28 results about "Sequence annotation" patented technology

The invention relates to the technical field of nuclear power equipment quality management and control, in particular to a nuclear power unit quality defect source analysis and total value chain tracing method, which comprises the following steps: S01, collecting total value chain multi-modal data including structured data, logs, texts and sensor time sequence data, and carrying out BIO labeling, BERT coding, BiGRU-Attention feature extraction and CRF sequence labeling; constructing a mixed storage data resource pool; s02, mining association rules by adopting a dynamic pruning improved Apriori algorithm, processing sample imbalance in combination with chi-square test and an NSGAII algorithm, and analyzing defect causes; s03, a dynamic knowledge graph containing multiple types of nodes, relations and threshold attributes is constructed, and rapid defect tracing is achieved through entity linking and probability path searching; the objective of the invention is to solve the problems of difficulty in defect source calibration, low tracing efficiency and the like in nuclear power equipment quality control.

The invention discloses a bidirectional reversible conversion method and system between a peptide molecule SMILES and a sequence expression. The core innovation lies in that a new sequence description syntax is defined to retain information of a polypeptide special bond and specific modification of amino acid; a main chain atom index and adjacency traversal topology identification algorithm is adopted, and end group and topology integrated detection and coding are carried out; a residue recognition algorithm for main chain cutting and template library matching is compatible with any standard or non-standard amino acid residues, an extensible end group library / monomer template library and an automatic increment mechanism, and automatic recognition and sequence annotation of S-S disulfide bonds; the invention relates to a high-fidelity assembly algorithm of HELM anchor points and topology aware cyclic peptide processing. The method solves the problems of incapability of supporting a complex polypeptide topological structure, poor reversibility, insufficient expansibility of a monomer library and the like in the prior art, can be widely applied to scenes of quantitative structure-activity relationship model construction, large-scale polypeptide data cleaning and the like, and has remarkable practicability and innovativeness.

The invention provides a periodical knowledge graph construction method, a periodical knowledge question-answering method and a periodical knowledge graph construction device. The periodical knowledge graph construction method comprises the following steps: performing sequence labeling method knowledge extraction on an obtained periodical text to be processed to obtain a knowledge labeling sequence; performing vocabulary network strategy entity alignment on the knowledge labeling sequence to obtain an aligned knowledge sequence, performing priority strategy entity disambiguation on the aligned knowledge sequence to obtain a disambiguation knowledge sequence, and performing knowledge reasoning completion on the disambiguation knowledge sequence to obtain integrated journal knowledge; and performing knowledge graph construction according to the integrated periodical knowledge to obtain a periodical knowledge graph. Primary knowledge extraction is carried out through a sequence labeling method, knowledge entities of different data sources are aligned through a vocabulary network strategy, periodical knowledge of different sources can be effectively integrated, ambiguous content between entities is eliminated through priority strategy entity disambiguation, missing values and blank values are complemented through knowledge reasoning, the knowledge content can be effectively verified, and the accuracy of the periodical knowledge is improved. Therefore, the data quality of the periodical knowledge graph is improved.

The invention discloses a few-sample triple extraction method and system, computer equipment and a storage medium, and the method comprises the steps: obtaining a support set sample and a query set sample through a basic data set, and generating an embedded vector representation of each sentence in the support set sample and the query set sample through a pre-trained language model; integrating the relationship semantic information between the entities through an attention mechanism to form enhanced relationship semantic information; carrying out average processing on the embedded vector representation of the support set sample to obtain an initial prototype, and constructing an enhanced prototype in combination with the relationship semantic information; performing similarity comparison on sentences in the query set and the enhanced prototypes to realize extraction and classification of relationships; and determining the position of each lexical item in the sentence based on a sequence labeling strategy and a model-independent meta-learning algorithm, and combining the recognized head entity, relation and tail entity to form a complete triple. According to the method, the prototype network algorithm and the model-independent meta-learning algorithm are combined, so that the triple generation quality can be improved.

