2167 results about "Information extraction" patented technology

The invention relates to a bill voucher information extraction method based on multi-mode and OCR model fusion. The method comprises the following steps: S1, obtaining an image of a bill voucher; s2, preprocessing the image; s3, identifying the preprocessed image by using an OCR engine to obtain the text content and the corresponding two-dimensional coordinates of each text block; s4, taking the recognized text segments and the original image as input, performing joint coding by using a pre-trained multi-modal model, evaluating and outputting the matching degree of each text segment and a predefined field category by the model, and determining candidate texts of each field and confidence of the candidate texts; s5, accurately positioning and extracting the key field, and verifying the consistency of the OCR output and the semantic result; s6, if the verification result conflicts or the identification reliability of a certain field is lower than a threshold value, error correction operation is carried out; and S7, outputting the structured bill voucher information. Through multi-modal fusion and iterative correction, the error rate of non-standard voucher information extraction is effectively reduced, and the method is suitable for various voucher formats and complex scenes.

The invention discloses a government affair intelligent interaction and information extraction method and device, equipment and a medium, and relates to the technical field of digital government affair, digital cities, intelligent interaction and the like. The traditional manual item-by-item filling is converted into end-to-end automatic processing, so that the operation steps of a user are remarkably reduced, the filling burden of a hundred-item-level form is solved, and the filling efficiency is improved; and an ID voice corrector is adopted to realize three-layer progressive verification, so that the output ID offset of the multi-modal large model is effectively inhibited, the accurate mapping of field identifiers is ensured, and meanwhile, a lightweight knowledge graph is adopted to automatically capture logic rules among fields, interspecific compliance conflicts of government affair scenes are intercepted in real time, the logic error risk is reduced, and the filling accuracy is improved.

The embodiment of the invention provides a test case generation method and device.The method comprises the steps that a test case generation task is determined, and the test case generation task carries a target document, a task type and a document type of a to-be-generated test case; analyzing the target document according to the document type by using an information extraction agent to generate an analysis result of the target document; generating an intelligent agent by using a test point, and generating an initial test point according to the task type and the analysis result; and generating a first test case corresponding to the test case generation task by using a test case generation agent according to the initial test point and the analysis result. The analysis logic of a qualification test expert is simulated through a plurality of agents, and the efficiency and integrity of test case output are greatly improved.

The invention belongs to the technical field of natural language processing and multi-modal information extraction, and particularly relates to a multi-modal named entity recognition method based on semantic alignment and cross-modal graph fusion, which comprises the following steps: S1, acquiring a data sample containing a text sequence and image content; s2, encoding the text and the image into vectors respectively; s3, similarity is calculated through a trainable bilinear function, and optimization is carried out through loss comparison; s4, cross-modal attention is used to enhance association information between modals; s5, determining the proportion of reserved image information through a modal matching module; s6, introducing a gating mechanism to dynamically fuse visual and text features; s7, realizing local and global information complementation by a cross-modal graph fusion model; and S8, inputting the fused representation into the CRF layer to predict the entity type. According to the method, fine semantic alignment can be realized in a weak image-text correlation context, and balance between local entity recognition and global semantic understanding can be achieved.

The invention provides an electronic medical record information extraction system and method, and belongs to the technical field of medical information extraction. The method aims to solve the problems of inaccuracy, nonstandardization and inconsistent logic when information is extracted from a free text medical record. According to the scheme, the method comprises the steps that cue words containing structured field definitions and rules are generated; inputting the cue word and the medical text into a large language model to obtain a preliminary result; calling a medical knowledge base to correct terms in the result; and performing logic verification on a corrected result, including time sequence and cross-field consistency verification, so as to generate final structured medical record information. According to the method, a closed loop is formed by guiding type extraction and multi-stage verification and by introducing a feedback correction mechanism, so that the accuracy, the normalization and the logic consistency of the medical record information are remarkably improved, and a high-quality data basis is provided for clinical application.

