190 results about "Data expansion" patented technology

The invention discloses a drug combination patent intelligent identification method and device based on a large language model, and the method comprises the steps: obtaining a standard data set built based on drug combination labeling information of patent data, carrying out the data expansion of the standard data set, and generating an initial training set; a parameter efficient fine tuning technology is adopted, the initial training set is utilized to train the base large language model, and an initial recognition model is generated; screening and identifying difficult samples in the unlabeled patent data by using the initial identification model, and adding the difficult samples into the initial training set to form an enhanced training set; performing iterative training on the initial recognition model by using the enhanced training set and adopting a multi-task learning framework in combination with a comparative learning mechanism to obtain a drug combination patent recognition model; the to-be-recognized patent data is input to the drug combination patent recognition model, and a drug combination information recognition result is obtained.The accuracy, data efficiency and model interpretability of drug combination patent recognition can be remarkably improved, and the computing resource requirement and the manual review cost are reduced.

The invention discloses an expressway bridge construction state real-time monitoring method and system, and relates to the technical field of bridge construction monitoring. An expressway bridge construction state real-time monitoring system comprises a data acquisition and processing module, a data expansion and analysis module, a multi-point data fusion module, a state comprehensive evaluation module and a construction scheme adjustment module. According to the method, data interpolation and expansion are carried out on the preprocessed vibration monitoring data through the Kriging interpolation method, the spatial autocorrelation between the vibration monitoring data can be fully utilized, and the monitoring data are expanded, so that the problem of insufficient coverage of monitoring points can be effectively solved, and the integrity and precision of the monitoring data are improved; the change trend and the distribution rule of vibration in space can be reflected more accurately, a more comprehensive and reliable basis can be provided for evaluation of the highway bridge construction state, and the state evaluation accuracy of the highway bridge construction state real-time monitoring method and system is improved.

The invention provides a double-current comparison and DHI combined equipment fault detection method and system, and belongs to the technical field of power equipment state monitoring and fault diagnosis. The method comprises a time sequence perception adversarial enhancement module, a generative adversarial network (GAN) data expansion module, a double-flow contrast attention network (D-CAN) feature extraction module and a dynamic health index (DHI) calculation module. The core lies in that a fault sample with time sequence correlation is supplemented through a physically constrained GAN, robust features are extracted by using a ResNet1D and Transform fused double-flow network, and a health state is quantified in combination with unsupervised clustering and mahalanobis distance. Through simulation and experimental verification, zero-delay detection of the early fault of the transformer can be realized, the output health index and the 3D visualization result can provide an accurate basis for operation and maintenance of the transformer, and the diagnosis accuracy, the data utilization rate and the dynamic adaptability of state evaluation are remarkably improved.

The invention provides a data compression method, apparatus and device, and a storage medium. The method comprises the steps of obtaining an original data stream transmitted through a serial port; determining the data type of the original data flow according to the original data flow; determining a corresponding target compression algorithm according to the data type; compressing the original data stream according to the target compression algorithm to obtain compressed data; the defects of low efficiency and even data expansion during data abrupt change in a fixed compression mode are effectively overcome, and the data transmission efficiency and the bandwidth utilization rate of serial port communication in a resource limited environment are remarkably improved.

The steam generator state real-time monitoring method based on artificial intelligence belongs to the field of artificial intelligence and comprises the following steps: S1, data acquisition and labeling; S2, sample generation is performed by using a quantum generative adversarial network based on random projection embedding to realize data expansion; S3, the expanded data is input into a feature extraction model to perform training of the feature extraction model, and a five-layer fully connected neural network is used for feature extraction; S4, the feature-extracted data is input into a feature dimension reduction model to perform training of the feature dimension reduction model, and a self-encoding neural network algorithm based on local preserving projection is used to realize feature dimension reduction; S5, the dimension-reduced data is input into a classifier to perform training of the classifier model; and S6, steam generator state recognition and monitoring are performed.The steam generator state real-time monitoring method based on artificial intelligence can solve the problems of insufficient sample quantity and lack of data diversity and enhances the robustness of the model when the model has noise or fuzzy classification boundary data.

