748 results about "Syntax" patented technology

The invention discloses a natural language-to-SQL (Structured Query Language) method and system based on RAG (Random Access Gateway) enhancement, and the method comprises the steps: constructing a query intention graph through dependency syntax analysis, recognizing and complementing semantic missing components, and forming complete semantic representation; vector representation is carried out on the business term segments by adopting vectorization coding, accurate definitions of business terms are obtained from a factory structured knowledge base, and an enhanced context set is formed through expansion retrieval in a low-confidence region; an SQL template mapping network is established based on historical query records, a mapping relation matrix is generated through field candidate matching, mapping conflict positions are identified, and multiple SQL candidate sequences are generated; grammar verification is carried out on the candidate sequence to identify grammar errors, semantic consistency verification is carried out to calculate the intention alignment degree, and an optimal SQL statement is selected through a deviation correction factor; and performing formatting processing and statistical abstract on an execution result, and providing data query capability for scenes such as factory quality management and equipment maintenance.

Systems, methods, and devices that relate to intelligent query decomposition and parallel routing for specialized model processing are disclosed. In one example aspect, the system receives a query from a user comprising a request relating to a particular domain. The system determines, using a decomposition model, a set of sub-queries based on semantic boundaries, syntactics, tasks, relationships, and rules relating to particular domains. The system inputs the set of sub-queries into a routing model to determine a set of specialized models. For each sub-query, the system routes the sub-query to a respective specialized model, generates an output, and assigns a confidence score. The system detects conflicts among outputs using a conflict detection model configured to identify discrepancies. The system generates an aggregated output by combining outputs according to a weighted aggregation algorithm prioritizing higher confidence scores and conflict resolution rules, then displays the aggregated output.

The invention provides a complex question and answer method and system based on adaptive task deconstruction and multi-modal evidence aggregation, belongs to the technical field of natural language processing, and designs a dynamic Few-shot prompt construction method based on dependency syntax fingerprints to ensure that a prompt template is matched with a question structure; the invention discloses a dynamic problem deconstruction method based on confidence evaluation and auto-reflection. The method comprises the following steps: recursively decomposing a problem tree by using a large language model; converting the problem tree into a standardized linear task execution sequence by a problem tree context dependence specification and task sequence generation method; obtaining a high-correlation evidence set of each task based on an evidence generation method of two-way recall and cross encoder rearrangement; and the task sequence is reasoned and dynamically optimized by a question answer extraction method based on double-strategy aggregation reasoning. According to the method, the accurate complex question and answer result can be provided on the premise of ensuring the question disassembling quality, restraining error propagation and comprehensively recalling evidences.

Computer-implemented methods and systems for processing geometry replacements are disclosed. The methods include decoding / encoding a syntax element associated with a coding mode from / into a bitstream associated with geometry displacements; and reconstructing / converting, based on a coefficient configuration associated with the coding mode, a plurality of quantized transform coefficients from / to a plurality of zero-run length codes.

The invention relates to a man-machine interaction dialogue method, system and device based on a natural language and a medium. The method comprises the steps that firstly, multi-modal interaction data is acquired and preprocessed, and segmented words and syntax are analyzed through a natural language processing technology to construct intention feature vectors; combining the intention feature vector with a historical dialogue record, and using a pre-trained language model to generate context semantic elements containing a semantic relationship; if the context semantic elements are matched with the preset scene feature library information, predicting a user intention change trend by adopting a reinforcement learning model to obtain an intention prediction result; and finally, evaluating user intention change based on an intention prediction result, extracting associated domain knowledge by utilizing a knowledge graph if significant change occurs, and inputting the associated domain knowledge into a dialogue generation model to obtain a natural language reply sequence. According to the method, the understanding precision of the user intention is improved, the dynamic prediction of the intention change is realized, the relativity and coherence of reply are guaranteed, and a more efficient processing path is provided for natural language man-machine interaction.

