16 results about "Cybertext" patented technology

The invention relates to the field of computer text sentiment analysis, in particular to a knowledge enhancement implicit sentiment analysis method, device and equipment based on ChineseBERT. The method comprises the steps of obtaining target text information; the target text information is composed of one or more target sentences; an improved ChineseBERT model is adopted to extract position embedding, character embedding, font embedding and pinyin embedding from the target sentence, and target sentence embedding representation is obtained; the font embedding is determined by radicals and components of each character of the target sentence; extracting knowledge entity vectors from the target sentences by adopting a pre-trained knowledge base to obtain knowledge base representation of the target sentences; according to the target sentence embedding representation and the target sentence knowledge base representation, obtaining an emotion label category of the target sentence; the emotion label category of the target sentence is the target emotion of the target user about the target theme. According to the method, the web text sentiment classification accuracy can be effectively improved.

The invention relates to the field of natural language processing and graph database query, in particular to a Cypher generation method and system based on a directional control mode, comprising three parts of data preprocessing, directional control mode design and graph database query. According to the method, the problem of the uncertainty of the Cypher generated by the LLM is effectively solved through the design of the directional control mode; the Schema is dynamically generated according to the user input, so that the data scale is reasonably controlled on the premise of ensuring the accuracy of the generated Cypher, and the performance reduction caused by processing excessive data is avoided; various advanced optimization means are comprehensively applied, including but not limited to lexical and syntactic analysis, de-noising processing, standardized conversion and the like on text data, the processing capacity of the system on various complex text data is effectively improved through the means, and the processing capacity of the system on various complex text data is effectively improved regardless of academic literatures with strict structures and web texts with various styles. And the system can accurately respond, and the adaptability is obviously enhanced.

The present invention discloses a language steganalysis method based on knowledge injection and knowledge encoding, which belongs to the field of information hiding. First, a language steganalysis system model based on knowledge injection and knowledge encoding is constructed. The system model preprocesses the input sentence with the help of a knowledge graph to complete the knowledge injection. Then, BERT is used on the sentence tree and the visible matrix to complete the extraction of semantic features and perform knowledge injection semantic encoding. During the preprocessing, a KE module of graph structure modeling is used to extract knowledge from the input sentence and the knowledge graph to obtain a mini-graph, and the mini-graph is knowledge encoded by GAT. Finally, the captured entity node features and the representation vector obtained from the knowledge injection module are connected in series and added to a fully connected layer. The system model predicts whether the input text is a normal carrier or a steganographic carrier through the output of the fully connected layer. The present invention solves the fragmentation problem of network text and makes the results of language steganalysis more accurate.

A BERT-TextRank text classification method based on RAdam and cosine annealing comprises the following six steps: S1, data preprocessing: performing cleaning, word segmentation and data set division on web text data; s2, compressing the text: compressing the data obtained in the step S1 to obtain text content with a large amount of information; s2, improving the stability and convergence of the model: after the text in the S2 is obtained, training by using a BERT model, and improving the stability and convergence of the model by using an RAdam optimizer; s4, circularly updating the parameters: when the BERT model is trained in the S3, circularly updating the parameters by using a Lookahead optimizer; s5, dynamically adjusting the learning efficiency to avoid falling into local optimum: in the step S4, dynamically adjusting the learning rate by using a cosine annealing learning rate scheduler to avoid falling into local optimum; and S6, model performance verification. According to the method, the stability and convergence of the model are improved by compressing the long text, and the learning rate is dynamically adjusted to avoid local optimum, so that the text classification performance of the BERT model is enhanced, and the classification task is more excellent in performance.

This invention provides a method and apparatus for identifying online nuisance text, comprising: preliminarily judging the target online text by extracting URL links from the target online text; if the judgment cannot be made, calculating the invalid information score and generating a pinyin list, a keyword list, and a keyword pinyin list for the target online text; calculating the online nuisance score for each keyword by analyzing the distribution of the character elements of each keyword in the target online text and the distribution of the keyword pinyin in the pinyin list of the target online text; revising the online nuisance score based on the invalid information score, and obtaining the online nuisance text recognition result based on the revision result. This invention can accurately identify online nuisance text through fuzzy matching of online nuisance keyword characters and pinyin, and can effectively address information hiding methods such as segmentation, reverse order, vertical text arrangement, and homophones in the target text.

