17 results about "WordNet" patented technology

The invention relates to a network threat report attack knowledge graph automatic construction method and system based on a large language model, a storage medium and a program product, and the method comprises the steps: carrying out the iterative processing of extracted entities and relationships through a clustering method based on the large language model, and generating an initial attack knowledge graph; according to the invention, aggregation processing is carried out on a plurality of technology example threat reports belonging to the same attack technology through an attack technology graph template generation mechanism, a standardized attack technology standardized template library is established, and automatic attack technology tagging of new threat reports is realized by adopting an attack technology alignment method based on Word2Vec and WordNet, so that the automatic attack technology tagging of the new threat reports is realized. And a complete attack technology knowledge graph is constructed, so that a security analyst can quickly understand an attack path and a key threat point, and the automation degree and the accuracy of threat intelligence analysis are remarkably improved.

The invention discloses a refined password structure generation method. The method comprises the following steps: inputting a password and identifying a special character string in the password; segmenting and marking the unmarked password according to the type to obtain a letter segment L, a number segment D and a symbol segment S; finely classifying the divided letter segments L; and obtaining a fine structure of the password according to a fine classification result. According to the scheme, the WordNet dictionary system is utilized to perform full-coverage semantic recognition and classification on the English character strings, the problem of insufficient model precision caused by semantic information loss in a traditional PCFGs password structure analysis method is solved, and a high-practicability refined structure representation and generation method is provided for password analysis.

The invention belongs to the technical field of aspect category sentiment analysis, and particularly relates to an aspect level sentiment distinguishing method based on an attention mechanism and external knowledge. Aiming at the problems of inaccurate and incomplete aspect category sentiment analysis and the like, a text sequence is coded based on BERT and BiLSTM, and meanwhile, internal association between context and aspect categories is modeled by using specific BiLSTM, so that embedded representation of aspect category and context information fusion is formed; a common sense knowledge graph enhancement module is designed, a synonym set is searched for each token of an input text through WordNet / synonym forest, and expression obtained by specific BiLSTM is enriched through embedding of a knowledge graph; by designing a multi-aspect attention module, the correlation between each aspect category and vector representation containing context perception and knowledge perception is calculated, and deeper understanding and deduction of implicit emotion semantics of the text are realized.

The invention discloses a knowledge-guided image search recall method and system and a server, and belongs to the technical field of information, and the method comprises the following steps: 1, when an image is stored in a cloud storage system, extracting an image semantic feature vector of the image by adopting a visual encoder of a Chine-CLIP model, and storing the image semantic feature vector in a database; 2, when a search statement is input, entity recognition is conducted on the search statement through a BERT model, and all entities in the search statement are extracted; 3, the entities are matched with words in a Chinese WordNet knowledge base, and concept hierarchies of all the entities are obtained; 4, according to the concept hierarchy, performing normalization calculation to obtain a similarity threshold value; and 5, extracting a text semantic feature vector of the search statement, performing similarity calculation on the text semantic feature vector and the image semantic feature vector, and obtaining a recall result based on a similarity threshold. According to the method, the recall rate and accuracy of image search can be effectively improved.

The application relates to a signature-based set semantic similarity connection method, and belongs to the fields of databases and information retrieval. The method comprises four parts: firstly, a classification tree construction step: a classification tree is constructed according to a WordNet knowledge base given a data set; secondly, a set signature step: each set in the data set is signed to obtain a corresponding signature data set; thirdly, a data preprocessing step: the sets in the signature data set are sorted to obtain a sorted data set; and finally, a connection processing step: self-connection is performed on the sets in the sorted data set to obtain a set of semantic similarity results. The method is based on signature prefix filtering technology and length filtering technology, and finally realizes the set semantic similarity connection method, so that the set semantic connection efficiency can be effectively improved.

The present invention relates to a method, system, storage medium and program product for automatically constructing a network threat report attack knowledge graph based on a large language model. The method generates an initial attack knowledge graph by iteratively processing the extracted entities and relationships through a clustering method based on a large language model. At the same time, the present invention aggregates multiple technical example threat reports belonging to the same attack technology through an attack technology graph template generation mechanism, establishes a standardized template library for standardized attack technologies, and adopts an attack technology alignment method based on Word2Vec and WordNet to realize automatic attack technology labeling of new threat reports, construct a complete attack technology knowledge graph, facilitate security analysts to quickly understand attack paths and key threat points, and significantly improve the automation and accuracy of threat intelligence analysis.

