121 results about "Syntactic structure" patented technology

Certain aspects of the present disclosure describe a method of information retrieval. In certain aspects, the method includes identifying a set of relevant nodes of a document graph embedding semantic units associated with the document based on a document search query. The method further includes reconstructing a structural context for each relevant node in the set of relevant nodes. The method further includes processing the set of relevant nodes and the structural context of each relevant node with a large language model to generate a contextual response to the document search query.

The invention discloses a large model defense method based on multi-view image-text conversion, and relates to the technical field of artificial intelligence security. The method comprises the steps of obtaining an image-text dialogue prompt word text, extracting syntactic structure parameters and semantic parameters of statements, splicing the syntactic structure parameters and the semantic parameters into a multi-modal tensor, and expanding a spliced vector into a plurality of structure vectors according to semantic relationship density to form a semantic structure vector group. According to the method, semantic density splitting and image space mapping of the multi-modal tensor are utilized, the cross-modal correlation analysis capability is enhanced, the image-text mixed attack path is accurately identified, and the entity mapping relation between the pixel gradient and the regional mask is combined, so that two-way verification of image-text semantic consistency is realized, and semantic fault vulnerabilities of single-modal detection are eliminated; a path intensity and instruction word dynamic weight fusion mechanism is adopted, the abnormal risk level of a statement structure is quantified, the adaptive limitation of a static rule to semantic variation is broken through, and the illegal content output probability is reduced.

The invention relates to the technical field of natural language processing, in particular to an AI reading management and control method and system based on artificial intelligence, and the method comprises the following steps: carrying out text word segmentation processing on an input original text, segmenting the text into independent sentences, recognizing basic word units in each sentence, analyzing semantic adjacency relationships and syntactic structure features among vocabularies, and carrying out word segmentation processing on the word units; screening and extracting potential phrases representing paragraph meanings, and establishing a candidate semantic unit set; according to the method, through word segmentation, syntactic structure recognition and semantic adjacency analysis of the original text, potential phrases capable of representing paragraph significance are extracted, the candidate semantic unit set is constructed, and modeling of the semantic structure in the text is achieved. And associating the set with the reading fixation duration and the playback action of the user sentence by sentence to obtain a reading behavior response of each semantic fragment, and executing semantic weighting and reading behavior cross analysis according to the reading behavior response. Through the linkage mode, the semantic focus actually focused by the user at present can be recognized.

The invention discloses a multi-channel short text matching method integrating external knowledge and syntactic structure, belonging to the field of deep learning technology, the method is based on the acquired text to be matched, based on the semantic relationship of the semantic original in the external knowledge base HowNet, the semantic similarity between words is calculated by topological distance, and the semantic original similarity matrix between words is determined; the attention weight of each word in the text is obtained by calculating the attention score of the text; according to the semantic original similarity matrix between words and the attention weight of each word in the text, the semantic feature vector of the text pair integrating the semantic original information is generated; by parsing the dependency relationship of the text and constructing a dependency structure graph, the nodes, edges and features of the graph are encoded as vector representations, and the syntactic structure feature vector of the text is obtained; the semantic feature vector and the syntactic structure feature vector are fused to obtain a comprehensive feature vector and input it into a classifier, and the text matching result is output. The method can achieve accurate matching of short texts.

The invention discloses a teaching course recommendation method and system based on English learning data, particularly relates to the field of semantic processing, is used for solving the problem of poor pertinence of a traditional English learning course, and comprises the following steps: aiming at systematic difference of native language and English expression on a syntactic structure, constructing a language structure difference map and extracting a structure offset label; the method comprises the following steps: performing dependency syntactic analysis on semantic consistent sentence pairs of multi-language aligned corpora to generate a structural difference feature set; on the basis, a semantic-grammar dimension mapping graph is constructed in a classified mode, and a general structure expression vector is established for graph nodes. A teaching course is divided into knowledge point units in combination with a context label, and a mapping relation between a structure label and the course is established. The system performs structure analysis and semantic matching on sentences input by the learner, identifies structure migration type expression errors, and recommends accurate teaching content according to context and structure labels.