The invention relates to an access control strategy automatic generation system and method based on multi-task learning, and the method comprises the steps: carrying out the word segmentation, cleaning and embedded vector conversion of an original access control text through a data preprocessing module, and constructing a normative input format; the feature sharing layer module is used for extracting deep semantic features of a text through multi-layer bidirectional coding and an attention mechanism and providing unified representation for downstream tasks; the access control statement identification module is used for judging whether each sentence in the text is an access control statement or not and realizing automatic identification of strategy related contents; and the attribute extraction and annotation module is used for annotating words in the access control statements and extracting subject, object and operation access control attributes. A word coding layer and a sentence coding layer are shared, local and global attention mechanisms are combined, key information of a text is extracted, the semantic understanding ability is enhanced, and cooperative training of statement recognition and attribute extraction is achieved; a conditional random field CRF structure is used for sequence labeling, and the structural rationality of attribute labels is ensured.

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 present invention relates to the technical field of product label extraction, and specifically, to a product label extraction method based on Internet big data and AI large language models. It includes the following steps: S1. Use web crawler technology to capture the text data of products on the Internet; S2. Adopt the TF-IDF algorithm to determine the important words in the text data, and combine the Skip-Gram model to capture the semantic associations between words. In the process of capturing the semantic associations between words, introduce the weight reflecting the user browsing frequency and the user behavior feature vector to optimize the capturing process; S3. Based on the extracted important words and the semantic association information between words, use a large-scale pre-trained language model to generate product labels; S4. Combine the sequence annotation model BERT and the conditional random field CRF to locate and classify the product labels, and output the finally extracted product labels. The technology of the present invention can effectively locate and classify product labels by combining the BERT model and the conditional random field (CRF) layer.

The invention belongs to the technical field of computers, and discloses a script processing method and device, equipment and a readable storage medium, and the method comprises the steps: determining a target code line meeting a preset tracking condition from an original script; inserting an output command for outputting a line number in front of a target code line of the original script to obtain a test script; executing the test script to obtain execution process information, and sequentially extracting line numbers output in the execution process from the execution process information to obtain a line number sequence; and inserting the execution sequence number annotation behind the target code line of the original script by utilizing the line number sequence to obtain a marked script with an execution sequence annotation. According to the method and the device, the marked script with the execution sequence annotation can be obtained, identification, analysis and correction of logic or grammar errors in a program can be assisted, and real and reliable execution sequence information is provided for script debugging.

Provided are a difference quantification comparison method for an adaptive immune system, and the use thereof. The method comprises obtaining at least one of a BCR heavy chain sequence of a B cell, a BCR light chain sequence of the B cell and a TCR β chain sequence of a T cell of a sample to undergo comparison, and sequencing same; comparing the determined sequence with a gene sequence in the IMGT database to obtain sequence annotation information of the corresponding sequence, and further constructing a 3D graph displaying the adaptive immune condition of the sequence; then by means of using a minimum transformation cost method, quantifying an immune state difference between samples to be tested and between a sample to be tested and the database that has undergone the test. The method for quantifying immune differences can be used for evaluating the immune state of biological samples, and can also be used for evaluating influences of various therapy and intervention methods on the immune system, so as to judge the effects of the therapies and interventions, including but not limited to the drug efficacy, the vaccine efficacy, etc.

The present application relates to the technical field of bid evaluation system, in particular to a bid document structured information extraction and intelligent bid evaluation integrated system, which comprises a rule analysis module, a constraint calculation module, a field construction module, an element integration module and a consistency verification module.In the present application, semantic boundary recognition and sequence annotation are performed on the scoring clause text to make the scoring condition expression structured and analyzable, a constraint parameter strength analysis is introduced to form a weight sequence, different conditions are presented with a distinguishing degree in the review, the bid document field comparison is focused on high correlation content, and the element correlation relationship is constructed in combination with the paragraph and chapter position information, the consistency and conflict review is carried out at the bid evaluation element level, the redundant field influence is compressed, the scoring basis integrity and logical coherence are enhanced, the review process expression is clearer, and the result formation path is more checkable and stable.

The present invention discloses a sequence annotation method for unstructured railway knowledge entities. First, a function and interface for importing TXT / JSON format files are constructed; then, a mode selection interface and guiding buttons are designed; next, according to common annotation methods, BIO and BIOES annotation functions and interfaces are designed, and a custom tag function mode and related interfaces and buttons are constructed; a railway professional vocabulary database is constructed; sequence annotation is completed through entity retrieval and classification, and a railway pure corpus database is constructed; the number of display fields and entities is statistically shown; and the export of TXT / JSON annotation sequence files is designed. The present invention can provide accurate and large amounts of unstructured annotation data for natural language processing technologies in the railway field, collect pure unstructured corpus texts for railway entity annotation, and lay a foundation for constructing an intelligent railway knowledge graph.

