22 results about "Word graph" patented technology

1. The name of the design product: electronic device's word book word list scene word graph user interface. 2. The use of the design product: for an electronic device. 3. The design points of the design product: the interface content of the graphical user interface in the screen. 4. The picture or photo that best indicates the design points: front view. 5. The product carrier is the conventional design, and the rear view, left view, right view, top view, and bottom view are omitted. 6. The use of the graphical user interface: for the user to switch 10 scene word books, and manage the words of each word book through the word list. 7. The human-computer interaction mode of the graphical user interface: the front view is the initial interface. Click the expand word list details button in the front view to enter the interface change state diagram.

The invention relates to the technical field of generalization encryption, and discloses a generalization processing method and system for text data in economic big data, and the method comprises the steps: firstly carrying out the standardization and word segmentation of original text data, and carrying out the statistics of a word pair co-occurrence relation through a preset sliding window parameter; then, according to co-occurrence counting, the correlation strength of word pairs is calculated and is not negative, and a weighted word graph with the correlation strength as the edge weight is constructed; calculating a normalized graph matrix and performing feature analysis to obtain a second feature value and a second feature vector, thereby calculating an edge-level sensitive value and determining word-level sensitivity; screening a high-sensitivity word set according to a threshold parameter, generating a window radius in a feature vector coordinate space according to a coordinate difference between a high-sensitivity word and a peak-causing neighbor node and a radius parameter, forming a word bucket, and combining overlapped intervals; and finally, generating bucket codes for each word bucket by adopting an encryption algorithm, replacing words in the buckets, and outputting generalization encrypted text data with privacy protection and structure availability.

The invention relates to the technical field of hotspot monitoring, in particular to a hotspot event dynamic monitoring method and device based on public information.The method comprises the steps that a public information text set is obtained, word segmentation operation is conducted on each public information text in the public information text set, and a word segmentation sequence of the public information texts is obtained, performing hot word extraction based on the word segmentation sequence to obtain hot words of the word segmentation sequence, namely a hot word set of the public information text set; and performing hot word graph modeling on the hot word set based on a frequent item set to obtain a hot word graph structure of the hot word set. According to the method, community detection is carried out on the hot word graph, so that the relationship and aggregation trend between the hot words can be deeply analyzed, and the association degree between different hot words and the community to which the hot words belong can be identified, and therefore, the evolution process and the internal structure of the event can be understood from multiple dimensions, and complex social events can be better understood.

This invention relates to a method for identifying hot words in customer conversations based on large-scale model technology. The identification method is as follows: model training and construction; users upload batches of historical conversation texts or access conversation streams in real time through the system interface; the system automatically segments the input text into sentences, labels roles, and unifies the encoding format; the trained model processes the preprocessed conversation text; conversation summaries are generated based on hot word graphs; and the results are visualized and output. Compared with existing technologies, this invention achieves accurate identification and classification of the deep meaning of hot words through a multi-dimensional tagging system and semantic understanding; it couples hot word identification and summary generation through multi-task learning and semantic graphs, making the generated summaries both focused and coherent; it supports automated and intelligent analysis of massive conversation data, greatly improving the efficiency and depth of customer sentiment analysis, and providing direct data support for product optimization, service improvement, and risk warning.

This natural language processing device comprises: a first input unit; a second input unit; a first word extraction unit; a second word extraction unit; a correspondence relationship determination unit; and an output unit. The first word extraction unit receives an input of a first target, which includes a natural language description. The second word extraction unit receives an input of a second target, which includes a natural language description. The first word extraction unit extracts at least one first word from the first target. The second word extraction unit extracts at least one second word from the second target. The correspondence relationship determination unit determines the presence or absence of a relationship between the first word and the second word. The output unit performs output processing on the basis of the results of determining the presence or absence of a relationship. The correspondence relationship determination unit: uses the first word as a start node; searches for, from the start node, a word graph in which at least one complementary word related to the first word is connected by an edge indicating a relationship between the first word and the complementary word; and determines the presence or absence of a relationship between the first word and the second word on the basis of whether it is possible to trace back to the second word.