The invention discloses a river flow missing data reconstruction method, which comprises the following steps of S1, constructing a river network topological structure, and quantifying hydraulic correlation; s2, spatio-temporal feature fusion and multi-source information extraction; s3, performing multi-task cooperative flow reconstruction and confidence coefficient prediction; s4, dynamic weighting and result correction of meteorological factors; and S5, performing anomaly detection and model dynamic updating. According to the method, a river flow missing data reconstruction method is set, the steps are mutually fused and used, and topology-aware space-time diagram convolution is performed: a river network topology structure is encoded into a weighted adjacency matrix for the first time, space correlation features are extracted through a diagram convolution network, and the problem that a traditional method ignores hydraulic connection is solved; a multi-task collaborative learning mechanism: synchronously outputting a flow reconstruction value and confidence, combining topological smooth constraints, and realizing reconstruction reliability quantification while ensuring precision; and meteorological dynamic weighted correction: dynamically adjusting the node weight based on the real-time rainfall intensity, and accurately adapting to the nonlinear response of the water flow in the heavy rainfall period.

A document information extraction method and apparatus based on image-text modal fusion, and a storage medium, relating to the technical field of artificial intelligence. The method comprises: acquiring a text block in a picture to be processed; extracting a semantic vector from the text block on the basis of a pre-trained NLP model, extracting a visual vector by using computer vision technology, and fusing the semantic vector and the visual vector by means of an attention mechanism to form an image-text fused feature representation; constructing a fully-connected directed graph on the basis of image-text fused feature; on the constructed graph network, performing graph attention convolution on "node-edge-node" triplet feature sets; dynamically weighting important "text-position-text" triplet information by means of a self-attention mechanism; and outputting a feature vector in which text, vision and position information are fused. By deep fusion of text, vision and position information, the present disclosure significantly improves the accuracy and robustness of text information matching, thus adapting to complex and diverse image-text environments.

The invention discloses a cross-modal eye fundus image generation method and system based on a generative adversarial network, relates to the technical field of medical image processing, and constructs an eye fundus focus perception and edge consistency generative adversarial network by taking a cyclic consistency generative adversarial network as a baseline. The core of the method is that a lesion perception mixed attention module is embedded in a bottleneck layer of a generator so as to strengthen the extraction capability of fine features of a lesion area; an edge information extraction module is designed, and key edge features are accurately extracted in combination with Roberts edge detection, wavelet transform and non-local mean denoising; and a joint loss function containing edge consistency loss is constructed, and the semantic consistency of a focus structure during cross-modal generation is ensured by minimizing the feature difference between the source image and the generated image. According to the method, the problems of disordered content, inconsistent structure and unstable training of the generated image in the prior art are effectively solved, and the simulation degree and clinical availability of the generated image are remarkably improved.

The invention provides a knowledge question and answer library agent construction method and system. Efficient knowledge management and question and answer are achieved through cooperation of multiple agents. According to the system, firstly, a multi-modal information extraction agent is constructed, and heterogeneous data such as texts, images and tables are converted into structured vectors and stored; meanwhile, the knowledge graph is dynamically constructed and continuously optimized by the self-adaptive knowledge graph construction agent, and a new relationship is derived through combination of symbolic logic and a graph neural network, so that an evolvable knowledge network is formed. In the question and answer stage, a query analysis agent deeply analyzes the intention of a user and generates sub-queries; retrieving the vector library and the knowledge graph in parallel by the retrieval enhancement generation agent; and the reasoning and synthesizing agent integrates multi-source information and generates an accurate answer with a complete source label through a large language model. Dynamic knowledge management, precise semantic analysis and system self-evolution are achieved, and the method is particularly suitable for professional field scenes needing high-reliability questions and answers.

The invention relates to a cross-modal document information extraction method based on space-semantic alignment, and belongs to the field of artificial intelligence, computer vision and natural language processing. According to the method, the spatial feature and semantic information bidirectional alignment model is designed, by constructing the spatial feature and semantic feature bidirectional alignment model, the document layout information can dynamically adjust attention distribution of text semantic features, meanwhile, semantic information reversely optimizes the spatial features, collaborative modeling of spatial layout and semantic information is achieved, and the document layout efficiency is improved. Therefore, the accuracy and robustness of complex document information extraction are improved. According to the method, a hierarchical cross-modal information extraction model is designed, through the hierarchical cross-modal information extraction model, the overall structure of a document is recognized on the global level, local key content is focused on the regional level, fine modeling is conducted on fine-grained texts and visual elements on the entity level, and accurate recognition of a cross-modal entity and the semantic relation of the cross-modal entity is achieved; and the generalization ability and applicability of information extraction are enhanced.