The invention provides a small sample channel state information data expansion method based on a generative adversarial network, and the method comprises the steps: generating a vivid time-frequency domain channel sample through a Wasserstein generative adversarial network based on physical constraints under the condition of rare or missing drive test data; and a time-frequency joint discriminator is combined to effectively distinguish real and forged signals. Statistical authenticity of a generated sample is improved through joint time-frequency domain feature discrimination, a physical constraint module is embedded in a generator, and channel physical characteristics are maintained through forced power normalization and a spectrum matching mechanism. A GAN framework with gradient penalty is adopted in the whole training process, and the training stability is ensured. And data sample generation when the nodes are quickly deployed to a new environment is facilitated.

The invention discloses a software defect prediction method based on cGAN and DGRRC, and the method comprises the steps: extracting static code features and defect labels of a software module, and carrying out the preprocessing, and obtaining an original sample set; inputting defect tags in the original sample set into a conditional generative adversarial network (cGAN) for defect sample synthesis and data expansion to obtain a class balanced expansion set; a dynamic greedy correlation-redundancy feature selection DGRRC method is adopted to screen features in the class-balanced expansion set according to correlation and redundancy, and a data set containing core features is obtained; and inputting the data set containing the core features into a Meta-Ensemble model based on an attention mechanism to carry out fusion and software defect prediction. The method combines the advantages of generative data enhancement, feature selection and ensemble learning, and aims to improve the accuracy and robustness of defect prediction from multiple aspects.

The invention discloses an R-tree spatial index design method oriented to a DRAM-NVM hybrid storage architecture, relates to the technical field of computer data storage, and provides a write optimization spatial index HR-Tree under the DRAM-NVM hybrid architecture. The core design thought is that internal nodes are deployed on a DRAM, leaf nodes are placed on an NVM, and a targeted data read-write operation process is designed; in the aspect of an index structure and an operation mechanism, a minimum expansion strategy is adopted around a scene of less reading and more writing, a leaf node data structure and an in-situ updating algorithm on the NVM are designed in a targeted manner, and the write request processing efficiency can be improved on the premise of ensuring data consistency. And the multi-character data expansion and efficient fault recovery are provided, so that the actual requirements of the user are better met by allowing more flexible personalized configuration and shortening the service pause time. The method is suitable for the application fields of computer technology, database technology, data storage and the like.

The application discloses a battery data expansion and energy management closed-loop method for complex traffic flow, and relates to the technical fields of new energy vehicle battery management and artificial intelligence control. The application is aimed at the problems of battery high dynamic operation data scarcity under complex traffic flow conditions, poor generalization of existing energy management strategies, and open-loop data generation being separated from real vehicle control, and first constructs associated data sets of traffic flow dynamic conditions and corresponding battery operation responses; then constructs a conditional generation adversarial network introducing battery physical constraints, directionally generates battery response data and constructs an expanded data set; based on the expanded data set, a deep reinforcement learning energy management strategy is trained offline, and finally the strategy is deployed to a vehicle-mounted control system, and online closed-loop fine-tuning is performed through real vehicle operation data. The application improves the robustness of the energy management strategy under complex conditions and effectively reduces the energy consumption of the whole vehicle.

Embodiments of the present application relate to a speech recognition apparatus, a method, and a program. A speech recognition apparatus, a method, and a program capable of improving speech recognition performance are provided. A speech recognition apparatus according to an embodiment includes a data expansion unit, a sound score calculation unit, an adjustment unit, a sound score merging unit, a lattice generation unit, and a search unit. The data expansion unit generates a plurality of expanded speech data based on input speech data. The sound score calculation unit generates a plurality of sound scores based on each of the plurality of expanded speech data and a sound model. The adjustment unit generates a plurality of adjusted sound scores by performing resampling on the plurality of sound scores, respectively. The sound score merging unit generates a merged sound score by merging the plurality of adjusted sound scores. The lattice generation unit generates a merged lattice based on the merged sound score, a pronunciation dictionary, and a language model. The search unit searches for a speech recognition result having the highest likelihood from the merged lattice.

