6166 results about "Contextual information" patented technology

The invention discloses a multi-round knowledge-guided question-answering method and system fusing a large language model and a knowledge graph. The method comprises the following steps: S1, constructing the knowledge graph; s2, performing retrieval and clarification; s3, extracting labels and classifying questions; s4, performing scene guidance and dynamic retrieval; and S5, answer generation and formatting output. The method aims at solving the fuzzy problem in complex policy and regulation questions and answers, and the accuracy of user demand analysis and the comprehensiveness of answers are improved. According to the method, a knowledge graph is taken as a core, and multi-path semantic analysis and problem guidance capabilities are provided by constructing a hierarchical structure covering first-level items, second-level items, scene categories and keyword nodes. In combination with strong semantic comprehension and generation capabilities of the pre-trained large language model, the system can dynamically track context information in user input, iteratively access related nodes along different paths of the knowledge graph, and gradually clarify user intentions.

The disclosure presents a multi-agent AI system utilizing specialized Large Language Models (LLMs) to automate and enhance software development workflows. This system integrates a memory-augmented generative pre-trained transformer (MemGPT) agent for dynamic context management, a Critic Agent for semi-adversarial quality feedback, and other specialized agents for task delegation and execution. The MemGPT agent interacts with an embedding storage to manage extended contextual information, enabling the system to handle complex software projects with enhanced accuracy and efficiency. This innovative approach significantly reduces manual intervention, streamlines the development process, and improves software quality, offering a robust solution to the challenges of modern software development environments.

A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

An example operation may include one or more of receiving context of a user during an inquiry of a feature via a software application, executing a waiting period via the software application, during the waiting period, selecting an animation to display via the software application based on the context of the user and the feature inquiry wherein the animation provides contextual data associated with the feature, wherein the contextual data is based on a determined need of the user, displaying the animation via the software application during the waiting period, and determining if the user has accepted the feature via the software application. At least one portion of the example operation: integrates with an artificial intelligence (AI) chatbot, interacts with the AI chatbot, is performed by the AI chatbot, and / or is associated with an AI model.

One or more data streams may be used for controlling multi-system interaction. For example, a data stream may be received, and a surgical option associated with a surgical instrument may be selected based on the data stream. A control signal associated with the surgical instrument may be generated based on the selected surgical option. A surgical device may receive an external data stream from a source external to the surgical system. The device may derive, based at least on the external data stream, decision contextual information. The device may select a surgical option associated with a surgical instrument based on the decision context information. The device may generate a visual indication of the decision context information associated with selecting the surgical option. The device may generate a control signal associated with the surgical instrument based on the selected surgical option.

The invention provides an intelligent vulnerability mining platform construction method and system based on a large model. The intelligent vulnerability mining platform systematically identifies and analyzes potential security risks, collects and identifies code snippets with the security risks, arranges the code snippets into risk code paragraphs, identifies target code paragraphs, determines known vulnerabilities, generates context information, captures key events in actual operation, and records real execution paths and state changes. The method comprises the steps of generating a dynamic execution track, simulating different paths, generating an attack vector path, predicting unknown vulnerabilities and credibility scores of the unknown vulnerabilities, testing prediction results of high-credibility scores, confirming and generating real vulnerability information, recording the information to a vulnerability knowledge base, and generating a security report containing vulnerability description, influence ranges, risk levels and repair suggestions. According to the technical scheme provided by the embodiment of the invention, the detection accuracy and efficiency of the security vulnerabilities in the software system are improved.

An Applicant Assistant System may receive, from a user device, a user input indicating a query or task associated with information displayed in a user interface. The device may determine one or more components associated with the user interface and access component metadata of the determined one or more components, the component metadata for each of the one or more components indicating one or more of a fact, a data link, or an action. A prompt comprising at least some of the component metadata, at least some context information, and an indication of one or more available response elements may be provided to a large language model (LLM). The LLM may response with one or more response elements that may be processed by the System, such as to cause updates to the user interface on the user device.

The invention discloses an intelligent question answering system construction method and system based on an LLM large language model, and the method comprises the steps: carrying out the corpus aggregation from a plurality of heterogeneous data sources, and dynamically capturing the text data related to a target domain; preliminarily screening the text data, and based on semantic similarity and a text quality scoring rule, removing redundant and low-quality text data or text data irrelevant to a target field; performing diversity analysis on the text data, and generating diversified text data with high similarity with real data through an adversarial generation technology; performing multi-level semantic annotation on the text data, and generating a training sample by analyzing context information in the annotated corpus; and converting the training sample into a standard format sample, and training an LLM large language model by using the standard format sample to serve as an intelligent question-answering system of a target domain. By utilizing the embodiment of the invention, the intelligent level of the intelligent question-answering system in various application scenes can be effectively improved, and further development of the intelligent question-answering technology is promoted.

