16 results about "Concept extraction" patented technology

The invention provides a concept-based self-interpretation text classification method and device, and the method comprises the steps: carrying out the text coding of a target text, and obtaining a coding feature; constructing a concept extractor model based on a competitive attention mechanism, extracting concept features by taking the coding features as input, and obtaining a concept attention score of the target text; obtaining a concept intensity feature of the target text based on the concept attention score; and constructing a text classifier model, and performing text classification on the target text through the text classifier model based on the concept strength features. According to the unsupervised text classification method capable of being explained in the process, semantic concepts are automatically extracted by utilizing a competitive attention mechanism, meanwhile, an evaluation framework is designed, the understandability of the extracted concepts is evaluated by utilizing the capability of a large language model, iterative fine tuning is performed on a network by utilizing feedback provided by the large language model, and the classification efficiency is improved. Therefore, the extracted concept is easy to understand by human beings.

The invention discloses an intelligent mining method for dispatching knowledge of a water-wind-light complementary system based on a large language model, which belongs to the technical field of dispatching of the water-wind-light complementary system and comprises the following steps: S1, constructing an ontology model in the field of water-wind-light dispatching according to'demand traction-reuse verification-concept extraction-semantic modeling-formalized implementation '; s2, collecting and processing data; s3, the RoBERTa-BiLSTM-CRF architecture is trained, and entity mining is achieved; s4, realizing relation mining by combining a mixed relation mining method with a three-layer semantic constraint mechanism; s5, performing multi-dimensional fusion on entity semantics; s6, relying on Neo4j graph database storage, combining a man-machine natural language interaction interface of the generative LLM and realizing knowledge base iteration updating. According to the intelligent mining method for the scheduling knowledge of the water-wind-light complementary system based on the large language model, multi-source data collaborative fusion and mining are achieved, and core knowledge support is provided for multi-energy collaborative scheduling and optimization decision making.

The invention discloses a real-time context sensing dynamic cue word generation method based on large model translation. The method comprises the steps of initialization, context sensing and core concept extraction, dynamic cue word generation, new concept recognition and list updating. According to the method, a traditional static translation process is converted into a dynamic process with memory and state maintenance capabilities, a global core concept list is constructed and dynamically maintained in real time, and dynamic cue words containing determined standard translations are automatically generated in the translation process; the global consistency of the translations on core concepts such as term named entities is remarkably improved, the problem that core concept translations are inconsistent in long document translation is fundamentally solved, and the method is suitable for professional fields such as technical documents, academic papers and commercial reports with extremely high term consistency requirements.

The application discloses a new engineering major Chinese knowledge concept extraction method based on a dictionary, and comprises the following steps: 1) obtaining a new engineering related subdivided major, and converting all course teaching materials and syllabuses into text data; 2) using relevant text data to obtain corresponding words through word segmentation processing, and training a word2vec word vector model and an original word vector on the basis; 3) obtaining a large number of relevant course major vocabulary sets through a crawler technology, selecting corresponding major keywords as seeds, inputting the seeds into the trained word2vec model, obtaining words with a similarity above a threshold, and jointly forming a new engineering knowledge concept dictionary with the segmented words; and 4) constructing an NECE model, recognizing knowledge concepts of original course materials, and storing a concept set. The application can use the word2vec model to construct corresponding course major vocabulary sets and word vectors, and use the NECE model to realize extraction of major course concepts, thereby laying a data foundation for construction of an education system knowledge graph.

The application discloses a large-scale knowledge graph construction method for a financial field, relates to the technical field of knowledge graphs, and aims to solve the diversified large-scale knowledge graph construction problem caused by the heterogeneity and independence of large-scale field knowledge. The application comprises the following steps: S1, acquiring financial and economic data from an open knowledge base, performing concept extraction and knowledge extraction, and then constructing a large-scale knowledge graph; S2, constructing a common-sense knowledge base based on the large-scale knowledge graph; S3, expanding the common-sense knowledge base by using the large-scale knowledge graph; and S4, performing common-sense knowledge base-large-scale knowledge graph joint representation learning by using a graph representation learning module. The application integrates multiple data sources and various types of knowledge in the financial field, solves the problems of data dispersion, redundancy and inconsistency existing in the key knowledge base in the financial field, provides a more comprehensive and consistent knowledge view, realizes the sharing and interaction of large-scale data, and makes the query and reasoning of financial knowledge more efficient.