Document type specific adapters of a document analysis system are used to provide for additional document types or document specialization when generating answers to user submitted questions targeting information included in a document image provided with the user submitted question. The document analysis system receives a visual question answering (VQA) prompt comprising a document image and a question defining information to be extracted from the document image, generates tokens based on the document image and the question, and adjusts encoding of the tokens using document type specific adapters of a transformer model to extract the information from the document image. A classifier of the document analysis system may determine whether the document image matches a document type supported by the document type specific adapters.

The invention provides a dermatoscope image segmentation method, and relates to the technical field of medical image processing, and the method comprises the steps: inputting a to-be-segmented image into an improved encoder module, carrying out the multi-scale feature information extraction, and obtaining a deep advanced semantic feature map; inputting the deep advanced semantic feature map into the bridging module, and performing context information modeling and cross-scale feature fusion to obtain a fused feature map; inputting the fused feature map into the decoder module, and carrying out layer-by-layer up-sampling and feature integration to obtain a reconstructed feature map; inputting the reconstructed feature map into the boundary sensing double-branch module, and performing collaborative feature processing; wherein the main branch outputs a binary segmentation mask, and the auxiliary branch is used for measuring a sign distance function diagram to provide boundary perception supervision; obtaining a binary segmentation mask output by the main branch as a segmentation result; compared with an existing model, the optimized dermatoscope image segmentation model is higher in recognition accuracy.

The invention discloses a resume analysis method and system based on multiple large language models, and belongs to the technical field of large language models.The resume analysis method and system based on the multiple large language models.The resume analysis method and system based on the multiple large language models comprise the following specific steps that firstly, model parallel analysis is conducted, simultaneously inputting the data into at least two heterogeneous large language models through an application program interface; and each large language model independently performs information extraction and analysis according to the model structure and the training data of the large language model, and outputs a structured data result containing a plurality of preset fields. Through the multi-model parallel analysis and conflict re-judgment mechanism, the misjudgment risk of a single model is effectively reduced, the robustness of the whole system is improved, the resume analysis accuracy is remarkably improved, the model pool is automatically optimized and updated through the dynamic scoring mechanism, and the problem that the model is difficult to select and update is solved.

The invention relates to the technical field of image analysis, in particular to a cushion foaming forming quality detection method and system based on machine vision, and the method comprises the steps: collecting image data, carrying out the iterative screening of the image data, and selecting a detection sample; the method comprises the following steps: collecting a three-dimensional point cloud of a detection sample, calculating the flatness of a seat cushion by using the three-dimensional point cloud, carrying out modeling by using polarized light reflection to obtain surface cell uniformity, and carrying out feature extraction on the three-dimensional point cloud through a three-dimensional mapping model to generate a three-dimensional semantic model; extracting mechanical characteristics by using the time sequence pressure map, and generating a cushion digital model; variational self-coding is carried out on the cushion digital model, and an abnormal feature map is generated; performing information extraction and pixel-by-pixel multiplication on the abnormal feature map by using a learnable convolutional layer to generate an abnormal enhanced map; and inputting the abnormal enhancement graph and the seat cushion digital model into a multi-channel network model for final evaluation. According to the method, the image data is analyzed, and the performance of the cushion is subjected to index quantification, so that the deep detection of the quality of the cushion is realized.

The invention relates to the field of text processing, in particular to a bidding document information extraction method. Comprising the following steps: segmenting a bidding and tendering file into pages, and identifying the pages to obtain corresponding texts; generating complementary text description for images and tables in the page and adding the complementary text description to the tail of a text corresponding to the page to form an enhanced text block sequence; matching a label from the text block sequence according to a pre-constructed hierarchical label system, and generating a corresponding cue word template according to the label and a pre-constructed cue word template library; inputting the cue word template, the enhanced text block sequence and the context text abstract as a combination into a large language model to obtain a structured extraction result with a hierarchical relationship; and matching the extracted entity content with a local dictionary, carrying out aggregation arrangement on a result after the matching is passed, and outputting a structured data file. On the premise that the model does not need to be retrained, the illusion risk of the generated content is reduced.