Automatically investigating security incidents and generating security incident reports using a Large Language Model (LLM). A computerized system receives an incoming Security Alert Message pertaining to a possible security-related incident. The system automatically feeds into the LLM at least: the content of the Security Alert Message; the metadata of the Security Alert Message; context information describing a security domain; and organization context information pertaining to users and machines of that organization. The system automatically prompts the LLM to automatically investigate the Security Alert Message and to automatically generate a detailed Incident Report pertaining to the Security Alert Message.

The invention provides a service data security protection method and system for digital enterprise management, and the method comprises the steps: obtaining an access request sequence initiated by a target user at a service operation terminal, generating a dynamic access control strategy vector according to a historical behavior track associated with an access operation identifier, and carrying out the dynamic access control strategy vector; analyzing the dynamic access control strategy vector through a strategy decoder, and generating a real-time access permission instruction; based on the real-time access permission instruction, performing homomorphic encryption mapping on a sensitive data segment in the request context information to generate a ciphertext transmission channel, and performing security parameter synchronization on the ciphertext transmission channel and the cross-department conjoint analysis model; and calling a federated learning framework to carry out multi-modal feature fusion on the real-time operation flow of the service operation terminal, generating an abnormal operation confidence score, triggering a cross-level interception protocol when the abnormal operation confidence score exceeds a dynamic threshold, and rolling back the current session state to a security baseline version. According to the invention, the accuracy and response timeliness of anomaly detection can be improved.

The invention relates to the technical field of medical image diagnosis, and discloses a medical image automatic diagnosis method and system based on deep learning. According to the method, multi-modal medical image data of a target object is acquired and standardized, a two-channel convolutional neural network is utilized to extract features, the features are processed through cross-modal feature fusion, adaptive attention weight distribution and other technologies, a cascaded two-way long-short-term memory network is adopted for modeling, abnormity is detected based on a probabilistic graph model, and the target object is identified. And the nidus is segmented by a multi-scale context information enhancement module, and finally a diagnosis suggestion is generated by a diagnosis inference engine driven by a knowledge graph. The system comprises a multi-modal image acquisition interface module, a distributed feature calculation cluster, a visual interaction terminal and a security audit module. According to the method, the accuracy and efficiency of medical image diagnosis can be improved, comprehensive diagnosis reference is provided for doctors, and meanwhile data safety and privacy are guaranteed.

A three-dimensional point cloud semantic segmentation method based on graph convolution and a grouping vector attention mechanism adopts a network structure of a U-Net style, feature extraction and propagation are performed on point cloud through multi-level feature coding and decoding, each level firstly centralizes and standardizes local neighborhood features through a geometric affine module, and then the local neighborhood features are subjected to feature extraction and propagation; the capturing capability of the model on the diversity of the local region is enhanced; secondly, constructing a local neighborhood graph, and designing an asymmetric edge feature learning function to extract local topological information; deep edge features are further extracted in combination with a residual network; and finally, selectively fusing local features and global context information under the condition of low parameter quantity by using a grouping vector attention mechanism, and performing cross-level feature interpolation up-sampling to an original scale to complete point cloud segmentation. The method can significantly improve the point cloud segmentation precision, and is suitable for the perception of a mobile robot and other devices carrying a three-dimensional sensor on a complex scene.

Conducting user research with human users is time consuming and expensive. Provided with quality training data that represents human users having different personae, models can be trained to offer responses that can emulate different human users. The models may offer synthetic users that can extract information from and respond to inputs to the models. The inputs can include prompts and responses can include answers to the prompts. In some cases, data about human users can be used to build different synthetic user memories, which may be used to generate different prompt chains corresponding to different users. The prompt chain can be used to prompt a model to respond based on the contextual information in the synthetic user memory.

The invention discloses a Transform-CNN medical image segmentation method and system based on multi-scale fusion semantic enhancement, and relates to the technical field of image segmentation, and the method comprises the steps: collecting medical image data, and constructing a medical image data set; constructing a medical image segmentation network model; training the medical image segmentation network model through the medical image data set; and inputting real-time acquired data into the trained medical image segmentation network model to obtain a medical image segmentation result. According to the invention, double encoders, LGDA modules and the like are adopted to capture multi-scale global features of kidney tumors and enhance representation, and the LGDA module is used for adapting to size and form changes of the kidney tumors; the MLCF module is used for supplementing information of the main encoder; the PSE module captures multi-scale global semantic information and integrates local context information, local features are fused through the SAM module, and kidney tumor positioning in an endoscope image is achieved.

