54 results about "Similarity query" patented technology

The invention discloses an engineering design document compliance inspection method, electronic equipment and a storage medium, and the method is based on an OCR and a large language model, and comprises the following steps: standardizing the character recognition and extraction of a document; standardizing character error check and manual correction of the text; performing structured processing on the corrected standard text; vectorization processing of core text content and construction of a standard query system; presetting a specification set range corresponding to each chapter of the design document; carrying out vectorization and similarity query on characters selected by a user in the text editor; corresponding standard content is provided for the user; the method can improve the efficiency and accuracy of specification reference in the document, facilitates the dynamic update management of specification contents, and facilitates the guarantee of the correctness of reference specifications.

The invention discloses a single-stage generative sequence recommendation method, which belongs to the field of personalized recommendation systems, and comprises the following steps: S1, item code representation: performing formalized representation on items according to attribute granularity, and generating code representation of the items through a large language model and a product quantization technology; s2, constructing a user interaction sequence: splitting the user interaction sequence into a plurality of attributes to form an interaction sequence consisting of project attributes; s3, generative sequence recommendation: improving an encoder architecture of Transform, including a sequence projection layer, a spatial aggregation layer and a conversion layer, so as to adapt to a sequence recommendation task; s4, recommendation item prediction: based on the user interaction sequence, learning probability distribution, and generating prediction of a next interaction item; according to the method, prediction of the next item possibly interacted by the user can be directly generated, similarity query does not need to be carried out in the candidate set, and the sequence recommendation effect is effectively improved.

The invention discloses a geological text translation method based on a large language model and retrieval enhancement generation, and aims to identify a geological text named entity as a keyword and retrieve and query a professional dictionary database to perform enhancement translation. According to the method, when entity recognition is carried out on a fine tuning large language model, a syntax-aware entity pruning (SAEP) method is provided for data enhancement, controllable noise is introduced, and the named entity recognition effect of the large language model is improved. When a vector database is constructed and retrieved, geological classification labels are added to data information based on a data level, and a data similarity query threshold value is set, so that the accuracy of information retrieval is improved, and the illusion problem of a general large language model caused by the lack of professional domain knowledge of training data is effectively reduced.

The invention discloses a similarity query method and system for any long-time sequence data, and the method comprises the steps: firstly, extracting permutation entropy spectrum features of subsequences from segmented feature representation; then, through data index construction, extracting a prefix feature vector represented by segmented entropy, and constructing a spatial index based on an Euclidean distance; finally, through query processing, the candidate set is filtered based on lower bound distance query, and accurate similarity query is achieved. According to the segmented entropy representation, the influence of data standardization on distance measurement can be effectively avoided, unified and efficient query processing is achieved for query requirements of any length, the space overhead of indexes is remarkably reduced, the query efficiency is improved, and the method has high robustness and is suitable for large-scale popularization and application. The method can play an important role in the fields of big data and data mining, artificial intelligence, databases and the like.

The invention relates to a spatial-temporal trajectory similarity query method based on an improved LCSS, and belongs to the field of channel traffic control. The invention aims to solve the defects of the traditional LCSS algorithm in the process of processing the inland ship trajectory data. According to the method, the spatial position and the course of the trajectory are comprehensively evaluated by introducing course information, so that the similarity between the trajectories is more comprehensively reflected, and the query precision is improved. Meanwhile, a distributed architecture is adopted, similarity distance calculation tasks are processed in parallel, and the query efficiency is effectively improved. In addition, the method supports the query of a short spatio-temporal trajectory segment and a specific short time period, and meets the requirements under different application scenarios. The method can be applied to multiple fields of route optimization, abnormal behavior monitoring, false target discrimination, port throughput statistical analysis and the like, and provides effective technical support for inland waterway traffic control.

The invention relates to an inland ship AIS trajectory similarity query method and system based on locality sensitive hashing, and belongs to the technical field of ship space-time trajectory data processing. According to the method, character dimension reduction processing is firstly carried out on spatio-temporal trajectory data, the trajectory data is converted into a character sequence, and the calculation complexity is effectively reduced; then, a MinHash signature and an LSH technology are utilized to classify and retrieve the character sequence, and historical trajectory data similar to the query trajectory is quickly found. And finally, extracting a target track section meeting a similarity threshold value through an LCSS and a sliding window algorithm, and realizing motion change similarity query and spatial position similarity query. The method has the advantages of high calculation efficiency, flexible functions, high applicability and the like, and provides effective support for applications such as inland ship navigation behavior analysis, navigation safety monitoring, channel management optimization and the like.

