the DNA of the receptor; s40, performing allele spectrum comparison on the HLA gene of the receptor and the HLA gene of the mesenchymal stem cell, and calculating the matching degree; s50, judging the matching degree of the receptor and the mesenchymal stem cells according to the matching degree; and S60, storing the HLA genotyping result of the mesenchymal stem cells and the matching degree in a database, and establishing a matching library for matching the donor mesenchymal stem cells and the receptor. According to the method, a set of standardized system is established, compatibility evaluation of a donor and a receptor at the allele level is achieved, the immunological rejection risk caused by HLA mismatching is effectively predicted and avoided before treatment, and the in-vivo survival and implantation efficiency of MSCs is improved.

The present invention discloses a method and system for identifying fire points in a substation based on dynamic morphological perception and a light point library, and belongs to the technical field of fire point identification in electric power facilities. The method comprises: three-dimensional modeling of the substation area to obtain a three-dimensional scene model, and calibrating the positions and observation angles of different cameras in the three-dimensional scene model; respectively obtaining real-time images of the same area taken by cameras with different observation angles at the same time; respectively extracting scene images with the same observation angle as the real-time image from the three-dimensional scene model; and performing multi-directional dynamic identification of fire points based on real-time images and scene images at different observation angles. By constructing a three-dimensional scene model, the present invention can perform multi-directional collaborative analysis based on real-time images and scene images at various observation angles, thereby improving the accuracy of identifying fire points in substations.

The invention discloses a method for calculating DNB type critical heat flux density of a high-flux reactor arc-plate-shaped fuel assembly. The method comprises the following steps of: 1, carrying out geometric modeling and grid division on a coolant channel of the arc-plate-shaped fuel assembly; 2, solving a two-fluid model control equation and a turbulence model to obtain phase field and flow field distribution; 3, solving a bubble number density group balance equation to calculate bubble diameter distribution; 4, based on the near wall surface flow field, a bubble stress balance dynamic model is adopted to solve bubble characteristic parameters; 5, calculating each heat flow component by adopting an improved wall surface heat flow distribution model; 6, establishing a heat conduction-convection-turbulence superposition interphase heat transfer model and calculating a phase change mass source item; 7, medium physical properties and boundary conditions are set, and the gas-liquid integral number, the speed, the pressure and the temperature are solved in a coupling mode; 8, calculating the density of the stepped loading heat flow; and 9, determining the critical heat flux density according to the boiling curve turning point, the critical void fraction and the outlet bubble group distribution. According to the method, the critical heat flux density of the high-flux reactor arc plate-shaped fuel assembly can be effectively predicted.

The invention discloses an inspection method and device for a power transmission line in a mountainous area, electronic equipment and a storage medium. The method comprises the following steps: acquiring an acquisition image of a mountainous area power transmission line; according to the collected image, based on a pre-trained mountain fire smoke detection model, determining an inspection result of the power transmission line in the mountainous area; wherein the forest fire smoke detection model is obtained by training a pre-established target detection network based on a pre-acquired smoke data set; the smoke data set comprises multiple types of smoke samples, and the number of the smoke samples of each type is the same; the target detection network comprises a feature extraction structure and a branch structure; the feature extraction structure is sequentially connected with the branch structure, and the branch structure comprises a feature measurement unit, a regression unit and a classification unit. According to the technical scheme, the problems of low accuracy and poor reliability of forest fire smoke detection are solved, distance measurement is carried out on the extracted features, the distinction degree between different types of samples is increased, and therefore accurate identification of forest fire smoke is achieved.

The invention provides a digital turning and dynamic test analysis integrated device for a vertical water-turbine generator set, and relates to the technical field of water-turbine generator maintenance and fault analysis, and the device comprises a key phase sensor which is used for taking a key phase signal as a triggering point of data collection when the set rotates; the large shaft positioning unit is used for synchronously acquiring data of each measurement section and automatically marking angles during manual moving point turning; the throw sensor is used for measuring throw data of each guide bearing in the operation process of the turning gear or the unit; the acquisition extension set is used for receiving data from the key phase sensor, the large shaft positioning unit and the throw sensor, carrying out primary processing on the data and then sending the data to the analysis host through a wireless network; and the analysis host is used for calculating and displaying the data sent by the acquisition extensions and providing technical support for unit state evaluation and fault diagnosis.

The application provides a method for spatial domain identification based on spatial multi-omics data, belongs to the technical field of bioinformatics, and solves the problems that the prior art cannot fully utilize spatial multi-omics data and cannot identify discrete spatial domains, and comprises the following steps: step 1, obtaining a spatial multi-omics comprehensive data set and performing pretreatment; step 2, constructing a deep neural network model; step 3, training the deep neural network model based on the pretreated spatial multi-omics comprehensive data set; and step 4, inputting to-be-detected data into the trained deep neural network model to perform spatial domain identification.

The invention discloses a complex network high-order module and link prediction method based on low-order network reconstruction, and the method comprises the steps: complementing a missing network structure through low-order link prediction, recognizing a potential high-order module in a prediction network, combining the topological features of nodes and edges, and discriminating a real high-order structure through a machine learning model. And finally, high-order network reconstruction is realized. According to the method, a low-order and high-order structure collaborative modeling mechanism is established, and the limitation that only binary interaction is processed traditionally is broken through; the method is suitable for various high-order network modeling tasks, does not depend on a fixed motif form, and has good universality and expandability.