The invention discloses a cockpit active recommendation system and method based on a knowledge graph and semantic reasoning, and relates to the technical field of intelligent cockpits. The system receives natural language voice input of a user, executes voice recognition and semantic analysis, extracts user intention, keywords and slot entities, generates structured semantic information, constructs or calls a knowledge graph structure with semantic relation edges in combination with environment context information, and obtains the knowledge graph structure with the semantic relation edges. Semantic path reasoning is carried out based on the path dependence weight and the semantic similarity, a semantic edge label guided graph attention mechanism is introduced to calculate a path consistency score, a candidate recommendation set is generated, the semantic fitting degree and the path score are fused to sort and output recommendation content, and the graph edge weight and the user portrait are updated based on user feedback. According to the method, semantic understanding precision, recommendation path interpretability and system adaptive capacity are improved, and the method is suitable for personalized voice recommendation, man-machine interaction and scene linkage control tasks in an intelligent cockpit.

The invention provides a feature fusion method and system based on multi-modal medical data, and belongs to the technical field of medical data processing. According to the method, the structural relationship, such as a patient network, a biological pathway and an anatomical structure, in the medical data is modeled by using # imgabs0 #, the extracted structured features are input into # imgabs1 # to capture global context information, and a self-adaptive mechanism can dynamically adjust the feature weights output by # imgabs2 # and # imgabs3 # according to the data modality, so that more accurate feature fusion is realized. Experimental results prove that the model provided by the invention is superior to other baseline models on a plurality of multi-modal medical data sets.

The invention discloses a block chain-based medical data management method, system and device, and a medium, and relates to the field of information management. The method comprises the following steps: acquiring medical data, analyzing content attributes and context information of the medical data through a first smart contract on a block chain, and generating a first sensitivity level identifier; based on the first sensitivity level identifier, performing differential encryption on the medical data through a second smart contract on the block chain, and generating verification information; partitioning the differentially encrypted medical data, constructing a data structure together with the verification information, and storing the data structure into a block chain; in response to the received access request, verifying an authority certificate in the access request and the type of the access request through a third smart contract on the block chain, and generating an access authorization certificate; and outputting target medical data corresponding to the access request based on the access authorization certificate. By implementing the technical scheme provided by the invention, the full-life-cycle safety management and control of the medical data from collection, storage to sharing is realized.

The invention relates to a remote education data processing system which comprises the following steps: under a remote teaching task, pre-defining a task intention and a data expectation point; a semantic timestamp and a task binding label are printed on each data fragment; mapping the collected confusion data including silence, eye movement drift and prediction into a unified learning semantic vector; a micro-expression + interactive behavior + time sequence decision path ternary modeling mode is introduced, and a potential cognitive intention corresponding to the feature combination is recognized; teaching context information is fused; constructing a cognitive state mapping model; reasoning a current cognitive state label from multi-modal sensing data; searching intervention track VS effect feedback data in a historical database; generating a predicted intervention behavior sequence by using a sequence modeling algorithm; a dynamic combination suggestion chain including light prompt, content reconstruction, personalized practice and tutoring invitation is adopted; and superposing the cognitive state sequences of all students into a group cognitive trajectory map.

The invention discloses an LLM-driven complex report OCR error self-correction method and system, and the method comprises the following steps: S1, obtaining complex report image data, executing OCR processing, and constructing an original field data set; s2, extracting context information, identifying semantic contradiction fields, and generating a to-be-corrected field set; s3, the pointer generation network generates a plurality of field correction candidates to form a candidate field set; s4, constructing a dobby machine model, selecting an optimal field correction result, and forming a correction field output set; s5, executing format analysis, and extracting a chart title field, a legend field and a data region text; s6, generating a corrected field result of a chart title field according to a chart structure semantic consistency mechanism; and S7, performing field restoration and format reconstruction, and outputting structured report data. According to the method, intelligent error correction and structured reconstruction of fields in a complex report are realized by fusing a large language model, a pointer generation network and a multi-arm machine mechanism.

