49 results about "Semantic gap" patented technology

The invention discloses a medical image treatment method and system for multi-source heterogeneous data, and relates to the field of medical image treatment, and the method comprises the steps: firstly, respectively extracting an image embedding vector and a text embedding vector from original medical image data and a description text thereof through a deep learning model; then, the vectors of the two different modes are fused, and a unified semantic embedding vector is formed; based on the unified vector, through semantic similarity calculation with a standard term library, candidate mapping can be automatically generated, and dependence on rigid artificial rules is eliminated. More importantly, a closed-loop mechanism of manual auditing-feedback learning is introduced in the scheme, high-confidence mapping is adopted automatically, low-confidence mapping is audited by experts, and an auditing result is absorbed into a mapping knowledge base, so that the system has continuous learning and self-evolution capabilities, and a semantic gap of cross-mechanism data can be eliminated more intelligently and more accurately.

This invention belongs to the field of medical image processing technology, specifically relating to a method for abdominal multi-organ medical image segmentation based on a state-space model. Addressing the shortcomings of existing technologies such as the difficulty of CNNs in modeling long-distance dependencies, the high computational complexity of Transformers, and the large semantic gaps, incomplete segmentation contours, and easy organ encroachment issues in VM-UNet skip connections, this solution makes key improvements: It constructs an improved VM-UNet-Skip architecture, placing skip connections before downsampling to reduce the semantic gap between the small decoder features; it introduces a multi-scale global-local information aggregation module, capturing global anatomical dependencies through multi-head Mamba units and enhancing local detail representations with a convolutional gated feedforward network; and it relies on the VMamba encoder-decoder to achieve efficient feature extraction and reconstruction. The method flow includes: constructing initial feature representations through patch embedding layers, extracting multi-scale hierarchical features through the encoder, enhancing features through an information fusion module, and fusing and mapping the enhanced features to obtain the segmentation result through the decoder. This invention effectively improves the segmentation accuracy of abdominal multi-organs, solves the problems of insufficient contour integrity and organ encroachment, while reducing the number of model parameters and computational complexity, providing reliable technical support for clinical diagnosis and surgical planning.

The present application relates to the technical field of medical image computing and artificial intelligence, in particular to a sugar metabolism cross-modal image generation method based on a WARPNet framework, based on the WARPNet framework, through three core steps of multi-scale feature coding, weighted attention cross-modal reasoning and context perception generation, precise synthesis from MRI to PET is realized. The innovation lies in introducing a learnable sugar metabolism semantic prior weight in cross-modal reasoning, modulating feature attention, thereby explicitly guiding the model to focus on key metabolic areas, effectively solving the semantic gap problem between anatomical and functional modalities. The method improves the quality, physiological reasonableness and cross-dataset generalization ability of the synthesized image, and has application potential in auxiliary diagnosis, treatment planning and medical research.

The application belongs to the technical field of data retrieval, and particularly relates to a traditional Chinese medicine auxiliary syndrome differentiation system based on semantic analysis. The system comprises a traditional Chinese medicine symptom preprocessing module, a dynamic inverted index construction module and a semantic retrieval matching module. The preprocessing module extracts symptom entities and degree modifiers of the inquiry text through a traditional Chinese medicine field dependency syntax analysis tree, maps them to a standard symptom word library and converts them into weight coefficients. The dynamic inverted index construction module establishes an inverted list with the standard symptom words as index keys, and appends the bias values of the basic syndrome vectors and the document syndrome vectors after the document identification. The semantic retrieval matching module generates a query vector with weight coefficients according to a symptom query request, calculates the inner product of the query vector and the bias values in the inverted list, eliminates the document identification below the preset threshold, and outputs the syndrome conclusion corresponding to the remaining documents. The application solves the semantic gap and the synonym omission problem caused by the non-standardized expression of traditional Chinese medicine.

The application relates to the field of material data processing and discloses a cross-source material data semantic alignment method and device, a complete technical path from multi-source material data collection, semantic feature extraction, semantic embedding representation, object entity alignment, attribute alignment to relationship organization is constructed, the method and device can face multi-source heterogeneous material data such as literature, experiments, calculation and industrial production, fully combine semantic representation learning and intelligent analysis capability, realize unified semantic modeling and alignment at the attribute layer and the relationship layer, further eliminate the semantic gap between cross-source data, realize unified semantic modeling and standardized expression of cross-source material data, and improve material data integration, organization, retrieval and reuse capability.

