174 results about "Document level" patented technology

A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.

A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.

The invention discloses a SysML model automatic generation system based on mixed AI and domain knowledge, and the system comprises a preprocessing module which is used for carrying out the text preprocessing and structural enhancement of an engineering document of a PDF or Word version; the NLP extraction module is used for identifying six types of core entities by adopting aviation corpus fine tuning BERT, constructing a document-level relational graph by utilizing GNN, modeling a cross-paragraph dependency relationship, calling LLM for semantic fuzzy sentences to generate a thinking chain, extracting a reasoning path and solving ambiguity; the rule conversion engine module is used for mapping the entity relation graph into a SysML memory object tree; and the controllable generation module is used for carrying out limited decoding on the LLM by utilizing a Guidance framework. The invention further discloses an automatic SysML model generation method based on the mixed AI and domain knowledge. According to the method, the problems of low manual modeling efficiency and poor semantic consistency in traditional MBSE implementation are solved.

The invention relates to the technical field of document-level relation extraction, and discloses document-level relation extraction and preprocessing integrating an enhanced entity and multi-level representation, aiming at integrating a plurality of mentions and obtaining global representation of the entity, for a document D with the length of L, a given document # imgabs0 # representation, and xt represents a token at a position t (in natural language processing, the document is extracted, and the document is extracted and preprocessed. Token usually refers to a minimum semantic unit in a text, such as a word, a sub-word or a character, is used as a marking entity, a special mark * is used for marking the starting position and the ending position of the entity, and a context embedding vector H of a document D is obtained through a pre-trained BERT model. According to the document-level relation extraction of the fusion enhanced entity and the multi-level representation, the proposed MFDRE provides an effective solution for the long-distance dependence problem in the DocRE, the MFDRE obtains the global representation of the entity in the document by using a pre-training language model BERT, the local representation of the fusion entity pair and the supplementary representation of the entity pair under span expansion are fused, and the representation capability of the entity node is remarkably improved.

A system and method for generating question-answer pairs is disclosed. The system and method can receive a document. A sentence and / or a further sentence in the document may be identified. A syntactic map for the sentence and / or the further sentence may be generated. Noun phrases and prepositional phrases may be identified based on the syntactic map. Sentence level questions may be generated based on phrases identified using natural language processing (NLP) techniques. Document level questions can also be generated based on syntactic maps generated and NLP techniques.

The invention discloses a hierarchical retrieval enhancement generation method and system. The method comprises the following steps: determining question information to be retrieved according to a hierarchical retrieval enhancement generation task; performing document-level retrieval on an external knowledge base based on the problem information to obtain a most relevant document set; slicing the most relevant document set according to paragraphs and performing paragraph-level retrieval to obtain a most relevant paragraph set; slicing the most relevant paragraph set according to sentences and performing sentence-level retrieval to obtain a most relevant sentence set; performing fragment generation operation on each sentence in the most relevant sentence set by utilizing a sliding window, and then performing fragment-level retrieval to obtain a most relevant fragment set; and carrying out information integration on the most relevant fragment set and knowledge in the model by utilizing a large language model, and carrying out context information supplement by utilizing factual knowledge obtained based on an external knowledge graph to obtain a context answer text of question information. According to the scheme, the accuracy and the reliability of a retrieval result can be remarkably improved.

Systems and methods are disclosed for training an electronic document extraction model, including the generation of the training data to train the model based on sampling a pool of electronic documents based on a rareness metric of the documents. Each electronic document has a document-level rareness metric generated, with the document-level rareness metric being based on one or more of a structural rareness metric or a content rareness metric of the document. The structural rareness metric measures the rareness of the document structure, which may be irrespective of the text content of the document. The content rareness metric measures the rareness of the document content, which may be irrespective of the document structure. The electronic documents are sampled based on the document-level rareness metrics to increase the number of rare documents in the training data without unduly biasing the sampling to optimize the training data for training the extraction model.