The invention discloses a text recognition method based on sequence recognition and a related device, and the method comprises the steps: obtaining a target image, carrying out the feature sequence extraction of the target image through a deep convolutional neural network model, obtaining n feature sequences (n is an integer greater than 1), labeling each feature sequence in the n feature sequences, and obtaining n sequence labels through the recurrent neural network model, transcribing the n sequence labels through the recurrent neural network model to obtain a target label sequence, and determining a target text based on the target label sequence. By adopting the embodiment of the invention, the text recognition efficiency is improved.

The present invention relates to a method for ancient Chinese character image recognition and semantic parsing. First, an original image containing irregular deformation and material diversity is obtained from the surface of a cultural relic. Noise and light interference are eliminated through adaptive filtering. The main inclination angle is then calculated based on the distribution of stroke features, and inclination correction is performed to obtain a processed image. A region growing algorithm based on stroke features is then used to separate independent characters, and a deep convolutional network is used to extract feature vectors for recognition. Finally, a conditional random field algorithm is used to optimize sequence annotations based on contextual information from an ancient Chinese character corpus to obtain semantic output. If the result is unsatisfactory, the inclination correction parameters are adjusted retroactively and iteratively optimized to improve overall recognition accuracy. This method can effectively address the problems of irregular deformation and material diversity in ancient Chinese character images, improving recognition accuracy and semantic parsing reliability.

The present invention discloses a sequence annotation method and system enhanced based on a dynamic knowledge graph. The method includes: S1. Mining basic attribute information and related entity information from text information with sparse basic attributes and missing attributes to construct a knowledge graph; S2. Mapping each Token of the input sequence to an entity node of the knowledge graph and extracting a local subgraph; S3. Performing feature extraction through a graph convolutional network to obtain the entity embedding features of each Token; S4. Fusing the original features of each Token with the entity embedding features; S5. Inputting the fused features of each Token into a BiLSTM model to obtain the output features of the input sequence; S6. Inputting the output features of the input sequence into a CRF model to obtain the final comprehensive features of the input sequence. The present invention introduces a GCN model on the basis of BiLSTM and CRF to generate knowledge graph-based features, and fuses the original input features and the features generated by GCN, achieving better performance in sequence annotation in text with sparse basic attributes and missing attributes.

The present invention discloses a sequence annotation data augmentation method, device, equipment and medium based on adversarial interpolation. The method includes: obtaining first sample data containing sequence annotations; inputting the first sample data into a preset language model to output candidate word vectors that conform to the context semantic constraints, and forming enhanced second sample data according to the candidate word vectors; using the method of adversarial interpolation to interpolate the first sample data and the second sample data to obtain interpolated enhanced sample data. According to the sequence annotation data augmentation method provided by the embodiments of the present disclosure, a language model is used to provide candidate word vectors that conform to the context constraints, and adversarial interpolation is used to consider the task characteristics, so as to generate more difficult samples that are likely to cause misjudgment by machine learning algorithms, improve the effect of the sequence model under low resources, and solve the problem that the lack of labeled data affects the accuracy of the model.

The invention discloses a method for constructing a metagenomic functional annotation correction model, relates to the technical field of metagenomic functional annotation, and discloses the following steps: step 1: dividing a reference amino acid sequence of known function according to the types of front-end deletion, back-end deletion, and double-end deletion; step 2: using an HMMsearch tool to import an incomplete amino acid sequence set into an HMM functional annotation model to be corrected for annotation, and obtaining scores, domain coverage, and sequence coverage results corresponding to the sequences; step 3: inputting four factors, namely, scores, domain coverage, sequence coverage results, and amino acid sequence deletion types, in the HMMsearch annotation results into a machine learning model as features, and taking whether the function of the reference amino acid is the same as that of the model as a category, performing model training, and finally obtaining a correction model of the HMM model for the incomplete amino acid sequence annotation results.

