2601 results about "Text processing" patented technology

The invention provides a medical text big data intelligent labeling and knowledge graph construction method and system, and relates to the technical field of medical text processing, and the method comprises the steps: recognizing entities in a medical text through a pre-trained deep bidirectional coding model and a multi-level entity recognition network, and carrying out the normalization processing in combination with a medical knowledge base, according to the method, the semantic association degree between entities is calculated, a relation extraction result is optimized based on comparative learning, comprehensive relation representation is obtained through fusion of multi-granularity coding and a gating mechanism, the entity relation is determined in combination with an inference rule network, a medical knowledge graph is constructed based on an initial knowledge graph, and the accuracy of medical text entities and relation labeling can be effectively improved. And a more perfect medical knowledge graph is constructed, which is helpful for assisting medical diagnosis and decision making.

The invention discloses a multi-modal large model federated training platform and a heterogeneous data alignment algorithm. The algorithm comprises a time sequence data processing module, a text processing module, an embedded generation module, a local federated learning module, a comparative learning alignment module, a global model aggregation module and a privacy protection verification module. The time sequence data processing module generates a time-frequency matrix signal; the text processing module outputs a text feature signal; the embedding generation module generates a time sequence embedding vector and a text embedding vector; the local federal learning module forms a local encryption signal; comparing the learning alignment module and generating a gradient signal; the global model aggregation module processes the gradient signal through a federated average algorithm and forms a parameter update quantity; and the privacy protection verification module generates confusion gradient signals and transmits the confusion gradient signals back to each module for data alignment. According to the multi-modal large model federation training platform and the heterogeneous data alignment algorithm, the problem that effective alignment and fusion of a logging curve and a geological report are difficult due to modal difference and semantic gaps can be solved.

A real-time system for the multimodal generation of virtual reality scenes based on artificial intelligence for the creation of immersive three-dimensional environments from natural language narratives, consisting of: a speech capture module configured to continuously record a user's spoken narrative via one or more directional microphones, preprocesses the captured signal by noise reduction and temporal alignment, and outputs a digital speech stream; A speech-to-text processing unit that is operationally coupled to the speech capture module and configured for real-time speech recognition using a continuous neural transformer model. The unit is trained to transcribe natural language utterances into structured text data while maintaining contextual continuity throughout the evolving narrative. a semantic interpretation processing unit that is communicatively linked to the speech recognition unit and configured to perform natural language understanding techniques to extract contextual entities, spatial references, temporal relationships, and object attributes from the transcribed narrative; the engine includes a large language model that is fine-tuned for spatial reasoning tasks; a scene graph generation module configured to transform the interpreted semantic data into a structured, hierarchical representation that defines nodes for identified entities and edges for corresponding relationships, with each node associated with metadata describing geometry, position, orientation, texture, and linking attributes between objects; a multimodal image-language model processor coupled with the scene graph generation module, wherein the processor is configured to retrieve, adapt, or synthesize appropriate three-dimensional elements from a pre-trained visual-lexical embedding space and align these elements with their semantic and spatial definitions derived from the scene graph; a scene assembly and rendering controller configured to create a cohesive virtual scene from the aligned assets, perform real-time rendering using a GPU-accelerated ray tracing pipeline, and produce a stereoscopic visual output that corresponds to the evolving narrative; A head-mounted virtual reality visualization device connected to the rendering engine and configured to display the generated immersive environment to the user in real time. The device features motion sensors and inside-out tracking cameras to detect head and body movements, dynamically updating viewing angles and perspective within the rendered scene; and a bidirectional feedback module integrated into the head-mounted device and connected to the semantic interpretation processing unit; the module is configured to interpret corrective commands, gestures, or supplementary comments from the user to refine or modify specific scene elements without interrupting the real-time visualization; The system continuously updates the virtual scene as the narrative develops, ensuring temporal synchronization between speech input and rendered output below a defined latency threshold, thus enabling a natural, dialogic construction of complex three-dimensional virtual environments.