The application relates to the technical field of multi-modal data processing, in particular to an insurance clause compliance verification method and system, electronic equipment and a storage medium. The application can effectively bridge the semantic gap between medical data and insurance clauses, eliminate the underwriting mismatch caused by inconsistent expressions, significantly improve the accuracy and compliance of automatic underwriting, and ensure that the reasoning process is interpretable and the conclusion is traceable, thereby reducing the risk of claim disputes.

The application relates to the technical field of information processing, and discloses an RAG retrieval enhanced information processing method based on adaptive semantic matching. The method comprises the following steps: if a plurality of historical questions continuously asked by a user and a current question all comprise at least one same keyword, the plurality of historical questions continuously asked by the user are acquired; a weight is determined according to a semantic gap between the current question and the plurality of historical questions, and a weighted semantic vector matrix of the current question is constructed according to the weight; semantic extraction is performed on each knowledge segment in a knowledge base to obtain a knowledge semantic vector matrix; a plurality of knowledge segments are screened according to the similarity between the weighted semantic vector matrix and the knowledge semantic vector matrix; and the plurality of knowledge segments and the current question are input into a language model to obtain an answer output by the language model. The application improves the fitting degree of the answer of the language model and the question, and avoids repeated questioning of the user.

The application discloses a cross-modal hash retrieval method and relates to the technical field of cross-modal learning. The method comprises the following steps: 1) a cross-modal feature learning network comprising an image network, a text network and a label network is used to map each triple information to a high-dimensional Hamming space through a feature fusion graph attention classification learning module; 2) a SwinT-S (SwinT Small model) model is used to extract semantic features of images; 3) a graph attention feature fusion attention module is used to perform deep fusion alignment on the obtained image semantic features and text semantic features; 4) a deep text feature extraction network is used to optimize the generation of text hash codes and generate high-quality text hash codes; and 5) a linear layer (Linear) and a Tanh (t) function are used to map text features into hash code lengths required by the application. The application has the beneficial effect of effectively reducing semantic gap problems, fusing different modal features and improving the performance of cross-modal hash retrieval.

This invention belongs to the field of artificial intelligence technology and discloses a passport cross-modal retrieval method and system based on knowledge graph constraints. It aims to address the problems of domain semantic gap, lack of complex semantic parsing capabilities, and black-box nature of the retrieval decision-making process in existing technologies. This invention achieves a unified approach to high-precision retrieval and interpretability of the reasoning process under complex semantic understanding by constructing a passport multimodal knowledge graph, designing spatial inductive bias, building a multi-granularity feature deep fusion mechanism, and generating a visual evidence chain.

The application belongs to the field of intelligent construction and robot technology, and relates to a robot operation description automatic generation method, an intelligent operation method and a hardware platform, which comprises the following steps: constructing a semantic analysis engine containing a process classification dictionary and a construction process knowledge base, reading a BIM model file and screening to-be-operated components; based on the geometric topological features and volume attributes of the components, deducing and establishing a local operation space containing a grabbing coordinate system, an approaching coordinate system and an installation coordinate system; using semantic mapping technology, converting static component attributes into dynamic robot atomic action sequences, and automatically injecting dynamic constraint parameters according to material physical attributes; and finally generating a standardized robot operation description file containing timing logic and spatial information. The application can bridge the semantic gap between BIM design data and robot control data, realize precast component installation process teaching-free autonomous operation, and significantly improve construction efficiency and safety.

The application discloses a channel shuffle-based image segmentation method and device, equipment and medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring a target image to be segmented, and performing down-sampling on the target image to be segmented to obtain a feature map; the feature map is input into a local branch and a global branch of a target neural network in parallel, so as to extract fine-grained features and macro semantic features; the local branch obtains a multi-scale feature tensor by performing multi-scale convolution on the feature map, and obtains the fine-grained features based on the multi-scale feature tensor and a channel shuffle technology; the fine-grained features and the macro semantic features are adaptively fused to obtain corresponding target multi-scale features, and the target multi-scale features are up-sampled to perform image segmentation. Through adaptive fusion of the fine-grained features and the macro semantic features, dynamic integration of the two-way features is realized, and the problem of information conflict caused by a semantic gap in static fusion is solved.