The invention discloses a semantic generation method and device, equipment, a medium and a product. The method comprises the steps that a labeled sentence pattern set corresponding to a text corpus of a vehicle-mounted service is generated through a sequence labeling model; constructing tree structures of all sentence patterns in the labeled sentence pattern set to obtain all tree structures corresponding to the labeled sentence pattern set; and combining all the tree structures based on the editing distance to obtain corpus semantics of the text corpus, and if the corpus semantics do not meet a preset condition, correcting the corpus semantics to obtain corrected corpus semantics. The annotated sentence pattern set corresponding to the text corpus of the vehicle-mounted service is generated through the sequence annotation model, the annotation efficiency is improved, and the sentence patterns are clearly presented by constructing the tree structures of all the sentence patterns in the annotated sentence pattern set, so that all the tree structures are conveniently combined through the editing distance, the combined tree structures are more accurate, and the annotation efficiency is improved. And thus, the obtained corpus semantics are more accurate.

The embodiments of the present application disclose an image processing method, apparatus, computer equipment, and storage medium. The image processing method includes: obtaining an image to be identified, performing character recognition processing on the image to be identified, and obtaining a recognition result; wherein the recognition result includes a recognized data sequence, and the data sequence includes one or more of a character sequence, an image sequence, and a position sequence; performing sequence annotation processing on the data sequence based on a multimodal feature sequence of the data sequence to obtain a structured category of each data in the data sequence; and creating a structured document corresponding to the image to be identified based on the data sequence and the structured category of each data in the data sequence. By adopting this application, the efficiency and accuracy of converting images into structured documents can be improved.

The invention discloses a method and equipment for constructing a bar code gene database for eDNA analysis and a medium, and belongs to the technical field of gene database construction. According to the method, a standardized preprocessing process is deployed for each data source, and a taxonomy mapping system based on same-object different-name analysis and multi-level backtracking inference is combined, so that the sequence annotation success rate and integration efficiency of the heterogeneous data sources are improved, high fault-tolerant analysis of non-standard and incomplete taxonomy names is realized, and data waste is reduced. Meanwhile, taxonomy information synchronous updating and traceability checking are constructed, batch optimization and correction of historical data are supported while the quality of newly added data is guaranteed, and long-term accuracy and scientificity of a database are guaranteed.

The application discloses an application method of a sequence search tool CircBLAST considering gene sequence evolution rearrangement, and belongs to the technical field of bioinformatics. The method flow comprises the following steps: firstly, all protein sequences are cut according to the length of a required word_size, a data set is constructed in combination with sequence annotation data, and is written into a database; then, a request sequence is prepared, and is cut into small fragments of word_size; further, a search matching, construction of a circular sequence and sequence alignment are carried out to complete a retrieval process; finally, an alignment result containing matching fragments, a similarity score and the like information is generated, is used for presenting to a user for viewing and judging the reliability of matching. The application considers the evolution rearrangement of gene sequences, significantly improves the accuracy of sequence alignment, and can find more reordered sequences.

The application discloses a bidirectional reversible conversion method and system between peptide molecules SMILES and sequence expressions, and the core innovation is that: a new sequence description grammar is defined to retain the information of special bonds of polypeptides and specific modifications of amino acids; a topological identification algorithm of main chain atom index and adjacency traversal, end group and topological integration detection and coding; a residue identification algorithm compatible with any standard or non-standard amino acid residue of main chain cutting and template library matching, an expandable end group library / monomer template library and an automatic increment mechanism, automatic identification and sequence annotation of S-S disulfide bond; a high-fidelity assembly algorithm of HELM anchor points and topologically-aware cyclic peptide processing. The application solves the problems that the prior art cannot support complex polypeptide topological structure, has poor reversibility, and has insufficient monomer library expansion, and can be widely applied to quantitative structure-activity relationship model construction, large-scale polypeptide data cleaning and other scenes, and has obvious practicability and innovation.

Disclosed is a method for training an entity recognition model, including: constructing a training set; and inputting the training samples in the training set into the entity recognition model to obtain the sequence annotation prediction output and the entity matching prediction output of the sentences in the training samples, determining the sequence annotation loss of the sentences based on the sequence annotation prediction output of the sentences and the sequence annotation labels of the sentences; determining the entity matching loss of the sentences at least partially based on the entity matching prediction output of the sentences and the metaphor entity labels of the sentences; determining the total loss of the entity recognition model, where the total loss is the weighted sum of the sequence annotation loss and the entity matching loss; and iteratively performing training to minimize the total loss of the entity recognition model, so as to obtain a trained entity recognition model. This application also relates to corresponding entity recognition methods and related systems, devices and media. This solution can comprehensively and efficiently identify the entities of interest including metaphor entities.