The invention provides a field NL2SQL data automatic synthesis method and system based on a large language model, and the method comprises the steps: building an SQL template library through collecting a public data set and real business query data, carrying out the grading according to the SQL complexity, and forming an SQL template set covering different difficulties; specific SQL queries are generated based on an SQL template library and a large language model, verification is carried out through multiple mechanisms such as grammar check, execution verification and result dimension consistency check, and correctness and performability of the SQL queries are ensured. Generating a plurality of candidate natural language questions according to the verified SQL query and the large language model, calculating a semantic consistency score of each candidate question and the SQL query through a cross consistency evaluation mechanism, screening out the question with the most consistent semantics as a final question-answer pair sample, and meanwhile, eliminating low-quality samples by setting a consistency threshold value, so as to obtain a final question-answer pair sample; and the data accuracy and consistency are further improved.

The invention provides an official document auditing method, device and equipment based on a large model and a medium, and the method comprises the following steps: preprocessing an official document to realize format and language standardization; using a retrieval enhancement generation (RAG) technology to complete vectorization conversion and fragmentation processing; then grammar and semantic analysis is carried out through a text analysis module fused with the large model, and matching detection is carried out according to a preset rule base in combination with an automatic rule engine module; then, deep auditing is conducted by means of a machine learning auditing model, content problems are recognized, manual rechecking is triggered in case of high uncertainty or key content, and an auxiliary tool is provided; receiving an audit opinion optimization model and a rule base; and finally outputting a result, and feeding back the problem by generating a report without annotation. The document auditing efficiency and accuracy can be improved, continuous optimization is supported, and the method is suitable for multiple scenes.

The invention relates to the field of computer software, and provides an AI-based low-code visual component dynamic generation method and system. The method comprises the following steps: receiving a component demand description input by a user, and converting the component demand description into structured cue word data to obtain an initial cue word sequence; retrieving matched template data and grammatical rule data from a component knowledge base according to the initial cue word sequence, and fusing the template data, the grammatical rule data and the initial cue word sequence to obtain an enhanced cue word sequence; performing semantic analysis and code generation processing on the enhanced cue word sequence through a large language model to obtain a component source code; and performing real-time rendering processing on the component source code through a component rendering engine, and generating an interactive component instance in a preview interface to obtain reusable component resources. According to the method, the code quality consistency is ensured, and the development efficiency is improved.

The invention discloses a natural language and machine vision-based alignment method, which comprises the following steps of: providing a three-level alignment architecture, and respectively extracting local-global features of a visual scene and grammar-semantic features of a natural language by adopting a double-flow feature extraction network; through a space-time attention enhanced cross-modal alignment module, a dynamic gating mechanism is adopted to complete feature space adaptive projection; a joint optimization strategy is constructed based on comparative learning, and vision and language embedding space consistency is optimized by using a multi-granularity comparative loss function. And meanwhile, semantic topology constraint and visual causal reasoning are introduced, so that the calculation complexity is reduced, and the task robustness is improved. Through experimental test data, the Top-1 accuracy rate of the method in image-text retrieval reaches 92.3%, the visual question and answer F1 value is 83.4%, the model parameter quantity is reduced by 40%, the method can be widely applied to the fields of intelligent interaction systems, automatic driving scene understanding, industrial quality inspection knowledge base construction and the like, and the semantic perception and reasoning ability of a multi-modal system is remarkably improved.

The invention relates to an AI-driven code automatic completion method, device and equipment and a storage medium thereof, and the method comprises the steps: constructing a grammar structure and variable definition of a code through semantic analysis, analyzing inter-line logic association and a variable transfer chain based on context-dependent modeling, the problem that in the prior art, a completion result deviates from an intention due to semantic fault is solved. A variable function and a logic target are identified in combination with deep semantic reasoning, a multi-path candidate scheme is generated, semantic complete paths are screened, and the defect of logic consistency deficiency in a multi-path decision scene is overcome; finally, path selection is dynamically optimized by fusing historical behavior data of a developer, a basic code is generated through template instantiation, a personalized completion result is output through logic verification and style adaptation, the intention understanding accuracy and the style adaptation capacity under a complex code scene are improved, and intelligent completion which is logically coherent and conforms to developer habits is achieved.

