22 results about "Approximate matching" patented technology

A mapping method is configured to perform the following: extracting, through analysis of a global semantic map, pathways traversable by a vehicle; processing data acquired during motion of said vehicle and estimating a trajectory thereof; selecting pathways to which the estimated trajectory is fitting; processing imagery data acquired during motion of said vehicle and generating a local semantic map indicative of scenery components and properties determined for each of the identified scenery components; mapping said local semantic map onto said global semantic map; generating hypotheses concerning possible locations of the vehicle on the semantic map along one of the pathways based on approximated matches between the estimated possible path and said plurality of traversable pathways extracted from the semantic map; and determining from said plurality of hypotheses a most likely location of the vehicle on the semantic map along one of the pathways based on one or more likelihood functions.

The invention provides a multi-target accurate retrieval method and system in a security video, and relates to the field of interdisciplinary application, and the method is characterized in that the method comprises the following steps: carrying out the standardized preprocessing of an original security video, and deploying an improved YOLOv8 model on a preprocessed key frame to carry out the high-precision multi-target detection. The method has the advantages that the appearance, motion and semantic complementary features of the target are synchronously extracted by improving the YOLOv8 model, cross-frame association and trajectory modeling are realized by adopting an enhanced DeepSORT tracker, and a compact feature index database and a three-level progressive retrieval mechanism are constructed in combination with a locality sensitive hashing algorithm; according to the method, the multi-target retrieval precision and efficiency in massive videos are remarkably improved, the target relevance and the complex scene semantic understanding ability are enhanced, meanwhile, the calculation overhead is greatly reduced through rapid approximate matching and a hierarchical retrieval strategy, and the requirements of security application for high accuracy, rapid response and real-time intelligent research and judgment are met.

Classification and preprocessing algorithms are applied to at least one reference document and a natural language command provided as input by a user to a development environment for computer programming. Approximate matching of keywords in user commands with data in the reference document is performed with a fuzzy hash map and used to develop information metrics that produce a ranking of candidate actions. Selection criteria are then used to select an action from multiple candidate actions to perform the desired operation in the development environment.

A system includes a processor that accesses a sequence of device events S from IoT network traffic and a plurality of user activity signatures, each user activity signature U in the plurality of user activity signatures being a known sequence of device events. The processor is configured to infer a user activity by way of approximate user activity signature matching.

The application provides a non-equal-value connectable data table direct query method based on LSH, and the method is based on the LSH method commonly used in a high-dimensional data approximate matching method, indexes of column dimensions are constructed in a candidate data table according to a similarity threshold, hash values of query columns in a query data table are generated by using the same hash function, and the connectable data table satisfying the similarity threshold is searched in the indexes of the created candidate data table; the method only needs to provide the data table needing rich data, namely the query data table, the candidate data set and the similarity threshold, and the connectable data table satisfying the similarity threshold can be quickly found in the candidate data set, and the query data is enriched; the algorithm does not have redundant pretreatment, does not need additional calculation steps, and is simple in design and easy to realize, and the query efficiency of the non-equal-value connectable data table query algorithm is improved.

This invention discloses an AI voice query system for cultural and tourism information in a two-wheeled vehicle rental scenario, belonging to the field of intelligent transportation and voice interaction technology. The system collects user voice data via an in-vehicle voice terminal, obtaining GNSS latitude, longitude, heading, speed, and timestamps, which are then sent to a server. The server recognizes the voice, outputs the optimal transcription and uncertain results in N-best or obfuscated network / word lattice form, constructs a weighted query graph, and recalls a set of candidate POIs based on POI name approximation matching index. A forward cycling corridor is constructed based on heading and speed to spatially prune the candidates. Cycling accessibility costs are calculated on the road network, and combined with rental fences and return points for filtering or correction, resulting in composite costs and ranking to determine target POIs. Prefetching and caching based on corridors and high-frequency intents are used to adapt to weak network environments, thereby improving the stability of recall and ranking under noisy conditions and reducing irrelevant computational load.