The invention discloses a news image customization description generation method and device based on a multi-modal large model, and the method comprises a visual content extraction and scene graph generation module which enables the image content to be structured into a visual scene graph represented by triples, enables the elements in the scene graph to be mapped to the region of the image through the positioning of the visual scene graph, and enables the elements to be mapped to the region of the image; obtaining a corresponding visual element area; the entity association analysis and news context integration module is used for guiding the multi-modal large model to analyze a named entity corresponding to each visual scene element in the visual scene graph in a news context; outputting a visual scene graph set for replacing the news named entities and a knowledge mark set of the entities; and the case learning-based customized news description generation module searches cases similar to the currently input news theme and the user-defined rule by utilizing similarity query, and constructs a case learning context for the multi-modal large model in combination with the searched similar cases and the user-defined rule demand. The device comprises a processor and a memory.

The invention discloses a multivariate time sequence data distributed similarity query method and system.The method comprises the steps that firstly, prefix feature vectors are extracted from all dimensions of a multivariate time sequence through prefix features; then, through data index construction, spatial indexes are constructed for the feature vectors of all the dimensions respectively; then, through query processing, a filtering candidate set is queried on each sub-index based on the lower bound distance; and finally, through candidate set intersection taking and subsequent processing, accurate similarity query is completed. The dimension-based distributed index provided by the invention can effectively support unequal-length queries, has relatively high expandability and robustness, and can play an important role in the fields of big data, data mining, artificial intelligence, databases and the like.

A system for performing a cascade search includes an associative memory array, a controller, a similarity search processor, and a precision match processor. The associative memory array stores a plurality of multi-part data vectors stored in at least one column of the associative memory array. Each vector in the column has a first portion and a second portion aligned with each other. The controller controls the associative memory array to perform a similarity search of a similarity query on the first portion and a precision search of a precision query on the second portion. A similarity matching processor generates a match row including a match bit indication aligned with each similarity-matched column. Matching rows indicate which columns have a first portion that matches the similarity query. A precision match processor outputs, from among the similarity-matched columns, a precision-matched column having a second portion that matches the precision query.

The invention discloses a power equipment fault diagnosis and control strategy recommendation method based on a knowledge graph, and relates to the technical field of power equipment diagnosis, and the method comprises the steps: collecting power equipment operation parameters, defining a node type and a relation type of the knowledge graph, and constructing a power equipment fault diagnosis knowledge graph; the method comprises the following steps of: extracting node features of nodes, and storing obtained node vectors into a vector database by taking optimization of a space distance between adjacent node vectors as a target to realize similarity query and semantic matching between the nodes; performing multi-hop reasoning in the knowledge graph by taking the alarm node as a starting point, screening a high-confidence path as a diagnosis conclusion, and generating a power equipment strategy recommendation list; evaluating the execution effect of the power equipment strategy recommendation list, adjusting the edge weight of the mapping knowledge domain corresponding relation, dynamically updating the structure and node vector of the power equipment fault diagnosis mapping knowledge domain, and achieving the self-adaptive optimization of the power equipment fault diagnosis mapping knowledge domain. According to the invention, the power equipment fault diagnosis capability is improved.

The invention discloses a super-dimensional vector similarity query-oriented high-energy-efficiency coarse-grained in-memory query method, which comprises the following steps of: segmenting a super-dimensional vector, performing query operation on each segment of input super-dimensional vector, and calculating a Hamming distance between the input super-dimensional vector and the corresponding segment of stored super-dimensional vector; comparing each section of input super-dimensional vector with a storage section step by step, and compressing the Hamming distance between each section of super-dimensional vector into a binary code with a fixed length; and summarizing the compressed codes of the Hamming distance of each segment, and calculating the matching degree between the super-long-dimension input feature vector data and the storage category data by fusing the compressed Hamming distance information of the input super-dimension vector of each segment and the stored super-dimension vector of the corresponding segment. According to the method, the matching degree between the super-long-dimension input feature vector data and the storage category data can be efficiently calculated, so that low-complexity coarse-grained super-dimension vector similarity query is realized.

This invention discloses a method and apparatus for reachability query based on Top-k spatial keywords, relating to the field of spatiotemporal databases. The method includes: designating points v on road e, where v includes intersections and endpoints; designating roads between two adjacent v as road segments r; establishing a road network G; obtaining a trajectory set by recording historical trajectories according to road network G; and mapping the location o initiating a spatial text object query in road network G to road segment r0 on road e, thus establishing a spatial location of the spatial text object and the target road segment r0. i Corresponding; the search trajectory set contains data from road segment r0 to the target road segment r within the query time period. i The reachability of a trajectory is assessed. This invention provides a query algorithm that balances reachability, spatial proximity, and text similarity, implemented through the design of spatiotemporal indexes and spatial-text object indexes (such as the STOI structure). During the query process, reachability pruning, spatial proximity pruning, and text similarity pruning are performed respectively to accelerate the query speed.