The present invention discloses a method for predicting and controlling mutations in an online group opinion evolution system, belonging to the technical fields of text mining and mathematical modeling. By processing network text data, system variables of group opinion evolution are obtained; and a mutation model of group opinion evolution is established based on catastrophe theory; an elasticity index model of the system is constructed from the mutation model to analyze the possibility of opinion mutation and the danger of system state, thereby predicting mutations. A method for finding the threshold of the system elasticity index is proposed based on the elasticity index model, and opinion mutations are prevented according to the comparison result between the elasticity index and the threshold. Furthermore, a control method for the elasticity index is proposed, and a random search algorithm for reducing the system elasticity index is proposed to reduce the possibility of system mutations. Thus, the present invention can accurately describe and predict the mutation phenomenon of the online group opinion evolution system, and can reduce the possibility of group opinion mutations with less time consumption.

The present invention discloses a method and device for identifying credible online false information, comprising the following steps: obtaining a first text to be detected, performing feature extraction on the first text to obtain deep semantic features and text element features; performing syntactic dependency analysis on the first text to obtain text style and extract syntactic dependency features; performing sentiment feature splicing on the first text to obtain sentiment feature features; performing feature splicing and multi-feature fusion on the deep semantic features and text element features, syntactic dependency features, and sentiment feature features of the first text to obtain fused features; inputting the fused features into a pre-trained online false information recognition model, and outputting a recognition result for the first text. The present invention improves the recognition performance of online text content and balances the accuracy and interpretability of the recognition model.

The present invention relates to the technical field of natural language processing, and particularly to a method and device for identifying inter-organization relationships based on web text mining. The method includes: obtaining web texts; preprocessing the web texts to obtain processed texts; constructing triples based on the processed texts to obtain an initial training set; fine-tuning a preset large language model using a low-rank adaptation fine-tuning method according to the initial training set to obtain a first inter-organization relationship recognition model; constructing an incremental training set based on the processed texts using the first inter-organization relationship recognition model; performing incremental training on the first inter-organization relationship recognition model using the incremental training set based on a preset number of training rounds to obtain a second inter-organization relationship recognition model; obtaining the web texts to be recognized; and inputting the web texts to be recognized into the second inter-organization relationship recognition model to obtain the recognized inter-organization relationships. The present invention is an accurate and efficient method for identifying inter-organization relationships for unstructured texts.

The present invention provides a method for discovering interest communities in social networks, which relates to the technical field of community discovery. The present invention establishes a new deep learning model based on the traditional Text CNN model, which can support the input of multiple social network texts, and combines the similarity between social network texts to propose a multi-text interest modeling method based on Text CNN combined with similarity, and proposes a user interest feature modeling method combining network structure and interactive behavior. The LM network algorithm is used to construct a user influence model, and then the results based on SMB-TextCNN are adjusted according to the model results, attention relationships and @ behavior information. Finally, based on the results of SIBUIM, a method for discovering interest communities based on k-means overlap is proposed. This method takes into account the structurality of social networks and the content of nodes, and can divide Sina Weibo users into overlapping interest communities.

The invention discloses a campus forum content management method based on artificial intelligence, and relates to the field of web text processing. The method comprises the following steps: firstly, obtaining post data in a preset time range in a campus forum to obtain a post set; preprocessing the post set, inputting the post set into a pre-trained identification model, identifying posts involving negative contents, and taking the posts as a target set; constructing a topological structure chart of the posting set according to the overlapping degree of the topics involved among the posts and the sequence of the publishing time, and calculating the connectivity of each post according to the topological structure chart; and calculating the influence of the negative content in the campus forum by integrating the connectivity of each post in the target set. The invention further provides a corresponding device, equipment and a storage medium, the recognition accuracy of the negative content in the campus forum is improved, and comprehensive evaluation on the influence of the negative content in the campus forum is achieved.

