244 results about "Document classification" patented technology

The invention relates to the technical field of medical data management, in particular to a medical data document classification and marking system which comprises a document structure analysis module, a semantic information identification module, a classification and marking module and a document intelligent label module. According to the method, document visualization and retrieval efficiency is improved by analyzing document content and extracting titles, texts and appendixes, analytic performance and operability of data are enhanced by identifying key information and semantic relations and accurately extracting and labeling medical terms, medicine research data and medical record records, storage is optimized according to priorities in combination with classification and marking, and the method is high in practicability and easy to popularize and use. Clinical values and application scenes of documents are clarified, document management processes are refined, management compatible with clinical data formats is formed through structured storage of marked data and classification label generation, storage normalization and retrieval efficiency are improved, the requirement for accurate information calling in clinical tests is met, document management capacity is improved, and the document management efficiency is improved. And support is provided for improvement of clinical decision-making and research efficiency.

The invention discloses a multi-literature intelligent classification and automatic review generation method based on a large language model, which is characterized by comprising the following steps of: retrieving literatures or uploading local literatures, and extracting text contents; identifying keywords by utilizing an algorithm or a large language model; converting the keyword into a vector form by using a vectorization model; summarizing the research direction of the clustering result by using a large language model; comprehensively summarizing the single literature and literatures in different research directions by using a large language model; and executing the steps of reviewing, quotation insertion and the like through a large language model and a vectorization semantic matching technology. Compared with the prior art, the method has the advantages that the efficiency and quality of document classification and review generation are remarkably improved, technologies such as text vectorization, topic clustering and large language model generation are well fused, efficient and accurate multi-document review automatic generation is achieved, the method is suitable for interdisciplinary academic document analysis and information integration application, and the method is suitable for popularization and application. Wide application potential is shown.

A cloud-based network security system (NSS) is described. The NSS uses a sandbox to safely detonate and extract information about a document and uses machine learning algorithms to analyze the information to predict whether the document contains malicious software. Specifically, during the detonation, static and dynamic information about the document is captured in the sandbox as well as character strings from images in the document. The dynamic information (and sometimes the static information) is input to an AI or machine learning model trained to provide an output indicating a prediction of whether the document contains malware. The character strings are compared with a batch of phishing keywords to generate a heuristic score. A validation engine combines the output from the AI or machine learning model and the heuristic score to classify the document as malicious or clean. Security policies can then be applied based on the classification.

Embodiments are directed towards a computer-implemented method for identifying one or more matching elements from a taxonomy present in a document. The method may include identifying the document, the taxonomy, and a question that may be processed by a large language model (LLM). The method may further include applying at least one taxonomy augmented generation (TAG) tactic from a set of TAG tactics to the identified document and to the identified taxonomy. The method may also include generating an input prompt that may be configured to be used as an input for the LLM, where the input prompt may include a document context derived from the document, a taxonomy context derived from the taxonomy, and the question to be processed by the LLM. The method may further include providing the input prompt to the LLM, and receiving a response generated by the LLM.

Methods and systems are presented for classifying a digital image of a document using a machine learning model framework. The machine learning model framework is configured to provide a classification output based on a fusion of features corresponding to different modalities and extracted from the digital image. The machine learning model framework includes multiple encoders. Each encoder is configured to encode features corresponding to a distinct modality into a respective embedding. Different embeddings generated by the multiple encoders are fused together using one or more fusion techniques. The fused embedding is provided to a machine learning model for classifying the document.