The invention discloses a combined entity relationship extraction method based on semi-supervised learning and a large language model. The system comprises three modules, namely a data enhancement module, a semi-supervised joint extraction module and a large-scale language model fine adjustment updating module. The data enhancement module (1) is used for implementing a double enhancement strategy on unmarked data, weak enhancement retains syntactic structures and topological features of entities and relationships, and strong enhancement adopts a large language model which is finely adjusted in advance to generate semantic equivalent disturbance; (2) a semi-supervised joint extraction module which obtains a preliminary extraction model through training of marked data, and then generates prediction on unmarked data based on the preliminary extraction model; (3) a large-scale language model fine-tuning updating module which realizes parameter-efficient large-scale language model fine-tuning by using low-rank self-adaption and dynamically adjusts through a semi-supervised extraction result; and (4) fusing prediction results of the three modules to obtain a final joint extraction model. According to the method, semi-supervised learning, a large language model and joint entity relation extraction are creatively combined, the problem of scarcity of artificial label data in the professional field of an existing joint entity relation extraction method is solved, more efficient information extraction is provided, and therefore the overall performance of a joint extraction model is improved.

The invention discloses a psychological counseling intelligent recommendation method and system based on artificial intelligence, and relates to the field of psychological counseling cross technology, and the method comprises the steps: calculating a three-dimensional emotion vector according to an emotion axis space and a syntactic structure, constructing a psychological semantic tensor by using a tensor outer product, generating a user intention tensor by using a prototype weight, and carrying out a flattening operation. Obtaining a final intention vector; combining the structural potential energy deviation and the spectral distance to construct a matching factor tensor; constructing a factorization machine model, predicting a matching score, generating a prediction score matrix, screening by using a Top-K selection method, generating recommended content, and constructing a visual interface to display the recommended content. According to the method, the fine granularity and accuracy of emotional representation are improved through emotional axis space and syntactic dependency analysis, the matching precision of intention and resources is improved through comprehensive calculation of semantic gravitation intensity and spectral distance, and the expression ability of matching factor tensor is enhanced through fusion of structural potential energy deviation and spectral distance.

The invention discloses a Chinese text grammar error correction method combining syntactic information and a pre-training language model, and the Chinese grammar error correction capability can be effectively improved by fusing the syntactic information into the pre-training language model Chine BART. The method comprises the following steps: importing a data set and converting the data set into a target format; syntactic information is generated by utilizing HanLP, part-of-speech tags and dependency relationships are converted into vectors, and the vectors are fused with default word embedding; in the encoding stage, a syntax-enhanced multi-head self-attention mechanism and a residual network are used; in the decoding stage, a self-attention mechanism and an encoder-decoder attention mechanism are combined with syntactic information for generation, and a decoder is gradually optimized in combination with a residual network; a plurality of candidate sentences are generated by using Beam Search, and the optimal candidate sentence is selected according to syntactic consistency and semantic rationality. According to the method, the syntactic information and the pre-training language model are combined, so that the model learns semantic information of sentences and pays attention to the syntactic structure, and the Chinese grammar error correction capability of the model can be improved.

The invention provides a self-adaptive perception event element extraction method, which comprises the following steps of: firstly, acquiring data from open source resources of multiple fields, cleaning and labeling to construct a high-quality multi-field event element extraction data set, and then extracting event elements from the multi-field event element extraction data set by utilizing the constructed multi-field event element extraction data set. According to the method, two different types of event element extraction models are trained and finely adjusted, the two different types of models are a traditional deep learning model and a large model, then the length, syntactic structure, dependency relationship and vocabulary richness characteristics of a sentence are analyzed, complexity evaluation indexes are constructed, and the complexity of the sentence is evaluated. The method comprises the steps of automatically determining the complexity level of each sentence on the basis of the indexes, classifying the sentences, finally selecting a self-adaptive model according to the sentence complexity evaluation result, and finally integrating the result and outputting the result. By means of the scheme, self-adaptive extraction model selection is achieved, and the accuracy and efficiency of event element extraction are improved.