The invention relates to the technical field of voice recognition, in particular to an LED multi-dimensional information issuing method based on voice intention recognition, which comprises the following steps of: decoding an input voice signal to generate a decoded word graph, positioning a preset LED multi-dimensional information semantic slot position in the decoded word graph and extracting similar competition paths; and calculating to obtain a high-confidence ambiguity candidate set. When voice signals are processed, similar candidate word combinations can be extracted from an ambiguous recognition path by constructing a decoding word graph and positioning LED multi-dimensional information semantic slots, posterior probability differences are further calculated to form an ambiguous candidate set, and a clear distinguishing basis is introduced in a scene with similar recognition precision but semantic conflicts, so that the recognition accuracy of the voice signals is improved, and the recognition accuracy of the voice signals is improved. And fuzzy recognition caused by path divergence in the word graph is relieved. The clarified questions embedded with the competition words are synchronously presented in a voice and LED dual-channel form, so that the user feedback is more targeted, and the ambiguity clarification efficiency is improved.

The invention relates to the technical field of voice recognition, and discloses a medical term recognition method, device and equipment and a medium, and the method comprises the steps: obtaining mixed voice data; performing language labeling on the mixed voice data, and determining language boundary tags of Cantonese, Mandarin and English voice segments contained in the mixed voice data; running special speech recognition engines corresponding to Cantonese, Mandarin and English in parallel, decoding the mixed speech data, and generating candidate word graphs of three languages; performing cross-language alignment on the candidate word graph of the three languages to obtain an aligned word graph; recalling the candidate medical terms from the aligned word graph to obtain a candidate medical term list; and screening final medical terms from the candidate medical term list by using a pre-trained language model. According to the method, the canestrun mixed speech in the same sentence is effectively processed, the recognition problem caused by language mixing and semantic ambiguity is solved, and the recognition accuracy of the medical terms is remarkably improved.

The invention provides a reinforcement learning handwriting generation method and system based on writing content keeping and writing style migration, and the method comprises the steps: inputting to-be-identified material detection image data and corresponding reserved sample image data into a handwriting generation system, and enabling the system to recognize writing content from a material detection image through a text information extraction model, outputting a corresponding text and converting the text into a spliced word graph of a standard word stock; then, style coding is conducted on reserved sample image data through a handwriting generation model in the system, content coding is conducted on the text, content information and style information are fused, the condition diffusion generation process is controlled, and finally a new handwriting image which is the same as the detected material in content and consistent with the reserved sample in style is generated. According to the method, the identification problem that no reference material exists when the reserved sample content is inconsistent with the detected material content during handwriting identification in the prior art can be effectively solved, the writing content is accurately kept, efficient migration of the writing style is realized, expert suggestions are effectively integrated, and the generation quality of the handwriting image and the objectivity of the identification process are improved.

The technical solution utilizes an LLM based on a GNN model to provide multilingual and multi-dialect text processing. The system can receive a query in a first language, the query corresponding to a wordpiece. The DPS can generate a first vector for a first wordpiece in response to inputting the wordpiece into a GNN trained based on a corpus, the wordpiece corresponding to a word graph that indicates associations between wordpieces in multiple languages. The DPS can generate a second vector for a second wordpiece in response to inputting the wordpiece into an LLM trained based on a plurality of interactions. The DPS can establish a priority for one of the first wordpiece or the second wordpiece based on at least a first weight of the first vector and a second weight of the second vector, and provide a response to the query using the first wordpiece or the second wordpiece according to the priority.

The long document classification method and device based on hierarchical multi-granularity interactive graph convolution network can construct a network to depict complete hierarchical structured information of a long document and perform information interaction between graphs under the condition of controlling model calculation complexity.The method comprises the following steps: (1) obtaining hierarchical multi-granularity representation of a long document; (2) performing multi-layer hierarchical superimposed paragraph graph convolution, sentence graph convolution and word graph convolution and corresponding inter-graph interaction; (3) in order to fuse semantic information of different granularities and different scales, maximum pooling is used to respectively aggregate the final layer output of the paragraph graph and the output of each layer of the sentence graph and the word graph.