An electronic device comprises a hallucination detection system. The hallucination detection system can execute a hallucination detection method. The hallucination detection method comprises implementing a conversion step, an authenticity detection step, and a result output step. The conversion step comprises: generating a plurality of output wordnets according to the output text. The authenticity detection step comprises: generating multiple pieces of authenticity information by a trained graph embedding model. Each of the multiple pieces of the authenticity information indicates whether one of the output wordnets is determined to be non-hallucinated or hallucinated by the graph embedding model. The result output step comprises: generating result of hallucination detection according to the multiple pieces of the authenticity information. The graph embedding model is trained through a plurality of positive wordnets and a plurality of negative wordnets generated from domain knowledge data.

The application relates to the technical field of industrial manufacturing, and discloses a method and system for improving the completion parameters of understanding user input, which comprises the following steps: inputting an industrial standardized file, generating a semantic label, reasoning through the industrial standardized file and the semantic label, obtaining an optimized industrial standardized file, and obtaining an industrial rule set and a text parameter set input by a user. The application realizes accurate semantic label generation based on a WordNet synonym set, solves the polysemy ambiguity problem, calculates the similarity between a candidate parameter and a user conversation through an improved Levenshtein distance algorithm and a compensation mechanism, accurately captures the potential demand of the user, improves the consistency with the actual input intention of the user, multiplies the initial weight value, the click rate and the time decay factor to sort the candidate parameters, balances the instant production demand and the historical experience in the industrial scene, and significantly improves the accuracy, adaptability, efficiency and interpretability in four dimensions.

The invention relates to a signature-based set semantic similarity connection method, and belongs to the field of databases and information retrieval. Comprising four parts of contents: firstly, a classification tree construction step: giving a data set, and constructing a classification tree according to a WordNet knowledge base; secondly, a set signature step: signing each set in the data set to obtain a corresponding signature data set; then, a data preprocessing step: sorting the signature data set to obtain a sorted data set; and finally, a connection processing step: performing self-connection on sets in the sorted data sets to obtain a semantic similar result pair set. Based on the signature prefix filtering technology and the length filtering technology, the set semantic similarity connection method is finally realized, and the set semantic connection efficiency can be effectively improved.

The present invention provides a method and apparatus for measuring the semantic similarity of words by integrating the SAO and Bayesian models, which relates to the technical field of calculating the semantic similarity of words. This method is an innovative method for measuring the semantic similarity of words, which integrates the extraction of the SAO (subject-action-object) structure and the Bayesian model. First, the SAO structure is extracted from the text, and then the occurrence frequencies of similar words are statistically counted based on these structures, which is used as a measure of the similarity of words. At the same time, semantic knowledge bases such as WordNet are also utilized to obtain the semantic similarity parameters of words, and these parameters and statistical results are integrated through the Bayesian model to calculate the posterior probability of the semantic similarity of words. The innovation of this method lies in that it not only utilizes the advantages of the statistical-based method but also combines the knowledge-based method, providing a new perspective to understand and quantify the similarity between words.

The present invention claims protection for a weight Bayesian classifier and an ontology mapping method for semantic ontology, which comprises the following steps: S1: Parsing the ontology: Parsing the ontology participating in the ontology mapping through the Jena package in Java, extracting concepts, and using the WordNet semantic dictionary to complete the expansion of concepts; S2: Determining weights using the harmony search algorithm: Introducing a dynamic weight mechanism to reduce the impact brought by its assumption of conditional independence of attributes; S3: Constructing a weight Bayesian classifier: Establishing a weight Bayesian classifier through the weights obtained in the previous step, converting the ontology mapping problem into a classification problem, calculating the maximum posterior probability to complete the classification; finally, saving the output classification result into the AllergoGraph database. The present invention adopts the harmony search algorithm, uses the classification error rate as the objective function, calculates the global optimal weight and assigns it to the weighted naive Bayesian classifier; the present invention proposes a new way of generating solutions to improve the optimization ability of the harmony search algorithm.