A text detail map-based method for supervising end-to-end text detection and recognition, pertaining to the field of text processing. The method comprises the following steps: given an input image containing text in any shape, processing the input image by means of two separate processing branches; designing a text attention head (TAH), and designing a feature pyramid enhancement fusion module (FPEFM); the FPEFM performing feature self-enhancement at different sizes, fusing text image local features and global text position information extracted by a TAH module, and fusing features extracted by the TAH from feature maps of different sizes; stacking a plurality of FPEFMs to continuously enhance the feature representation capability of a model and the depth of the model; and sampling the feature maps to a unified size to obtain a final enhanced feature map.

A computer program comprising instructions which, when executed by a computer, cause the computer to perform the following operations: Receiving an input document (104), wherein the input document (104) contains content elements including at least one text element; Performing a lossless hierarchical text processing process (106) in which the input document (104) is reproduced as a hierarchical representation (108) in which all text elements from the input document (104) are preserved verbatim and organized according to a structure of the input document (104), the lossless hierarchical text processing process (106) comprising: Prompting a generative language model to generate the hierarchical representation (108), wherein the prompt instructs the generative language model to generate the hierarchical representation (108) without summarizing or omitting any of the text elements; and Performing a retrieval unit generation process (110) in which retrieval units (112) are generated based on the hierarchical representation (108) and stored in a memory accessible by a generative client language model for retrieval-enhanced generation.

The invention belongs to the technical field of text processing, and relates to a text factual proofreading method and system based on a large language model. The method comprises the following steps: constructing a task-adaptive large language model cue word framework; decomposing the text into a plurality of independent simplified fact expression texts; generating a fact query statement; establishing a local own knowledge base and a trusted website library; performing fine tuning training to obtain a trained large language model; performing three-way parallel judgment verification by using the trained large language model; and outputting a judgment verification result and an information source. According to the method, the powerful text analysis processing capacity of a large language model is fully utilized, error accumulation is reduced, and higher-precision proofreading is achieved; according to the method, multiple knowledge bases are supported, knowledge bases dynamically changing along with time can be obtained, a specially-assigned person does not need to be assigned to carry out real-time maintenance and custom fact texts, high precision and high real-time performance of facts are ensured, factuality verification is carried out, and the situation that correction is delayed due to delay caused by updating waiting of the local knowledge bases is avoided.

The invention discloses a speech recognition and natural language processing integration method and system, and the method comprises the steps: carrying out the multi-modal data fusion according to a speech signal of a user, context text information and environment sensor data, and obtaining a fused multi-modal feature vector; inputting the multi-modal feature vector into a speech recognition model based on an adaptive deep neural network, and performing speech-to-text processing to obtain text output; inputting the text output into a semantic analysis model based on a graph neural network, and performing context semantic analysis and user intention recognition to obtain semantic representation of the user intention and a confidence score of the semantic representation; and according to the semantic representation and the confidence score thereof, dynamically adjusting parameters of the speech recognition model and the semantic analysis model by using a feedback optimization technology based on reinforcement learning, and generating a model optimization strategy. According to the embodiment of the invention, the accuracy of speech recognition and the semantic comprehension capability of natural language processing can be improved.

The invention discloses a combined visual question and answer method based on core-to-global semantic fusion reasoning, and belongs to the technical field of image and text processing, and the method comprises the steps: obtaining image data and text question data; inputting the image data into the semantic feature extraction model to obtain image global features and visual core features; inputting the text problem data into the semantic feature extraction model to obtain text problem global features and text core features; transmitting the image global feature, the visual core feature, the text problem global feature and the text core feature to a preset multi-modal semantic fusion model to execute multi-modal semantic learning of different levels; fusing the learning results of the single-level language; and according to the target answer prediction vector, calculating to obtain a target prediction answer. According to the method and the device, the technical problems of inaccuracy in reasoning and model instability caused by inaccurate semantic alignment, feature redundancy and noise interference of multi-modal information in the prior art are solved.

The invention belongs to the technical field of text processing, and particularly relates to an intelligent legal text analysis method based on a legal concept pedigree, which comprises the following steps of: preprocessing an input legal text, identifying key legal concepts in preprocessed text data by using a natural language processing technology, constructing a legal concept pedigree knowledge graph, and analyzing the legal concept pedigree. And carrying out deep analysis on the preprocessed text data, identifying a logic relationship in the legal text, and providing legal provision matching and case retrieval services for a user through an intelligent algorithm. By integrating an advanced data processing technology and a natural language processing technology, a legal concept pedigree knowledge graph is constructed, and efficient and accurate analysis of legal texts is realized. The method not only improves the accuracy of legal concept recognition, but also can deeply mine the logical relationship between legal provisions by constructing the knowledge graph of the legal concept pedigree, thereby providing powerful support for legal reasoning.