The invention discloses a header field-based report similarity analysis method and device and a medium, and the method comprises the steps: recognizing header regions of a plurality of reports according to header identifiers of the reports; obtaining a structured header field of the header area of each report by analyzing the field of the header area; performing text vectorization processing on the structured header field of each report header area, and converting each structured header field into a header vector; traversing the header vector of each report, and executing similarity query by taking the header vector of each report as a query vector in sequence and taking the header vectors of other reports as comparison vectors to obtain the similarity between each query vector and each comparison vector; determining similar fields of each query vector by comparing the similarity with a similarity threshold value; and performing quantitative analysis on the similar fields corresponding to the query vectors to obtain a field similarity analysis result of the multiple reports. According to the method, the report similarity analysis efficiency and accuracy are improved.

The invention discloses a cache data processing method for intelligently analyzing operation habits of investment users, and relates to the technical field of cache data processing. The method comprises the following steps: acquiring basic information of a user; detecting whether the user basic information exists or not; if yes, reading matched user data according to the user basic information, and analyzing the user data to generate a user caching strategy; and if not, constructing a user fuzzy portrait through the user basic information, then performing similarity query through the user fuzzy portrait and historical user data to obtain user data with the highest similarity, and generating a user emergency caching strategy according to the user data with the highest similarity. According to the cache data processing method provided by the invention, the initial use experience of a new user can be effectively improved, and the cache data can be fully optimized by collecting and utilizing the user data, so that an intelligent investment service is provided for the user.

The application discloses a power grid malicious traffic detection method and system based on adaptive integration, relates to the technical field of power grid network security, and aims to solve the problem that the prior art cannot effectively detect encrypted malicious traffic in a resource-limited power grid edge environment. The application comprises the following steps: a client collects traffic data, monitors its own resource state and performance index, encapsulates the user demand into a request, and sends the request to a server; the server constructs a query feature vector, performs similarity query in a historical strategy library to quickly reuse or fine-tune the strategy, and if no strategy is found, an adaptive integrated decision algorithm is started to generate an optimal integrated learning scheme; the scheme is sent to the client, the client loads and runs the scheme and detects traffic features; and when malicious traffic is detected, the client triggers a security response action. According to the technical scheme, the detection strategy can be dynamically adjusted according to actual resources and demands without decrypting the traffic, and the optimal balance between detection effect and resource consumption can be achieved under the condition of resource limitation.

The invention provides a copyright registration method and system, a storage medium and a program product, and relates to the technical field of block chains. The copyright registration method is applied to a multi-block chain system comprising a main block chain and a plurality of sub-block chains, and the current sub-block chain generates a feature value corresponding to copyright data to be processed and performs similarity query on the copyright data to be processed in the plurality of sub-block chains based on the feature value, so that the copyright registration result is obtained. The distributed computing power of the current sub-block chain is fully utilized, the computing power consumption of the main block chain is further reduced, the main block chain evaluates whether the copyright registration processing of the data volume is supported or not based on the current computing power, and when the current computing power supports the copyright registration processing of the data volume, the copyright registration processing of the data volume is completed. And carrying out copyright registration processing on the to-be-processed copyright data so as to avoid the overload of the computing power of the main block chain.

A method for explaining an answer of a similarity query. A knowledge graph includes nodes including first and second nodes, edges that represent relations between pairs of nodes, and attributes that are associated in the knowledge graph with at least one edge or with at least one node. The similarity query includes the first node and the second node. The method includes providing embeddings of the first and second node of the similarity query, and providing an answer to the similarity query, the answer including a distance between the first node and the second node; determining an output of a model, the model being configured for determining the output for explaining the answer to the similarity query depending on the embeddings of the first and second nodes, and the attributes, the output including at least one value that indicates the contribution of one of the attributes to the answer.

The present invention discloses an optimization method for similarity query based on trajectory representation learning. The trajectory similarity query of the present invention represents a trajectory as a vector, and in the vector space, the Euclidean distance between two vectors is used to find the trajectory closest to the query trajectory. The present invention proposes a trajectory representation learning model PT2vec based on road network partitioning. PT2vec takes into account the spatial features of the trajectory and the topological constraints of the underlying road network to embed the trajectory into a low-dimensional vector space, designs a loss function based on spatial and topological information to accelerate the training of the model, improve the accuracy of the model, and effectively solve the problem of excessive calculation time for large-scale trajectory similarity. At the same time, in order to reduce the trajectory query space and improve the query efficiency, the PT-GTree index is used to prune the trajectories in the query database.