The application discloses a powder pressing process parameter optimization method based on digital twinning, which comprises the following steps: constructing a powder pressing process digital twinning model construction and twin data generation module, which constructs a powder pressing process digital twinning model based on filling parameters, material parameters and process parameters, and generates twin data; constructing a quality parameter and energy consumption parameter prediction model construction module, which realizes twin data expansion based on the twin data expansion network, and trains the quality parameter and energy consumption parameter prediction model based on the expanded data; and constructing a process parameter optimization module, which optimizes the process parameters through a particle swarm optimization algorithm based on the quality parameter and energy consumption parameter prediction model. The application can solve the problem that the process parameters are difficult to be accurately optimized under the condition that the powder pressing process data is insufficient, effectively improves the quality of the finished powder column while reducing the energy consumption of the pressing process.

This invention relates to the technical field of combining artificial intelligence with traditional Chinese medicine (TCM), and discloses an AI-based intelligent image analysis system for TCM tongue diagnosis. The system includes: an image acquisition and preprocessing module, which receives raw tongue image data from a tongue image acquisition device via a hardware interface and performs multimodal correction processing on the raw tongue image data to generate standardized images; and an environment adaptation module, which is connected to the image acquisition and preprocessing module via a data interface. This invention reduces image errors caused by the shooting environment and equipment through multimodal correction in the image acquisition and preprocessing module, and combines this with a data expansion and enhancement module to generate diverse case images to improve the dataset. This effectively solves the problems of poor image quality and insufficient case coverage, reduces reliance on doctors' experience and subjective judgment, reduces differences in judgment among different diagnostic subjects regarding the same tongue image, and improves the accuracy and stability of diagnostic results.

The application relates to the field of automobile electronics and provides a parking space data expansion method, which is based on the scene requirement of a deep learning algorithm in an image recognition technology, extracts a parking space line image from a collected real scene parking space image to generate a foreground database, extracts a parking space background image except the parking space line to generate a background database, and through separation and combination of the parking space line and the background image, the number of simulated real scene parking spaces can be effectively expanded; wherein, a reference parking space line is generated by acquiring a parking space line feature of any parking space line image, a target parking space set is generated according to the reference parking space line and a preset distribution rule, further, the number of simulated real scene parking spaces is expanded by forming parking space images with different preset distribution rules, so that the data acquisition difficulty and the acquisition cost are reduced, the scene coverage rate is improved, and the image recognition efficiency is improved.

The application provides a data expansion method and device, the method comprises the following steps: obtaining N groups of real source data, each group of real source data contains a data sequence; dividing the data sequences in the N groups of real source data into a plurality of sequence combinations, each sequence combination is a calculation group; performing weighted calculation on each calculation group according to the sequence number requirement of weighted average calculation, to obtain the weight value allocated to each calculation group; performing weighted average on the data sequences in each calculation group according to the weight value allocated to each calculation group, to obtain the data expansion sequence of each calculation group. In the data expansion method, the calculation results of all calculation groups are not all considered all data sequences, therefore, in the case that some part of data sequences are abnormal, more calculation results are not affected because they do not involve abnormal data sequences, which greatly avoids the influence of abnormal sequences in small data on the final data expansion sequence.