The invention discloses a text keyword desensitization method, system and equipment based on a large model and a medium, belongs to the technical field of large model and natural language processing, and aims to solve the technical problem of how to automatically identify and desensitize sensitive information, improve the accuracy of sensitive information identification and further improve the text processing efficiency. According to the technical scheme, the method comprises the steps of data collection; preprocessing the data; marking sensitive information; segmenting the data; selecting a basic model; finely adjusting the model; training the fine-tuned large language model, and obtaining and storing the trained fine-tuned large language model; preprocessing the to-be-processed text data; detecting sensitive information, formulating a desensitization strategy and implementing desensitization processing, performing desensitization verification on the text after desensitization processing, and optimizing and improving the fine-tuned large language model according to a verification result; and packaging the optimized and improved fine-tuned large language model into an API (Application Program Interface) service for an application program to call.

The invention discloses an automatic tagging method and system for a fine tuning instruction set of a large language model, and the method comprises the steps: obtaining to-be-tagged original corpus data; performing desensitization and cleaning preprocessing on the to-be-labeled original corpus data; based on the scene of the original corpus data, matching a corresponding pre-trained large language model to label the corpus data, and generating a labeled label field; verifying the labeled label field through a regular statement, wherein verification comprises verification of the data content and the data format of the label field; and according to the scene of the original corpus data, assembling the generated label fields on the basis of an SQL (Structured Query Language) to form a fine tuning training set of a matched large language model. According to the method, a systematic judicial data analysis and labeling process is formed by processing judicial corpus data, so that rapid analysis and labeling of judicial data in the judicial vertical field are realized, and enabling of a text processing task in the judicial field is realized by a large language model.

The invention relates to the artificial intelligence technology, can be applied to service system platforms such as medical health and financial science and technology, and discloses a data processing method, device, equipment and medium based on a hybrid expert model.The method comprises the steps that to-be-processed data is input into the hybrid expert model, routing probability distribution is obtained, the Tsallis entropy of the routing probability distribution is calculated, and the Tsallis entropy of the routing probability distribution is calculated; generating a prediction result according to the Tsallis entropy; evaluating loss based on an auxiliary entropy loss function, constructing a subspace, and adjusting pre-training parameters in the subspace to obtain an optimized hybrid expert model; and obtaining a target prediction result according to the optimized hybrid expert model. According to the dynamic routing mechanism, experts are flexibly selected, an entropy loss function is assisted to optimize a routing decision, uncertainty is reduced, and model convergence is accelerated; and interference of new tasks on old tasks is eliminated through re-parameterization and subspace design, so that the model achieves good balance between stability and plasticity, and generalization and adaptability of model data processing are improved.

The invention discloses a text generation method, electronic equipment and a storage medium, and relates to the field of large model technology and text processing. The method comprises the following steps: acquiring to-be-processed data; based on the data structure information of the to-be-processed data, a target map of the to-be-processed data is constructed, and the target map is used for describing different entities in the to-be-processed data and the incidence relation between the different entities; generating a target problem of the to-be-processed data based on the target map, and identifying a problem type of the target problem; and generating a reply text of the target question based on the target question and the question type. The technical problem that the text generation effect is poor in the prior art is solved.

The invention belongs to the field of artificial intelligence, and particularly relates to a long text processing method and related device.The method comprises the steps that for long text data to be processed in a current session, context information corresponding to all text fragments is extracted from the long text data; the context information is stored in different storage areas of an external memory module; the external memory module comprises a short-term memory area and a long-term memory area; the short-term memory area is used for storing first context information of which the importance reaches a preset condition in the current session; the long-term memory area is used for storing second context information repeatedly appearing in a plurality of sessions; the plurality of sessions comprise a current session and / or a historical session; the first context information and the second context information are input into a large language model, and natural language processing of the long text data is achieved through the large language model. According to the method, the long text processing efficiency and accuracy can be improved, and the context memory ability and the flexible adaptability of the model are enhanced.

