37 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 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.

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.

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 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 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 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 relates to the technical field of database information retrieval, in particular to a length-independent set similarity query method based on a B + tree and application thereof. Through pre-construction of length partitions, key generation and index construction, in the query stage, length partition indexes are utilized, length filtering, key boundary generation and combined bucket difference filtering are used, key boundaries are directly generated, a large number of sets which are impossible to be similar are filtered, candidate sets are reduced, and therefore the query efficiency is improved. The objective of the invention is to solve the problem of how to reduce candidate sets so as to reduce the calculation cost in a multi-candidate-set scene.

The invention provides an intelligent semantic matching distributed knowledge base query method, apparatus and device. The method comprises the steps of obtaining a query request input by a user; preprocessing the query request to obtain target query data; processing the target query data to obtain key information, intention types and retrieval strategies; according to the target query data, performing similarity query in a vector knowledge base to obtain a preliminary screening result; the vector knowledge base is updated according to a preset rule; according to the key information and the intention type, performing correlation judgment on the preliminary screening result to obtain an intermediate screening result; and filtering and sorting the intermediate screening result according to the retrieval strategy to obtain a target screening result. According to the method, the timeliness, the matching precision, the resource utilization efficiency and the expandability of knowledge query can be improved.

The invention provides a vector data similarity query method and device, equipment and a medium, and the method comprises the steps: dividing a plurality of pieces of vector data to be queried into a plurality of data buckets, and storing the vector data included in each data bucket to a corresponding storage area; determining neighbor data buckets associated with the data buckets, constructing directed edges between the data buckets and the corresponding neighbor data buckets, and generating a data bucket dependency graph; based on the data bucket dependency graph and the capacity of the target cache, determining a processing sequence when the plurality of data buckets are written into the target cache; and sequentially writing each data bucket and the corresponding neighbor data bucket into the target cache from the storage area according to the processing sequence, determining the distance between two pieces of vector data respectively belonging to each data bucket and the corresponding neighbor data bucket, and screening vector pairs of which the distance is smaller than or equal to a preset threshold value from the plurality of pieces of vector data. Therefore, I / O waste is effectively reduced, and operation and maintenance and hardware investment are reduced.

This invention describes a privacy-preserving keyword-based similarity query method for smart healthcare. This method is based on a typical medical data outsourcing system scenario. This outsourcing system includes three participants: a treatment center, a querying user, and a cloud server. The outsourcing system also includes six modules: 1) a system initialization module, 2) a data organization module, 3) a data encryption module, 4) a query trapdoor generation module, 5) a query service module, and 6) a data decryption module. Based on in-depth research and analysis of existing privacy-preserving technologies and research results for similarity queries and keyword matching, this invention implements a secure and efficient keyword-based multidimensional similarity query solution and application system for smart healthcare.

The present invention discloses a method, electronic device and storage medium for checking the compliance of engineering design documents, which are based on OCR and a large language model. The method includes the following steps: text recognition and extraction of standard documents; text error checking and manual correction of standard texts; structured processing of the corrected standard texts; vectorization processing of core text content and construction of a standard query system; preset standard set ranges corresponding to each chapter of the design document; vectorization and similarity query of user-selected text in a text editor; and providing corresponding standard content to the user. The method can improve the efficiency and accuracy of standard references in documents, facilitate dynamic update management of standard content, and ensure the correctness of referenced standards.

The application provides a distributed index construction method based on improved iSAX coding, first, aiming at the digital feature selection problem, in order to increase the coding similarity of similar data, a similarity digital coding is designed, and through the transposition of the matrix, the problem of different weights of high bits and low bits of each digital coding in the whole digital coding is solved. Secondly, aiming at the problem of high time consumption in the traversal process caused by the too high index tree, a B+ index tree based on the similarity digital coding is designed, the number of child nodes is increased, the height of the tree is reduced, and the access speed of adjacent nodes is improved. And a leaf partition snake-shaped packing algorithm is designed, which guarantees the load balance, shortens the leaf node packing time, improves the index construction speed, and improves the overall index construction speed compared with the traditional distributed index construction algorithm, and provides a more efficient index framework for the similarity query process.

