25 results about "Conditional random field" patented technology

This invention relates to the field of named entity recognition technology, and discloses a multimodal named entity recognition method and apparatus based on deep interaction of text and image features. The method includes: acquiring original text and an original image; extracting multimodal features from the original text and the original image respectively to obtain a text feature sequence and an image feature sequence fused with multi-scale features; performing cross-modal deep interaction fusion on the text feature sequence and the image feature sequence to obtain an interacted multimodal feature sequence; performing context-aware adaptive gating fusion on the interacted multimodal feature sequence to obtain a fused feature sequence; and performing conditional random field sequence decoding on the fused feature sequence to obtain an entity label sequence. This invention achieves deep bidirectional interaction and dynamic adaptive fusion of multimodal information, effectively solving the text ambiguity problem and improving the accuracy of named entity recognition.

The application provides a metadata intelligent identification method and device based on semi-supervised learning, and the method comprises the following steps: generating a metadata keyword identifier according to a conditional random field, wherein the metadata keyword identifier is used for extracting metadata features corresponding to any identification; acquiring an initial labeled data set, training the metadata keyword identifier according to the initial labeled data set to generate a metadata classifier; acquiring an unlabeled data set, predicting the unlabeled data set according to the metadata classifier to generate a prediction result; generating an intermediate training data set according to the prediction result; cyclically self-training the metadata keyword identifier and the metadata classifier according to the intermediate training data set to obtain a cyclically self-trained metadata classifier; and identifying metadata intelligently according to the cyclically self-trained metadata classifier. Through the application, the problem of low metadata identification construction efficiency in the related art is solved.

Embodiments of the present application provide a sensitive entity recognition model training method, a sensitive entity recognition method, a computing device, a computer readable storage medium and a computer program product. The sensitive entity recognition model training method comprises: performing word segmentation processing on unstructured text and generating a sample label sequence based on a preset rule annotation; inputting a word segmentation sequence into a bidirectional encoding layer to generate a semantic vector, so as to determine an emission score of each label corresponding to the word segmentation; inputting the emission score into a conditional random field layer to obtain a transition score between adjacent labels, and combining the emission score and the transition score to determine a joint probability of each label corresponding to the word segmentation sequence; outputting a predicted label sequence based on the joint probability; and finally training the bidirectional encoding layer and the conditional random field layer with the objective of minimizing the difference between the sample and the predicted label sequence. The technical solution provided by the embodiments of the present application realizes accurate sensitive entity recognition.

The application discloses a network security vulnerability knowledge graph construction method based on HPO-BiLSTM-CRF, which comprises the following steps: collecting public vulnerability data from related databases in the network space security field, preprocessing, and constructing a data set; analyzing and extracting existing data source feature information, and constructing a network security vulnerability domain ontology model CSVDO; based on the optimized bidirectional long short-term memory network and the conditional random field fusion model HPO-BiLSTM-CRF, realizing named entity recognition and relationship extraction; adopting an integrated entity alignment method for knowledge fusion, matching different instances of the same object in different ontologies based on an improved similarity measurement algorithm, and constructing a knowledge graph; carrying out knowledge graph embedding, storing the result into a graph database, and completing knowledge graph construction and graphic visualization. The application can improve the efficiency of entity recognition and relationship extraction in network security vulnerability knowledge, and has the advantages of high efficiency and high accuracy compared with other graph construction methods.

The application discloses a rock slope multi-mode instability probability analysis and risk evaluation method based on a borehole constraint condition random field, and belongs to the technical field of geotechnical engineering and engineering geology.The application realizes reasonable expression of spatial heterogeneity of rock mass mechanical parameters by constructing a conditional random field which is strictly consistent with measured data under limited borehole survey data conditions, greatly improves the authenticity of a numerical model and the reliability of analysis results, and effectively overcomes the defects of insufficient result reliability caused by lack of measured constraints in unconditional random fields; the application can identify various instability modes of a rock slope under different parameter space distribution conditions through a large number of multi-sample numerical simulation, quantitatively calculates the occurrence probability of various instability modes, can comprehensively grasp various risks possibly existing in the rock slope, and improves the accuracy and engineering applicability of the rock slope stability analysis and risk evaluation, instead of only focusing on a single most dangerous case.