The present invention discloses a method for entity recognition based on meta-learning. First, meta-training data and meta-testing data are prepared, and a sequence annotation model for entity recognition is constructed. The meta-training data is then input into the model, and the loss value is returned to obtain new model parameters and saved. The meta-testing data and the new model parameters are input into the model, and the adjusted model parameters obtained by returning the loss value are used to update the sequence annotation model parameters to complete a round of training. The training is continued until a preset number of cycles is reached, and a meta-model is obtained. Finally, the trained meta-model is used to train on the target domain. After the training is completed, the final model is obtained, and the final model is used to predict and identify unlabeled sample data in the target domain. The present invention is used for entity recognition with a small number of labeled samples. By training on a source domain corpus with a certain amount of labeled samples, a higher accuracy rate can be achieved when training on a target domain corpus with a small number of labeled samples.

The present invention discloses a sentence-level relation extraction method and device based on deep feature fusion, the method comprising: obtaining the semantic features corresponding to each term based on the Bert pre-trained language model; combining the semantic features to obtain the correlation matrix L between terms calculated by the attention mechanism under the relation m; m ; Based on the incidence matrix L m , predict the association matrix A between terms under relationship m m ; Based on the incidence matrix L m Combined with semantic features, calculate the object features of the word as the subject element and the subject features as the object element; splice the semantic features with the object features and the subject features respectively; perform sequence annotation on the splicing results to obtain the subject annotation features and object annotation features of the corresponding word under the relationship m to determine whether the word is a subject entity, object entity or non-entity; based on the subject entity, object entity and association matrix A in the sentence m , and obtain the relationship triple under relationship m. The present invention can solve the problem of overlapping relationships among SEO, EPO, and SOO.

The present application relates to the technical field of natural language processing, and provides a method, apparatus, computer device, and storage medium for determining text labels. The method includes: obtaining a spliced text, where the spliced text includes the spliced candidate labels and the target text; encoding each single character in the spliced text to obtain a word vector corresponding to each single character; using an attention mechanism to interact with each single character according to the word vector to obtain a feature vector corresponding to each single character in the candidate label; performing sequence annotation classification on each single character in the candidate label according to the feature vector to obtain a sequence annotation result corresponding to each single character in the candidate label; and determining a target label corresponding to the target text according to the sequence annotation result. Using this method can improve the accuracy of text label determination.

This invention proposes an event argument detection method and system based on label sequence consistency modeling. It mainly includes word sequence semantic encoding, word label sequence annotation, error-prone label sequence generation, and contrastive learning regularization. Word sequence semantic encoding uses BERT and a trained language model to learn semantic representations of preprocessed words, incorporating event type information into the representation vector. Word label sequence annotation uses a fully connected network to predict the probability distribution of the label corresponding to each word. Error-prone label sequence generation generates error-prone label sequences according to a certain strategy based on the probability distribution of the word label sequences. Contrastive learning regularization constructs a regularization loss based on the contrastive learning between error-prone label sequences and correct label sequences, improving the consistency of word sequence labels.

The present invention belongs to the technical field of information extraction, and particularly relates to a single-stage joint entity relation extraction method and system based on an enhanced sequence annotation strategy. First, an entity relation extraction model is constructed and trained. The entity relation extraction model includes an encoder for encoding an input text sequence to output a corresponding word vector representation, a labeling component and an entity correlation matrix for performing label mapping on the word vector representation, and a decoder for decoding the label mapping result to extract relevant entity relation triples. In label mapping, the labeling component is used to label the word vector representation with a combined label composed of an entity position, the position of a word in the entity, and a relation type, and the entity correlation matrix is used to enhance the information interaction between the combined labels. Then, the target text sequence to be extracted is input into the trained entity relation extraction model, and the trained entity relation extraction model is used to output the relevant entity triples of the target text sequence, improving the relation entity extraction effect.

This application discloses an interaction method, interaction apparatus, smart device, and computer-readable storage medium. The method comprises: obtaining a user statement; processing the user statement based on sequence annotation to obtain the control intent of the user statement and the corresponding word slot for each control intent; and providing feedback on the user statement based on the control intent and the word slot to achieve interaction with the user. This application solution can improve the recognition accuracy of user statements by smart devices, enabling good interaction between the smart device and the user.