The present invention provides a speech recognition system decoding method, system, and storage medium. The method includes preprocessing the speech data to be recognized to obtain a speech feature frame sequence; feeding the speech feature frame sequence into a trained deep neural network, randomly performing dropout on each layer of the deep neural network except the output layer using a dropout strategy, repeating this operation N times to obtain N different deep neural networks, thereby achieving sufficient sampling of the same deep neural network; performing a forward propagation process on the input speech feature frame sequence using the N different deep neural networks based on the dropout strategy to obtain forward calculation results of N different deep neural networks; feeding the forward calculation results into a decoder, and merging them using the synchronous merging unbiased decoding algorithm proposed by the present invention to obtain an unbiased decoded word graph. The present application can eliminate the bias of the decoding results of the speech recognition system, obtain high-quality unbiased decoding results, and improve the performance of the speech recognition system.

The application relates to an artificial intelligence technology and discloses a text keyword association method, which comprises the following steps: adding a plurality of semantic feature layers in a pre-constructed basic vector conversion network to obtain an original vector conversion model; performing model training on the original vector conversion model by using a business text data set to obtain a standard vector conversion model; extracting a candidate association word set based on the word frequency and point mutual information value of the words in the text to be associated; performing vector conversion on the candidate association word set by using the standard vector conversion model to obtain an association word vector set; performing association word association on a target keyword in the candidate association word set based on the similarity of each vector to obtain an association word graph. The application also relates to a blockchain technology, and the association word graph can be stored in a node of the blockchain. The application further provides a text keyword association device, an electronic device and a readable storage medium. The application can improve the accuracy of text keyword association.

The present disclosure presents a method, an apparatus, and a computer program product for note recording. A set of text segments in a target window and a set of locations corresponding to the set of text segments may be obtained. A word graph corresponding to the target window can be constructed according to the set of text fragments and the set of positions, and the word graph comprises a plurality of words in the set of text fragments and a plurality of edges connecting the plurality of words. A current word that is currently input into the note may be detected. A word suggestion for the current word can be generated according to the word graph, and the word suggestion comprises words located behind the current word in the target window.

The invention relates to the technical field of data processing, and provides a digital archive classification recording method and system convenient for query and search, and the method comprises the steps: collecting a plurality of to-be-processed archives, and extracting the abstract and original text of each to-be-processed archive; extracting a plurality of effective words from the abstract of the to-be-processed file, and screening core words of a plurality of abstracts; further screening to obtain core associated words of the abstract, and obtaining supplementary words of the original text to form candidate words of the file to be processed; constructing a word graph to obtain an initial score of each candidate word; iteratively updating the score of each candidate word in the word graph to obtain a final score of each candidate word; obtaining a plurality of theme clusters of the to-be-processed file; obtaining a top-layer core word and a plurality of sub-tag core words of each topic cluster; constructing a tree structure; and according to the tree structure, the to-be-processed file is concluded and recorded. The method aims at solving the problem that traditional digital archive classification depends on fixed dimension division, so that the multi-dimension searching efficiency is influenced during searching.

This invention relates to the field of language processing technology, and also to the field of artificial intelligence technology, particularly to a text correction method, apparatus, electronic device, and storage medium. The method involves acquiring text to be processed, inputting the text into a feature encoding model to obtain a first feature vector, inputting the first feature vector into a text error type classification model to output a first probability value, a second probability value, and a third probability value, inputting the first feature vector into a first graph convolutional neural network model based on a homophone graph network to obtain a second feature vector, inputting the first feature vector into a second graph convolutional neural network model based on a similar-looking character graph network to obtain a third feature vector, weighting the first, second, and third feature vectors to obtain a fused feature vector, and inputting the fused feature vector into a transformer model to obtain the correction result. This method solves the technical problem of homophone and similar-looking character errors in text.

This invention discloses a graph kernel-based text data classification method to improve computational efficiency and reduce memory consumption while maintaining high classification accuracy. The invention mainly includes acquiring the textual and structural information of documents, converting the documents into word graphs, using a graph kernel method to measure the similarity between two documents to obtain a similarity matrix of the document set, and then using the similarity matrix as input data to train an SVM model to classify unknown documents. The aim of this method is to provide users with a high-accuracy text classification method while ensuring a better user experience, allowing users to easily obtain the documents they need and filter out unnecessary ones.