This invention discloses a time-series segmentation method for hydraulic support action states that integrates physical priors, belonging to the field of intelligent coal mining technology. First, pressure monitoring data of the hydraulic support columns is obtained from the hydraulic support pressure monitoring system database to construct a multi-dimensional feature vector containing poor directionality, and a sample-level undersampling strategy based on the majority class proportion is used to balance the data distribution. Second, a temporal convolutional network model optimized with rare stage recall rate is constructed to output a frame-level probability distribution. Finally, the aggregated action stages are input into a conditional random field model with a frozen physical transition matrix for global logical correction. This invention effectively solves the problems of missed detection and fragmented prediction of key actions under long-tail distribution, and significantly improves the recognition accuracy and logical completeness of rare actions such as initial support and support shifting by eliminating illegal state transitions through physical hard constraints.

This invention relates to a named entity recognition method based on a pre-trained language model and a progressive convolutional network, comprising the following sequential steps: encoding natural language based on the pre-trained language model to obtain a representation set LS; inputting the representation set LS into a progressive convolutional network module, and using the progressive convolutional network module to progressively fuse the encodings of adjacent layers from low to high levels to obtain an aggregated distributed representation AR that integrates the features of all layers of the pre-trained language model. c ;Utilizing the CRF model, i.e., Conditional Random Field, to decode and aggregate distributed representations (AR) c This invention achieves named entity recognition. Instead of introducing external knowledge or operations to enhance entity information and improve named entity recognition accuracy, it focuses on the results obtained using the available computing power. It utilizes the proposed progressive convolutional network module to extract the full-layer representation of the pre-trained language model, overcoming the deficiency of insufficient information mining from the pre-trained language model and reducing the complexity of introducing external data for computation.

This invention relates to a method and system for colorectal cancer MRI image segmentation based on multi-dimensional feature fusion, belonging to the field of medical image processing technology. The invention first collects multi-source data from colorectal cancer patients and preprocesses the data, constructing a multi-scale feature extraction module to obtain image feature data. Then, through a multi-dimensional feature fusion module, it integrates seven dimensions of features: texture, shape, grayscale, modal correlation, lifestyle, functional metabolism, and tissue specificity, combining a spatial-channel attention mechanism to achieve feature selection and weight allocation. Finally, it decodes features using a U-Net network and optimizes the segmentation boundary using a fully connected conditional random field (CRF) with an adaptive potential function. This invention improves the accuracy and robustness of colorectal cancer MRI image segmentation through multi-modal data integration, multi-scale feature extraction, multi-dimensional feature fusion, attention mechanism empowerment, and the combination of U-Net network decoding and CRF post-processing.

This invention discloses an intelligent generation method and system for power project material lists based on multimodal document parsing and knowledge graph semantic mapping, belonging to the fields of artificial intelligence and power engineering. It includes: a first stage of unified parsing and semantic encoding of text documents, engineering drawings, and tabular data to generate a semi-structured raw information set; a second stage of named entity recognition and type labeling of the raw information set based on a bidirectional long short-term memory network and a conditional random field hybrid model to generate a structured entity set; on this basis, a knowledge graph for the power material domain is constructed, a standard key point rule base is established, and semantic mapping and information completion are performed through a multi-level matching mechanism and knowledge reasoning; after quality control, a standardized material list is generated. This invention achieves intelligent and automated generation of power project material lists, improving the accuracy and efficiency of material list generation.