This invention belongs to the field of multimodal data processing technology and discloses a multimodal data alignment and enhancement method based on semantic consistency, aiming to solve the problems of semantic gap and insufficient generalization of multimodal data models. The method includes: acquiring original multimodal data on the same semantic topic, performing noise and anomaly processing and format normalization on the multimodal dataset; extracting semantic features of each modality from the multimodal dataset and normalizing and adapting them to construct a shared semantic space; achieving semantic consistency alignment between modal feature vectors of each modality through a cross-modal alignment mechanism; accordingly, performing intra-modal and cross-modal enhancement on each modality and its shared feature vectors, and integrating and deduplicating to obtain an aligned and enhanced multimodal dataset. This invention achieves accurate semantic alignment of multimodal data, improves data diversity, effectively enhances the generalization ability of multimodal learning models, and is applicable to artificial intelligence scenarios that rely on multimodal data collaboration, demonstrating strong practicality.

The application discloses a community cross-domain recommendation system based on multi-modal large model alignment, and relates to the technical field of artificial intelligence recommendation. The system includes multi-modal alignment, prompt construction and teacher-student alignment modules. First, the multi-modal large model is used to convert the heterogeneous images and text data of interest points into unified structured semantic labels, realizing cross-modal feature alignment. Second, the user's auxiliary travel history is introduced and combined with the thinking chain reasoning mechanism to accurately decouple the preference differences of users in the resident mode and the tourist mode. Finally, a two-stage strategy of supervised fine-tuning and direct preference optimization is adopted to efficiently transfer the reasoning ability of the large teacher model to the lightweight student model. The application effectively solves the semantic gap and preference deviation problem in off-site recommendation, realizes real-time recommendation within seconds while ensuring high accuracy, and is suitable for online travel services and location service scenarios.

The present application relates to the technical field of multi-modal abstract generation, in particular to a multi-modal abstract generation method and system based on keyword prediction enhancement, comprising the following steps: 1) obtaining multi-modal abstract data, wherein the multi-modal abstract data comprises text, images corresponding to the text, and text keywords, the text keywords are obtained by calculating entities in the intersection of the original text and the reference abstract, and provide reliable training data for subsequent visual key information extraction; the present application effectively uses a small model as an auxiliary model to extract keywords to assist a large model in performing a multi-modal abstract generation task, more effectively guides the large model to generate a multi-modal abstract by using this framework, can lock core information in the text, thereby obtaining more robust and stronger fact consistency results, effectively solves problems such as focus shift, visual redundancy, and semantic gap between different modalities, and improves the quality of abstract generation.

The application discloses a large model and knowledge graph enabled intention driving network design method, comprising the following steps: S101, a user inputs a user intention through a front-end natural language interaction interface, and performs a pretreatment operation on the user intention; S102, a pretreated user intention is classified based on a few-shot learning method, and a large model cooperation method extracts key information of the user intention and constructs an intention knowledge graph based on the key information; S103, a network state knowledge graph is constructed; S104, an application program interface provided by an underlying layer is called by using intention understanding and reasoning capability of the large model, so that mapping of the user intention to an underlying network strategy and issuing are realized; and S105, the large model performs dynamic real-time adjustment based on network state knowledge graph information. The application realizes intention semantic mining, adaptation of intention demand and underlying resource capability, so as to bridge a semantic gap between the user intention, strategy management and the underlying network, and improve network operation efficiency.

The application relates to a dual-light fusion super-resolution integrated method and device based on semantic guidance. The method comprises the following steps: performing heteroscale shallow coding on obtained infrared images and visible light images to obtain first and second initial multi-modal features; obtaining multi-modal semantic fusion features according to the first and second initial multi-modal features; inputting the fusion features into a noise prediction diffusion model and outputting a definition perception semantic, wherein the semantic fuses clear latent representations of dual-mode information; inputting the semantic into a definition perception visual-language model and outputting a high-level semantic embedding; generating an initial fusion image according to the high-level semantic embedding, and generating a final fusion image according to the initial fusion image. Thus, the semantic gap and resolution mismatch problem in the fusion of heterogenous images in the related art is solved, the problems of blurred details, insufficient thermal target saliency, inconsistent semantics and low resolution in the fusion image are avoided, and high-quality and high-semantics-consistency integrated fusion and super-resolution reconstruction are realized.