The invention discloses an entity linking method and system based on a large language model, and the method comprises the steps: carrying out the enhancement of the context of a given entity reference item in an entity document through a large language model, generating a candidate entity list for the entity reference item, and generating description information for each candidate entity in the candidate entity list; constructing a question and answer task of a single choice question for each entity reference item; constructing a reference graph by utilizing the entity reference items and the candidate entity list to obtain association degrees among the entity reference items; all the entity reference items are sorted, question and answer pairs of the preset number of entity reference items with the highest association degree of the current entity reference items are selected as dialogue contexts according to the sorting result, single choice questions are sequentially input into a large language model for answering, and the entity linking result of each entity reference item is obtained. According to the method, the potential relation between the entity reference items can be effectively captured, and the method is good in performance on the entity link task of the document level.

The invention relates to a document retrieval method and system based on electric power semantic enhancement and electronic equipment, belongs to the technical field of natural language processing, and solves the problem of low retrieval accuracy caused by low complex knowledge utilization rate and insufficient electric power professional semantic understanding in the prior art. Comprising the following steps: receiving user query content, and obtaining a query embedding vector by utilizing a modal joint embedding model; based on the electric power knowledge graph, utilizing a large language model and a text embedding model to obtain a structured query vector of user query content; according to the query embedded vector and the structured query vector, obtaining a plurality of candidate documents and document-level similarity scores and page-level similarity scores thereof, and further obtaining a comprehensive similarity score of each candidate document by using a double-path prediction model; and obtaining a total score according to the document-level similarity score, the page-level similarity score and the comprehensive similarity score of each candidate document, and selecting a plurality of candidate documents with the highest total score as a retrieval result. And the retrieval precision is improved.

The invention provides a document-level relation extraction method based on mixed prompt tuning, which comprises the following steps of: constructing a document-level knowledge graph module by utilizing historical documents, and acquiring and processing entity and relation structure information; a sentence-level semantic retrieval enhancement mechanism is designed, and context information is matched and retrieved based on semantic relevancy; providing a mixed prompt tuning method, and performing efficient parameter fine tuning on the large language model; and finally, aggregating the document-level knowledge graph and sentence-level semantic retrieval to enhance and generate an output result of a SetRAG mechanism, and carrying out document-level relationship prediction. According to the method, the domain knowledge based on the atlas and the semantic knowledge based on retrieval are combined, so that the problems that entities and relation interaction information are difficult to capture and cross-sentence relation reasoning is difficult in existing document-level relation extraction can be effectively solved, and meanwhile, efficient and accurate document-level relation extraction is realized; and the performance of the public test data set is obviously improved.

The invention provides a question and answer pair generation method and system, and the method comprises the steps: constructing a knowledge base according to obtained knowledge data, the knowledge base comprises a text data set of a document level and a text block data set of a unit level, and constructing knowledge maps corresponding to the text data set and the text block data set, the knowledge graph is used for representing relevance among different documents in a data set, the data set comprises the text data set and the text block data set, the documents in the text data set and the text block data set are sampled respectively to obtain sampled documents, and the sampled documents are stored in the text data set and the text block data set; and according to the sampling document and the knowledge graph corresponding to the sampling document, generating a question and answer pair. The richness, comprehensiveness and diversity of automatically generated question and answer pairs are improved.

The invention discloses a document-level relation extraction method based on multi-task learning and knowledge distillation, and the method comprises the steps: obtaining a to-be-extracted document text, inputting the to-be-extracted document text into a trained document-level relation extraction model, and outputting a corresponding document-level text relation; the document-level relation extraction model comprises a feature extraction module, a teacher model and a student model, and the training process of the model comprises the following steps: pre-training by utilizing manually labeled document data through multi-task learning to obtain the teacher model; using a pre-trained teacher model to carry out evidence complementation on the document data of which the evidence information is not labeled; training a student model by using the document data after evidence completion; the trained document-level relation extraction model comprises a feature extraction module and a trained student model. According to the method, the context semantic information in the document can be accurately extracted, the problem of data sparsity is effectively relieved through knowledge distillation, efficient extraction of the document-level relationship is realized, and the performance of the model in a complex context is remarkably improved.