The application discloses a public key searchable encryption similarity query method with forward security, belongs to the field of cryptography, and is applied to cloud database retrieval query privacy protection.The application realizes the method as follows: 1, a key generator generates public parameters; 2, the key generator generates keys required in subsequent steps; 3, the key generator judges whether a time stamp meets a condition; if the condition is not met, the key generator repeats step 2; 4, a data owner encrypts data; 5, a mode provider and the key generator interact to generate a trapdoor; and 6, a service provider and the mode provider interact to perform similarity query and return a query result.Compared with the prior art, the application solves the technical problem of improving data security, mode security and forward security by using the public key searchable encryption similarity query in the similarity query scene.

The invention discloses an efficient video data distributed retrieval method and system, and the method comprises the steps: converting video data into a feature vector sequence through an image feature extraction technology; then, prefix features of the sample sub-feature sequences are constructed and extracted through data indexes, and spatial indexes are constructed on all sub-feature dimensions respectively; finally, through query processing, candidate sets are queried and filtered on all the sub-indexes based on the lower bound distance, and accurate video retrieval is completed through the intersection of the candidate sets and the follow-up processing process. By applying the multivariate time series data distributed similarity query method provided by the invention, distributed storage and efficient query of large-scale video data can be realized, and query contents can be quickly identified and positioned in a massive video database for given video paragraphs or semantic descriptions. The video data distributed index structure provided by the invention can effectively support video retrieval with unequal durations, has relatively high spatial ductility, and can play an important role in the fields of big data, data mining, databases and the like.

The invention discloses a similarity query method for polygonal geographic data in a spatial database, and belongs to the technical field of spatial databases and geographic information. The method aims at solving the problem that in the prior art, when mass data are processed, the shape similarity searching efficiency is low. The core of the method comprises the following steps of: firstly, converting each polygon into a fixed-length digital signature with translation and zoom invariance through normalization, gridding and MinHash coding; secondly, the signature is divided into blocks (Band), an index is built, and the signature is stored in a distributed No-SQL database such as Apache Cassandra; and finally, during query, a candidate set is quickly filtered out by using a Band key of a query signature, accurate geometric similarity calculation and sorting are performed on the candidate set, and Top-K most similar polygons are returned. According to the method, efficient and accurate real-time shape similarity query in a large-scale spatial database is realized through a filtering-refining two-stage strategy, and the query efficiency and the system expandability are remarkably improved.

Embodiments automate software discovery and delivery by decoupling repository understanding from change implementation. To aid the product- and technical-discovery phases of the SDLC, a large language model parses source code to produce human-readable technical documentation stored in a documentation store and machine-readable representations comprising vector embeddings linked in a graph store. When product requirements are received via a conversational user interface or a programmatic API, the system generates a change plan. An LLM identifies affected subsystems using graph and similarity queries, composes structured prompts, and conditions automated code transformation tools; communicated through a machine-to-machine orchestration layer (e.g., a Model Context Protocol (MCP) gateway); to generate candidate artifacts. Artifacts are validated by policy gates and packaged as a reviewable change record with documentation, embedding, and graph updates staged in a pre-deployment overlay; upon promotion, the system atomically commits the staged updates. Telemetry from review and deployment informs subsequent planning.

A computer-implemented method (300) for processing a sample image of a medical condition is disclosed, which comprises: processing (305), by a set of computer vision models for a medical modality associated with the medical condition, the sample image to obtain a set of determination related to a plurality of predicted diagnoses for the medical condition; processing (310) the sample image to determine an associated visual embedding to be used as a query for querying a database; querying (315), based on vector similarity between the determined visual embedding and the respective keys in the plurality of the entries, the database to retrieve a top-k most similar entries from the database; and processing (320), by a medically-trained generalist foundation model (GFM) using the set of determination as reference context and images corresponding with the retrieved top-k most similar entries, the sample image to make a predicted determination on the medical condition shown by the sample image.

The application provides an image detection method and device, electronic equipment and storage medium, comprising: collecting an image to be processed; using a pre-trained image encoder to extract features of the image to be processed to obtain target image features; inputting training set text features and the target image features into a pre-trained contrast network to perform feature matching calculation to obtain a target image query result value; performing similarity calculation on the target image features and training set image features to generate a target similarity matrix; performing nonlinear mapping calculation on labels and the target similarity matrix based on first target hyperparameters to generate a target similarity query result value; performing weighted calculation on the target image query result value and the target similarity query result value based on second target hyperparameters to obtain a target classification result value; and the target classification result value is used to indicate a detection result of the image to be processed. Thus, the application can be more conveniently and quickly applied to various different application environments.