To efficiently and effectively classify a large amount of document and text data by an LLM.SOLUTION: The present invention relates to a text classification system 1 which classifies documents accumulated in a document DB 14 by categories, and the text classification system has a classification processing part 12 which lets an LLM 2 proposes one or more categories based upon a classification policy specified by a user, a search processing part 13 which searches the document DB 14 for documents belonging to the respective proposed categories, and a UI processing part 11 which presents the respective categories and the numbers of documents belonging to the respective categories to the user.SELECTED DRAWING: Figure 1

In an approach, a processor performs document layout analysis on a document generating a plurality of textual regions; extracts characteristics from each of the plurality of textual regions and associates the respective characteristics to the respective textual region as metadata; classifies each of the plurality of textual regions as an optical character recognition (OCR) region, non-OCR valuable region, or non-OCR non-valuable region using a classifier; performs OCR on each OCR region generating an OCR output; identifies associated constant OCR data from a constant OCR data repository for each non-OCR valuable region; merges the associated constant OCR data with the OCR output generating a complete OCR data for the received document; performs data extraction on the complete OCR data to identify data fields and key-value pairs generating extracted data; and determines whether the extracted data is valid based on a set of rules.

Systems and methods described herein provide a document processing service using customizable schemas. First user input includes a document and second user input identifies a classification schema. The classification schema is retrieved to obtain first prompt content. Prompt data is generated. The prompt data includes the first prompt content and second prompt content that includes a document classification instruction. The prompt data and document content of the document are processed by a large language model to obtain a classification result for the document. The classification result is presented via a user interface at a user device.

The invention discloses a document multi-classification method based on cooperation of a large language model and a deep learning algorithm, relates to the technical field of document classification, and solves the technical problem of low final classification efficiency caused by the fact that different document types are not considered in the prior art. According to the method, user documents and historical data are collected, the user documents are input into an LLM model, document key information and important keywords are extracted, prediction tags are obtained by combining document theme prediction, and the prediction tags and the important keywords are bound to obtain classification tags; setting an information coefficient based on historical data, calculating according to the classification label and a set correct prediction label to obtain a prediction correct rate, and combining the prediction correct rate with the information coefficient to obtain a document classification confidence coefficient; setting a confidence coefficient threshold according to the historical data, comparing the document classification confidence coefficient with the confidence coefficient threshold, and obtaining a classification state according to a comparison result; and adjusting and optimizing the large language model based on the classification state to obtain a final classification confidence coefficient.

The invention relates to an AI intelligent document processing method based on a large language model, and the method comprises the steps: receiving the input of an original document, and obtaining the text features, visual layout features and semantic structure features of the document through a multi-modal feature extraction module; processing the multi-modal features by using a layout-aware attention mechanism, and generating an incidence matrix of document elements; inputting the extracted features into a pre-trained large language model, and generating an intermediate representation containing an association relationship between document elements; and dynamically selecting a processing path according to task requirements, wherein the processing path comprises but is not limited to document classification, information extraction, content generation or question and answer response. According to the AI intelligent document processing method based on the large language model, through an attention mechanism of layout perception and an experiment on a standard data set, table structure recognition F1-score is improved, the cross-page element association accuracy is greatly improved, the vision-text feature alignment loss is reduced, the processing time of a 100-page PDF document is greatly shortened through a dynamic partitioning processing strategy, and the processing efficiency of the 100-page PDF document is greatly improved. And the memory occupancy peak value of the GPU is reduced.

The invention discloses a reimbursement process optimization method and device based on a multi-modal model. The method comprises the following steps: receiving a to-be-reimbursed material submitted by a target object; performing image recognition and text extraction on the to-be-reimbursed material to obtain document classification information and reimbursement text information of the to-be-reimbursed material; determining a reimbursement type based on the information by using a reimbursement classification model; comparing the feature information of the target object and the above information with fields in the reimbursement application form, and if missing information does not exist, directly generating a target reimbursement application form according to the above information; otherwise, filling the missing information submitted by the target object into the reimbursement application form to generate a target reimbursement application form; and submitting the target reimbursement application form to enter a reimbursement process. The technical problem that the efficiency and accuracy of the reimbursement process are low due to the fact that the traditional financial reimbursement process generally depends on manual operation, the operation process is tedious and time-consuming, and errors are prone to occurring in the prior art is solved.