The embodiment of the invention provides a directional training method and device for an enterprise project text processing model, and the method and device achieve the screening of high-quality training samples through the construction of a project text scoring model and the multi-dimensional evaluation of the text coverage degree, the technical correlation degree and the structural integrity. And analyzing a text structure relationship based on the knowledge graph and the graph convolutional network, and constructing a differentiated text template library. The system performs directional training on a pre-training large model in combination with an enterprise portrait vector, and continuously optimizes model parameters and a knowledge base by adopting an incremental learning strategy. According to the method, the defects of a traditional technology in the aspects of training sample screening, knowledge structure analysis and model personalized customization are effectively overcome, and the practicability and adaptability of a project text processing model are remarkably improved.

The invention relates to a model fine tuning method, a text processing method, a medium, equipment and a program product. The method comprises the following steps: acquiring a vocabulary and an embedded layer parameter of a large language model from a server; respectively carrying out confusion processing on the word list and the embedded layer parameter to obtain a target word list and a target embedded layer parameter; sending the target embedded layer parameter to a server, so that the server updates the embedded layer parameter of the large language model into the target embedded layer parameter to obtain a new large language model; performing word segmentation and index conversion operation on the text sample by utilizing the target word list to obtain a first lexical element index corresponding to the text sample; and sending the first lemma index to a server, so that the server performs fine adjustment on the new large language model based on the first lemma index. Thus, the server side can be prevented from obtaining the corresponding relation between the embedded vector and the lexical element, and therefore the model effect can be better guaranteed through fine adjustment operation on the premise that data of a server side user is effectively protected.

The embodiment of the invention discloses a community governance decision generation method and device based on a knowledge graph. The method comprises the following steps: collecting community governance data; performing information extraction and text processing on the community governance data by adopting a data extraction model to generate structured data; constructing a causal analysis atlas, a decision treatment atlas and a space-time correlation atlas by using the structured data; fusing the causal analysis graph, the decision governance graph and the space-time association graph to obtain a community governance knowledge graph, wherein the community governance knowledge graph supports semantic-based query and reasoning; acquiring resident appeal information, and performing risk reasoning based on a preset reasoning rule to obtain a risk reasoning result; and based on a risk reasoning result, in combination with spatio-temporal information defined by a spatio-temporal association graph, querying in the community governance knowledge graph, and generating a community governance scheme according to a query result. According to the invention, the dynamism, the accuracy and the intelligent level of community management can be improved.

The invention provides a multi-recall-based RAG text processing method and device and a medium, and the method comprises the steps: processing a corpus used by an RAG to obtain a plurality of document blocks; respectively carrying out the following processing on each document block, and then storing a processing result: calling an RAG embedding model to carry out vectorization processing, carrying out keyword indexing processing by utilizing ElasticSearch, and calling an LLM model to generate a plurality of hypothetical problems; performing semantic enhancement processing on the prompt word of the user to obtain a new prompt word; based on the new cue word, performing multi-path recall on the RAG embedding model, ElasticSearch and a plurality of hypothetical problems to obtain a document block set summarized according to ranking; calling an LLM model to screen out a plurality of target document blocks from the document block set; according to the preset number of document blocks, the target document blocks are cut, and a final context output result is obtained; and combining the new cue word and the context output result as an output answer of the LLM model.

A computerized-method for comprehensive text-summarization quality-assessment with rank-based normalization and weighted-hierarchical-ranking strategy. The computerized-method includes: (i) receiving an original-text and a summary-text that has been generated by a (GPT)-based LLM that has been provided the original-text and a text-prompt; (ii) operating a text-processing NLP module on the original-text and the summary-text to yield a processed-text of both; (iii) measuring the summary-text to assess text-summarization-quality thereof by operating a plurality of metrics to yield a metric-score; (iv) operating ranked-based normalization on each metric-score to yield a normalized-score; and (v) operating an aggregation based on weighted-hierarchical-ranking strategy of the normalized scores to yield an interpreted final-quality score. The interpreted final-quality score indicates a comprehensive text summarization quality assessment of the summary-text, and the plurality of metrics includes: (i) grammatically; (ii) Flesch-Kincaid (FK) readability; (iii) topic coverage; (iv) compression ratio; (v) cosine similarity; (vi) NER accuracy; (vii) BLEU; and (viii) ROUGE.

