20results about How to "Improve retrieval performance" patented technology

The invention discloses a computer data management system and method, and relates to the technical field of data management, and the method comprises the steps: reading a heterogeneous data set, dividing the heterogeneous data set into text, time sequence and binary data groups according to data types, extracting a core field of each data group, and generating a deduplication feature and an index feature, setting a sliding window based on the data type and generating a window index feature abstract; calculating a comprehensive similarity score between the data blocks according to the sliding window, screening a similar data block set, determining a reference data block and a redundant data block, clustering the reference data block to generate an initial cluster, and if the global deduplication rate and the clustering preprocessing validity do not meet preset conditions, re-initializing the sliding window; according to the method, the cluster structure is optimized and the cluster feature abstract is generated based on the retrieval popularity predicted value of the initial clustering cluster, the three-layer index structure comprising the global index, the intra-cluster index and the feature index is constructed, the retrieval efficiency is tested, the index hierarchy is optimized, and the storage efficiency and the retrieval performance of heterogeneous data management are remarkably improved.

The application discloses a cross-natural language code retrieval model training method, a cross-natural language code retrieval method, a device, equipment and a medium, and relates to the technical field of artificial intelligence and software engineering. The cross-natural language code retrieval model training method comprises the following steps: obtaining an original corpus database, and constructing training data according to the original corpus database; performing confusion and inversion on main language codes to obtain main language code samples, wherein the main language code samples comprise main language code positive samples and main language code negative samples; and training an initial model through a gradient inversion layer according to the training data and the main language code samples to obtain a target model. According to the application, the natural language-specific "fingerprint" features in the codes can be removed, the embedding space alignment direction can be unified, the sampling distribution deviation in the training process can be reduced, and the consistency and generalization capability of cross-language code retrieval can be improved.

The application relates to the technical field of storage computing, and discloses a system, a method and an electronic device for directly searching data in a storage medium, the system comprising a large-scale vector database, a nearest neighbor search operation unit and a host computer, the large-scale vector database is arranged in the storage medium and is used for storing a vector set; the nearest neighbor search operation unit is arranged in the storage medium; the host computer is provided with a CPU and a cache unit; when the nearest neighbor search operation unit receives an NNS_CSD instruction sent by the CPU, the vector of the database is read, similarity measurement is carried out, and the search result meeting the condition is sent to the cache unit, the application directly searches data in the storage medium, the NNS_CSD instruction is used to start the calculation in the storage medium, the nearest neighbor search operation unit in the storage medium is used for vector reading and similarity measurement, compared with a traditional architecture, the migration of data is greatly reduced, and the overall performance is improved.

The application discloses a retrieval method and related device. According to a to-be-retrieved input string, prefix matching is performed in a target dictionary tree to obtain a target leaf node. According to a remaining string of the to-be-retrieved input string, each full string in a data file corresponding to the target leaf node is checked to obtain a checking result of each full string, the checking result being used to indicate whether the corresponding full string matches the to-be-retrieved input string. If the checking result indicates that a target full string in the data file matches the to-be-retrieved input string, a word corresponding to the target full string is determined as a candidate of the to-be-retrieved input string. The application combines the target dictionary tree and the data file to perform retrieval, the target dictionary tree has the characteristic of high retrieval efficiency, and meanwhile, since the remaining string is a partial string of the to-be-retrieved input string, the time for performing retrieval in the data file is also reduced. Therefore, the retrieval efficiency and retrieval performance are improved, even the response performance of the entire input method is improved, and the input experience is improved.

A cross-view image retrieval method for unmanned aerial vehicle navigation, comprising the following steps: step one, first enhancing the image, step two, based on the ConvNeXt network for cross-view image retrieval for unmanned aerial vehicle navigation, multi-scale feature extraction is performed on the enhanced image; step three, multi-dimensional feature fusion is performed based on an attention mechanism; step four, after multi-dimensional feature fusion, the loss value is calculated, and a detection model is obtained based on the determined weight to perform image retrieval; through the multi-scale feature convolution and multi-dimensional feature fusion technology, the technical problems of insufficient matching precision and poor retrieval robustness caused by the differences in view, scale and structure between satellite images and unmanned aerial vehicle images are solved; the application also includes a system, a device and a medium for implementing the above method.