The application discloses a radar original echo data blind focusing imaging method, which comprises the following steps: based on the approximate periodicity model of one-dimensional original data amplitude signal and the PCM method, impulse repetition interval coarse estimation and fine estimation are carried out, so that the one-dimensional data is restored to a two-dimensional data matrix; the approximate matching filter model of the radar image is established by using the reference point echo and the approximate shift invariance model; the original two-dimensional echo data is divided into multiple blocks, the energy of each block is normalized, the reference echo is estimated by using the PCM method; and the radar image is restored by using the estimated reference echo through the matching filter method. The application can restore high-quality radar images from the original data without depending on the radar system parameters.

A technique of categorization of binary executable files comprising the following steps:a) a starting step of analysis of input and training data for containing semi-organized, partially monotonic sequences;b) a preprocessing step wherein potential sequences are discarded or accepted on the basis of preset statistical criteria;c) an encoding step of said accepted sequences with metadata;d) a storing step of the encoded sequences, wherein said sequences are stored as part of the data sequences digest containing information describing the spatial organization of the sequences, the monotonicity features thereof and other features valuable for approximate matching;e) a computing step of locality-sensitive hashes corresponding to said input and training data files.

The application discloses a three-party efficient private record linkage method and system for large-scale databases, and belongs to the technical field of privacy protection data linkage. The three-party efficient private record linkage method for large-scale databases comprises the following steps: first, second participants respectively perform non-redundant blocking on local records, and send the records to a linkage unit after adding differential privacy disturbance to generate candidate record pairs and randomly and uniformly distribute the candidate record pairs to both parties; a requested party encodes records by using a Bloom filter, encrypts the encoding and an offset list based on quadratic residues, and sends the encoding and the offset list to a requesting party; the requesting party calculates an encrypted intersection cardinality by homomorphic addition, and generates an encrypted similarity result in combination with an encrypted offset; the linkage unit decrypts the result, returns matching record numbers, and both parties output final matching record pairs. The application realizes low computational overhead, low communication volume, high scalability and approximate matching, and improves the efficiency of privacy protection record linkage in large-scale cross-institutional data integration scenarios.

The invention discloses an automatic blocking and labeling method for a legal document, which comprises the following steps of: segmenting the legal document into a plurality of text blocks by adopting a mixed blocking strategy, generating a vector form corresponding to each text block according to an embedded model, and storing all vectors into a vector database; according to the automatic blocking and labeling method for the legal document, the legal document is segmented into a plurality of text blocks by adopting a mixed blocking strategy, and on the basis of ensuring semantic integrity and coherence in the blocks, the structural characteristics of the document are fully utilized, and the blocking efficiency and accuracy are improved; and dividing the legal document into blocks, converting the blocks into vector forms, storing the vector forms into a vector database, and providing an appropriate vector database for large language model analysis of the legal document for subsequent approximate matching search.

The invention discloses a data resource classification method and device based on rule and semantic approximation and AI (artificial intelligence), and the method comprises the steps: setting a rule matching module, a semantic approximation matching module and an AI model, and sequentially starting the rule matching module, the semantic approximation matching module and the AI model to classify data resources to be classified. According to the data resource classification method and device, on the premise that the classification efficiency is considered, the data can be classified accurately and conveniently, and then the user experience is greatly improved.

The computing system generates a phoneme index for the input lexical elements and performs an approximate match analysis on the content lexical elements of the inverted index database based on the phoneme index for the input lexical elements. The inverted index database includes a first inverted index corresponding to a phoneme index of the content lexical element and a first normal method and a second inverted index corresponding to a phoneme variant of the content lexical element and a second normal method. The computing system returns one or more search results based on the approximate match analysis.