The invention relates to the technical field of copywriting analysis. The intelligent copywriting analysis method comprises the steps that based on user input information, an analysis task is generated, a task identifier is distributed to the analysis task, the analysis task is stored in an analysis storage database, meanwhile, the state of the analysis task is set to be an initial state, and the analysis task is stored in the analysis storage database; the initial state comprises to-be-executed or in-execution; when the state of the analysis task is to be executed, determining the execution opportunity of the analysis task based on a preset task scheduling strategy, and updating the state of the analysis task to be in execution; when the state of the analysis task is in execution, reading corresponding user input information from an analysis storage database according to the task identifier; semantic features and syntactic structures of information input by a user are extracted, key information in a text is recognized, and a corresponding analysis task type is matched according to the key information; and obtaining an analysis calculation result. The method has the effect of improving the copywriting analysis efficiency.

The invention belongs to the technical field of computers and text data processing, and particularly discloses an ancient book text-based information extraction method, a program product and electronic equipment, and the method comprises the following steps: obtaining a target ancient book text of which information is to be extracted; determining dependency syntactic structure information of the target ancient book text as target dependency syntactic structure information, the dependency syntactic structure information being used for reflecting grammar and semantic relationships between words in the target ancient book text; based on the target dependency syntax structure information, target information is extracted from the target ancient book text through a pre-trained ancient book text information extraction model, and the target information comprises idiom information, and / or object information, and / or emotion information. Through the technical scheme provided by the invention, the accuracy of ancient book text information extraction can be improved.

There is disclosed a method of automatically detecting a security vulnerability in a source code using a machine learning model, characterized in that the method comprises: obtaining the source code from a client codebase, wherein the client codebase is a complete or an incomplete body of the source code for a given software program or an application; and using a machine learning (ML) model to perform a ML based analysis on an abstract syntax tree (AST) for detecting a first security vulnerability over a static source code, the machine learning based analysis comprise (i) flattening the abstract syntax tree (AST) into a sequence of structured tokens, wherein the sequence of structured tokens comprises a semantic structure and a syntactic structure of the source code, (ii) implementing a natural language processing technique on the sequence of structured tokens for mapping the sequence of structured tokens to one or more integers, (iii) pre-training the machine learning model using an unlabeled source code as an input to predict a subsequent sub-token in the sequence of structured tokens and (iv) training the machine learning model on a labeled source code to predict a presence or an absence of the first security vulnerability.

The invention discloses an English emotion intonation reading device, which relates to the technical field of English emotion intonation reading and comprises a text input module, a semantic analysis module, an emotion recognition module, an intonation adjusting module, a speech synthesis module, an audio output module and a self-learning module. The text input module is used for acquiring an English text by typing, uploading a document and adopting an OCR (Optical Character Recognition) image recognition mode to obtain original text data; the semantic analysis module is used for analyzing original text data by adopting a method for analyzing a syntactic structure, keywords and context information to obtain semantic information of a text; the emotion recognition module is used for processing semantic information of the text in combination with a rule base and a deep neural network, recognizing emotion categories in the text and obtaining emotion tags; and the intonation adjusting module is used for adjusting voice expression parameters in the emotion label by adopting a strategy of controlling the speed, pitch, rhythm, pause and accent to obtain a voice regulation and control scheme.

The invention provides an mRNA field literature mining system based on deep learning, relates to the technical field of bioinformatics and natural language processing, and can effectively identify mRNA-related entities including genes, proteins, diseases and the like and semantic relationships thereof. According to the system, the latest BioBERT model and the Transform-CRF model are combined, efficient collaborative optimization of named entity recognition and relation extraction is achieved through a multi-task learning architecture, and the precision and efficiency of literature mining in the mRNA field are remarkably improved; specific terms and complex syntactic structures in the field of biomedicine can be effectively processed, redundancy is reduced through multi-task optimization, and the overall performance is improved; by fusing the pre-training knowledge of BioBERT and the sequence labeling capability of Transform-CRF, an innovative technical support is provided for deep mining and knowledge discovery of mRNA related literatures, and the method has a wide application prospect.