The invention discloses a construction project contract dispute judgment document classification system based on natural language processing, and relates to the crossing field of project management and natural language processing. The system comprises a document receiving module used for supporting dragging, dropping and reading of judgment documents; the text preprocessing module is used for preprocessing documents and screening phrases with dispute focus key information; the dispute type classification module is used for inputting and transmitting the text into a BERT-BiLSTM-Attention classification model to obtain the dispute type of the text; the dispute focus classification module is used for transmitting the text input into a RoBERTa-TextCNN-GLU classification model to obtain a corresponding dispute focus; and the system function module is used for displaying the text content and the classification result after inputting the judgment document to obtain a dispute type and a dispute focus corresponding to the document. The purpose of system design is to realize rapid information extraction of construction project contract dispute judgment documents, so that related enterprises can rapidly understand basic conditions of the judgment documents, and the enterprises can also be helped to establish a high-quality and sound project contract risk control system.

Embodiments of the invention disclose a document classification method and apparatus, a device and a medium. The method comprises the steps of obtaining a pre-generated classification corpus; obtaining a field vocabulary of the specified enterprise; obtaining keywords of the documents based on relevancy between preset vocabularies in the field vocabulary and the documents; respectively converting the training set documents and the test set documents in the plurality of document features into a first feature vector of each training set document formed by the relevancy of the keywords of the training set documents and a second feature vector of each test set document formed by the relevancy of the keywords of the test set documents; based on the first feature vector of each training set document, training to obtain a document classifier, the document classifier being constructed through a machine learning model; testing and evaluating the document classifier based on the second feature vector; and if the document classifier passes the test evaluation, deploying the document classifier so as to classify the newly added documents in the classification corpus through the document classifier.

The invention discloses an intelligent official document classification system based on label semantic comparison fusion perception, which can adaptively learn and adapt to different types of official document data, and does not depend on a fixed mode rule, thereby improving the processing capability of diversified data. By adopting an advanced artificial intelligence classification algorithm, the understanding and classification precision of the system on official document contents is improved, and particularly, when documents with similar label semantics are processed, nuisance can be accurately distinguished; the system can automatically learn and optimize a classification strategy, reduces manual intervention, and improves the working efficiency and the processing speed.

The invention discloses an intelligent talent information analysis method based on deep learning, which realizes automatic extraction and classification of resume, educational background, identity card and bank card information through intelligent analysis and document classification by adopting a deep learning technology and an improved OCR (Optical Character Recognition) model. Secondly, a sliding window is combined with a BERT-CRF model, the limitation of a traditional BERT model on the length of a long text is broken through, long document information can be completely recognized and extracted, automatic correction of image areas of an identity card and a bank card is achieved, and finally a data correction cleaning method is provided. And the BERT-CRF model is used for filtering and uniformly formatting and outputting the recognized text information, so that the information processing efficiency and the structuralization degree are greatly improved. By adopting the method and the device, through automatic document classification and key information extraction, the processing efficiency is greatly improved, the error probability is reduced, and an efficient, accurate and reliable information processing solution is provided for the talent recruitment process.

The invention provides a document classification method, which belongs to the field of data classification, and comprises the following steps: collecting original documents of different languages from a plurality of channels, and converting texts of different languages into a unified language representation form; extracting keywords in the document after language conversion, calculating word frequency and inverse document frequency of each keyword in the corresponding document, weighting the word frequency by adopting the inverse document frequency to obtain a plurality of TF-IDF weights, and converting the plurality of TF-IDF weights into a plurality of word embedding features; meanwhile, text data similar to the embedding features of the multiple words in the original document are labeled; inputting the plurality of word embedding features into a natural language processing model to train the model, and training the trained model again through the labeled document data to obtain a semantic encoder; and inputting the to-be-classified documents of different languages into a semantic encoder, and outputting a classification result. According to the method, the documents of different languages can be accurately classified by adopting two hierarchical training models, so that the document classification efficiency is improved.