The invention discloses a method and a system for acquiring real-time data generated by retrieval enhancement. The method comprises the following steps of: adding a self-defined XML (Extensible Markup Language) tag into a static text fragment of an RAG (Registered Assistant Generation) vector database in advance; performing similarity query search based on the RAG vector database according to a received retrieval query request; judging an XML (Extensible Markup Language) tag in the vectorization result according to the searched vectorization result, and rendering the obtained XML tag; and based on the rendered XML tag, calling an external service to obtain real-time data corresponding to the vectorization result. Through the technical scheme, the problem of real-time acquisition of the dynamic data in the static content is solved, the function requirement for Function Calling of a large language model is avoided, the realization is simple, the problem of calling a large language for multiple times is avoided, and meanwhile, the cost for calling the large language model is saved.

This invention discloses a data-driven method and system for estimating selectivity using the `like` predicate, relating to the field of query selectivity prediction technology for relational databases. The method includes the following steps: receiving a query statement containing a `like` predicate and determining the type of the `like` predicate; constructing a trie, finding the corresponding trie based on the type of the `like` predicate to convert the `like` predicate query into a numeric range predicate query; performing a similarity query in a cardinality estimation result database based on the numeric range predicate query; if there are similarity query results exceeding a set threshold, directly reusing the retrieved cardinality estimation results; if there are no similarity query results exceeding the set threshold, performing cardinality estimation using a data-driven model. This invention enables rapid cardinality estimation for SQL queries containing `like` predicates.

The invention 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 it is difficult to effectively detect and encrypt malicious traffic in a power grid edge environment with limited resources in the prior art. The method comprises the following steps: a client collects flow data, monitors own resource state and performance indexes, packages the flow data and user requirements 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 finely adjust a strategy, and starts an adaptive integrated decision algorithm to generate an optimal integrated learning scheme if the strategy is not found; the scheme is issued to a client, and the client loads and operates and detects traffic characteristics; and when malicious traffic is detected, the client triggers a security response action. According to the technical scheme, on the premise of not decrypting the traffic, the detection strategy is dynamically adjusted according to the actual resources and demands, and the optimal balance between the detection effect and the resource consumption is achieved under the condition that the resources are limited.

The application provides a stock pattern similarity query system and method based on domain generalization, and relates to the technical field of deep learning.The system comprises a data layer, a matching model layer and an analysis layer.The application obtains stock historical data, pre-processes the data, then uses an RReliefF algorithm to perform feature selection and data segmentation, uses a Lasso algorithm in combination with a domain generalization method to train a model, matches similar stock data, and obtains result analysis for feedback.The application can more accurately match similar stock data, and provide more reliable auxiliary results for users.

The present invention discloses a ship trajectory similarity query system based on dynamic upper and lower bounds, which includes a local spatio-temporal index, a primary priority queue, a secondary priority queue, and a record item for saving the global lower bound. The local spatio-temporal index is stored in the memory of each node in the computer cluster, and the local spatio-temporal index on each node corresponds to a trajectory storage partition. Aiming at the problems of large calculation overhead and high query latency in the ship trajectory similarity based on the Hausdorff distance, the present invention applies a method for calculating the upper and lower bounds of the Hausdorff distance based on the MBR of the edge-to-trajectory index item space to the threshold similarity query. Without additional distance calculation, the global upper and lower bounds of the Hausdorff distance that gradually approach the true distance value as the number of iterations increases are obtained, so as to realize the edge calculation and pruning process of the similarity value, avoid generating additional calculation overhead, and effectively reduce the query latency.

The present invention discloses a trajectory similarity query method and device based on data federation, relating to the fields of trajectory data mining and information retrieval. The query method comprises: numbering mobile devices within the data federation; constructing a federated index based on a spatial grid via a central server; and using a dynamic pruning algorithm to find a preset number of mobile devices that are most similar to the trajectory to be queried, based on the federated index and the numbering. The present invention utilizes the spatiotemporal characteristics of the trajectory to construct the federated index, filtering out mobile devices that do not meet the query criteria through similarity upper bound pruning, thereby reducing communication overhead. Simultaneously, the trajectory data to be queried is pruned based on the spatiotemporal characteristics of the trajectory data, reducing local computational overhead. The central server terminates the query process prematurely based on the dynamic pruning criteria, further improving query efficiency.