The invention discloses a method for predicting spraying characteristics of an internal combustion engine. The method comprises the following steps: establishing an original data set comprising data of working condition parameters and data of spraying characteristic parameters; calculating the deviation between the measured value and the calculated value of the existing spray characteristic formula, and correcting the existing spray characteristic formula; constructing a physical constraint system of spraying characteristics; extrapolating and expanding by adopting a Gaussian process regression method; performing interpolation enhancement by adopting a generative adversarial network; constructing a spray prediction model through deep learning; according to the method, an existing spraying characteristic formula is corrected through the deviation value, and the data expansion accuracy is improved; the limitation of small sample experimental data is effectively solved through data enhancement, Gaussian process regression extrapolation with priori knowledge is utilized to expand and cover limit working conditions, a correction formula and physical constraints are added into a generative adversarial network, details are further complemented, data breakpoints are eliminated, and a high-quality data set is constructed. And the generalization ability, the prediction precision and the physical rationality of the deep learning model are improved.

One aspect of the present application relates to a multi-sampling rate speech recognition training method and device. A training method for a multi-sampling rate speech recognition device is disclosed, the multi-sampling rate speech recognition device at least comprising a data expansion module and a speech recognition module, the training method comprising: inputting multi-sampling rate sample speech data features into the data expansion module to generate speech data features of a required sampling rate; inputting the generated speech data features and sample speech data features of the required sampling rate into a discrimination module to determine whether the generated speech data features are qualified; optimizing the data expansion module based on the determination result; inputting the speech data features determined to be qualified into the speech recognition module for training, and calculating a loss value of the speech recognition module; optimizing the discrimination module based on the determination result and the loss value of the speech recognition module; repeating the above steps until all the speech data features generated by the data expansion module are determined to be qualified.

The invention provides a vehicle control method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting third driving scene data collected in a vehicle driving process into a first model, and generating decision data of a vehicle; wherein the first model is obtained by performing pre-training based on first driving scene data and second driving scene data, and the second driving scene data is obtained by performing data expansion on the first driving scene data; and controlling the running track of the vehicle according to the decision data. According to the method, expandability of high-quality scene data can be achieved, the first model is trained through cooperation of the first driving scene data and the second driving scene data, the adaptability of the model to a complex driving scene is improved, a vehicle can make a reasonable decision autonomously in the driving process, and the driving efficiency is improved. Therefore, the safety and the stability of driving in different scenes are improved.

The invention relates to the technical field of high-voltage circuit breaker fault identification, and discloses a high-voltage circuit breaker fault identification method, system and device and a medium, and the method comprises the steps: converting a multi-state vibration signal of a high-voltage circuit breaker into a multi-state signal time-frequency diagram; performing data expansion on the multi-state signal time-frequency diagram, and dividing the multi-state signal time-frequency diagram into a training set and a test set; extracting a time-frequency graph feature vector of the training set, and performing parameter optimization on the fault classifier according to the time-frequency graph feature vector to obtain an optimized classification model; calculating verification model parameters according to the optimization classification model; and constructing a target fault prediction model according to the verification model parameters, performing fault prediction on the to-be-diagnosed high-voltage circuit breaker signal by using a target fault diagnosis model, and calculating a corresponding feature importance thermodynamic diagram and a target fault evaluation factor. According to the method, the accuracy of target fault category prediction can be improved, the fault reason is directly positioned through the feature importance thermodynamic diagram, and accurate identification of high-voltage circuit breaker fault detection is realized.

The present application belongs to the field of terahertz imaging and image processing, and particularly relates to a terahertz image data expansion method based on a space-frequency degradation model. The method mainly comprises the following steps: pre-screening and pre-processing a high-resolution image database to establish a high-resolution image library; simulating a terahertz Gaussian beam to perform fuzzy degradation processing on the high-resolution image using a Gaussian fuzzy kernel; simulating terahertz wave source fluctuation and sensor noise to add Gaussian noise; simulating low resolution of terahertz imaging, and reducing the image resolution using a bicubic downsampling method; simulating mutual interference of multiple terahertz waves during imaging, and using a scheme of adding a frequency domain mask to change the frequency domain features; simulating the case that low image contrast is caused by low terahertz wave source power, and using a gray scale compression method to compress the gray scale histogram of the image to obtain a final low-resolution image data set. The present application can effectively expand the super-resolution training set of terahertz images, thereby improving the training effect of the terahertz image super-resolution reconstruction task based on the deep learning method.