An AI-assisted document organization system includes an internet equipment, an identification equipment, a processing unit which is matched and connected to the internet equipment and the identification equipment. The processing unit includes a central processor, an artificial intelligence software and a document organization software. The document organization software includes document organization goals which include automatic document classification and identification, artificial intelligent data extraction, automatic data verification, automatic approval verification, compliance and regulatory compliance, document tracking and control, automatic reporting, and notification. The central processor drives the artificial intelligence software. The processing unit acquires document data through the identification equipment. The artificial intelligence software reads the document data and, based on the document organization goals set by the document organization software, to search relevant information via the internet equipment and intelligently calculate the best organization solution for the obtained document data. The database stores the classified and organized document data.

The invention relates to the technical field of artificial intelligence and engineering management, in particular to an intelligent review system for engineering industry documents based on a large language model, which comprises a multi-level review point library, a document access module, a document classification module, a large language model processing module and a review report generation module, the multi-level review point library is in four-level classification, covers review dimensions such as multi-service fields, professional classification, project stages and integrity, and provides review standards; the document access module supports multi-type document and multi-channel access; the document classification module performs automatic classification based on a BERT model of engineering corpus fine adjustment; the large language model processing module matches the examination point list, performs slice examination and outputs opinions; the review report generation module summarizes the opinions to generate a structured report, so that the whole-process intelligent review of the document is realized; according to the method, the problems of low efficiency, long time consumption of complicated documents, non-uniform standard and poor result consistency caused by difference of standard understanding of reviews in traditional manual review are solved.

The invention provides a document classification method and device, electronic equipment and a storage medium, and relates to the technical field of computers. And constructing a standard subject classification system at least comprising a standard subject identifier uniquely corresponding to the subject. Extracting a target literature meeting a preset condition; the preset condition is that at least one identifier consistent with the standard subject identifier exists in the original subject identifiers labeled for the literature in advance. And based on the standard subject identifier, processing the original subject identifier to obtain a target subject identifier of the target literature in the standard subject classification system. Equivalently, a standard subject classification system is used as a unified standard of document classification, and subject identifiers of documents from different sources are standardized, so that the target document and the target subject identifier form a high-quality training data pair. Training data is utilized to train a specified large model, a document classification model is obtained, and the classification performance of the model is improved. The subject identification of the to-be-classified literature is determined by using the literature classification model, so that the accuracy of literature classification is ensured.

The invention provides an agent construction method and system based on a large language model, equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the steps that a user interaction module is called to receive a first target document input by a user; calling a document analysis module to analyze the first target document to obtain a plurality of first chapter titles; calling an automatic mapping module to classify the plurality of first chapter titles based on a document classification model, and constructing a mapping relationship between the plurality of first chapter titles and a plurality of second chapter titles of a second target document based on a classification result; calling a large language model to respectively extract and summarize paragraph contents of the plurality of first chapter titles to obtain paragraph contents of a second chapter title; and calling a document output module to output the second target document according to a preset format. According to the agent construction method and system based on the large language model, the equipment and the medium provided by the invention, the accuracy of generating the review report by the agent can be improved.

The invention discloses a multi-page bidding document-oriented classification and key information extraction method and system, and the method comprises the steps: obtaining bidding document image data containing a plurality of pages, and constructing a corresponding document representation data set; performing structured modeling on bidding document image data corresponding to each page in the document representation data set, extracting and fusing multi-modal features, and constructing unified page representation; based on the unified page representation, document module type classification is carried out on the pages, and structure category labels which all the pages belong to are obtained; on the basis of the structure category labels of the pages, in combination with the multi-modal features of the corresponding pages, key information extraction operation is executed, and target field information contained in the corresponding pages is extracted; and outputting a structured result, wherein the structured result comprises the structure category label to which each page belongs and the corresponding target field information. According to the method, accurate classification of the pages in the bidding and tendering document is realized, targeted key information extraction is performed, and the method has relatively high accuracy, maintainability and actual landing capability.