The application provides a city safety risk information retrieval method based on text2sql, an electronic device and a storage medium. The process includes data integration and preprocessing, text2sql model construction and training, natural language query processing, SQL statement generation and execution, result processing and display. This method realizes the full automation of the operation of the user directly and accurately obtaining scattered risk information and obtaining intuitive visual results in natural language, to solve the three core problems of high technical threshold of non-professional user database retrieval, difficulty of multi-source heterogeneous data integration management, and insufficient accuracy of SQL generation caused by semantic gap and context loss in professional field query, which has important wisdom city theoretical innovation research significance and wide industrialization use value.

The application discloses a multi-rotor unmanned aerial vehicle target detection method in a complex scene, and relates to the technical field of computer vision and target detection. First, open-source multi-rotor unmanned aerial vehicle image data is used to construct a MUAV target training data set; second, a MUAV target detection network in a complex environment is constructed. Based on YOLOv11n, a residual attention module RAM is introduced into the YOLOv11n backbone network, and then the shallow fine-grained features of the MUAV target are strengthened. A learnable linear transformation gate unit layer is introduced into the neck network, the channel adaptive weighting mechanism of the GU layer is used to dynamically adjust the contribution of the shallow fine-grained features and the deep semantic features, and the semantic gap between the fused feature maps is effectively reduced. The improved YOLOv11n is called Im-YOLOv11n. Finally, the network performance is verified by using a test data set. The detection accuracy and other quantitative indicators of the Im-YOLOv11n are better than those of the models in the R-CNN series and the YOLO series. The Im-YOLOv11n has more stable detection performance in complex scenes such as insufficient light, complex background and occlusion.

The application discloses an industrial big data efficient retrieval service method based on an AI algorithm, and relates to the technical field of data retrieval.The application first realizes millisecond-level accurate alignment of time series, text and image multi-modal data through dynamic time warping and statistical interpolation cleaning;secondly, a layered feature extraction model constructed by RoBERTa, TCN and Swin Transformer is adopted, combined with cross-modal attention fusion and GAN feature enhancement, so that the semantic and trend features of industrial data are deeply mined;in the index and retrieval stage, a high-dimensional index structure constructed by a graph neural network GAT effectively alleviates the dimension disaster, and a mixed search strategy combining HNSW and LSH greatly improves the retrieval efficiency.Industrial knowledge graph is introduced for entity alignment and logical reasoning, which makes up for the semantic gap of traditional vector retrieval, and realizes the correlation expansion based on cause and effect and hierarchical relationship.Finally, the reordering model based on LambdaMART fuses multi-dimensional scoring and context perception mechanism, and dynamically optimizes the result ranking.

The application relates to a multi-modal emotion analysis method and system, wherein the method comprises the following steps: extracting text, vision and multi-dimensional fine-grained acoustic emotion prior features in a video to be analyzed; calculating the reliability weight of each mode through a mode fault detection and dynamic reliability routing door mechanism, intelligently silencing a low-quality mode and dynamically reweighting a high-quality mode; performing time sequence coding and mode decoupling on the weighted features to separate mode-invariant features and mode-specific features; performing cross-modal fusion by using a multi-head self-attention mechanism to generate a global emotion representation vector for emotion prediction. The application fills the acoustic semantic gap, solves the false positive noise problem caused by the over-sensitivity of high-order features, and realizes the balance between high sensitivity and high robustness.

This invention belongs to the field of computer vision technology. It proposes a text-to-point cloud cross-modal localization method and system based on a visual language model. The method converts 3D point clouds into a bird's-eye view image and a structured scene graph, the latter containing nodes with semantic and spatial location information. Natural language descriptions, the bird's-eye view, and the scene graph are input into a pre-trained visual-language model to generate cross-modal alignment features. Through a partial node association mechanism, the semantic information is selectively mapped to spatially matching nodes to determine the target node. Then, based on its spatial location, the original point cloud is retrieved to achieve accurate localization. This invention utilizes dual structured representation and explicit semantic-spatial alignment to effectively bridge the semantic gap between point clouds and language, improving the accuracy, robustness, and interpretability of localization. It is applicable to scenarios requiring language-guided 3D perception, such as autonomous driving and robotics.

This invention specifically relates to a cross-modal person re-identification method based on relation-aware adaptive learning optimization. This method uses a pre-trained visual-language large model as the feature extraction backbone. Addressing the problems of semantic gaps within modalities and insufficient negative sample coverage in existing technologies, it designs a semantic correspondence correction module to mine inter-modal relationships and optimize cross-modal alignment training objectives. It also designs an adaptive negative sample enhancement module to synthesize difficult negative samples based on inter-modal relationships and adaptively allocate weights according to the difficulty level to strengthen the learning of difficult samples. The method integrates semantic correspondence correction loss, adaptive negative sample enhancement loss, and the basic loss function, and fine-tunes the model using the Adam algorithm to achieve multi-objective collaborative optimization. This invention comprehensively mines multi-level sample relationships within and between modalities, optimizes the model learning process, and significantly improves the retrieval accuracy and model robustness of cross-modal person re-identification, possessing significant application value in fields such as security monitoring.