The invention provides a data query method and device, electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining query data input by a user; performing data expansion based on the semantics of the query data to obtain expanded data associated with the query data; in a query range, performing similarity matching on the query data and the extended data to obtain a matching result; and returning a query result corresponding to the query data according to the matching result. Semantic expansion is carried out on query data input by a user to obtain expanded data similar to the query data in semantics, and then data query is carried out through the query data and the expanded data obtained through expansion, so that more results similar to the query data in semantics can be matched, and when the user cannot provide an accurate query basis, the query efficiency is improved. A higher hit rate can be realized based on semantics, and query of data required by a user is realized.

The invention relates to the field of intelligent medical treatment, in particular to an allergy data processing method and device and a program product. Comprising the steps of obtaining a basic data set and a risk category label of a to-be-tested person; performing data expansion on the data set and the label of the risk category through a generative adversarial network to obtain expanded data; in the generative adversarial network training process, a generator generates preliminary synthetic data by using random noise and feature information of original allergy-related medical data, a discriminator distinguishes real allergy-related medical data from synthetic allergy-related medical data, and iterative training is performed on the generator and the discriminator; loss function calculation of the generative adversarial network generator comprises adversarial loss and feature comparison loss, calculation of the adversarial loss comprises random noise data and feature data of the allergic medical data, and calculation of the feature comparison loss comprises the allergic medical data. The application has good clinical value.

The application belongs to the technical field of deep learning, and discloses a time sequence anomaly detection method based on a difference component. First, the original independent samples are changed into dependent samples through permutation and combination of a small sample data set, the number of samples is expanded to obtain combined sequence samples, and then the difference component including a learnable kernel is used to generate a difference feature map of the combined sequence samples, and the difference feature map is input into a feedforward network for training. The application effectively solves the problem of unsatisfactory classification effect between complex data in small sample learning, and proposes a new data expansion method and classification component, so that the classification detection task can be efficiently realized without long time training.

The present disclosure provides a material property prediction method and device, which firstly acquires component data of a plurality of sample materials as training data, standardizes the training data, linearly interpolates the standardized training data to obtain a training data set, then trains a material property prediction model according to the training data set, inputs material data to be measured into the trained material property prediction model to obtain a material property prediction result, removes elements affecting the performance of the model by standardizing the training data, thereby improving the quality of the training data, and increases the size of the data set by using a linear interpolation method, which can be well applied to small sample material property prediction, and also uses a neural network composed of full connection layers to accurately predict the material property, and the method combining data expansion and neural networks is superior to the automatic machine learning method.

This application proposes a data augmentation method, apparatus, electronic device, and storage medium. The data augmentation method includes: acquiring a first dataset, the first dataset including first text and a corresponding first image; determining a corresponding second text based on the semantics of the first text; determining a second dataset from the first dataset based on the second text; performing a deduplication operation on the second dataset based on a preset deduplication strategy to obtain a third dataset, the third dataset including seed text and a seed image; determining augmented text from a database based on the semantics of the seed text; determining an augmented image from the database based on the image features of the seed image; and determining an augmented target dataset based on the third dataset, the augmented text, and the augmented image. This application relates to the field of multimodal data analysis technology and can improve the accuracy of multimodal data augmentation.