This application discloses a trademark retrieval database generation, retrieval method, and apparatus that enhances local features. The method involves constructing a multi-classification training set for trademark graphic elements and training it in an image multi-classification model to obtain a trademark element multi-classification model; constructing a target detection training set for important graphic elements based on trademark data and training it in an image target detection model to obtain a target detection model; inputting all trademark data into the trademark element multi-classification model for prediction and selecting trademark elements as field information; inputting all trademark data into the target detection model to detect important graphic element targets and extracting them into sub-images; inputting all sub-images and the original trademark data image into a trademark encoding model for encoding to obtain encoding vectors; and inputting the field information and encoding vectors into a vector database to obtain the trademark retrieval database. Using the trademark retrieval database provided in this application can significantly improve trademark retrieval results.

This invention discloses a supervised multimodal hash retrieval method and system based on label enhancement, belonging to the field of artificial intelligence and multimedia retrieval technology. The technical problem this invention aims to solve is how to better capture the similarity information between multimodal data points and achieve better performance and accuracy in multimodal retrieval tasks. The technical solution includes: data preprocessing: acquiring and organizing public datasets of image and text modalities, and dividing each public dataset into training, testing, and retrieval datasets; extracting deep features: using a pre-trained network model to extract features from the raw data of the public datasets of image and text modalities respectively, obtaining deep features of the image modality and the text modality; offline training; variable update and optimization; and online query. The system includes a data preprocessing unit, a feature extraction unit, an offline training unit, a variable update and optimization unit, and an online query unit.

A multi-modal transfer learning framework for video corpus segment retrieval, the learning framework is trained by a segmented pre-training transformer using image-text pairs, video-text pairs and a VCMR dataset to transfer the knowledge of ITR and VR to VCMR, so that better performance can be achieved on a relatively small VCMR dataset, comprising: a retrieval module, the retrieval module comprises a text encoder, a visual encoder and a video retrieval module; the text encoder adopts a segmented pre-training transformer to generate a query representation, and encodes the query representation to generate a text representation; the visual encoder is used to generate a video representation by adopting a visual transformer; the video retrieval module is used to retrieve video segments; a segment positioning module, the segment positioning module introduces L1 loss and IoU loss to directly predict the time span in a fine-grained manner.

The invention discloses an air and space big data intelligent data management system and method based on four-database collaboration and knowledge generation. A core layer adopts a temporary storage database, a controlled database, a product database and a knowledge database to form a four-database architecture; and the service layer adopts a data governance engine, a productization engine, a knowledge generation engine and an intelligent enabling engine. The system combines a data governance engine and a productization engine to carry out collaborative linkage to carry out data governance. Depositing knowledge assets into a knowledge base by relying on a knowledge generation engine; performing intelligent enabling application of each link of the data governance process by means of an intelligent enabling engine; and an intelligent enabling application effect is fed back, and knowledge assets in the knowledge base are optimized. According to the intelligent closed-loop data governance system, data governance implicit knowledge is converted into dominant knowledge and reused, the self-adaptability and the intelligent level of the data governance process are improved through knowledge reverse enabling, and then an intelligent closed-loop data governance system capable of self-learning, self-optimizing and continuously adapting to service requirements is formed.

This application discloses a training method, apparatus, device, and storage medium for a self-supervised learning model, belonging to the field of computer and internet technology. The method includes: acquiring a sample set; for a target text sample in the sample set, concatenating the target text sample with other text samples in the sample set to generate a first negative sample corresponding to the target text sample; and using the first negative sample to perform self-supervised training on a text feature extraction model; wherein the text feature extraction model is used to obtain feature information of the input text based on the input text, in order to match retrieval text with semantically similar characteristics to the input text. This application improves the text feature extraction model's ability to distinguish text information with small semantic differences, thereby enhancing the retrieval capability of the text feature extraction model.