The invention provides a software development system management method and system based on big data. A code review data set in remote collaboration software development is collected, a review knowledge graph is constructed based on time-space correlation characteristics of the data set, and graph nodes comprise review behavior modes correlated with geographical and time characteristics. Syntactic structure features of current code change are synchronously extracted, the syntactic structure features and historical review tracks in the knowledge graph are jointly coded, and a processing instruction containing version difference analysis priorities is generated. And determining an allocation strategy of the cross-regional review task by dynamically matching the processing instruction and the domain knowledge coverage range. And finally, according to a mapping relationship among the distribution strategy, the version priority and the quality evaluation node, generating an examination management regulation and control strategy adaptive to the software development system. According to the technical scheme provided by the invention, the management efficiency and precision of the software development system can be improved.

The invention discloses an aspect-level sentiment analysis optimization method based on multivariate external knowledge fusion, which relates to the technical field of sentiment analysis optimization, and comprises the following steps: constructing a multivariate external knowledge source comprising a Chinese sentiment dictionary, a domain knowledge graph and a user comment prior mode library; the sentiment module is used for providing vocabulary-level sentiment polarity, entity attribute relations and high-frequency evaluation semantic modes; semantic coding is performed on the input text and the specified aspect words to generate context semantic representation, and global semantic features and local position features are extracted in combination with aspect word position information; based on a semantic coding result, converting the multivariate external knowledge sources into structured knowledge representations, and dynamically adjusting contribution weights of various types of knowledge through a gating fusion mechanism to generate fused knowledge representations; performing dependency syntactic analysis on the input text, constructing an original syntactic structure, and calculating the correlation strength of each grammatical component and aspect words in combination with context semantic representation; and pruning the original syntactic structure according to the correlation intensity.

The invention relates to the technical field of data processing, in particular to an entity recognition method and device, equipment and a medium. In the embodiment of the invention, three independent feature extraction channels are analyzed through a BERT model, a convolutional neural network and a dependency syntax, a first feature vector, a second feature vector and a third feature vector are determined, the obtained three feature vectors are integrated, and a finally obtained target feature vector comprises deep semantic information and context information. The method has the advantages that feature fusion is realized, local features and syntactic structure information are also included, flexibility and expression ability of feature fusion are enhanced, complex text understanding and entity recognition ability of a named entity recognition model are remarkably improved in the entity recognition process, and the entity recognition effect and accuracy are improved.

The invention relates to the technical field of natural language processing, and discloses a knowledge injection and graph neural network-based open domain text information extraction method, which comprises the following steps of: extracting all noun phrases from input text data to construct a candidate entity set; combining the candidate entities in pairs, and constructing a self-attention incidence matrix of each entity pair; performing sequence sampling on the self-attention incidence matrix to generate a candidate triple sequence set; calculating semantic similarity between the candidate triple sequence and the input text data, and outputting the first k high-correlation triple sequences as initial information extraction results of the input text data; and performing dependency structure analysis on the initial information extraction result based on a graph neural network, and generating a triple sequence through redundant sequence labeling as a final information extraction result. According to the method, the recognition rate of the complex syntactic structure triad in the open domain information extraction task is remarkably improved, and meanwhile, the redundancy of the extraction result is effectively reduced.

The invention discloses an open type named entity recognition method and platform for social media, relates to the technical field of natural language processing, and aims to automatically optimize prompts for a large model based on a Monte Carlo tree search algorithm and reconstruct texts according to the prompts. A social media short text is converted into a low-noise formal text with a standard syntactic structure, and then a concept correction thinking chain template is utilized to extract named entities from a reconstructed text and classify the named entities. The method is used for carrying out open naming body recognition on the disordered social media short text under the condition that fine adjustment is not carried out.

The invention relates to an emotion detection method combining metaphor recognition and a syntactic structure, and belongs to the technical field of natural language processing and emotion analysis. The implementation method comprises the following steps: 1, tagging part-of-speech coarseness of a to-be-analyzed text by utilizing a natural language processing library; extracting and identifying a labeled result to obtain an emotion keyword; 2, performing fine-grained marking on the emotion keywords, and performing serial number marking on positions of the emotion keywords; 3, obtaining a feature vector, a segment vector and a mask vector; 4, screening to obtain a target word of the metaphor; 5, constructing a node relationship of the dependency tree; meanwhile, sorting and splicing are carried out, and then clauses are obtained; 6, performing emotion classification evaluation; the evaluation is used in emotional natural language text data processing; compared with the prior art, the method has the advantages that through cooperative work of the metaphor recognition model and the emotion detection model, the recognition precision of the expression emotion of the metaphor is improved, introduction of irrelevant information is effectively reduced, and high efficiency of emotion analysis is ensured.