The invention belongs to the technical field of aircraft fire extinguishing design, and provides a large amphibious aircraft water throwing efficiency data expansion method, which comprises the following steps: carrying out a pre-flight test of an aircraft to obtain test state points of aircraft water throwing efficiency, including typical test state points and atypical test state points; carrying out water throwing efficiency tests on different test state points, summarizing and analyzing test data, carrying out water throwing efficiency tests on test state points corresponding to invalid data again, summarizing the test data again, and fitting the test data to obtain different water throwing efficiency relation curves; and typical test state point results are extracted to fit coefficients of the water throwing efficiency relation curve, the coefficients are combed, a change relation curve of the water throwing efficiency and different test state points is constructed, and a change curve of the water throwing efficiency along with the water throwing height under each test state point of the airplane is expanded. According to the method, data validity judgment can be improved, the test process is accelerated, and unpredictability of environment variable control caused by an overlong test period is avoided.

The invention provides a video noise reduction data set construction method and system and an image processor, and the method comprises the steps: carrying out the data expansion based on a real shot video data set, and obtaining a first data set; performing first noise addition and first clipping processing based on the dynamic video noise reduction data set to obtain a second data set; performing second noise addition and second clipping processing based on the static video noise reduction data set to obtain a third data set; and constructing a video noise reduction data set based on the first data set, the second data set and the third data set. According to the construction method and system of the video noise reduction data set and the image processor provided by the embodiment of the invention, the construction cost of the video noise reduction data set is reduced, and the construction efficiency of the video noise reduction data set is improved.

This invention discloses a data storage method and system based on a scalable multidimensional learning index structure, belonging to the field of computer data storage. This system fully utilizes storage characteristics to organize data into memory and disk, significantly reducing disk I / O with minimal memory usage, accelerating data search speed, and supporting data expansion. This invention can be applied to multidimensional data indexing, typically represented by geospatial data, meeting the need for rapid multidimensional key searching in the high-dimensional key space of such data.

This invention provides a data expansion device that can increase the amount of historical performance data when sufficient historical performance data has not been accumulated. [Solution] The data expansion device includes means for acquiring time history data relating to the operation of the equipment, means for copying the time history data to generate duplicate data, means for changing the time information included in the duplicate data, means for varying the values ​​relating to the operation of the equipment included in the duplicate data within a predetermined range, and means for merging the time history data and the duplicate data.

The invention discloses a cross-domain small sample semantic segmentation method and device, equipment and a medium. According to the cross-domain small sample semantic segmentation method, a hierarchical data set is constructed through a controllable style offset synthesis image, and a style feature extraction and weight generation network is trained; a dynamic weight is generated based on the difference between the target domain image style representation and the source domain reference, feature layer level modulation is performed on the visual basis model encoder features, and the feature alignment problem is accurately solved; image semantic information is fused and supported through a memory attention mechanism, so that the problem of small sample semantic sparsity is effectively relieved; meanwhile, the synthetic data accurately controls style offset through a stable diffusion model, and uncontrollability of traditional generative data expansion is avoided. According to the method, the cross-domain small sample semantic segmentation performance is remarkably improved, and the problems of prompt mismatching, feature dislocation and out-of-control data expansion caused by domain offset are solved.

The invention discloses an oil-gas-water three-phase flow process data two-stage amplification and flow characteristic modeling method. The method comprises the following steps: step 1) establishing a probability gating circulation unit model of a multiphase flow pump flow characteristic; 2) predicting an input sample of each working condition by using a PGRU model; step 3) utilizing probability characteristics provided by the PGRU model to identify an area needing data amplification; step 4) based on an active noise elimination method, executing sample amplification on the identified area; (5) repeating the steps (2)-(4), identifying a to-be-amplified sample area of each working condition, and supplementing samples which are consistent with original data in distribution; 6) collecting all data from the steps 2-5 as original data of the TimeVAE model, and performing second-stage data amplification; and 7) training a multiphase flow pump flow characteristic prediction model by using all data obtained in the step 6). According to the method, two-stage amplification and flow characteristic prediction of three-phase flow process data can be realized under a complex and changeable oil-gas-water three-phase mixed transportation working condition.