The invention discloses a multi-relation extraction error propagation optimization method and device based on data collaborative enhancement, and the method comprises the steps: generating extended training data through grammar recombination and adversarial samples, carrying out the positioning and weighted sampling of a low-frequency relation according to an entity pair relative position, and obtaining an upper relation data set; and training an upper relation classifier based on the upper relation data set, and performing prediction through the trained upper relation classifier to obtain a prediction result and confidence distribution thereof. According to the method, through text enhancement and a weighted sampling strategy for relative position positioning based on entities, the problem of unbalanced data distribution is effectively relieved, the modeling capability of the upper relation classifier for long-tail distribution is remarkably improved, and therefore systematic optimization of the upper relation classifier for low-frequency relation recognition accuracy is achieved.

The invention relates to the technical field of artificial intelligence education, in particular to a Russian spoken language practice personalized recommendation method and system based on artificial intelligence, and the method comprises the steps: 1, outputting a phoneme sequence with a timestamp through Russian automatic voice recognition; 2, collecting an exercise interruption position and repeated read-after behavior data; 3, generating a dynamic learner portrait; 4, mapping high-frequency errors in the learner portrait into abnormal path weights of map nodes; 5, a lattice tail error option and a non-matching body verb interference item are injected; 6, when the voice fluency attenuation of the learner exceeds a dynamic threshold value, the sentence complexity is reduced; and 7, calculating an error rate descent gradient based on the exercise completion data, and dynamically adjusting the abnormal path weight of the knowledge graph. Through audio stream analysis and syntax tree construction, the system can accurately identify errors of the learner in grammar, pronunciation and other aspects, and the learning efficiency is improved.

A test question recommendation method based on large language model adaptive multi-level evaluation constructs a multi-level architecture including semantic consistency verification, fine-grained fact alignment and dynamic cognitive evaluation, and comprises the following steps: constructing an initialized data stream and executing dynamic random sampling; calculating discrete semantic entropy by using NLI bidirectional implication clustering so as to quantify and eliminate illusion content with high uncertainty; under the RAG framework, the test questions are deconstructed into atomic statements, and a fact deviation is corrected by calculating a retrieval relevance vector and a logical implication consistency score; analyzing and screening low-quality texts based on multidimensional language features of syntax and logic; vector fusion is carried out on the generated intention and the cognitive portrait of the student, and a dynamic evaluation index system adaptive to a specific teaching scene is constructed in real time by utilizing context learning. The problems of accuracy and adaptability of automatic question setting are effectively solved, and intelligent closed-loop control from test question generation to cognitive alignment is realized.

The invention provides a page component configuration method and device, equipment, a medium and a program product, and can be applied to the technical field of artificial intelligence and the field of financial science and technology. The method comprises the following steps: in response to a received component configuration request sent by an object, determining a target rule expression matched with a demand description text on the basis of a plurality of preset rule expressions, historical operation information of the object and the demand description text included in the component configuration request; based on a preset analysis engine, the target rule expression is analyzed into a target configuration instruction adopting a target programming language, and the preset rule expression and the target programming language have similar grammatical structures; and performing front-end page rendering based on the target configuration instruction to obtain a component configuration result corresponding to the component configuration request.

The invention discloses an agent training data set construction method and system combined with cross-modal learning, and relates to the technical field of agent training, and the method comprises the steps: obtaining multi-modal intelligence data from a multi-source database, extracting feature information, and projecting the feature information to a preset semantic space to obtain cross-modal alignment features; constructing an agent function call syntax tree based on cross-modal alignment features, analyzing the syntax tree into an instruction sequence, constructing an analysis reasoning chain, and generating a sample label and an interaction track; constructing a task dependency graph by using the sample labels and the interaction tracks, decomposing the task dependency graph into a plurality of parallel decision branches, and dynamically adjusting a processing strategy to form a training data set; mapping the training data set to an agent target space, optimizing and analyzing an inference chain through a training feedback channel, and outputting a standardized sample library; and finally inputting to-be-analyzed data into the trained agent, and generating an intelligence analysis report according to the analysis reasoning chain.