This invention discloses a multi-entity recognition method for Chinese resumes based on a BERT-BiLSTM-CRF joint model, belonging to the field of natural language processing and information extraction technology. The method performs deep semantic encoding on the original resume text using a pre-trained language model and generates offset mapping information. Then, it utilizes a bidirectional long short-term memory network to capture long-distance contextual dependencies in the text, enhancing sequence features. Next, it performs global decoding based on label transfer rules through a conditional random field layer to obtain the optimal word-level entity label sequence. Finally, based on the offset mapping information, the sequence is mapped and merged into a character-level entity recognition result. This invention effectively solves the problems of entity type ambiguity, insufficient capture of long-distance dependencies, and inaccurate entity boundary localization in Chinese resume parsing, and can accurately jointly identify multiple key entities in the three modules of educational background, work experience, and job expectations.

The application provides a ground area event identification method and device, and the method comprises the following steps: preprocessing original received event text in a certain professional field; loading a network model to automatically identify a certain area concerned event appearing in the event text in the certain professional field, and storing the identification result in a corresponding professional field event knowledge base; optimizing and training the Bi-LSTM network model according to the knowledge added in the knowledge base, returning to the previous step until no new knowledge is added; in response to the identification result of a dynamic event in a certain area on the ground, automatically extracting events in the event text in the certain professional field by using the optimized network model, and storing the field event in the professional field event knowledge base. The application can more accurately identify a large number of entities related to professional fields, and the conditional random field sequence labeling bias problem constrained by the professional field text entity is properly solved, and the complex feature engineering required by the CRF method can be omitted.

This invention discloses a medical named entity recognition method and apparatus based on context-aware spectral units and multi-scale networks, belonging to the fields of natural language processing and medical information processing technology. The technique first preprocesses the original medical text to obtain a standardized lexical sequence, encodes it using a pre-trained semantic model to obtain a context semantic vector sequence, and then extracts enhanced sequence features through a bidirectional gated recurrent unit network. These features are then input into a multi-scale context feature extraction network containing three parallel feature extraction units. Each unit performs feature projection, relevance calculation, weighted fusion, and bipolar rectification according to different window sizes. After fusing the multi-scale features, the sequence is passed through a fully connected classification layer and a conditional random field decoding layer, combined with the Viterbi algorithm to obtain the optimal named entity label sequence. This technique also constructs a recognition system including modules such as preprocessing, semantic encoding, and multi-scale feature extraction, suitable for named entity recognition of medical texts such as electronic medical records and medical literature.

This invention provides an AI-based method, system, and platform for automatic multi-document parsing. The method includes: acquiring a candidate set of ghost references and performing cyclical sequential joint inference using a conditional random field to obtain a ghost reference set; acquiring four-dimensional feature vectors based on the ghost reference set and the original document, constructing a Bayesian network using these vectors, and obtaining the inference result through inference via the Bayesian network; creating a document heterogeneous graph based on the ghost reference set and the original document, generating aggregated text node vectors through attention aggregation based on multiple edge types, and obtaining community results using a community adversarial strategy; constructing a document dynamic graph based on the community results and temporal data, obtaining hidden states by processing the temporal and spatial dimensions of the document dynamic graph, and outputting the parsing result. This method uses ghost references as a unified analytical clue and central feature to construct a multi-dimensional joint evaluation intelligent parsing framework to improve the depth of document parsing.

This invention belongs to the field of astronomical image processing, specifically relating to a sub-pixel localization and detection method and system for celestial objects based on conditional random fields (CRFs). It aims to address the problems of low recall and insufficient localization accuracy of existing detection heads for faint celestial objects. The invention includes: acquiring multi-scale feature maps; generating a target center saliency heatmap and an initial foreground mask; inputting these three into a CRF framework for collaborative optimization, using the initial foreground mask to construct a univariate potential energy and the pixel relationship graph to construct a binary potential energy, iteratively updating the foreground confidence probability and the sub-pixel offset pointing to the target center, and outputting the optimized foreground mask and offset field; fusing to generate the detection bounding box and sub-pixel-level center coordinates of the celestial object. This invention significantly improves the robustness of detection and sub-pixel-level localization accuracy for faint celestial objects by collaboratively optimizing foreground segmentation and offset regression through structured probabilistic inference.