The invention relates to an English translation training method based on a multi-modal corpus, and the method comprises the steps: collecting text, voice, image and context scene information data, constructing a multi-modal parallel corpus, and generating enhanced training data through a cross-modal alignment technology; a dynamic sampling strategy is adopted, related corpora are automatically weighted according to a field input by a user, and field adaptability is optimized; designing a mixed loss function, and performing joint training in combination with semantic similarity, syntactic structure and cross-modal consistency; an online feedback mechanism is introduced, and a corpus and model parameters are updated in real time through user error correction data. Through the multi-modal corpus and the dynamic training strategy, the problems that a traditional translation model is poor in field adaptability and high in data dependence are solved, and the accuracy, robustness and cross-field adaptability of the translation model are improved.

The invention relates to the technical field of natural language processing and artificial intelligence, and discloses a large-model complex instruction-oriented fine-grained intention recognition method, which comprises the following steps of: constructing a candidate analysis forest of an input instruction, and executing entity alignment of each node and a domain knowledge graph; performing semantic compatibility verification on the candidate dependency trees by utilizing entity relationships in the atlas, and screening an optimal analytic tree in combination with syntactic probability and knowledge consistency scores; if the analytic tree meeting the threshold value does not exist, a semantic conflict edge is positioned, and candidate mounting points are searched by using a map neighborhood relation to reconstruct a dependency structure; and finally, generating standardized data containing a structured analytic path based on the optimal analytic tree, and performing fine adjustment on the large model. According to the method, logic constraint and dynamic repair are carried out on the syntactic structure by introducing the knowledge graph, analysis errors caused by multiple modification or structural ambiguity in a complex instruction are effectively solved, and the accuracy and robustness of intention recognition of a large model in the vertical field are improved.

The invention discloses an output content detection method based on a semantic analysis detection model, and the method specifically comprises the following steps: S1, collecting multi-modal data, and carrying out the unified coding of the data, and generating a structured semantic vector; s2, analyzing the structured semantic vector, extracting a subject-predicate-object triple, and generating a dynamic semantic vector matrix; s3, constructing a two-channel semantic detection model, and outputting syntactic structure scores and semantic feature scores according to data in the dynamic semantic vector matrix; s4, calculating a comprehensive risk value according to the syntactic structure score and the semantic feature score, and performing dynamic joint decision making; s5, generating a three-dimensional detection report according to a decision result; and S6, dynamically adjusting and optimizing the model according to the content of the detection report. According to the method, multi-dimensional quantification of complex semantics is achieved, misjudgment and missed judgment of traditional single threshold judgment are reduced, a user is assisted in efficiently processing problems, and the long-term application requirement in a complex scene is met.

The invention discloses a grammar error correction method based on large model syntactic preference optimization. According to the grammar error correction method, syntactic relevance between retrieval example sentence pairs and syntactic relevance between the retrieval example sentence pairs are cooperatively utilized. On one hand, a Monte Carlo tree search algorithm is used for exploring the influence of syntactic structure differences among retrieval examples on error correction performance, search path selection is adjusted based on dynamic weights, and syntactic perception corpora containing hidden syntactic association are constructed. On the other hand, by constructing a syntactic preference alignment mechanism, syntactic knowledge contained in syntactic perception corpora is effectively utilized, dynamic adjustment of grammar error correction model parameters is achieved, and then the performance of the grammar error correction model in a complex grammar error correction task is improved. According to the method, a comprehensive contrast experiment is carried out on two Chinese error correction data sets and two English error correction data sets. Experimental results show that the method can effectively integrate the structured syntactic features in the retrieval examples, and effectively relieve the over-correction phenomenon of the grammar error correction model.