The invention relates to the technical field of information retrieval, in particular to a patent application process automatic management method and system, and the method comprises the following steps: carrying out the data preprocessing based on submitted patent application data through employing a fast Fourier transform algorithm and a lightweight data compression technology, and generating preliminary processing data; according to the method, the fast Fourier transform algorithm and the lightweight data compression technology are adopted to significantly improve the data preprocessing efficiency and accuracy, reduce noise interference and ensure the data quality, the convolutional neural network and the recurrent neural network are combined to deeply analyze patent images and text contents, and a comprehensive and deep analysis report is provided. The BERT model is used for semantic analysis and key concept extraction of patent description, document quality is improved, time sequence analysis and a market trend prediction algorithm provide accurate evaluation for market positioning of patent technologies, patent strategies are guided, an association rule learning algorithm provides powerful support in trend analysis in the technical field, and technology research and development and market guidance are assisted.

The invention discloses an interpretability method for a decision basis of a medical image classification model, and relates to an interpretability method for a classification model. A channel and a space attention mechanism are introduced in a prototype concept extraction stage, the model is guided to focus on a key semantic region related to a disease, background interference is reduced, and semantic discrimination and stability of a prototype concept vector are remarkably improved; a CARAFE up-sampling method based on content awareness is adopted to replace a traditional up-sampling mode, the problems of edge blur and structure distortion are effectively relieved in the prototype concept vector positioning and deconvolution visualization process, and important anatomical structures and focus contour information in medical images are better reserved; according to the method, semantic suppression of prototype concept vectors in a high-level semantic space is quantitatively analyzed in combination with an anti-fact intervention strategy, contribution of each prototype concept vector to model prediction can be objectively evaluated, and potential error correlation or redundant prototype concept vectors can be revealed, so that the fineness and credibility of model decision interpretation are improved.

The invention provides a multi-agent collaborative intelligent reply method and device, equipment and a medium, relates to the technical field of artificial intelligence, and is suitable for the financial field and the medical field. The method comprises the following steps: performing intention recognition on a target problem through an intention recognition agent to obtain a target intention; performing concept extraction on the target question through a concept extraction agent to obtain a target concept, the target concept including the first new knowledge; updating the first new knowledge to the initial knowledge graph through the dynamic updating agent to obtain a first knowledge graph; task planning is conducted on the target intention and the target concept through a task planning agent, a task sequence is obtained, and the task sequence comprises a target task; performing data reading on the first knowledge graph through the graph interaction agent and the target task to obtain target sub-graph data; and performing answer generation on the target sub-map data and the target question through the response generation agent to obtain a target answer. According to the invention, the accuracy of intelligent reply is improved.

The invention relates to the technical field of hierarchical industry classification, in particular to a hierarchical industry classification method and system based on AI semantic analysis. Comprising the steps of constructing an industrial knowledge base and an intelligent agent; collecting multi-modal data of a to-be-evaluated enterprise, and generating a business association packet of the to-be-evaluated enterprise by the intelligent agent according to the multi-modal data; generating an assessment path set of the to-be-assessed enterprise according to the industrial knowledge base and the business association packet; and constructing a hierarchical industry classification model according to the evaluation path set. The business basic portrait is established by collecting public data of an enterprise, the training mapping set of the to-be-evaluated enterprise is dynamically adjusted, and the semantic analysis model matched with the to-be-evaluated enterprise is quickly established, so that semantic interference of irrelevant industries is effectively shielded, the accuracy of business concept extraction is improved, and the classification accuracy and the adaptability to emerging business forms are improved; and a double-path verification model is constructed based on semantic vector similarity retrieval and business concept map reasoning, so that the business analysis efficiency is improved, and the industrial requirements of multi-standard hierarchical classification are met.

The invention discloses a difficult problem data synthesis method and system for an inference large model, and the method comprises the steps: carrying out the concept extraction of an existing mathematical data set, and obtaining a concept entity containing a mathematical concept, an application scene and an example; performing difficult problem synthesis on the randomly extracted concept group based on an existing reasoning big language model, generating an answer with a long reasoning chain form, and establishing a candidate difficult problem data set; and a method based on rules and large language model verification is adopted, correct difficult problems are screened out from the candidate data set, and a final difficult problem data set is obtained through long reasoning chain answering and reference answers. The invention provides an effective data synthesis method, a mathematical problem with high quality and high difficulty can be constructed, training and evaluation of a large language model are effectively supported during long reasoning chain solution, and a solid data basis and a technical path are provided for improving the model capability in a complex reasoning task in the future.