The present invention relates to the field of artificial intelligence, and discloses a medical image recognition method, device, equipment and storage medium, which are applied in the field of smart medical care to improve the recognition efficiency of medical images. The method of the present invention includes: receiving an initial image sent by a user terminal; classifying the initial image to determine the image type of the initial image; when the initial image is a medical feature image, performing image segmentation on the medical feature image through a preset dual attention network model to obtain a medical foreground image; correcting the medical foreground image to obtain a corrected medical foreground image; performing text detection on the corrected medical foreground image to obtain a target text; performing text recognition on the target text to obtain an identified field; performing correction check on the indicator field in the identified field to obtain a corrected field; classifying the corrected field to obtain a classification result, and sending the classification result to the target terminal.

The invention provides a map processing method, a medium and a program product, and relates to the technical field of laser mapping, according to the embodiment, under the condition of triggering loopback detection, a first relative pose between a current frame and a historical key frame is determined based on the current frame and the historical key frame obtained by a robot through scanning in a current scene; if the loopback detection is successful, determining whether the current scene is a gallery scene based on the point cloud of the historical key frame; if it is confirmed that the current scene is the gallery scene, according to the angle of the gallery in the world coordinate system and the mapping relation between the world coordinate system and the coordinate system where the gallery is located, the error in the first relative pose in the gallery direction is eliminated, and a second relative pose is obtained; according to the second relative pose, the contour map of the current scene is constructed, errors in the gallery direction (namely, parallel to the gallery direction) can be eliminated, at the moment, errors accumulated at the front end can be eliminated, and a correct contour map can be established.

The application discloses an air target single-photon laser three-dimensional histogram feature extraction method, and the operation steps are composed of a time correlation noise reduction module, a histogram accumulation module and a histogram feature extraction module. The application can extract target features under the conditions that the scale of a detector pixel is limited, single imaging point cloud data is sparse and there is atmospheric turbulence interference, and the stability of the features is enhanced.

The invention provides an equipment type identification method and device, equipment and a readable storage medium, and the method comprises the steps: obtaining electric signal information from a backboard CPLD of a backboard through an I2C channel, the electric signal information being electric signal information of a specified signal channel in sideband signals accessed from the backboard obtained by the backboard CPLD; judging the equipment type of hardware currently connected with the backboard according to the electric signal information; the electric signal information is generated according to level information generated by hardware currently connected with the backboard in a preset mode. Through the technical scheme of the invention, the electric signal information transmitted by the backboard CPLD is acquired and analyzed, accurate identification of the equipment type is realized, the configuration efficiency and accuracy are obviously improved, the error risk caused by manual setting is reduced, and the adaptability and stability of the system are enhanced.

The invention discloses an intelligent management and control method and system for cement concrete pavement cracks, and belongs to the field of road engineering.The method comprises the steps that sensitive switching parameters are set; the method comprises the following steps: controlling a collection traveling vehicle to move, pre-collecting road surface data, and constructing an initial reference data set; initializing a decision-making unit, inputting the initial reference data set into the decision-making unit, and outputting decision-making data; selecting an infrared sensor and / or an imaging sensor to carry out image data acquisition, and constructing an image data set; performing defect identification on the image data set, and recording abnormal coordinates and a disease feature set according to an identification result; and calling the pavement file, carrying out maintenance strategy matching, and carrying out intelligent management and control on the pavement according to a matching result. The technical problem that intelligent and precise detection and maintenance cannot be performed on the pavement crack in the prior art is solved, and the technical effect of intelligent management and control of the pavement crack through sensor acquisition, intelligent analysis and precise matching is achieved.

The application relates to a device abnormal state general identification method and device based on power quality data, a computer device, a storage medium and a computer program product. The method comprises the following steps: acquiring a trained identification model, and a labeling accuracy of each state label corresponding to the trained identification model, and determining a model accuracy corresponding to the trained identification model. The trained identification model is used for performing state identification on each target frequency spectrum, and a corresponding predicted state type is obtained. In the case that the predicted state type is an abnormal state, a state label matched with the abnormal state is used as a to-be-verified state type, and based on the labeling accuracy and the model accuracy, an abnormal probability corresponding to the to-be-verified state type is obtained through cumulative probability distribution calculation. The abnormal probability is subjected to effectiveness verification, and whether the target power device is abnormal is determined based on the effectiveness verification result, so that the effectiveness of determining whether the target power device is abnormal is greatly improved.

The present disclosure provides a specific transposon insertion marker of japonica subspecies and its application. First, the specific transposon insertion marker is located in the nucleotide region from 23,880,821 to 23,881,056 of chromosome 6 of the Nipponbare reference genome version IRGSP-1.0, which is a transposon with a length of 236 bp, and the varieties of japonica subspecies contain the transposon insertion, while the varieties of other rice subspecies do not contain the transposon insertion. Further, the application of the above specific transposon insertion marker is provided. The specific transposon insertion marker of japonica subspecies of the present disclosure has important application value in the precise identification of rice subspecies, the classification of germplasm resources, the screening of breeding materials, the purity detection of hybrid rice germplasm, and the like, and can significantly improve the efficiency of molecular marker assisted selection and shorten the breeding period.