The invention relates to the technical field of project intelligent management and control, and discloses a multi-agent power grid project intelligent monitoring, management and control and evaluation system and method, and the system comprises a mixed data resource library, a multi-agent system, an index calculation module and a process control module. The mixed data resource library stores structured business data and unstructured documents; the multi-agent system comprises an information extraction agent, an index design agent, a code generation and treatment agent and the like, works cooperatively, and converts a high-level natural language management and control rule into an executable code; the index calculation module is responsible for executing codes according to a scheduling strategy and calculating quantitative indexes; and the process control module automatically identifies risks and executes management and control operations such as process locking according to the index result and a preset threshold value. According to the invention, the complex business logic can be automated and coded, the accuracy and timeliness of risk identification are improved, and refined and prospective intelligent management and control of the power grid project are realized.

The invention provides a vertical field data construction method based on a large model, which belongs to the technical field of data processing and artificial intelligence, and comprises the following steps: converting a vertical field source document into an intermediate format text, and segmenting the intermediate format text into a plurality of text blocks; inputting the text blocks into a pre-trained generative language model, guiding the pre-trained generative language model according to pre-designed cue words to generate a plurality of candidate questions according to the content of the text blocks, and performing preliminary screening and fine screening on each candidate question to obtain a question set; pre-defining a mode of a knowledge graph according to field characteristics of the vertical field, processing all text blocks based on an information extraction model, and constructing a field knowledge graph; and performing local context retrieval on each final question in the question set based on the text block of the question source, performing global knowledge retrieval based on the domain knowledge graph, and generating a final answer and a final thinking chain. The method is suitable for different vertical fields, the data quality can be effectively improved, and the problem generation accuracy is guaranteed.

The invention relates to an archive credible question and answer method based on graph context retrieval and knowledge graph enhancement, and belongs to the field of computer software and artificial intelligence. According to the method, the relation between key entities and entities in a historical file is extracted by using a multi-modal large language model MLLM, and low-confidence fields are automatically identified to generate marks needing to be manually rechecked, so that the correctness of information extraction is ensured while the workload of manual rechecking is reduced, and then based on a given knowledge base, the information extraction efficiency is improved. Previous related questions and answers are retrieved according to query questions to achieve context enhancement, and finally, credible answers are generated through a large language model (LLM) in combination with extracted information in historical archives. On the premise of keeping the value of the archive voucher, the processing efficiency and the knowledge service capability are remarkably improved.

Methods, apparatus, and processor-readable storage media for character-based representation learning for information extraction using artificial intelligence techniques are provided herein. An example computer-implemented method includes identifying, from unstructured documents, words and corresponding document position information using artificial intelligence-based text extraction techniques; generating an intermediate output by implementing at least one character embedding with respect to the unstructured documents using at least one artificial intelligence-based encoder; determining structure-related information for at least a portion of the unstructured documents using one or more artificial intelligence-based graph-related techniques; generating a character-based representation of at least a portion of the unstructured documents using at least one artificial intelligence-based decoder; classifying one or more portions of the character-based representation using one or more artificial intelligence-based statistical modeling techniques; and performing one or more automated actions based on the classifying.

The invention discloses a thermal power plant inspection robot path planning method, device and equipment and a storage medium, and the method comprises the steps: carrying out the semantic analysis and information extraction of an inspection task instruction, an equipment document and a historical inspection log through a large language model; obtaining a semantic importance score, a perception modal demand, recommended residence time and a shooting angle of each inspection target; establishing a multi-target path optimization model based on an improved ant colony optimization algorithm, and inputting the semantic importance score, the perception modal demand, the recommended residence time and the shooting angle into the multi-target path optimization model to obtain a joint scheduling sequence; the thermal power plant inspection robot is controlled to execute the joint scheduling sequence to perform autonomous navigation and perception tasks, the current path planning is adjusted according to the task completion condition, the intelligence, autonomy and adaptability level of the inspection robot can be remarkably improved, and the speed and efficiency of path planning of the thermal power plant inspection robot are improved.