The invention relates to the field of remote sensing image processing, in particular to a high-resolution remote sensing image semantic segmentation method based on multi-scale feature fusion, which comprises the following steps: acquiring a public remote sensing image data set, preprocessing the image, and constructing a training and testing set of semantic segmentation; a CTMFNet is designed, an encoder is composed of a lightweight residual module and an MS-Transform, and local space details and global context information are extracted; rID is adopted to reduce spatial information loss, LSFE is introduced to improve spatial positioning capability, and feature calibration is carried out in space and channel dimensions through DecoderAttn to realize boundary fine segmentation; inputting the training sample into the network for training to obtain a converged optimal semantic segmentation model; and inputting the test set into the model to obtain a semantic prediction map, and outputting a fine segmentation result of the remote sensing image through multi-scale fusion and boundary restoration. According to the method, the precision and robustness of ground feature extraction are effectively improved, the calculation cost is remarkably reduced while high segmentation precision is kept, and the method has good practical value and popularization prospects.

The invention relates to a power log intelligent analysis system based on a knowledge graph and a large language model. The power log intelligent analysis system comprises a data collection and preprocessing module, a knowledge graph construction and management module, a context understanding and correlation analysis module, a personalized report generation module and a multi-modal data integration module. According to the method, information such as equipment, events and operations in the power logs is structured through the knowledge graph and is associated with domain knowledge, so that deep understanding and association analysis of log contents are realized, and the problem of insufficient context understanding in a traditional method is solved. By utilizing the strong generation capability of a large language model and based on context information provided by a knowledge graph, a personalized report meeting roles and requirements of a user can be automatically generated, and the user experience and practicability of log analysis are improved; log data in various formats are integrated into the knowledge graph, a comprehensive summary report containing information such as charts and timelines is generated through a large language model, and the problem that heterogeneous data are difficult to integrate is solved.

The invention discloses an optical remote sensing image salient target detection method based on progressive attention enhancement, and belongs to the technical field of computer vision. The method comprises the following steps: preprocessing an original data set; inputting the preprocessed image into a hierarchical progressive fusion encoder, capturing a global irregular topological structure and local fine-grained image details, and realizing cross-hierarchical feature fusion; inputting the output characteristics of the encoder into a global context enhancement module, and capturing multi-level context information by adopting a parallel multi-branch structure; and inputting the output features of the hierarchical progressive fusion encoder and the global context enhancement module into a multi-scale progressive attention enhancement decoder, carrying out hierarchical decoding on the input features by adopting a saliency-guided attention mechanism, and gradually aggregating deep semantic information and shallow detail features to realize coarse-to-fine progressive optimization, so as to improve the robustness of the multi-scale progressive attention enhancement decoder. And finally generating a saliency map. The method can effectively improve the processing performance of an irregular topological structure and a complex context relationship in the optical remote sensing image.

The invention relates to a cerebrovascular three-dimensional evaluation method based on multi-scale feature fusion, and the method constructs a multi-scale feature fusion model which comprises a pilot segmentation network, a fusion segmentation network and a topology-style loss module. The pilot segmentation network is based on a dynamic Unet network, the response of the model to the complex boundary of the cerebrovascular image is enhanced, and the pathological detection performance is improved. The fusion segmentation network introduces a feature selection module, and effectively fuses the long-range dependence feature of the Transform layer and the local context information of the CNN layer, so that the model can accurately extract the cerebrovascular features under different scales. The topology-style loss module optimizes model parameters by combining a topology loss function and style self-consistency loss, restrains the topology continuity of a segmentation result, and effectively solves the problem that blood vessels are easy to break in a traditional segmentation method. The method effectively improves the cerebrovascular image segmentation precision.

Methods, systems, apparatuses, devices, and computer program products are described. A system may obtain a set of documents associated with a knowledge base for retrieval-augmented generation (RAG). The system may generate multiple representations of the information included in the documents using multiple knowledge extraction pipelines. For example, the system may generate a set of metadata-based vector embeddings based on the documents, a set of knowledge graphs based on the documents, and a set of hierarchical tree representations based on the documents. The system may receive a user query and may retrieve contextual information from the set of vector embeddings, the set of knowledge graphs, and the set of hierarchical tree representations to augment the user query for a large language model (LLM) prompt. The system may input the prompt to the LLM, and the LLM may output a response based on the user query and the contextual information.