The invention discloses a document classification method and electronic equipment, and relates to the technical field of computers.The document classification method comprises the steps that multi-dimensional information of a to-be-classified document is extracted from multiple dimensions, multi-dimensional feature vectors are extracted through different feature extraction methods according to different dimension information, and the multi-dimensional feature vectors are used for classifying the to-be-classified document; a weighted fusion method based on an attention mechanism is adopted to construct comprehensive document feature vectors, and meanwhile, importance weights of feature vectors of all dimensions are dynamically adjusted, so that features which contribute to classification greatly obtain higher weights, the effectiveness of feature fusion is improved, and the accuracy of feature fusion is improved. And finally, based on the pre-trained classification model, realizing accurate classification based on the document feature vector, thereby effectively solving the technical problem that the document classification accuracy and robustness are seriously insufficient, and achieving the technical effect of improving the document classification accuracy.

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.

A system for determining hierarchical relationship in batches of documents is disclosed. A data collection module receives one or more batches structured and unstructured documents. A metadata configuration module defines the plurality of metadata fields, enabling structured metadata extraction. The metadata extraction module identifies and extracts metadata attributes using an artificial intelligence model or extraction techniques. A first level verification module classifies documents as parent or child based on extracted attributes. A reviewer module allows specialists to manually validate classifications. A rule defining module enables user-defined match-up rules for parent-child and peer-to-peer relationships. A second level verification module refines classification using contextual analysis and generates structured data including the metadata attribute and the corresponding plurality of metadata fields, the parent-child relationship and the peer-to-peer. The structured data is reviewed, and confirmed, by the one or more specialist. A display module to provide reviewed structured data to the user.

The invention provides a financial document classification method based on dynamic resource allocation and an attention mechanism, and relates to the technical field of natural language processing and document intelligence, and the method comprises the steps: generating a hidden state sequence containing local context information through time step-by-step processing based on a numerical text sequence; screening a key Token according to the hidden state sequence, and dynamically allocating computing resources; performing global dependency relationship modeling on the key Token to generate a semantic representation vector; and calculating probability distribution of each receipt type based on the semantic representation vector, and determining the corresponding receipt type according to the probability distribution.

A data processing system implements a method for training machine learning modes, including receiving a set of one or more unlabeled documents associated one or more first categories of documents to be used to train machine learning models to analyze the one or more unlabeled documents, and fine-tuning a first machine learning model and a second machine learning model based on the one or more unlabeled document to enable the first machine learning model to determine a semantic representation of the one or more first categories of document, and to enable the second machine learning model to classify the semantic representations according to the one or more first categories of documents, the first machine learning model and the second machine learning model having been trained using first unlabeled training data including a second plurality of categories of documents that do not include the one or more first categories of documents.

A method is disclosed for analysing a data set to determine a first processes. First messages are provided, the first messages classified into a plurality of different classes with a plurality of different likelihoods, a single first message classified into different classes based on different criteria. From the first messages a first subset of the first messages is retrieved based on a combination of one or more classifications, a likelihood of the one or more classifications, and another classification for messages within the first subset of the first messages. The likelihood of the classifications has more than two (2) potential values.

A system includes a processor and a memory. When executed by the processor, the processor is caused to receive a document including at least one of structured data, semi-structured data, and unstructured data, analyze the metadata in the structured format to generate features enhancing the metadata in the structured format, produce classification data for the document based on the features enhancing the metadata in the structured format and the content in the unstructured format, automatically classify the document based on the classification data and store the classification data in a database structure. The classification data is used to effectively search for the document. The structured data includes metadata about the document in a structured format, the semi-structured data includes content of the document in an unstructured format and metadata about the document in the structured format and the unstructured data includes the content of the document in the unstructured format.