The invention relates to the field of graph processing, and discloses a graph approximate matching method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the smoothing of a to-be-matched non-Manhattan two-dimensional graph, and obtaining a smoothed non-Manhattan two-dimensional graph; breaking a target edge in the smoothed non-Manhattan two-dimensional graph, and segmenting the target edge into a plurality of edges to obtain a processed non-Manhattan two-dimensional graph; determining the number of edges in the processed non-Manhattan two-dimensional graph, and determining the preliminary similarity between the non-Manhattan two-dimensional graph and the reference graph based on the number and the corresponding number in the reference graph; and when the non-Manhattan two-dimensional graph is preliminarily similar to the reference graph, matching the edges of the non-Manhattan two-dimensional graph and the reference graph, and determining the similarity between the non-Manhattan two-dimensional graph and the reference graph. The number of times of matching calculation can be reduced and the approximate matching speed of the non-Manhattan graph can be improved by carrying out smoothing processing on the non-Manhattan two-dimensional graph and carrying out preliminary screening on the number of the edges of the non-Manhattan two-dimensional graph.

The application provides a semantic subdivision and modal alignment inference learning cross-modal retrieval method and a retrieval system. The semantic subdivision and modal alignment inference learning cross-modal retrieval method comprises the following steps: performing modal alignment on original modal features obtained after pre-training based on scaled dot-product attention, so as to realize re-aggregated projection modal alignment features for the original features; after the modal alignment data formed in the above step passes through a weight-shared multi-layer perception machine, a semantic approximate matching and correct matching method is used to realize semantic correct matching and approximate matching mining for the same category label cluster; and an Arc4cmr loss function, a mutual supervision contrast loss function, a contrast loss function between a picture-text feature similarity matrix and a similar label matrix are used to constrain the model. The cross-modal retrieval method further improves the accuracy of cross-modal retrieval.

The present application discloses a register address location method, device, and medium for device display data, relating to the field of industrial control communication technology. The method comprises: receiving visual display data obtained by a user from a device display module through a human-computer interaction interface, and collecting raw binary data from the device register through the MODBUS protocol; determining the data type of the visual display data, and based on the data type, performing binary conversion on the visual display data to obtain visual conversion data; matching a preset positioning algorithm to be applied based on the data type of the visual conversion data; if the data type of the visual conversion data is integer data, executing an exact matching algorithm; if the data type of the visual conversion data is non-integer data, executing an approximate matching algorithm to determine the source data corresponding to the visual conversion data in the raw binary data; and outputting structured information of the source data; wherein the structured information includes a point address, a data type, and a storage format.

The invention discloses a three-party efficient private record linking method and system for a large-scale database, and belongs to the technical field of privacy protection data linking. The large-scale database-oriented three-party efficient private record linking method comprises the following steps that: a first participant and a second participant respectively carry out non-redundant partitioning on local records, add differential privacy perturbation and then send the local records to a linking unit to generate candidate record pairs, and randomly and uniformly distribute the candidate record pairs to the first participant and the second participant; the requested party encodes the record by using a Bloom filter, encrypts the code and the offset list by using homomorphic encryption based on secondary residual, and sends the code and the offset list to the requesting party; the requester calculates an encryption intersection cardinal number through homomorphic addition, and generates an encryption similarity result in combination with the encryption offset; and the link unit decrypts the result and returns the matching record number, and the two parties output a final matching record pair. According to the method, approximate matching with low calculation overhead, low communication traffic and high expandability is realized, and the privacy protection record linking efficiency in a large-scale cross-mechanism data integration scene is improved.

The invention provides a retrieval enhancement generation method and system based on accurate sub-graph matching and a medium, and can solve the problem of inaccurate answer caused by the situation that complete dependence of a graph structure asked by a user cannot be obtained, a retrieval method and the like in related technologies. The method comprises the following steps: in an off-line preprocessing stage of a data graph G, constructing a layered R-Tree index for all paths with the length of 1-d in the data graph G; in the online retrieval stage, an accurate matching sub-graph set S and an approximate matching sub-graph set S'are obtained through an accurate sub-graph matching algorithm; wherein the precise matching sub-graph set S is a set of precise matching sub-graphs g of the data graph G, and the precise matching sub-graphs g and the normalized query graph q are isomorphic; the approximate matching sub-graph set S'is a set of approximate matching sub-graphs g 'of the data graph G, and the approximate matching sub-graphs g' are approximately matched with the normalized query graph q; and generating a credible answer based on the accurate matching sub-graph set S and the approximate matching sub-graph set S '.

