77 results about "Medical documents" patented technology

An intelligent analysis method based on medical document structure perception and multi-modal fusion comprises the following steps: carrying out structure topology modeling on a medical document, extracting visual layout, text meta-information, space coordinates and semantic keyword features, constructing a semantic topological graph and dynamically shielding irrelevant contents; selecting an extraction path according to a document type, performing deep semantic analysis and entity recognition on a text-type document, and performing visual enhancement OCR recognition on a scanning-type document; the features are injected into a medical knowledge graph, and feature fusion, semantic verification, relation reasoning and information completion are achieved through a graph neural network; a three-stage strategy optimization model of basic pre-training, domain adaptation and online reinforcement learning is adopted; and large-scale processing is realized through a dynamically aggregated distributed architecture. The method is used for intelligent analysis and structured conversion of documents of hospitals, medical insurance and medical scientific research. The problems that heterogeneous medical document analysis adaptability is poor, multi-modal fusion is difficult, medical knowledge utilization is insufficient, and large-scale processing efficiency is low are solved.

The invention provides a man-machine collaborative intelligent writing method and system for medical documents, and relates to the technical field of man-machine collaboration.The method comprises the steps that multi-modal clinical data of a patient is obtained for cross-modal semantic alignment, reasoning expansion is conducted based on a multi-level traditional Chinese medicine knowledge graph to generate a structured dialectical framework, and the structured dialectical framework is subjected to data processing; a logic consistency verification graph of a candidate medical record fragment set is constructed to solve semantic conflicts, and a medical record generation model is dynamically optimized in combination with clinical actual curative effect data, so that the intelligence degree, the standardization level and the clinical diagnosis and treatment value of traditional Chinese medicine medical record writing are improved.

The invention discloses a medical question and answer method based on knowledge graph and retrieval enhancement generation, and belongs to the technical field of natural language processing and knowledge management. The method includes the following steps that text blocks are obtained on the basis of medical document preprocessing and partitioning, and an abstract tree is constructed; entity relationship extraction is carried out based on the text blocks, and a knowledge graph is constructed; constructing a mapping relationship between the abstract tree and the knowledge graph, and obtaining a vector database; performing entity extraction and query association degree calculation based on user query, judging a retrieval type of the user query, and obtaining a corresponding retrieval result by utilizing the vector database according to the retrieval type; and inputting a retrieval result into the large language model to generate a result. Aiming at the defect of insufficient quality of intelligent questions and answers generated in the medical field by retrieval enhancement generation, the method disclosed by the invention has the advantages that depth and breadth can be considered by one-time retrieval by constructing an abstract tree and a knowledge graph, forming an abstract tree-knowledge graph double-layer index and dynamically typing according to the query association degree, so that the accuracy and efficiency of medical questions and answers are improved.

The invention provides a medical document intelligent generation method based on retrieval enhancement and multi-modal features, and relates to the technical field of intelligent retrieval, the method comprises the following steps: constructing a cross-modal semantic association map to realize semantic fusion and path reasoning of multi-modal medical data; retrieving relevant document segments from a knowledge base based on the atlas representation; and performing graph-guided sequence generation, converting a document skeleton according to a causal logic path, dynamically fusing candidate fragments and keeping semantic consistency. According to the method, the accuracy, logicality and clinical correlation of medical document generation can be improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

To provide a computer program, an information processing method, an information processing device, an information processing system, and an anonymization device that can be expected to support creation of a medical document based on medical information stored in a database, retrieval of medical information, or the like.SOLUTION: Receiving an input of identification information of a target patient, receiving an input of condition information related to generation of the medical document, acquiring one or a plurality of pieces of medical information from the database on the basis of the received identification information of the target patient and the condition information, and generating prompt information related to the generation of the medical document on the basis of the condition information; Inputting the acquired medical information and the generated prompt information to a language model, acquiring a medical document output by the language model, and displaying the acquired medical document on a display unit.SELECTED DRAWING: Figure 16