The present disclosure proposes a method, apparatus and computer program products for note taking. A set of text segments in a target window and a set of positions corresponding to the set of text segments may be obtained. A word graph corresponding to the target window may be constructed according to the set of text segments and the set of positions, the word graph containing a plurality of words in the set of text segments and a plurality of edges connecting the plurality of words. A current word currently input into a note may be detected. A word suggestion for the current word may be generated according to the word graph, the word suggestion containing a word located after the current word in the target window.

This application provides a speech recognition method, speech recognition device, electronic device, and storage medium, belonging to the field of financial technology. The method includes: acquiring target speech data; extracting acoustic features from the target speech data to obtain target acoustic features; decoding the target speech data based on a decoding model to obtain a target word graph; the target word graph includes word nodes and a speech feature sequence, the speech feature sequence including at least two speech words; constructing multiple candidate sentence paths based on the word nodes and speech feature sequence; initially scoring the speech words of each candidate sentence path to obtain a preliminary word score; correcting the preliminary word score based on the target acoustic features to obtain a target word score; filtering the candidate sentence paths according to the target word score to obtain a target sentence path, and concatenating the speech words of the target sentence path to obtain target sentence data. This application can improve the accuracy of speech recognition.

The invention discloses a word embedding optimization method based on a graph. The word embedding optimization method comprises the steps of obtaining a word co-occurrence graph based on a large-scale corpus; wherein the word co-occurrence graph is a directed weighted word graph; obtaining a transition probability between nodes based on the word co-occurrence graph and extracting importance scores of the nodes; based on the transition probability between the nodes and the importance score of the nodes, obtaining a plurality of word sequences through random walk sampling to construct a sampling corpus; and applying the character skipping model to a sampling corpus to obtain a final word vector. The invention provides a graph-based word embedding optimization method, which comprises the following steps of: converting a large corpus into a word co-occurrence graph, randomly extracting word sequence samples, and training word vectors on a sampling corpus; the method has stable operation time on a large-scale data set, and along with the increase of a training corpus, the performance advantages of the method become more and more obvious.

The invention discloses a false information processing method and device, a storage medium, a product and equipment, and the method comprises the steps: constructing a word graph based on a to-be-detected text, the word graph taking words in the to-be-detected text as nodes, and taking semantic association between the words as edges; extracting multi-dimensional heterogeneous features of nodes in the word graph by using a natural language model; performing feature embedding on the nodes in the word graph according to the multi-dimensional heterogeneous features of the nodes to obtain feature embedding representation of the word graph; inputting the feature embedded representation of the word graph into a graph neural network model for false information detection to obtain a detection result; and detecting the misleading degree of the misleading effect of the nodes in the word graph on the detection result by using a mask mechanism to obtain a word misleading ranking result. According to the method, false information can be efficiently and accurately detected, higher interpretability is achieved, the detection result is more transparent and credible, and the requirements of field experts and common users for interpretability can be met at the same time.

The application discloses a keyword extraction method based on statistical features and word graphs for single Chinese text, which comprises the steps of text preprocessing, calculating features of each word, calculating comprehensive scores of each word, sorting and filtering. The features of the word include word frequency features, position features, distribution span features, sentence frequency features, special word features and word graph scores. The application obtains accurate keyword extraction results and keyword scores with distinction based on statistical features and word graph information. The application has the following advantages: suitable for single Chinese text; lightweight, no model training and additional corpus; widely suitable for texts in different fields.

The invention relates to an ICLextRank dense point word extraction method based on fused semantics. The method comprises the following steps of text preprocessing, word graph construction, multi-feature fusion calculation and dense point word generation. The method comprises the following steps: firstly, performing sentence division, word segmentation, stop word removal and part-of-speech screening on an original document; secondly, constructing a word graph model based on a word co-occurrence relationship; then, the word features, the center features and the semantic features of the candidate words are synthesized for scoring, and text semantic vectors are extracted from the semantic features through a DistilBERT model and calculated through cosine similarity; and finally, sorting the candidate words according to the comprehensive score and outputting Top-K dense point words. According to the method, through combination of semantic fusion and centrality analysis, the accuracy and the intelligent level of dense point extraction are improved, and automatic auxiliary support is provided for electronic document secret setting.