The invention provides a word semantic similarity measurement method and device integrating SAO and a Bayesian model, and relates to the technical field of word semantic similarity calculation, the method is an innovative word semantic similarity measurement method, and SAO (subject-action-object) structure extraction and the Bayesian model are integrated; firstly, SAO structures are extracted from a text, and then the occurrence frequency of similar words is counted based on the structures and serves as a measure of word similarity. Meanwhile, semantic similarity parameters of the words are obtained by utilizing a semantic knowledge base such as WordNet and the like, the parameters and statistical results are integrated through a Bayesian model, and the semantic similarity posterior probability of the words is calculated. The method is characterized in that the advantages of a method based on statistics are utilized, a method based on knowledge is combined, and a new perspective is provided to understand and quantify the similarity between words.

The application discloses a zero sample event detection method based on a text entailment recognition model, and comprises the following steps: S1, obtaining initial text data from a NYT corpus and performing pretreatment, and obtaining separate sentence texts after the treatment; S2, using a WordNet to expand seed keywords; S3, using the expanded keyword set to screen the text data, when a text sentence contains keywords corresponding to a certain event type, the sentence has a considerable probability to express the event type; S4, using a text entailment recognition model to mark the data screened in the step S3; S5, further using the text entailment recognition model to screen the data obtained in the step S4; S6, using the data obtained in the step S5 to train the text entailment recognition model, and using the trained model to perform event detection on an ACE data set. The application focuses on optimizing the application of the text entailment recognition model in zero sample event extraction.

The present invention belongs to the field of information technology and relates to a method for generating medical text data, which includes obtaining a medical record sample, obtaining a new medical record sample by using MetaMap for professional medical name matching and replacement, and at the same time using the WordNet dictionary for synonym search and obtaining the current medical record sample by using the synonym replacement with the highest similarity, thus expanding the medical record sample data and solving the problem of data shortage in medical text classification training.

The present application discloses a security attribute calibration method, system, device and computer storage medium, which obtains labeled source domain data and unlabeled target domain data; determines the target domain data label of the target domain data based on the source domain data through a pre-trained neural network model; determines the candidate security attribute set of the target domain data based on the WordNet dictionary and the target domain data label; screens out the target security attributes of the target domain data at each vocabulary depth from the candidate security attribute set; and determines the security attribute calibration result of the target domain data from the target security attributes at each vocabulary depth according to the access control granularity. In the present application, the target domain data label of the target domain data is determined based on the labeled source domain data through a pre-trained neural network model, and the security attribute calibration result that meets the access control granularity can be obtained based on the WordNet dictionary and the access control granularity, thereby realizing fine-grained control of security attributes.

The invention discloses a heterogeneous model-oriented multi-granularity hierarchical semantic tree construction method. The method comprises the following steps of: generating an image feature vector set; forming a bottom layer of the hierarchical semantic tree according to the image and the sample label; constructing a representative semantic space according to the image feature vector and the WordNet data set based on a clustering method; using an MLP model to classify images to confirm an image center, and generating a semantic center set; the mapping relation between the image and the semantic center set noun is described as an OT problem, the mapping probability is solved with the purpose of minimizing the transmission cost, and an image pseudo tag is generated; updating the weight of the MLP model, constructing a loss function, and optimizing the MLP model; generating an optimal classification result based on the optimized MLP model, generating an image tag based on the optimal classification result by the CLIP model, and constructing an upper layer of the bottommost layer of the hierarchical semantic tree based on the image tag; and sequentially constructing other layers according to the method. The method is beneficial to maximizing the maximum potential of cooperative training of heterogeneous models.

The present invention provides an image clustering method based on a text-image pre-trained model, belonging to the technical field of image processing. The method includes: according to all nouns obtained from WordNet, using the text-image pre-trained model to select candidate words in the text modality, retrieving the candidate words for each image, and constructing a representation corresponding to it in the text modality; according to the image representation and the representation corresponding to it in the text modality, using the method of cross-modal mutual distillation to obtain the image clustering result. The present invention solves the problem that the text modality of the text-image pre-trained model cannot be effectively utilized in the case of unknown class names, resulting in poor image clustering effect and large computational overhead, and avoids consuming a large amount of human resources for image classification.