The invention discloses a medical document processing method and system based on a double-pipeline architecture, and relates to the technical field of document processing. According to the medical document processing method based on the double-assembly-line architecture, through a closed-loop process of document classification, preprocessing, double-assembly-line directional parallel processing and hierarchical vectorization storage, precise adaptation and efficient processing of multi-format and multi-type medical documents are achieved, the information loss rate and the key information truncation rate are greatly reduced, and the medical document processing efficiency is improved. According to the method, the document processing efficiency and the data standardization degree are improved, the warehousing success rate and the data traceability of the vector library are ensured, high-quality and structured data source support is provided for subsequent medical intelligent retrieval, clinical question and answer and retrieval enhancement generation system application, the knowledge base construction and maintenance cost is remarkably reduced, and the method is suitable for popularization and application. The problems that in existing medical document processing, medical semantics are not taken into consideration, so that key clinical information is easy to cut off, and a single processing flow cannot adapt to a structured guide and an unstructured case are solved.

The invention provides a medical document multi-language intelligent analysis system, relates to the field of language translation, and improves the accuracy and efficiency of professional term translation. The method comprises the following steps of: firstly, performing language recognition on an original text document by a recognition module through text unitization and context vector generation, and matching a corresponding corpus; then, a translation module carries out lexical element alignment on the source lexical elements through term bank injection and an AI model, the translation process is automatically optimized, and accurate translation of the terminologies is ensured; and finally, the reconstruction module accurately replaces corresponding contents in the original text document with translation output through the mapping file, so as to ensure that the document format and typesetting are consistent. Through the automatic and optimized translation process, the quality and efficiency of professional term translation are remarkably improved, manual intervention is reduced, and the translation requirement of a high professional standard is met.

The invention discloses a medical document knowledge extraction and structured processing system and method based on a large model. According to the system, a user demand is converted into a standard task mode through a task definition analysis module; the cue word automatic generation and optimal selection module generates and selects an optimal cue word according to the cue word automatic generation and optimal selection module; the constrained large model extraction module performs information extraction by using the cue word; the confidence evaluation and calibration module generates interpretable confidence by calculating multi-source signals and performing fusion calibration; the cue word strengthening and fallback retry module performs feedback retry according to the low-confidence result; and the result merging and consistency verification module finally outputs high-quality structured data. According to the method, the full-process automation and high adaptability of medical document information extraction are realized, the output quantifiable confidence provides a solid guarantee for the result reliability, and the practical value and the feasibility of the system are remarkably improved.

The invention discloses a medical document quality evaluation method based on a large language model, which comprises the following steps: acquiring medical document data, and generating medical document classification structured data; configuring a medical document quality evaluation rule according to the medical document quality evaluation method; and constructing a large language model input item by using the medical document classification structured data and the medical document quality evaluation rule, inputting the large language model input item into a large language model for processing, and outputting a medical document quality evaluation result. The invention further discloses a medical document quality evaluation system and device based on the large language model. The method has the following prominent effects: full-amount quality evaluation becomes possible, the method can adapt to expansion and development of the medical document, and quality monitoring of the medical document is changed into prevention in advance from afterward responsibility investigation; the large language model is applied to medical document quality control, the efficiency is greatly improved, and even quality evaluation can be carried out on past historical archives.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

The invention provides an intelligent medical insurance settlement auditing method, device and system based on multi-modal deep learning and interpretability, and aims to improve the intelligence and accuracy of medical insurance auditing, reduce manual intervention and improve the auditing efficiency. The method comprises the following steps: receiving multi-modal data, such as medical documents, diagnosis and treatment records, medicine information, image data and the like, and carrying out data cleaning and standardization processing; a multi-modal neural network model is adopted, a multi-channel convolutional neural network (CNN) is used for image feature extraction, and text data are processed in combination with a long short-term memory (LSTM) network; deciding and providing interpretation for the deep learning model using an interpretability technique (such as LIME); and an auditor carries out manual confirmation and modification according to system suggestions. According to the system, automatic and precise settlement auditing can be realized, a decision-making basis is provided for auditing personnel through the interpretability module, and the efficiency and the accuracy of settlement auditing are remarkably improved.