In order to obtain demand group financial information with high commercial value in group financial information, the application discloses an algorithm model for demand prediction of group financial information. BiLSTM (bidirectional long short-term memory neural network) and CRF (conditional random field) are used to extract feature words of group financial information, so that the group financial information is preliminarily processed, the feature words are obtained, the duplicate operation is performed to obtain the features of the training GBDT (gradient boosting decision tree) algorithm model, the word frequency digital vector is generated according to the word frequency of the feature words of the group financial information and the features of the GBDT algorithm model, the obtained word frequency digital vector is the training data of the training GBDT algorithm model, the GBDT algorithm model is trained in combination with the labeling of the classification result, and the demand prediction of the group financial information is performed by using the trained GBDT algorithm model. Through experiments, it can be obtained that the accuracy rate of demand prediction of the method reaches 87.3%.

Disclosed in the present invention is a rapid construction method for a knowledge graph of railway bridge design standards, comprising: S1, acquiring data and preprocessing same; and S2, using a BERT pre-training model and a Bi-LSTM model to convert a text sequence in the processed data into an annotated tag sequence, i.e., {y1,y2…yn}; (S3) using conditional random field (CRF) and graph neural network (GNN) technology to identify and annotate an entity, an attribute, and a relationship thereof to form a node and an edge of a knowledge graph, so as to obtain a complete knowledge graph (KG); and (S4) using a dynamic topology optimization algorithm to adjust a structure of the complete knowledge graph (KG) in real time. The method rapidly integrates and optimizes design standard data, reduces data redundancy, and effectively processes data additions and changes, thereby improving knowledge graph construction speed and maintenance efficiency.

This invention discloses a keyword search intent analysis method and system based on GEO, relating to the field of search engine optimization technology. The method includes: constructing an initial clustering structure; extracting locally anomalous node regions based on the local sparse distribution characteristics of semantic matching relationships between nodes and keywords in the initial clustering structure; reconstructing semantic paths between nodes based on the asymmetric topological characteristics of the contextual paths between nodes within the locally anomalous node regions, forming an optimized candidate semantic path set; and determining the subdivided search intent corresponding to the target keyword by combining the non-stationary topological characteristics of the state transition topology of the contextual sequences in the candidate semantic path set and using path state inference from a conditional random field model. This invention achieves the parsing of the multi-contextual semantic structure of search keywords, which is beneficial for the subdivided identification of search intent in a generative engine optimization environment.

This invention relates to a vertebral classification system and method for X-ray films based on segmentation-guided coding. The system employs a prompt information collector to acquire prompt information displaying prompt boxes and points. A segmentation coding device extracts features from the spinal X-ray image and simultaneously segments the vertebral regions based on the prompt information, generating shape and spatial location information for each vertebra, which is then encoded as positional embedding features for image enhancement during the fusion process. The segmentation coding device further fuses the image feature representations and positional embedding features using an attention-weighted approach to obtain a fused image feature sequence, promoting semantic alignment and image enhancement. Finally, a vertebral classification device calculates the image-text feature similarity score between the fused image feature sequence and the vertebral category list. This similarity score is then applied to the multilevel conditional random field (MLF) algorithm to obtain the vertebral classification results for the X-ray film.

The application discloses a message content extraction method and device, computer equipment and a storage medium, and relates to the technical field of big data. First, the message to be audited is converted into a keyword vector through keyword extraction and vector conversion. Then, a pre-trained domain classification model is used to classify the keyword vector by domain, and the business domain to which the message belongs is determined. According to the domain classification result, a matching target business domain knowledge graph is selected, and a vector representation thereof is generated. Next, in combination with the vector representation, a preset long short-term memory network model is used to perform semantic coding on the message to generate a semantic representation vector. Finally, based on the semantic representation vector, a conditional random field model is used to accurately identify key entities, attributes and relationships in the message. The application also relates to the technical field of blockchains, and the message to be audited is stored on a blockchain node. The application improves the accuracy and efficiency of message content extraction, and can automatically identify key entities, attributes and relationships.