The invention discloses a large language model security testing method based on evolutionary dynamic adversarial attacks, and relates to the technical field of security testing. Comprising the following steps: 1, creating a dynamic attack generation engine, constructing an adversarial evolution architecture by utilizing the dynamic attack generation engine, and generating a test sample based on the adversarial evolution architecture for a large language model security test; the method comprises the following steps: 1, establishing a large-scale language model, 2, calculating investigation parameters of harmlessness, honesty and helpfulness based on a Constancy AI principle, calculating a security alignment gap index SAGI by using the investigation parameters, and intelligently judging a value drift condition of the large-scale language model according to the security alignment gap index SAGI, 3, establishing a multi-modal joint defense engine, and carrying out intelligent judgment on the value drift condition of the large-scale language model according to the value drift condition of the large-scale language model. Steganalysis, syntax tree analysis and audio anomaly detection functions are integrated, and all-around threat detection coverage of texts, codes, images and voices is carried out on a detected large language model.

The invention discloses a large language model robustness visual diagnosis method based on multi-dimensional features and adversarial attacks. The method aims to break through a mode that traditional evaluation only depends on a single aggregation index, and a multi-dimensional text feature exploration system covering vocabularies, syntax, semantics and a structural layer is constructed, and a large-scale antagonism disturbance mechanism and a task self-adaptive quantification strategy are combined. And generating structured feature-adversarial instruction-robustness diagnosis data comprising the cue word to be evaluated and the corpus. On the basis, an interactive visual analysis system is constructed, and through bidirectional linkage of a feature statistical view and a semantic projection view, a user is supported to realize progressive exploration from macroscopic feature screening to microscopic semantic attribution under the double view angles of cue words and corpora, so that a root cause causing the fragility of the model is deeply diagnosed. According to the method, the key feature combination influencing the stability of the model can be identified, so that a basis is provided for directional optimization of the model, and the diagnosis depth of robustness evaluation is improved.

An assert statement generator employs a neural transformer model with attention to generate candidate assert statements for a unit test method that tests a focal method. The neural transformer model is pre-trained with source code programs and natural language text and fine-tuned with test-assert triplets. A test-assert triplet includes a source code snippet that includes: (1) a unit test method with an assert placeholder; (2) the focal method; and (3) a corresponding assert statement. In this manner, the neural transformer model is trained to learn the semantics and statistical properties of a natural language, the syntax of a programming language, and the relationships between the code elements of the programming language and the syntax of an assert statement.

The invention provides a constraint method and device for model structured output based on a finite-state machine, and relates to the technical field of network security, and the method comprises the steps: converting a structured constraint rule into a finite-state machine, constructing a shared vocabulary finite-state machine in combination with a model vocabulary, and dynamically limiting an output token range and a field sequence in a reasoning process. It is ensured that model output strictly conforms to preset field definition, value range and grammar rules, the problems of field missing and format disorder in a traditional mode are thoroughly solved, and results can be directly analyzed and utilized by a downstream system. According to the method, low resource occupation, high reusability and quick response are realized while output accuracy and structuring are guaranteed, and key technical support is provided for large-scale application of a large model in security scenes such as attack detection and vulnerability recognition.

The invention relates to the technical field of computers, in particular to a code sample optimization method and system based on a language large model, and the method comprises the steps: firstly, obtaining a source code sample, determining a code sample boundary, and generating a mark sequence; then, based on a compiling result, a static analysis result and a unit test result, a quality label is generated, and a training sample set is formed; then, taking a Transform neural network model of bidirectional context coding as an encoder, and carrying out training under the supervision of quality annotation to obtain a quality evaluation model; and finally, screening according to a preset quality score threshold to obtain a high-quality code sample set. According to the technical scheme, by combining the deep grammar analysis and context understanding of the code samples, the accuracy and efficiency of automatic screening are improved, manual intervention is reduced, and the method can adapt to automatic evaluation of a large-scale code library.