The application discloses an OCR-based medical document intelligent identification method and system, relates to the technical field of document identification, and comprises the following steps: collecting a medical document image through a mobile terminal, generating a binary image based on the collected image through a U-Net combined with multi-scale feature fusion and an attention mechanism, and performing clipping; based on the clipped binary image, extracting text information through an OCR model, and extracting structured fields according to the layout rules and geometric distribution of the medical document; and performing deterministic rule judgment and risk assessment on the structured data. The application reduces the image calculation complexity through standard gray scale processing, improves the text region feature extraction accuracy through the U-Net structure combined with the CBAM attention mechanism, realizes effective fusion of multi-scale features and noise suppression in combination with the Attention Gate, realizes text direction correction in combination with the Hough transform, and improves the text detection robustness and recognition accuracy.

This invention discloses a method, apparatus, and device for evaluating the quality of medical document images, relating to the field of medical technology. The method includes: acquiring a medical document image to be evaluated; detecting text boxes containing text content within the image; inputting the text boxes into a text fuzzy prediction model to obtain a fuzzy prediction result for the text boxes; and determining the quality of the medical document image based on the fuzzy prediction result. This method can accurately evaluate the quality of medical documents that are partially clear and partially blurred.

This application discloses a method and system for intelligent generation and quality control of medical documents, relating to the field of medical information technology. The disclosed method and system for intelligent generation and quality control of medical documents acquires multi-source medical data, constructs a medical semantic graph network, performs clinical logical reasoning, generates and verifies medical documents, and updates them based on feedback. It can automatically construct a patient-specific medical knowledge network, identify deep semantic relationships between clinical entities, generate logically rigorous professional descriptions, and improve the quality of medical documents and medical safety.

The application provides a medical intelligent verification method and system, and relates to the technical field of automatic verification. The multi-modal large model medical verification system provided in the application can automatically read, understand and check prescriptions and various medical documents, accurately aligns key information by using visual positioning technology, makes compliance judgment in combination with medical knowledge, and is fully explainable, traceable and does not produce hallucinations, thereby greatly reducing the workload of doctors and improving medical safety.

The present application relates to the technical field of artificial intelligence, in particular to a fine-tuned medical knowledge graph question answering system, comprising an input module, a medical Neo4j graph database module, a query module, a fine-tuned medical LLM module and an output module. The fine-tuned medical knowledge graph question answering system converts unstructured medical documents into structured entities, relationships and attributes by constructing a knowledge graph in the medical field and storing them in a Neo4j graph database. In the question answering process, the system first uses the fine-tuned medical large language model to understand the user's question, then generates a Cypher query statement to retrieve structured knowledge from the knowledge graph, and finally outputs the retrieval results and the generation results of the large language model. Compared with the pure large language model question answering system, the "hallucination" problem of the model in the medical professional field is effectively reduced, the accuracy, factuality and traceability of the answer are significantly improved, and the user can verify the rationality of the answer combined with the structured information in the knowledge graph.

The application provides a medical document image information extraction method and system based on computer vision, and relates to the technical field of medical document image processing. The application separates a medical record image into a layout reference layer and a dynamic data layer based on chrominance difference; extracts continuous line segments of the layout reference layer to construct a layout grid and obtain reference coordinates and a reference threshold; scans discrete pixel regions of the dynamic data layer, peels off occluded pixels, and performs connectivity compensation; calculates free coordinates and literal values of the repaired discrete pixel regions, and marks misaligned discrete pixel regions; calculates target mounting vectors based on spatial offset and semantic correction weight to complete position updating; and assembles target structured data according to spatial arrangement order. The application combines layout constraints and semantic verification to effectively improve the accuracy of medical record image information extraction.

This invention discloses a timing device that integrates multiple emergency operation buttons and generates structured medical records in real time, belonging to the field of emergency medical technology. It includes an intelligent terminal recording module, a data integration and communication module, and an intelligent processing and output module. These three modules work together to achieve real-time recording of emergency operations, integrated data transmission, and automatic generation of structured medical records. The intelligent terminal recording module is a dedicated emergency recording terminal equipped with a timing chip and a multi-touch screen. The touch screen interface is dynamically designed according to the ACLS / BLS resuscitation process and features one-button recording for various emergency operations such as chest compressions, bag ventilation, defibrillation, heart rhythm analysis, and adrenaline administration. The timing chip provides millisecond-level timestamps for emergency operation records, enabling precise binding of operation content to the time of occurrence. This significantly reduces the need for clinical manpower, eliminating the need for a dedicated recording nurse through an "operation-as-record" model, and also eliminating the need for manual re-entry of medical documents after resuscitation.