The invention discloses an unmanned aerial vehicle multi-modal feature fusion target tracking method and system based on natural language description, belongs to the technical field of computer vision and image processing, and solves the problem that in the prior art, when the quality of an image collected by an unmanned aerial vehicle is poor or image features are not obvious, the target tracking capability and the long-time tracking capability are poor. Natural language description is carried out on a traffic accident scene in an image of an unmanned aerial vehicle visual angle, and a language prompt is obtained; constructing a scene-context feature pyramid network to perform context information enhancement processing on the image of the view angle of the unmanned aerial vehicle to obtain a feature-enhanced image; respectively carrying out visual coding and language coding on the enhanced image and language prompt to obtain visual features and language feature vectors, and carrying out visual-language bimodal feature local alignment; and fully fusing the obtained aligned new language features with the visual features to obtain multi-modal features for target tracking. The method is used for multi-modal feature fusion target tracking of the unmanned aerial vehicle.

The invention relates to the technical field of information security, and discloses a data security management system and method in an intelligent power grid, and the system comprises a dynamic encryption and key management module which is used for carrying out the encryption and key management of the data of the intelligent power grid, determining an encryption algorithm according to the sensitivity of the data, and generating a corresponding key, the dynamic encryption and key management module transmits encrypted data and key information to the adaptive access control module so as to ensure the security of data access; and the self-adaptive access control module is used for managing access permissions of the user and the equipment and performing dynamic authorization according to the attribute label and the context information. Through dynamic encryption and adaptive key management, an encryption algorithm and a key length are adjusted in real time according to data sensitivity and a network environment, a quantum key distribution technology is combined, high security and quantum attack resistance of a key are ensured, and then security and real-time performance of data transmission are ensured.

The invention relates to the technical field of remote sensing image recognition, in particular to a remote sensing sewage area recognition method and system based on a graph structure and multi-stage enhancement. The method comprises the steps of performing data preprocessing and representation enhancement on an acquired remote sensing image; performing sewage salient region preliminary screening on the enhanced remote sensing image, including abnormal enhancement mapping construction based on local statistical distribution; pollution candidate graph extraction based on spatial structure prior driving; enhancing the response of the stable region based on a structure consistency enhancing mechanism of the polluted region; high-precision segmentation and identification of the sewage area comprises the following steps: constructing a multi-resolution residual pyramid structure; carrying out fine-grained boundary structure modeling and uncertainty suppression; generating a sewage distribution probability graph and optimizing structural consistency; according to the method, the multi-resolution residual pyramid structure is constructed, image context information under different perception scales is fully mined, and the sensitivity and edge integrity of the model to a sewage area under a complex texture background are remarkably enhanced.

Implementations relate to a drafting assistant that assists users in generating prompts for a language model that generates responses for text boxes for a web page. Implementations may receive a prompt from a user regarding an input for the text box, generate a modified prompt by incorporating contextual information identified from the web page, and provide the modified prompt to a generative language model, which generates a response for the modified prompt. The response is presented to the user and can be used as the input for the text box. Implementations dynamically engineer / enhance prompts based on the context of the web page, thereby facilitating more accurate and relevant responses from the generative language model.

The invention discloses an antagonism prompt detection method and device based on a large language model and a medium, and belongs to the technical field of artificial intelligence safety. The technical problem to be solved by the invention is how to overcome the defects of static rule lagging, high manual maintenance cost and insufficient context understanding in the security protection process of a large language model in the prior art, and dynamic, real-time and high-precision antagonism prompt detection is realized. According to the technical scheme, the method comprises the following steps: feature extraction: comprehensively analyzing semantic information, structural information and context information in a user text, extracting semantic features, structural features and context features, performing Min-Max normalization on the semantic features, the structural features and the context features, and splicing the semantic features, the structural features and the context features into a 128-dimensional joint vector, performing feature selection on the joint vector through an L1 regularization logistic regression model, compressing to 10-dimensional core features, and removing redundant information; carrying out resistance scoring; and dynamically defending.

The invention discloses an inquiry model training method and device based on a long thinking chain, and relates to the field of large models, semantic information is extracted through strategy network analysis of a model, and an initial step decision is generated in combination with context information in a historical memory library; sending the initial step decision into a reasoning path generator, and reasoning to generate a primary diagnosis disease source and an intermediate diagnosis step; sending the primary diagnosis source and the intermediate diagnosis step into a verification module, performing pathological logic verification according to a case diagnosis report and a medical knowledge base, and feeding back a verification result; the reasoning path generator updates the historical memory bank based on the feedback result, the preliminary diagnosis disease source and the intermediate diagnosis steps; the strategy network continues reasoning based on user feedback input and the updated context information in the historical memory bank, and finally an inquiry result is output. According to the scheme, technical means such as reinforcement learning, self-adaptive backtracking and memory enhancement are introduced into a long thinking chain reasoning framework, so that a large language model realizes multi-aspect comprehensive improvement in medical question and answer and auxiliary diagnosis scenes.