The invention discloses a zero sample document level relation extraction method based on a general large language model, which extracts entity relations in a document level text based on the large language model by establishing a cue word template, reduces the demand for a large amount of annotation data, reduces the cost and time of data preparation, and improves the extraction efficiency. And the relation extraction technology can be more easily applied to the field of data scarcity. According to the embodiment, the process of training through a training sample and parameter tuning is not needed, the result is obtained on the existing large model directly through the cue word, and dependence on the sample is reduced. And meanwhile, the influence of the quality of the labeled text on the extraction result is also avoided. Meanwhile, the relation extraction process can be carried out more quickly, and the model does not need to be trained / finely adjusted, so that the development period is accelerated. The demand of manual intervention is reduced, the labor cost is reduced, and the processing speed is improved. The method can adapt to different document types and fields.

The invention belongs to the technical field of natural language processing, and aims to identify and extract a relationship between entities from a long text so as to solve the problems of insufficient feature expression and inaccurate context information capture of an existing relationship extraction method. According to the method, a document-level relation extraction model based on multi-granularity feature fusion, an axis attention mechanism and evidence enhancement is provided, so that the extraction performance is improved. The model adopts multi-granularity feature fusion, and provides richer context information by combining local fragment features and global semantic features; attention weights in different axial directions are dynamically adjusted through an axial attention mechanism, and the accuracy of relation recognition is improved. Through evidence enhancement, the relationship between entities can be comprehensively understood and judged. The method is suitable for application such as knowledge graph construction, intelligent question and answer and information retrieval, and the performance of relation extraction in the long document can be effectively improved.

A method includes obtaining a hierarchical document structure of a raw document. The hierarchical document structure includes a multitude of sections arranged in a hierarchy of successive document levels. A hierarchical document graph having a graph hierarchical structure corresponding to the hierarchical document structure of the raw document is constructed. A hierarchical document graph corresponding to the raw document matching a user query is retrieved. A hierarchical search is performed on the hierarchical document graph to obtain a set of relevant nodes. A set of relevant content embeddings is retrieved from the set of relevant nodes. A large language model (LLM) generates a response to the user query from the set of relevant content embeddings. The response is presented in a user application.

The invention provides a document level event extraction method and device based on heterogeneous graph interactive learning and public context sensing fusion. The method comprises the following steps: acquiring a to-be-detected document; inputting a to-be-detected document into the trained event extraction model to generate an extraction result; comprising the steps that sentences in an input document and entity mentions extracted from the sentences are coded, and initial representation vectors of the sentences and the entity mentions are generated; constructing a heterogeneous graph of the input document, performing information interaction on nodes in the heterogeneous graph according to the initial representation vectors of the nodes, and generating global representation vectors mentioned by sentences and entities; performing binary classification on each predefined event type according to the global representation vector of the sentence and predicting the occurrence probability of each predefined event type; extracting a public context between any two entities according to the global representation vectors mentioned by all the entities so as to predict an adjacent matrix between any two entities, and extracting an entity combination; and combining and pairing the predicted event type and the extracted entity to generate an event record.

The invention provides a document-level knowledge extraction and fusion method and system based on a large language model, and belongs to the field of industrial robots, and the method comprises the steps: determining a required key information range, and building a keyword dictionary; dividing the document-level unstructured data by paragraphs according to the keyword dictionary to obtain divided sub-documents; building a software system by using an asynchronous architecture of a producer-consumer mode integrated large model, performing a knowledge extraction task on the divided sub-documents in sequence by using the software system, and extracting key information from unstructured data of the sub-documents; integrating and classifying all key information extracted from the same sub-document to obtain regular data, and performing knowledge fusion processing on the regular data; the correlation degree between paragraphs is matched with the keyword dictionary to divide the document, and the contents of the divided sub-documents are highly aggregated, so that the difficulty of processing complex documents by a large model is reduced, a producer-consumer mode is integrated in the large model, the system blockage is avoided, and the concurrent processing capability of the system is improved.