The application discloses a regional analysis method based on a space grid index, and relates to the field of geographic information system big data space analysis.The application comprises the following steps: creating a geographic feature point thematic data table, creating a grid index field for the geographic feature point thematic database table, creating a thematic data table, establishing a mapping relationship between each geographic feature surface record and the grid index table, calculating an index value when the query precision is n according to the created grid index value k, establishing a space relationship between each geographic feature point and the geographic feature surface, and screening out a statistical analysis result meeting the condition.The application has the advantages that the grid index field is established, the index creation cost is reduced, the maintenance cost is decreased, multi-size space indexes are supported, the precision requirements of different businesses are met, the retrieval performance is further improved when the precision requirement is not high, the operation efficiency is greatly improved by adopting hexadecimal character matching, and good scalability is maintained in the regional analysis direction.

The application realizes a commodity search method with query-related multi-aspect explainability by means of a method in the field of artificial intelligence. The search information of an input commodity is searched and the query commodity result is fed back by using a multi-path query perception graph convolution network for explainable commodity search. The multi-path query perception graph convolution network for explainable commodity search comprises two components: a query perception graph convolution sorter and a query perception multi-path reasoner. The query perception graph convolution sorter models the representation of a user and a commodity according to different knowledge relationship domains in a knowledge graph by using a graph convolution network. The query perception multi-path reasoner is responsible for exploring a query-specific multi-path from the knowledge graph to meet the search intention of the user. The two components share basic parameters and are collaboratively trained to constitute a complete network. The method can significantly improve the retrieval performance and generate better explanations for the search result.

The application discloses a hash code generation model training method and a hash code generation method, relates to the technical field of artificial intelligence, and comprises the following steps: sampling a batch of data from a text data set; inputting target text data in a text data sample in the batch of data into an initial hash code generation model to obtain a feature projection vector corresponding to the target text data, so as to determine a contrast loss value, an optimal transport distance margin loss value and a uniform distribution regularization loss value, and then determine a total loss value; based on the total loss value, updating model parameters of the initial hash code generation model, returning to the step of sampling a batch of data from the text data set until the model converges, and obtaining a target hash code generation model. The technical problem that a hash function in the related art cannot effectively distinguish similar vectors is solved, and the technical effect of effectively distinguishing similar vectors is achieved.

A method and system for image similarity recognition based on multi-feature fusion, relating to the field of image processing technology, is disclosed. The method includes: calculating the hash features of an input image and generating hash similarity and hash confidence values; when the hash confidence value is less than a hash confidence reference value, performing local feature extraction on the input image to generate local similarity and local confidence values; when the local confidence value is less than the local confidence reference value, performing deep learning feature extraction on the input image to obtain deep features and deep confidence values; determining the weight coefficients of the hash features, local features, and deep features based on the hash confidence value, local confidence value, and deep confidence value, respectively; performing feature fusion to generate a fused feature vector; and calculating the final similarity between the input image and the image to be compared based on the fused feature vector. Implementing this application can improve processing efficiency while ensuring the accuracy of image similarity recognition.

This invention belongs to the field of data management technology, specifically relating to a method and system for managing geographic information mapping data based on multi-source spatiotemporal features. The method includes: acquiring mapping data containing spatiotemporal coordinate attributes and generating time-granularity codes; selecting the optimal child node based on comprehensive cost when inserting data; when a node is overloaded, evaluating the spatiotemporal variability cost of candidate splitting strategies to select the optimal strategy; for newly generated leaf nodes, determining the reference object and differential accuracy level based on the spatiotemporal distribution of internal data objects, and storing the differential values ​​of the data relative to the reference object; extracting query feature vectors and matching historical query patterns to cluster centroids for data prefetching; and asynchronously updating the centroids and adjacency pointer transition probabilities in batches after the query. This invention improves the retrieval response performance of mapping data while effectively compressing data storage space by constructing an index structure and combining differential storage with predictive prefetching.