The invention provides a distributed network semantic model query method and device based on a multi-dimensional demand, and the method comprises the steps: a demand obtaining step: if a user semantic model query request message sent by an end-side device or a target node of an edge service node belonging to the same distributed network as the end-side device is received, sending the user semantic model query request message to an end-side device; if yes, obtaining multi-dimensional demand information including the target scene and a plurality of demand vectors; setting a weight for each demand vector of the target scene according to a mapping relationship between the demand vector of the scene type and the weight to obtain a weighted demand vector; a matching step: searching whether a semantic model matched with the weighted demand vector is contained in each locally cached semantic model or not by adopting an approximate matching algorithm; and if yes, sending the searched semantic model as a target semantic model to the target node, and forwarding the target semantic model to the end side equipment. The problems that multi-dimensional model requirements cannot be accurately matched, and retrieval time delay is large can be effectively solved.

The invention designs a non-Chinese term real-time voice transcription error correction method and a non-Chinese term real-time voice transcription error correction system for professional speech. The method comprises the following steps: firstly, segmenting a video into continuous time domain intervals based on slide picture change in the speech video; for the speech segments in each time domain interval, using a streaming automatic speech recognition model to obtain an original speech transliteration text; meanwhile, extracting English specialized vocabularies, English abbreviations, variables, Greek letters and mathematical function symbols in formulas in the current page of slides from the video stream, and constructing a non-Chinese term dictionary; then, English segments in the original voice transliteration text are searched for, and a corresponding structural body is constructed; sequentially adopting a spelling similarity detection method and a phoneme feature matching method to correct English professional vocabularies or abbreviation transcription errors, variable transcription errors and Greek letter transcription errors existing in the English fragments; and finally, correcting mathematical function symbol transcription errors and residual Greek letter transcription errors in the original voice transcription text based on Chinese character phonetic form coding by adopting an improved KMP approximate matching method, thereby finally generating an error-corrected voice transcription text. According to the invention, non-Chinese term errors generated by a voice recognition system for professional speeches can be accurately and efficiently corrected.

The invention discloses a knowledge graph construction method and system, and the method comprises the steps: obtaining the multi-source data of a power grid, and dividing the multi-source data into structured data and unstructured data; for the structured data, extracting causal, table and parallel relationships among data vectors; constructing an event model containing weight elements for the unstructured data; performing approximate matching on elements of the event model and the structured data vector, and defining causal, table and parallel relationships among events; constructing a three-dimensional knowledge graph based on the relationship between events; through three-dimensional event relation modeling and combination of dynamic matching verification of structured and unstructured data, intelligence of fault reasoning and decision support is realized, reasoning accuracy and efficiency of a large power grid model are improved, the problems of high misjudgment rate and difficult traceability caused by data splitting, flat structure and static updating in the prior art are solved, and the method is suitable for popularization and application. And the safety and the operation and maintenance response speed of the power system are obviously improved.

A computing platform may receive a GPU processing request for processing by a GPU system. The computing platform may identify an operation requested by the GPU processing request. The computing platform may identify whether or not the operation is stored in a hash table. Based on identifying that the operation is not stored in the hash table, the computing platform may identify whether an approximate match of the operation is stored in the hash table. Based on identifying that the approximate match is stored in the hash table, the computing platform may identify a first key stored, in the hash table, along with the approximate match. The computing platform may identify, using the first key, a location of a solution to the approximate match of the operation. The computing platform may obtain, from the location, the solution to the approximate match of the operation, and may apply the solution.

Techniques are disclosed for querying with semantic code expansion in a clinical data system. In one aspect, a method includes receiving a query containing a predicate specifying a clinical code and a semantic expansion parameter indicating a request for approximate matching. A vector embedding associated with the specified clinical code is retrieved from a pre-computed embedding index. A similarity search is performed in a vector space to identify semantically similar codes. Exact code mappings are retrieved for the specified clinical code from a mapping registry. A rewritten query predicate is generated include the exact code mappings and the semantically similar clinical code mappings. The rewritten query is executed against a clinical data store to retrieve results matching the exact and / or semantically similar codes. The results are annotated to distinguish between exact and semantic matches.