An object of a system according to an embodiment is to efficiently perform automatic generation of a medical document, error detection of a medical bill, and estimation of a medical cost.SOLUTION: The system according to the embodiment includes a medical document generation unit, an error detection unit, a cost estimation unit, a data collection unit, an analysis evaluation unit, and a proposal application unit. The medical document generation unit automatically generates a medical document using the generation AI. The error detection portion detects an input error or inconsistency of a receipt. The cost estimation unit estimates a medical treatment cost based on the treatment plan. The data collection unit collects data such as a medical record, a treatment history, and drug information of a patient. The assay unit analyzes the collected information and calculates a medical fee points. A proposal application part proposes the optimized medical examination plan and applies it to an actual medical examination process.SELECTED DRAWING: Figure 1

The invention discloses an intelligent generation and quality control method and system for a medical document, and relates to the technical field of medical information, and the intelligent generation and quality control method and system for the medical document comprises the steps: obtaining multi-source medical data, constructing a medical semantic graph network, carrying out clinical logic reasoning, generating and verifying the medical document, and updating based on feedback. According to the method, the individualized medical knowledge network of the patient can be automatically constructed, the deep semantic association between clinical entities is identified, the professional narration with strict logic is generated, and the medical document quality and the medical safety are improved.

The invention relates to a medical record summary generation method and device of an electronic medical record system based on a large language model, electronic equipment and a storage medium. The method comprises the steps of receiving multiple medical documents of a patient uploaded by a user and / or a dialogue text input by the user; extracting medical record contents of the patient from the plurality of medical documents and / or dialogue texts; searching similar diagnosis cases from a case library according to the medical record content, and constructing a medical knowledge graph according to the medical record content; according to the medical knowledge graph, the similar diagnosis cases and a preset cue word template, cue words are constructed, and the positions of the medical knowledge graph and the positions of the similar diagnosis cases are reserved in the cue word template; and inputting the cue word into a trained large language model of the electronic medical record system to obtain a medical record summary of the patient output by the trained large language model. By adopting the method, the medical record summary generated by the electronic medical record system based on the large language model is more accurate.

Provided is a method for converting medical documents, including: receiving a medical document to be processed input by a user and a target format requirement for the medical document to be processed; determining a target attribute document template based on the target format requirement; inputting the target attribute document template into a large language model to obtain the attribute information output by the large language model; initializing target document conversion parameters for a medical document processing engine based on the attribute information to obtain a target medical document processing engine; and performing format conversion on the medical document to be processed using the target medical document processing engine to obtain a medical document corresponding to the target format requirement. By initializing the target document conversion parameters for the medical document processing engine with the attribute information, the format conversion of medical documents can be achieved.

The application discloses a large language model intelligent agent construction method and system for personalized medical documents, and particularly relates to the technical field of medical artificial intelligence; when processing a new case, a set of example pairs matched with the new case is selected through a preset screening strategy, that is, the utility data and clinical data of the example pairs are analyzed, the example pairs are first screened through the clinical data, candidate example pairs are determined, and then the screening evaluation index of the candidate example pairs is analyzed, so that the set of example pairs is constructed, the new case input data is filled into the placeholder of the prompt word template, the selected set of example pairs is filled into the example area, the final execution prompt word is formed, the large language model is called, the final execution prompt word is used for interaction, and the draft content of the target chapter is obtained, so that the generated draft content can better adapt to the specific situation of the new case, content rigidity caused by fixed templates is avoided, and the pertinence of the document is improved.

The present application relates to a hospitalization medical record adaptive generation method and device, electronic equipment and storage medium, comprising: obtaining a medical record data set, classifying the medical record data in the medical record data set according to the diagnosis information of the department where the doctor is located, and generating standard medical record text corresponding to each category of medical record data. All medical documents under the standard medical record text are split by configuring scripts, and multiple paragraph contents corresponding to the medical record written by the doctor are extracted. A paragraph association dictionary is constructed according to the paragraph content. The paragraph association dictionary, the paragraph content and the paragraph name list corresponding to the multiple paragraph contents are fused to generate the medical record writing configuration of the doctor individual. The large model is called to iterate the multiple paragraph contents corresponding to the patient medical record data according to the paragraph name list, and the document paragraph conforming to the medical record writing configuration is generated. By analyzing the written medical record of the doctor individual, individualized configuration information is generated, the flexibility of medical record generation is higher, and it is more in line with the writing style of doctors.