The techniques discussed herein enhance the operation of content generation and analysis systems. Namely, textual content applications such as technical documentation, creative writing, and content moderation. This is accomplished through generating a graphical representation of a body of text (e.g., a document). The graphical representation can comprise a plurality of nodes representing the words of the document and a plurality of lines that join the nodes representing a level of association between individual words. As such, the graphical representation can capture the semantic and syntactical structure of the associated document while omitting the original textual content. The graphical representation can be subsequently evaluated for complexity based on the density of nodes and lines. Accordingly, the disclosed system can assign a score to a document based on the evaluation of the graphical representation. In addition, various documents can be ranked based on such scores.

The embodiment of the invention provides an ancient book proofreading method and device and a storage medium. In the method, each ancient book page of an ancient book file is divided into a plurality of ancient book segments, a text segment corresponding to each ancient book segment is generated, and a first ancient book character of each ancient book segment corresponds to a second ancient book character in the corresponding text segment; according to the first ancient book character in any ancient book segment, performing letter proofreading on the second ancient book character in the text segment corresponding to any ancient book segment to obtain first proofreading information; according to the syntactic structure in any ancient book page and the first proofreading information in the text page, performing word and sentence proofreading on the text page to obtain second proofreading information; and according to the first and / or second proofreading information in the text file corresponding to the ancient book file, carrying out grammar proofreading on text contents with impaired meanings in the text file to obtain a corrected text file. In this way, the ancient book recognition text can be corrected from multiple dimensions of characters, words, sentences and semantics, and the accuracy of the recognition text is improved.

The invention provides an aspect-level sentiment analysis method and device based on a large language model, and the method comprises the steps: firstly extracting syntactic structure information of a to-be-predicted statement, and then fusing the syntactic structure information of the statement into the large language model to achieve aspect-level sentiment classification. In the fusion process, parsing of syntactic structure information, extraction of viewpoint information and analysis of sentiment polarity are completed in sequence through a large language model, and a final aspect-level sentiment classification result is obtained. According to the method, syntactic information is effectively fused into the aspect-level sentiment classification process of the large language model by utilizing a method of multiple understanding and reasoning of the large language model, and the accuracy of the large language model in aspect-level sentiment classification can be effectively improved through multi-step understanding and reasoning. And specific prompt statements are formulated for executing different steps for the large language model, so that the performance of the large language model on aspect-level sentiment classification tasks is effectively improved.

The present application discloses a method for calculating sentence similarity, a related device, and a computer storage medium, wherein the method includes: obtaining two sentences to be compared and a decay factor; vectorizing phrases in the two sentences to be compared respectively to obtain a word vector for each phrase in the two sentences to be compared; determining the word vector similarity between the two sentences to be compared based on the word vector of each phrase in the two sentences to be compared; generating a syntactic structure binary tree of each sentence to be compared according to a preset sentence structure division rule; and determining the sentence similarity between the two sentences to be compared based on the decay factor, the syntactic structure binary tree of each sentence to be compared, and the word vector similarity between the two sentences to be compared. Compared with the prior art method of calculating the similarity between sentences based only on the syntactic structure binary tree, the present application is more accurate.

The application discloses a machine translation software defect detection method based on combined semantics, comprising the following steps: S1, obtaining different Chinese translation sentences of the same English source sentence from different translation software; S2, using a word alignment model to correspond English words in the source sentence with segmented Chinese words in the Chinese translation sentences; S3, using a sentence compression model and a syntactic structure analysis method to obtain a main part and each additional part of the English source sentence respectively and form a sub-sentence set; S4, aligning each part of the English source sentence obtained in the step S3 with the corresponding translation part to obtain aligned translation of the main part and the additional part of the source sentence; and S5, detecting errors, including semantic similarity calculation and synonym checking.

Embodiments of the present invention provide a method and apparatus for text sentiment classification, relating to the field of data processing technology. The method comprises: extracting, for each character in a text to be classified, character semantic information representing the semantic meaning of the character based on the character's position in the text to be classified; obtaining, based on the position of each character in the text to be classified, syntactic structure information representing the syntactic structure of the text to be classified; and determining, from preset sentiment categories, the target sentiment category to which the sentiment expressed in the text to be classified belongs based on the character semantic information and the syntactic structure information of each character. Application of the embodiments of the present invention enables classification of the sentiment category of the sentiment expressed in the text.