The invention belongs to the technical field of natural language processing and information summarization, and particularly relates to a semantic integrity driven iterative event venation construction method and a computer program product, the method comprises the following steps: 1, preliminary event venation construction: screening a document related to a target event from a multi-source web text, and constructing an initial event development sequence; step 2, semantic integrity detection and reflection analysis: performing semantic integrity detection on each event in the initial event development sequence, identifying missing basic semantic elements, and generating a list of semantic elements to be complemented; step 3, iterative completion and final event venation output: based on the to-be-completed semantic element list, generating element-oriented query to perform directional retrieval, and integrating new information obtained by retrieval into the event venation; and 4, repeatedly executing the steps 2 to 3 to form an iteration closed loop of generation-reflection-complementation until an iteration termination condition is reached, and outputting a final event context.

The present invention provides a method and device for detecting a sample stance based on hierarchical contrastive learning. The method includes the following steps: 1) collecting data: in social network media, collecting social network text data, the social network text data including the topic text of the discussion and the user's comment text on the topic. 2) constructing a dataset based on the collected data, with the source topic target dataset with known stance labels as the training set; and the destination topic target dataset without stance labels as the test set; 3) establishing a sample stance detection model, outputting the predicted probability of the stance held by the comment text with respect to the topic text; 4) training the sample stance detection model with the training set until the sample stance detection model converges to obtain a stance prediction model; 5) inputting the topic text and comment text to be predicted into the trained stance prediction model, and outputting the probability of the stance held by the comment text with respect to the topic text.

The invention provides an information identification method and system based on a network index. The method comprises the following steps: capturing network text data from a plurality of online resources by using an optimized web crawler; constructing and maintaining an inverted index based on the web text data, wherein the inverted index is used for accelerating retrieval of keywords in the captured web text data; performing natural language data processing on the web text data; performing sentiment analysis and subject classification on the web text data after natural language data processing by using the trained deep learning model to obtain an analysis result; a time sequence model is constructed according to the reverse index and the analysis result, the time sequence model is suitable for data fluctuation characteristics in different time periods, the abnormal peak value of the information is judged according to the time sequence model, and the method can effectively, rapidly and accurately recognize and analyze the information on the network, so that the network quality is improved. The accuracy and efficiency of information identification are improved, and powerful data support is provided for decision makers.

The application discloses a network text public emotion mining method and system based on supervised learning, and establishes a coding framework of network text multidimensional public emotion according to research literature, expert opinions and experience of dissemination science; coding training is conducted on each coder so that each coder reaches consistency; network text is captured, and each coder carries out scoring processing according to the given coding framework; a text feature expressing a topic and content in the network text is extracted by using a LIWC dictionary, and a text data set is constructed; a supervised machine learning method is used, network text scoring and the text data set are combined for training, a text analysis model is obtained through matrix parameter adjustment and cross-validation methods; and the evaluation subject attribute in new network text and multidimensional public emotion scores are obtained by using the text analysis model. The application can accurately and professionally evaluate the public emotion of short texts, and solves the problem of lack of Chinese annotation materials of short text public emotion in the evaluation of daily situations.

The application provides a text security judgment method and device based on consensus verification, and belongs to the technical field of natural language processing. The method comprises the following steps: obtaining a target text; inputting the target text into a judgment model to obtain a judgment result output by the judgment model, wherein the judgment result is used to indicate whether the target text is a safe text, the safe text does not include harmful expressions, the harmful expressions include a first harmful new word, and the first harmful new word is a word with harmful word meaning in the target text; wherein the first harmful new word is determined based on consensus verification, and the consensus verification is based on information searched by a search engine. The harmful new word with different word meanings in the context and the independent use can be accurately identified, the identification ability of implicit harmful network expressions is enhanced, and the accuracy and comprehensiveness of network text harmful content detection are improved.