The invention discloses a Chinese long text-oriented hybrid automatic abstract generation method, and relates to the technical field of natural language processing. According to the method, an extraction type abstract method in an unsupervised mode is taken as a first stage, the complexity of a model is reduced, meanwhile, information loss is avoided, and long text content is compressed. Then, a generative abstract module is constructed based on comparative learning, document-level coding representation containing context semantic information is fused into the training process of the model, so that the model effectively guides the generated abstract to be compared with a standard abstract text, irrelevant information is prevented from being generated, and the problem of exposure deviation generally existing in the generative text abstract is solved; and the abstract generation quality is improved while the model complexity is reduced.

The invention discloses a small sample unified granularity relation extraction method based on a large language model, which comprises the following steps of: firstly, giving a specific task description as a part of an input context of the large language model; thirdly, giving an analogous example to the large language model as context demonstration; in order to better prompt the position information of the entity of the large language model in the context, performing entity enhancement on the context input into the large language model; and finally, a mode for serializing the relation triad is defined, and thinking chain reasoning information is fused in the mode, so that a large language model can be helped to perform relation extraction by utilizing thinking chain prompts. According to the method, context learning, thinking chain and entity enhancement technologies are introduced for unified granularity relation extraction tasks including a sentence level, a document level and a cross-document level, the powerful reasoning ability of a large language model is fully played, and the effectiveness of the model in the unified granularity relation extraction task, especially in a small sample scene, is improved.

Systems and methods are provided for generating and training a relation extraction model configured to extract document-level relations. Systems obtain a knowledge database that comprises a plurality of entity tuples and a plurality of relation types, use the knowledge database to generate annotated relation instances based on relation instances that are identified in a set of unlabeled text, generate a training dataset comprising the annotated relation instances and the set of unlabeled text, and generate the machine learning model via modular self-supervision. Systems and methods are also provided for using a relation extraction model to extract document-level relations in specific use scenarios, such as for extracting drug response relations from full-text medical research articles.

The invention provides an end-side adaptive document structure understanding method, which comprises the following steps of: uniformly rendering and normalizing a to-be-analyzed document, and outputting a page-level pixel grid and basic metadata; executing lightweight layout analysis and region classification to obtain a bounding box, a reading sequence and a region type label of each region in the page; each document area is routed to a corresponding special analysis channel for parallel analysis, and each analysis channel outputs a structured intermediate result and confidence; performing consistency verification and completion reasoning on intermediate results output by each channel, and generating a traceable verification evidence chain for low-confidence fragments; all channel results after verification are fused into a unified document-level structured output; and for a new document type or a continuous low-confidence mode, starting an adaptive process of a parameter efficient fine tuning technology to generate a channel-level increment weight packet, and updating model parameters of an analysis channel. The method has the beneficial effect that parallel accurate analysis of different elements such as tables, formulas, texts and the like can be realized.

A global segmenting and analysis service of a provider network may receive documents (e.g., posts, product reviews) from different applications. The service may analyze the documents to identify target entities and sentiment. The service may generate different levels of sentiment data and store data into a segmented database. For example, the service may store within-document level sentiment, document-level sentiment, and multi-document level sentiment for a target entity. The service may also update the entity taxonomy automatically or with only a small number of sample documents. The client may query the service for the segmented sentiment data.

This invention relates to systems and methods for performing double-level ranking of documents. The system implements methods for retrieving documents based on a pre-processed user query to generate a document level ranking of one or more documents that are determined to be relevant. The system implements methods for aggregating one or more sub-topic snippets from the document level ranked documents. The system further implements methods for generating a topic level ranking of the one or more sub-topic snippets. Once topic level ranking of the one or more sub-topic snippets has been performed, the system implements methods for transmitting the topic level ranked one or more sub-topic snippets to a user associated with the user query.