An embodiment for classifying documents using unsupervised text analysis with concept extraction. The embodiment may obtain a generic description for a document by: extracting concepts from headings and descriptions of a target document using natural language processing, matching the extracted concepts to generic abstracts obtained from an abstract database, where the abstract database is independent and separate from the target document, and processing the generic abstracts to lemmatize words and remove common words to form the generic description. The embodiment may process an available series of technical classifications. The embodiment may perform bidirectional analysis to determine a most relevant technical classification for the target document based on the generic description for the target document. The embodiment may assign the most relevant technical classification to the target document.

A system, method, and program for providing information are capable of outputting more accurate output sentences and related reference-attached explanatory sentences in response to input sentences such as questions. [Solution] Based on the reference concept data 112 corresponding to the text data of the arcuate member 130 extracted by the concept extraction unit 103, reference expert knowledge data 116 is acquired, and then text data 118 of an explanatory text with references is acquired based on access to the generation AI system 108, thereby providing highly accurate answers, advice, explanations, etc. for the input text.

The application discloses a retrieval method based on semantic concept extraction, which comprises: obtaining query features; performing similarity calculation on the query features and candidate features in a candidate feature database to obtain a similarity ranking result; and returning the similarity ranking result as a retrieval result. The candidate features are obtained by performing feature extraction on images in an image database: extracting basic semantic elements from the images; performing semantic concept cutting to obtain semantic concept features; and performing L2 regularization, PCA whitening and a further round of L2 regularization on the semantic concept features to obtain the candidate features. The semantic concept features extracted by the application can cover instance levels and image levels, so that the extracted features can describe global and local image semantic information, thereby unifying image retrieval and instance retrieval in a set of frameworks, and thus the application can be used for both instance retrieval tasks and image retrieval tasks.

This invention discloses a reinforcement learning-based standard alignment method for automatically determining and optimizing terminology definitions. The method first constructs a structured instruction fine-tuning dataset integrating expert instructions and standard terminology, and performs supervised fine-tuning on a basic large language model to obtain a concept extraction model and a multi-dimensional judgment model. Second, the concept extraction model is used to analyze the superordinate concepts and distinguishing features of the target term, and the multi-dimensional judgment model automatically evaluates the definition to be optimized across six dimensions: accuracy, conciseness, appropriateness, substitution principle, circular definition principle, and negation form principle. Finally, a composite reward model is constructed, combining the multi-dimensional evaluation results with the semantic similarity to the standard definition, and the GRPO reinforcement learning algorithm is used to iteratively optimize the definition generation strategy until the semantic similarity between the generated revised definition and the standard definition exceeds a preset threshold. This invention achieves automated, standardized, and standard-aligned terminology definitions, significantly improving the quality and consistency of terminology definitions in standardized documents, and is applicable to intelligent standard-setting scenarios in professional fields such as medicine, law, and finance.

The invention relates to a financial concept question-answering method and system based on a dynamically-amplified personal wealth management standard concept library, and discloses a financial concept question-answering method based on the dynamically-amplified personal wealth management standard concept library, which comprises the following steps of: 1, preprocessing a user question; comprising problem segmentation and concept extraction; 2, inquiring whether each concept after preprocessing is in a database or not; 3, performing synonym judgment on each concept in the step 2 and a concept in a database; 4, performing networking retrieval on each concept in the step 3 to obtain explanations corresponding to the concepts; and 5, finally embedding the prompt words to generate a final prompt word, and submitting the final prompt word to the Deepseek-v3 model to generate a final answer. According to the method, the dynamically updated financial concept knowledge base is constructed and realized, so that the continuously expanded and rapidly evolved knowledge requirements in the financial field can be efficiently met.

Regarding systems, methods, and programs for providing information, the aim is to enable the output of more accurate output text and related explanatory text with references in response to input text such as questions. [Solution] Based on the reference concept data 112 corresponding to the arch-shaped member 130 text data extracted by the concept extraction unit 103, reference expertise data 116 is acquired, followed by the acquisition of text data 118 of explanatory text with references based on access to the generation AI system 108, thereby obtaining highly accurate answers, advice, explanations, etc. for the input text.