Disclosed in embodiments of the present application are an encoding method, a decoding method, a code stream, an encoder, a decoder, and a storage medium. The decoding method includes: decoding a relevant syntax element of a current block; according to the relevant syntax element, determining to use an intra-template matching prediction (TMP) (IntraTMP) merged intra prediction mode to perform prediction on the current block; determining a matching block of the current block on the basis of a TMP mode, and determining a first predicted block of the current block according to the matching block; determining a second predicted block of the current block on the basis of a non-template matching intra prediction mode; and merging the first predicted block and the second predicted block to determine a final predicted block of the current block.

The invention discloses a security and robustness automatic testing method for a large language model in the medical field, and the method comprises the steps: constructing a field perception harmful problem generator which can automatically learn and map medical knowledge to potential harmful queries; according to the method and the system, the real security boundary of the large language model in the medical field can be efficiently and systematically evaluated, and particularly, the evaluation depth and the evaluation breadth are provided in complicated situations involving professional knowledge misleading or potential harm. A generator is optimized through a customized weighted composite reward function, so that the model is effectively guided to generate a field perception harmful problem which has high harmfulness, is coherent and smooth and conforms to grammar, and the quality and pertinence of a data set are remarkably improved; according to the framework, the dependence on a large amount of time-consuming manual intervention is fundamentally eliminated by integrating automatic scoring and a multi-index similarity filtering mechanism of a hazard detection model.

The invention discloses a bug repairing method and system based on a grammar semantic tree, and the method comprises the steps: extracting a repairing mode fusing a grammar structure and a semantic intention from a historical bug repairing case, and guaranteeing the accuracy of the mode through program slicing guided by a key entity and iterative verification; on the basis of a double-constraint mechanism of grammar mergibility and semantic consistency, a specific mode is generalized to construct a hierarchical grammar semantic tree knowledge base; a knowledge base is used for generating a plurality of candidate patches for new vulnerabilities, single high-quality patches are generated through structure, grammar and semantic three-dimensional clustering and in-cluster integration and fusion, and the patches are output after heuristic sorting. According to the method, the defects that in the prior art, semantic understanding is shallow, and patch quality is unstable are overcome, and repairing accuracy, generalization ability and engineering practicability are remarkably improved.

A device for decoding a bitstream of encoded mesh data is configured to in response to determining that first transform parameters are overridden, infer a value of a second syntax element to be equal to a first value indicating that second transform parameters are present in the bitstream of encoded mesh data; in response to the value of the second syntax element being equal to the first value, determine the second transform parameters from a second syntax structure; in response to determining that the first quantization parameters are overridden, infer a value of a third syntax element to be equal to a first value indicating that second quantization parameters are present in the bitstream of encoded mesh data; and in response to the value of the third syntax element being equal to the first value, determine second quantization parameters from a third syntax structure.

The invention relates to the technical field of data expansion, in particular to a malicious prompt data set expansion method based on Mongolian. According to the method, high-frequency roots and affixes in a Mongolian basic malicious prompt corpus and a universal corpus are extracted, morphological analysis is combined, targeted malicious prompt samples can be constructed, the diversity and authenticity of a Mongolian safety evaluation data set are enhanced, candidate malicious prompt samples are optimized by adopting a genetic algorithm, and the safety evaluation accuracy of the Mongolian safety evaluation data set is improved. According to the method, the expansion sample is enabled to better conform to syntax and semantic rules of the Mongolian, effectiveness of the attack sample in the Mongolian scene is ensured, the expansion data set is enhanced by using the antagonism generation strategy, robustness and antagonism of the data set are improved, attack behaviors possibly occurring in a real scene can be simulated, and the robustness and the antagonism of the data set are improved. Therefore, an effective sample generation tool is provided for safety evaluation in a Mongolian scene, and the anti-attack capability of the Mongolian model is improved.