The application discloses a power transmission line text named entity recognition method and system based on a GRTCN network. In view of the problems of semantic ambiguity and entity boundary ambiguity caused by flexible expression, non-standardized terms and strong context dependence in power transmission line construction text, a double-channel parallel architecture containing a bidirectional long short-term memory network and a gated residual time convolution network is constructed, wherein the gated residual time convolution network dynamically screens key context features through a gating mechanism and captures long-range dependence by combining a residual time convolution; a double-affine attention mechanism is further introduced to realize deep interaction and adaptive calibration of double-channel heterogeneous features, and finally, global structured prediction is performed through a conditional random field. The application can significantly improve the robustness to term variants and dynamic context, and provides reliable technical support for power transmission construction knowledge base construction.

Embodiments of the present disclosure provide a text similarity matching method and device, equipment, medium and program product, relating to the technical field of computer. The method comprises: obtaining a first text and a second text; on the one hand, a syntax analyzer is used to mark the syntax attribute of each word segmentation, and then the semantic similarity between the two texts is calculated; on the other hand, a conditional random field is used to mark the key label of each word segmentation, and then the key similarity between the two texts is calculated; according to the comparison of the key similarity and the fusion threshold, the first fusion weight and the second fusion weight are determined; based on the first fusion weight, the second fusion weight, the semantic similarity and the key similarity, the similarity between the first text and the second text is calculated. The method separates the calculation of semantic similarity and key similarity, solves the misjudgment problem caused by confusing sentence structure and entity semantics, and improves the robustness and accuracy of text similarity matching in complex business scenarios.

The application provides an event causal relationship detection method fusing part-of-speech and dependency relationship features, converts a causal relationship detection task into a sequence labeling task at a short text level, generates an initial word embedding vector by using a pre-trained RoBERTa model, adds part-of-speech features to the word embedding vector to enhance the feature representation of a word, converts event text with a causal relationship into a representation of a dependency directed graph, and uses the dependency relationship between words as an edge feature of the dependency directed graph, improves an edge feature graph attention network model and a learning process, and combines the word embedding vector with the part-of-speech features and the graph embedding vector into a linear layer and a conditional random field to obtain a final causal relationship detection result. The application fuses part-of-speech and dependency relationship features in the event causal relationship detection task, and enhances the semantic representation of a causal sentence in the event causal relationship detection task.

This application discloses a method, apparatus, and electronic device for marking fingering in piano sheet music, relating to the field of piano technology, and invented to improve the effect of fingering marking. The method includes: determining the position of the key corresponding to each marking unit on the piano and whether the corresponding key is a black or white key; determining the distance between the key corresponding to each marking unit in the sheet music and the key corresponding to the previous marking unit; obtaining a first feature vector based on the pitch of each marking unit, the position of the corresponding key on the piano, whether the corresponding key is a black or white key, and a first network layer in a preset fingering generation model; obtaining a second feature vector based on the first feature vector, the distance between the key corresponding to each marking unit and the key corresponding to the previous marking unit, and a second network layer in the preset fingering generation model; and using the second feature vector as input to a conditional random field in the preset fingering generation model to obtain the fingering sequence for each marking unit.

The present application relates to the technical field of data privacy protection, in particular to a privacy protection method and system for unstructured teacher comment text. The present application comprises text preprocessing and pre-training model labeling to generate candidate labels; vectorization and semantic encoding to extract context dependence; generating comment level representation, enhancing and constraining output feature sequence through role perception; bidirectional LSTM modeling time sequence, fusing pre and post context information; conditional random field decoding, introducing context constraint to modulate label transition, outputting entity labels; judging and evaluating behavior based on enhanced features, reconstructing state and checking, mapping to desensitized text, and outputting after consistency check. The present application can identify sensitive evaluation content of teacher comments in a complex semantic environment, and can balance the integrity of educational evaluation during privacy protection to adapt to the actual needs of safe processing of teacher comments in the educational informationization scene.