A system for extracting a number of data elements from one or more data sources. A text representing tables using a markdown language is extracted from spreadsheets and or other grid-based documents. The text is provided to a language model with a prompt. The prompt may be a chain-of-thoughts prompt. The prompt includes several requests and / or steps that cause the language model to extract one or more tables from the spreadsheet and output the tables using the markdown language or a different markdown language. The tables extracted from the spreadsheet are converted into table chunks and indexed for retrieval by a retrieval augmented architecture. When a prompt to extract particular information from the spreadsheet is provided, one or more relevant table chunks are identified and provided to a language model for extraction. Using the language model to separate tables improves information extraction accuracy while maintaining downstream instructions.

The invention discloses a knowledge document-oriented method for structurally and stably presenting large language model output. The method comprises the following steps of: preprocessing a knowledge document and converting the knowledge document into a text by a system; the back-end service module adopts a prompt word engineering technology based on a preset JSON mode, constructs a structured prompt containing clear instructions and output format constraints, calls a large language model to carry out analysis and information extraction on text contents, and forces the model to generate structured JSON data following the preset mode; the back-end service provides access to the structured JSON data for the front-end application; and the front end executes templated mapping rendering according to a preset user interface component template isomorphic to the JSON mode, and fills the content of each field of the JSON into a corresponding visual component. According to the method, through the cooperation of the back-end constraint prompt word engineering and the front-end modularized template rendering, the defects that the output content format of a large language model is unstable and is difficult to be directly applied to standardized interface presentation are relieved.

The invention discloses an information extraction data annotation and training system based on a large language model, and relates to the technical field of information extraction, and the system comprises a data set construction module which is used for constructing a pre-training data set and a fine tuning data set; the model continuous pre-training module is used for carrying out continuous pre-training on a preset general large language model based on the pre-training data set to generate a field adaptive pre-training model; the model fine tuning module is used for performing supervised fine tuning training on the domain adaptive pre-training model through a two-stage course learning strategy based on the fine tuning data set, and generating an information extraction model; the retrieval enhancement generation module is used for performing entity-semantic retrieval on an input text based on a preset knowledge base, outputting context information related to the input text, and outputting structured information of the input text based on the context information and an information extraction model, the problems of insufficient generalization ability, poor field adaptability and disastrous forgetting of a general large language model are solved, and the accuracy and robustness of information extraction are improved.

The invention belongs to the technical field of engineering information intelligent processing, and relates to a highway bridge drawing multi-modal information extraction and semantic understanding method and system.The method comprises the steps that firstly, self-adaptive judgment is conducted on a vector drawing and a scanning drawing, geometric distortion correction, drawing frame and title bar positioning and layout segmentation are completed, and then the vector drawing and the scanning drawing are obtained; constructing a hierarchical document structure comprising texts, tables, images and two-dimensional drawing objects; then, a front-end target detection network and a rear-end cross-modal document understanding model are fused, and detection and relation reasoning of elements such as view blocks, labels, symbols and tables are achieved; and image-text feature alignment is further performed by using a visual coding network and a text coding network, structural description conforming to engineering semantics is generated by means of a multi-modal language model, an engineering parameter database is established, and parameter query and multi-modal question and answer output are supported. According to the method, the accuracy and efficiency of automatic acquisition and semantic understanding of the key information of the highway bridge drawing are improved.

A data processing system and method include receiving a set of documents to summarize a trend across the set of documents, inputting the set of documents into an information extraction model, executing the information extraction model to extract a first plurality of text segments, determining a second plurality of text segments based on the first plurality of text segments, determining a third plurality of text segments from the second plurality of text segments, generating a compressed representation of the set of documents from the third plurality of text segments to include in a prompt for a language model, inputting the prompt into the language model, and executing the language model to generate the summary based on the prompt for the set of documents.

The invention discloses a method for constructing a large mineralization potential evaluation model based on LLM, and relates to the field of models.The method for constructing the large mineralization potential evaluation model based on LLM comprises the following steps that 1, a mineral geological map file is converted into a structured JSON format data set; step 2, constructing cue words, wherein the cue words at least comprise geological information extraction cue words, function task cue words and entity, relation and attribute extraction cue words; compared with the prior art, the method has the beneficial effects that the large mineralization potential evaluation model constructed by the method realizes text and map multi-mode mineral product geological map information identification and analysis, automatic mineralization geological feature analysis, mineralization feature information extraction and mineralization potential evaluation; the problems that in the prior art, man-made subjective influence exists, professional knowledge dependence is high, the geological information recognition accuracy rate in the recognition process is low, and information is lost during knowledge retrieval are solved.