This invention discloses a centralized document management and access control system and method for medical information platforms, relating to the field of medical information processing technology. The system includes a centralized document management module, an access control module, and an audit management module. The centralized document management module extracts metadata, performs structured mapping, and constructs associated indexes for medical documents from multiple medical information subsystems, achieving centralized document management. The access control module performs multi-attribute fusion decisions based on user attributes, document attributes, and environment attributes, and achieves fine-grained access control through policy conflict resolution and dynamic adjustment of permission status. The audit management module uses a chain-record structure to associate and store permission decisions and document operations, enabling traceability and integrity verification of audit data. This invention effectively solves the problems of decentralized medical document management, inflexible access control, and difficulties in audit traceability, improving system security and management efficiency.

The invention relates to the field of medical documents, and discloses a medical document writing assistant comprising an end interaction module which constructs a graphical user interface through Python-tkinter, is used for receiving patient identity information and document time range instructions input by medical staff and displaying the generated medical documents, and is in butt joint with a hospital heterogeneous information system through an HL7FHIR standard interface, so that the medical documents can be written in the hospital; and medical data of the specified patient in the corresponding time range is acquired in a sending mode, wherein the medical data comprises an inspection result, an image diagnosis report, a doctor's advice record and vital sign data. Clinical dilemma is broken through full-process automatic design, a front-end interaction module quickly receives an instruction, a data acquisition and standardization module concurrently calls multi-system data based on an HL7FHIR standard, and serial waiting is avoided; the intelligent processing module automatically completes data structuring through a regular expression and a medical pre-training model, the document generation module dynamically fills content based on a template, a standard document can be generated within several seconds, and the efficiency is improved by dozens of times compared with manual efficiency.

A document creation support apparatus acquires information representing a plurality of regions of interest included in a medical image, acquires position information representing a position designated by a user in the medical image displayed on a display device, selects, based on the position information, two or more regions of interest from among the plurality of regions of interest, and derives an evaluation index for each of the two or more selected regions of interest as a target to be in a medical document.

The application discloses an AI-based medical examination information recognition method and system, and relates to the technical field of medical image processing and character recognition. The method aims to solve the problem that the traditional OCR method uses unified preprocessing parameters for the whole image, which cannot adapt to internal quality differences, resulting in limited recognition effect. The method mainly includes: preliminary processing and recognition of medical document images, calculation of risk values by comprehensively considering the confidence of the character area and the image quality parameters, and screening of high-risk target areas; dynamically adjusting the region boundary box according to the test item rules; generating a second set of adaptive preprocessing parameters by iterative optimization for the region; enhancing the target area using the parameters, and synthesizing with the rest of the region image, and finally recognizing and outputting the results. The application can accurately locate and adaptively enhance the low-quality area in the image, effectively improve the accuracy and robustness of complex medical document character recognition, and is suitable for the automatic processing of medical documents such as test reports.

The application provides a medical document retrieval method and system based on a hierarchical knowledge graph, relates to the technical field of medical document retrieval, and comprises the following steps: analyzing and segmenting an original medical document to obtain a standardized medical text unit sequence; adopting a parent-child node index strategy to construct node pairs; constructing a hierarchical medical knowledge graph, wherein the hierarchical medical knowledge graph comprises a clinical decision ontology layer, a medical entity association layer and a document node layer arranged from top to bottom; receiving a user query, adopting a collaborative retrieval strategy to retrieve a basic retrieval database, and obtaining an extended candidate document set; extracting document content features and graph structure features based on the hierarchical medical knowledge graph for each candidate document in the extended candidate document set, inputting a learning ranking model for re-ranking, and obtaining a retrieval result. The application can improve the semantic ranking accuracy of medical document retrieval and make the generated answer have complete knowledge link traceability.