The invention relates to the technical field of text processing, and provides an engineering management report generation method and system based on natural language processing, which are used for realizing deep analysis of construction logs and providing a comprehensive and accurate decision basis for engineering management. The method comprises the steps that a construction log text set generated in the engineering construction process is acquired, natural language processing is conducted on the construction log text set, key entities and progress events in each construction stage description unit are extracted, and a construction feature set containing entity identification information and event time sequence information is obtained; performing semantic alignment processing on the construction feature set and a preset engineering specification knowledge base to generate specification association information between the construction stage description unit and an engineering specification requirement; and performing structured integration processing on the standard associated information based on a hierarchical template matching algorithm to generate a structured report text meeting the engineering management requirements.

The present application provides a training method for a text processing model, a training apparatus for a text processing model, an electronic device, a program product, and a storage medium. The method comprises: acquiring a sample text set; splicing at least two independent sample texts among a plurality of independent samples texts to obtain a plurality of spliced sample texts; on the basis of the plurality of spliced sample texts, calling an initialized text processing model to perform feature extraction processing to obtain a plurality of spliced sample features; on the basis of each spliced sample feature, calling a masked attention mechanism to perform prediction processing to obtain a predicted text, wherein the masked attention mechanism comprises: masking each independent sample in the spliced sample features; on the basis of the difference between the predicted text and a sample label, determining a loss function; and on the basis of the loss function, performing parameter update processing on the text processing model to obtain a trained text processing model.

Presented herein are interactive graphical user interfaces (GUIs) for providing automated, real-time interactive assistance to a human user creating electronic documents. In certain embodiments, the GUI includes an alphanumeric text processing region, an AI-generated text region, and a reference list region. The AI-generated text region contains one or more alternative blocks of text responsive to a user query and based on specific references (e.g., articles, books, or other written works). The references are listed in the reference list region of the GUI.

The invention relates to the technical field of language data processing, in particular to a language data processing method and system, terminal equipment and a storage medium. The method comprises the following steps: acquiring current round dialogue data of a user; performing dialogue language text processing according to the current round dialogue data of the user to obtain current round dialogue language feature data; carrying out anonym detection on the current round dialogue language feature data, and carrying out dynamic historical anchor point screening to obtain cross-round screening anchor point list data; performing multi-round dialogue intention evolution reasoning according to cross-round screening anchor point list data to obtain an interaction adjustment intention representation strategy; and according to the interaction adjustment intention representation strategy, carrying out current round dialogue language key referring word determination so as to realize cross-round dialogue type language referring word identification. According to the method, the cross-round dialogue type language anonyms are accurately recognized through multi-round dialogue situation and multi-modal clue language data processing.

The invention relates to the technical field of natural language processing, and discloses a knowledge base question and answer platform construction method based on a large language model, which comprises a knowledge acquisition module, a data preprocessing module, a text processing module, a vectorization module, a question understanding module, a mixed retrieval module, a prompt generation module, an answer generation module and an answer quality analysis module. A secondary inquiry processing module and a feedback learning module; according to the method, a semantic segmentation algorithm is combined with semantic retrieval and keyword retrieval, so that the flexibility is high; normalized prompts are constructed, input is performed according to correlation sorting, and the accuracy of answers is improved; multi-dimensional confidence evaluation is introduced, strict multi-layer security and compliance filtering is set, and the reliability of the system is ensured; the relevance of multiple rounds of dialogues is judged and complemented, so that interaction is more natural and efficient; knowledge is collected and updated in real time, a knowledge base and a retrieval strategy are continuously optimized, and a closed loop of data-application-feedback-tracing-optimization is formed.