A low-quality remote sensing image depth hash retrieval method, system, device and medium based on vector quantization, the method comprising: first, obtaining high-quality and low-quality remote sensing images as input, extracting the features of high-quality and low-quality remote sensing images through a deep convolutional neural network respectively, and inputting them into a vector quantization module to quantize them into independent discrete spaces to generate quantized features, then generating hash codes for image retrieval through a deep hash network, and finally obtaining feature representations and constraining the feature representations by applying a loss function, which includes Pairwise Loss, reconstruction loss and cross-entropy loss, to ensure semantic information retention, feature distance constraint and collaborative learning of the encoder, codebook and decoder; the system, device and medium are used to implement the method; the present application improves the retrieval accuracy of low-quality remote sensing images, reduces the storage space occupation and computing overhead, improves the robustness and generalization ability of the model, and ensures high retrieval performance.

The invention provides a pre-training language model retrieval method and system based on knowledge graph enhancement, and the method comprises the steps: carrying out subgraph division processing on a domain knowledge graph, and generating a subgraph index matched with a user retrieval type; updating the domain knowledge graph and the sub-graph index by adopting an incremental training method of a graph neural network; user query is decomposed into an entity set and a relation path through entity recognition, entity disambiguation, entity linking and relation extraction operation; positioning a corresponding sub-graph index based on the entity set and the relation path, and extracting a related sub-graph from the domain knowledge graph; and respectively coding the head entity, the relationship and the tail entity in the related sub-graph triad into basic vectors, and performing semantic fusion processing on the basic vectors to generate knowledge prompt vectors. The method has the advantages of accurately capturing domain structured association logic and responding to domain dynamic iteration knowledge in real time.

The invention relates to the technical field of public health information. The invention discloses a public health data retrieval method based on natural language processing. The public health data retrieval method comprises the steps that S1, a natural language retrieval instruction of a user is received; s2, analyzing an instruction through a large language model of the semantic analysis component, generating a vector value, retrieving metadata and an index component, and generating a retrieval expression; s3, checking and adjusting the expression through a semantic analysis confirmation component; s4, the data retrieval code generation component determines table attributes and association according to the expression, and SQL is generated; and S5, calling the SQL query database by the data retrieval execution component, and returning a packaging result to the user. By means of natural language processing and multi-component cooperation, the public health data retrieval threshold is lowered, and the accuracy is improved. Users can retrieve through daily languages, and non-technical users can efficiently obtain data. The system confirms a component multi-dimensional verification retrieval expression through semantic analysis, and ensures that data is matched with requirements.

The application relates to the field of footprint identification, and discloses a barefoot footprint comparison method and device based on deep learning. The method comprises the following steps: obtaining a to-be-identified barefoot footprint, and determining a toe region and a sole region in the to-be-identified barefoot footprint through a footprint segmentation unit; determining a plurality of intermediate target barefoot footprint traces corresponding to the to-be-identified barefoot footprint in a barefoot footprint trace database according to the toe region through a toe region identification unit; determining a final target barefoot footprint trace corresponding to the to-be-identified barefoot footprint in the plurality of intermediate target barefoot footprint traces according to the sole region through a sole region identification unit, and taking the final target barefoot footprint trace as an identification search result; wherein the toe region identification unit is obtained through training of toe region data sets of a plurality of barefoot footprint traces. The application can improve the speed of footprint identification search in the barefoot footprint trace.

The present application relates to a kind of condition text-commerce picture retrieval method and system based on hierarchical style.The method includes the following steps:1. establish condition text-commerce picture database.2. the average feature of image block is interacted with image block feature by sliding window mechanism and two-stage self-attention mechanism, and the common feature of image block is obtained.3. the common feature is fused with image block feature through graph reasoning network, and useless image block feature is filtered out through local area filtering network, and the difference feature of image block is obtained.4. the common feature and difference feature are fused by low layer-high layer interaction to obtain style feature.5. with style feature as query sample, according to query sample retrieval target picture.The present application can fully exploit image fine-grained information and spatial context information, and learn the fusion alignment between the visual features containing style and the modified text, which achieves higher retrieval accuracy than existing methods.