The invention belongs to the technical field of engineering data processing, and particularly relates to a digital twinning-based engineering completion delivery data information extraction method, which comprises the following steps of: acquiring completion site entity data, constructing a digital twinning body of building information model and live-action three-dimensional fusion, and fusing semantic tag information based on an improved ICP (Inductively Coupled Plasma) algorithm. Performing space coordinate alignment and attribute association on the digital twinborn body to generate a completion information dynamic twinborn mapping map; a multi-level rule inference engine is used for extracting information items conforming to delivery standards, a dynamic risk propagation model is used for simulating the influence of data deviation on a delivery result through multi-node consensus verification data of a construction party, a construction party and a supervisor, and information extraction weight parameters are corrected in real time; and dynamically generating a delivery data packet and a visual auditing report and synchronously updating the digital twin archive library in combination with engineering change records and acceptance specifications. Therefore, the problems of incapability of capturing engineering parameter fluctuation, poor transmission efficiency and the like in the prior art are solved.

The invention discloses a remote sensing image semantic change detection method based on semantic enhancement Transform and three-dimensional convolution, and aims to solve the problems of insufficient semantic and change information fusion and difficult narrow and long ground feature feature extraction in the existing method. According to the method, an SET-3DC network is constructed, 'feature extraction-feature interaction-semantic enhancement-change information fusion 'is taken as a core link, multi-scale dual-time-phase features are extracted through a dual-branch feature extractor (DFE), cross-branch feature interaction is realized through a channel feature exchange module (CFE), and multi-scale dual-time-phase features are extracted through a multi-scale dual-time-phase feature extraction module. A semantic branch decoder (SEAA-SD) based on semantic enhancement and axial attention strengthens local details, global semantics and narrow and long ground feature features, a change information extraction module (CIE) based on three-dimensional convolution fuses multi-source change information and aligns time-space correlation, and a network is optimized in combination with a joint loss function. Through multi-module cooperation and innovative structural design, the precision and internal consistency of semantic segmentation and change detection are improved, and the method is suitable for a high-precision remote sensing image semantic change detection scene.

The invention relates to an intelligent medical record generation and quality control method and system based on a large model, belongs to the technical field of medical information and artificial intelligence, and solves the problems of low writing efficiency and non-uniform quality of medical records in the prior art. Comprising the following steps: constructing a medical field knowledge enhancement large model which has the capabilities of intention recognition, medical record generation, term standardization check, format integrity check, information extraction and logic consistency check; when input information of a to-be-generated medical record is received, generating a complete medical record through intention recognition and medical record generation capability of the medical field knowledge enhancement large model and the constructed medical record template library and medical database; and when a medical record to be subjected to quality control is received, quality control suggestions are generated through the capabilities of term standardization check, format integrity check, information extraction and logic consistency check of the medical field knowledge enhancement large model and the constructed medical knowledge graph. And efficient generation and quality control of the medical record are realized.

The invention discloses a fastener defect automatic identification method based on deep learning, and the method comprises the following steps: S1, collecting fastener image data, and generating a standardized image sample; s2, executing edge feature enhancement and multi-scale filtering operation to generate an image feature map; s3, inputting into an improved TransNeXt model, and outputting a defect stage label, an identification confidence coefficient and a feature coding vector; s4, screening the position of the suspicious region, executing a local region decoding operation, and generating a defect response thermodynamic diagram; s5, extracting a bounding box, morphological characteristics and response intensity distribution of the maximum response region, and constructing a defect candidate region set; s6, non-defect areas are screened out, and a final defect recognition result is obtained; and S7, constructing a defect distribution diagram and a statistical information table, and outputting a defect type, a position coordinate, an area estimation value and an identification confidence level. According to the invention, high-precision automatic identification and structured information extraction of fastener defects are realized.