The invention belongs to the technical field of document analysis, and particularly relates to a multi-algorithm collaborative PDF document intelligent analysis system which comprises a preprocessing module used for recognizing the type of a PDF document, performing layout correction on a scanning document PDF and uniformly adjusting the scanning document PDF into a vertical storage format; the layout analysis module is used for identifying page element categories based on a target detection algorithm, and processing element superposition and separation problems through a merging de-duplication or priority discarding strategy; and the text processing module is used for analyzing all places with characters in the PDF based on the OCR, outputting the characters and corresponding textbox coordinates, and dividing the contents of the text blocks in combination with layout analysis. The system can extract characters of the PDF of the scanned copy, distinguish element types such as titles, texts, tables and formulas, solve the problem of confusion of cross-page tables, column texts and characters with similar shapes, and can completely reserve the content structure of the document.

The invention belongs to the technical field of text processing, and particularly relates to a method and system for retrieving DOCX document content based on keywords, which comprises the following steps: analyzing an Office Open XML structure of a DOCX document, combining with multi-dimensional features such as style names, and utilizing a title classification score model to accurately distinguish a title and a text, so that a semantic hierarchical structure of the document is effectively reserved; and secondly, a multi-level semantic extension mechanism is introduced, and a Sension-BERT, a HowNet knowledge base and a Word2Vec model are fused, so that intelligent extension of synonyms and synonyms of keywords is realized, and the recall rate and semantic understanding ability of retrieval are remarkably improved. And in addition, a BM25 model is combined with paragraph length normalization and structure position weight to calculate a correlation score, so that retrieval results are sorted more accurately and reasonably. The construction of the reverse index is combined with the position coding and compression optimization strategy, and the retrieval efficiency and the storage performance are both considered.

The invention provides a multi-modal retrieval method and device, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining query information and a preset data set; in the text space, based on the matching degree of the query information and each piece of preset data, determining multiple pieces of first candidate data from the preset data set; in the multi-modal space, determining a plurality of second candidate data from the preset data set based on the similarity between the query information and each piece of preset data on the coding unit; and fusing the plurality of first candidate data and the plurality of second candidate data to obtain a query result corresponding to the query information. According to the method, the multi-modal data is mapped to the text space, the text is used for retrieval, the text processing capacity in multi-modal retrieval can be improved, the similarity of the data on the coding unit is used for searching in the multi-modal space, the data of different modals can be better understood, and then the accuracy of the multi-modal retrieval can be effectively improved.

The invention provides an article generation method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of large models, agents and text processing. According to the specific implementation scheme, the method comprises the steps of obtaining a writing request, and identifying the writing request to obtain a writing requirement; respectively generating a draft outline and available materials according to the writing requirements; adopting the available materials to rewrite the draft outline to obtain a target article outline; and generating a target article according to the target article outline. Through the technical scheme, the article generation quality can be improved.

The invention discloses a method for improving long text processing efficiency and accuracy, and relates to the technical field of natural language processing and large language models.According to the method, text word segmentation embedding, sliding block preprocessing, YaRN position code injection, dynamic sparse attention calculation, multi-level attention fusion, graded KV cache management and output generation are sequentially executed; position drift is inhibited through logarithmic scaling, and key contexts are adaptively screened according to the attention activeness, so that the attention calculation complexity is close to linearity; in million-level Token reasoning, the video memory occupation of the method is reduced, the remote dependency recall rate is improved, and the method is suitable for scenes such as document analysis, code auditing and multi-mode streaming understanding.

The invention discloses a vertical field large model-oriented high-quality data set construction method and system, and relates to the technical field of text processing, and the method comprises the steps: selecting seed text data, carrying out long text processing, segmenting the seed text data into a plurality of text segments, processing the text segments by using a large model tool to generate seed question and answer pairs, and constructing a seed question and answer pair; auditing and optimizing are carried out according to a preset auditing standard; making an instruction generation data set for the cue word, the text fragment and the seed question and answer pair according to a preset organization rule, performing fine adjustment on a pre-selected base model by using the instruction generation data set, and performing iterative optimization on the large model by testing the performance of the large model after fine adjustment and adjusting and optimizing parameters, thereby obtaining an intelligent extraction large model IELM; and based on the intelligent extraction big model, processing the text data by utilizing a preset script code, automatically generating knowledge question and answer pair data corresponding to the text data, and performing format conversion processing to obtain an instruction data set which is used for a training data set of the vertical domain knowledge big model.