The invention discloses a federal mixed vector similarity query method for multi-source science and technology data, and belongs to the technical field of big data and privacy computing. The invention provides a novel two-stage federal mixed vector similarity query method, which comprises the following steps that: in a first stage, each data owner represents own science and technology data as a vector and puts the vector into a vector database; then, each data owner retrieves a plurality of candidate vectors in a local vector database, and submits a discrete interval formed by vector distances between candidate objects and query vectors to the TEE; then, the TEE derives a distance threshold value for each data owner, and pruning is carried out on candidate objects; and in the second stage, the TEE collects screened candidate objects of all the data owners, aggregates the id corresponding to the final answer vector, and returns the corresponding science and technology data to the querier. According to the method, the dependence on a low-efficiency privacy computing technology is broken, and the balance of high accuracy, high efficiency and high security is realized.

The invention relates to the field of computer vision, and discloses a feedback-based image quality diagnosis method and system, a medium and equipment, and the method comprises the steps: carrying out the training or fine tuning of a multi-modal large model, and obtaining a trained multi-modal large model; performing scene similarity or image similarity query on the to-be-diagnosed image in the dynamic quality diagnosis expert database, if the query result is similar, fusing the query result into the standard Prompt to generate an enhanced Prompt, asking questions for the multi-modal large model by the enhanced Prompt, outputting scene description, diagnosis scores and evaluation reasons, and obtaining a diagnosis result of the to-be-diagnosed image. And a diagnosis result of detailed description of image quality; if the query result is dissimilar, questioning the multi-modal large model by a standard Prompt, and outputting a packet diagnosis result; and determining whether the diagnosis result is stored in the dynamic quality diagnosis expert database or not according to user requirements so as to dynamically update the dynamic quality diagnosis expert database. According to the invention, the diagnosis processing result can be aligned with the cognition of the user, and the accuracy of diagnosis is improved.

The technology disclosed relates to a computer-implemented method for detecting data posture of a computing environment. The method includes performing a scan of one or more data structures, detecting a plurality of classified data substructures based on the scan of the one or more data structures and, for each respective data substructure, transforming a plurality of data items from the respective data substructure into a respective data substructure signature using a signature encoder. The method includes applying a similarity query to identify a set of data substructures, from the plurality of classified data substructures, having a threshold level of similarity based on data substructure signatures associated with the set of data substructures.

To provide a data structure, a method for explaining an answer of a similarity query and a method for training a model.SOLUTION: In a computer implemented method for explaining an answer of a similarity query, a knowledge graph includes nodes including first and second nodes, edges that represent relations between pairs of nodes, and attributes that are associated in the knowledge graph with an edge or a node. The method includes: providing embeddings of the first and second nodes of the similarity query, and providing an answer to the similarity query, the answer including a distance between the first node and the second node; and determining an output of a model, the model being configured for determining the output for explaining the answer to the similarity query depending on the embeddings of the first and second nodes, and the attributes, the output including one value that indicates the contribution of the attributes to the answer.SELECTED DRAWING: None

The invention discloses a data similarity query method and device fusing comparative learning and a graph neural network, and relates to the technical field of artificial intelligence, and the method comprises the steps: mapping a request into a request node, and constructing a request graph; selecting a graph attention network model as an initial model, sampling each request node to obtain a positive sample node and a negative sample node, constructing a triple, establishing a contrast learning task, and training the graph attention network model; embedding representation is output based on the graph attention network model, a request node abnormity judgment method is constructed, an abnormity score of a request node is calculated, and when the abnormity score is larger than an abnormity threshold value, the request node is marked as an abnormal request; taking the embedded representation of the request node as a data point, and constructing M layers of nearest neighbor indexes; according to a real-time exception request sent by a user, K candidate exception requests are searched based on M layers of nearest neighbor indexes and are ranked to obtain K similar exception requests, and exception detection based on data similarity is realized.

Embodiments of the present disclosure relate to a massively parallel processing database for sequence and graph data structures. The systems and methods disclosed herein may include a parallel processing graph database solution for protein sequence analysis to determine viable therapeutic agents for a given condition, and may include determining a protein sequence for the given condition; using the sequence database to compare a query sequence of a sequence of a given disorder to sequences of other known proteins in the sequence database; based on the comparison, using the sequence database to determine a similarity of the query sequence to sequences of other known proteins in the sequence database; and based on the similarity of the sequences, querying the graph database to identify potential therapeutic agents that can have an inhibitory effect on a given condition.