The invention belongs to the field of natural language processing in computer intelligent information processing, and discloses a document level relation extraction method and system based on information gain and prototype comparative learning. The invention provides a document-level relation extraction model based on a graph structure, which considers two aspects of extracting more accurate node features and relieving data imbalance. The problem that an existing document-level relation extraction model generally adopts a graph-based model and faces inherent data imbalance is solved. At present, the problems that noise interference is caused by irrelevant nodes and edges in the node feature updating process, the learning ability of a model to a real relation is insufficient due to too many negative samples in a document, and all different relation types cannot be accurately predicted through multi-label classification exist in research.

Systems and methods for document processing that can process and understand the layout, text size, text style, and multimedia of a document can generate more accurate and informed document representations. The layout of a document paired with text size and style can indicate what portions of a document are possibly more important, and the understanding of that importance can help with understanding of the document. Systems and methods utilizing a hierarchical framework that processes the block-level and the document-level of a document can capitalize on these indicators to generate a better document representation.

The invention discloses a document-level event extraction method based on an interleaving argument association matching algorithm, which relates to the field of natural language processing and comprises the following steps of: performing data enhancement on original data of a document-level event to generate an enhanced training data set; defining event types and argument roles corresponding to the event types, and constructing a structured event template; constructing a prompt template, and performing multi-task optimization on the UIE model in combination with the enhanced training data set; extracting an entity, a trigger word and an argument in the target document, and generating a structured recognition result; and carrying out structure recombination by adopting an interleaving argument association matching algorithm to generate a document-level event extraction result. According to the method, through data enhancement, prompt template construction and an interleaving argument association matching algorithm, the adaptability of the model under the condition of data deficiency is improved, error accumulation is reduced, cross-paragraph argument association is accurately recognized, and the accuracy and integrity of document-level event extraction are remarkably improved.

The invention discloses an event causal identification method and device based on an iterative graph neural network, equipment and a medium, and relates to the technical field of artificial intelligence and machine learning, and the method comprises the steps: carrying out the sentence coding and event extraction of an input text, and obtaining a sentence embedding and event mention result; then, sentence-level embedding and document-level embedding of the event are generated using a multi-granularity context awareness mechanism. Then, constructing an initial event causal graph structure, and encoding the initial event causal graph structure to obtain graph embedding; and finally, dynamically updating an event causal graph structure by combining sentence-level embedding, document-level embedding and graph embedding through an iterative graph optimization mechanism, and realizing accurate identification of the event causal relationship. Through a multi-granularity context perception mechanism and an iterative graph optimization mechanism, local and global context information is effectively integrated, the accuracy and robustness of document-level event causal relationship recognition are improved, and the method is particularly excellent in performance when processing long texts and cross-sentence causal relationships and can better adapt to complex document structures.

The invention discloses a document-level relation extraction data synthesis method based on large model reverse generation, which is characterized in that a knowledge graph sampling method based on random walk is adopted, sub-graphs with coherent themes are sampled from an external knowledge graph, and the sampling probability of triples is dynamically adjusted, so that the knowledge graph sampling efficiency is improved. The method specifically comprises the steps of sampling a triple set from a knowledge graph, dynamically adjusting the sampling probability, performing data enhancement, generating corresponding document data based on the triple set, performing a reflection correction mechanism and the like. Compared with the prior art, the method has the advantages that model training is not needed, the synthetic data is generated only depending on the reasoning ability of a large language model, high accuracy and high recall rate of document-level relation extraction synthetic data labels are ensured, the credibility of the data is improved, a solid foundation is provided for subsequent model training, and the method is worthy of popularization and application. The method not only reduces the labor cost, but also solves the problem that it is difficult to obtain enough high-quality annotation data in the specific fields of education, medical treatment and the like, and has a good application prospect.

A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.

The invention relates to a supply chain document digital management method and system, and the method comprises the steps: obtaining a supply chain document image, and carrying out the element recognition, and obtaining a document element set; judging the ownership state of the receipt element set to generate ownership information; performing receipt identification and storage analysis on the receipt element set based on the ownership information to obtain receipt level information; and storing and recording the receipt element set according to the receipt level information to obtain a secure storage log. According to the invention, the traceability and auditing integrity of the document data can be enhanced.