A device may be configured to perform spatial extrapolation based on information included in a neural-network post-filter characteristics message. In one example, a neural-network post-filter characteristics message includes a syntax element indicating a purpose of the neural-network post-filter characteristics message is spatial extrapolation. In one example, a syntax element indicating overlapping horizontal and vertical sample counts and patch size related syntax elements are inferred based on a purpose being spatial extrapolation. In one example, a syntax element indicating overlapping horizontal and vertical sample counts and patch size related syntax elements are constrained based on a purpose being spatial extrapolation.

A method of video encoding includes performing context modeling to determine a context model for each of a number of bins of syntax elements corresponding to residues of a region of a transform skipped block in a current picture. The number of the bins of syntax elements being context coded does not exceed a maximum number of context coded bins set for the region. The method further includes encoding, according to Block Differential Pulse Code Modulation (BDPCM), the syntax elements based on the determined context models. When the maximum number of context coded bins is reached, remaining bins of syntax elements are encoded based on a bypass model.

The invention relates to the technical field of document duplicate checking. The document duplicate checking method comprises the steps that according to syntactic dependency structures in text information of a document to be subjected to duplicate checking and text information of a plurality of comparison documents, keywords and context dependency relationships of each sentence are recognized, a semantic map is constructed, and the semantic map is subjected to duplicate checking; mapping the keywords and the context dependency relationship to corresponding concept nodes in the semantic graph, constructing a semantic sub-graph of the document to be subjected to duplicate checking and a plurality of semantic sub-graphs of the comparison document, and comparing the structural similarity between the semantic sub-graph of the document to be subjected to duplicate checking and the semantic sub-graphs of the comparison document to obtain a structural similarity score; and based on a node sequence in the semantic subgraph of the document to be subjected to duplicate checking, constructing a disturbance semantic subgraph, calculating a disturbance score fluctuation range, screening a comparison document of which the structural similarity score is higher than a preset threshold value and the disturbance score fluctuation range is lower than a disturbance tolerance threshold value, and outputting duplicate checking difference information. The method and the device have the effect of improving the document duplicate checking accuracy.

The invention provides an automatic object-level authorization vulnerability detection method based on a large language model, which comprises the following steps of: firstly, identifying a sensitive resource table through SQL (Structured Query Language) grammar analysis, and analyzing an operation path from a tracking request parameter to the sensitive resource table by utilizing a forward data stream; then, performing context sensing analysis on the database operation by adopting LLM to infer object-level sensitive operation; thirdly, recognizing program logic and a conditional protection mechanism in database query through static analysis, and recognizing custom verification logic such as method-level annotation and administrator permission in combination with an LLM and character string matching method; and finally, judging whether the sensitive operation lacks user-defined verification, ownership SQL constraint and access control conditions at the same time or not by integrating the mechanism, and generating a vulnerability report according to the judgment result. The invention further provides an automatic object-level authorization vulnerability detection system based on the large language model. Therefore, the detection precision can be effectively improved, and false alarm and missing alarm are remarkably reduced.

The invention discloses a Text-to-SQL (Structured Query Language) method based on a large language model. The method comprises a database mode linking module, a context information enriching module, a dynamic decomposition SQL (Structured Query Language) generation module, an execution feedback optimization module and a selection module based on self-consistency. Performing multi-path recall screening on related tables, columns and value fields in a database through a mode link; the mode information of the database is expressed through context information enrichment, key information is extracted, and a question is re-described; aiming at the problem of different complexity, different SQL generation schemes are designed, and a plurality of candidate SQL statements are generated; checking and correcting grammar and semantic errors existing in the SQL statement by executing feedback optimization; and through voting and a binary selection model, selecting the most accurate SQL query as a final SQL. The method can effectively solve the problems of enterprise data increase, difficulty in complex SQL generation and the like, improves the conversion accuracy and efficiency, enhances the adaptability to different database modes, and has important practical value.