The application discloses an online production quality detection system based on multi-modal data and belongs to the technical field of industrial detection. The physical semantic unification of multi-modal features is completed from a feature input layer, the problem that each modal feature only retains statistical semantics and has no physical semantic correlation in a traditional scheme can be avoided, a generated feature map with a physical label directly provides a physical semantic benchmark for a subsequent physical information neural network detection model, all features are aligned according to spatial coordinates, the same position of each modal feature corresponding to a workpiece is ensured when multi-modal fusion is performed subsequently, and fusion errors caused by spatial misplacement are avoided. Through three types of collaborative technical means, i.e., a physical property anchoring mechanism, a hidden layer physical alignment constraint and a physical consistency verification threshold, and the core optimization direction of a physical information neural network detection model embedded with a physical loss, cooperation is formed, and the semantic gap problem can be solved from the root through the physical label unified multi-modal semantic benchmark.

The application discloses a multi-source data fusion enterprise credit report intelligent generation method and product. The method comprises the following steps: constructing and registering a heterogeneous data tool library based on an MCP protocol; an LLM analyzes a natural language instruction input by a user; a multi-source API is dynamically routed and scheduled through an MCP server; unified structured data is obtained by performing entity alignment on the obtained multi-source heterogeneous data, and then performing conflict resolution based on a time decay factor credibility weighting mechanism; feature calculation and association mining are performed based on fusion true values, and then a dynamic Prompt is constructed by combining analysis features and user intentions; a large language model generates a credit report and adds a data source anchor point. The application fundamentally alleviates the calculation deviation caused by the cross-modal semantic gap, effectively suppresses the "data illusion", and generates a report that guarantees the flexibility of natural language interaction while achieving commercial compliance levels in terms of accuracy and auditability.

A computer-implemented broker entity receives from a requesting device a request for one or more target values of state information that have sought target semantic meanings; obtains one or more source values of state information that are associated with given source semantic meanings; obtains at least in part from a transformation library one or more transformations, wherein each transformation maps one or more first values that are associated with first semantic meanings to one or more second values that are associated with second semantic meanings; applies the one or more transformations or a new transformation obtained based on the one or more transformations to the source values of state information, thereby obtaining the one or more target values of state information; and transmits the one or more target values to the requesting device.

The present application relates to the technical field of traditional Chinese medicine, and in particular to a traditional Chinese medicine constitution intelligent identification and dynamic interpretable conditioning scheme generation system, comprising a bimodal encoding module and a hybrid routing fusion module, a generative conditioning engine, and an online-offline closed-loop updating module. Through the tongue surface bimodal feature alignment and rule-neural network hybrid dynamic routing architecture, the present application effectively overcomes the semantic gap between heterogeneous modalities and the limitations of single black box decision. On the self-built 12000 real data set, the Top-1 accuracy rate of traditional Chinese medicine constitution identification is greatly increased from 72.3% of the prior art to 89.7%. At the same time, with the generative conditioning engine integrating strict medical safety verification and SHAP numerical contribution degree echo, not only is the dynamic prescription generation of multi-dimensional perception and thousands of methods for thousands of people realized, but also the "black box" trust crisis of AI diagnosis is completely broken, and the blind evaluation satisfaction of professional traditional Chinese medicine practitioners is significantly improved from 3.2 points to 4.6 points.

The present application belongs to the technical field of hydrological forecasting, and in particular to a physical constraint basin hydrological real-time forecasting method based on semantic causal reasoning. In view of the semantic gap of multi-source heterogeneous data and the missing problem of physical mechanism existing in the prior art, the following scheme is proposed: first, a knowledge graph within a basin is constructed based on water conservancy text data; second, a semantic causal reasoning is performed by using a large language model combined with the knowledge graph to dynamically identify key disaster-causing factors and generate an input feature set; then, a semantic constraint prediction network is constructed, which realizes the spatio-temporal aggregation of upstream station features through a knowledge graph attention mechanism, and modifies the forget gate by introducing a rainfall attenuation coefficient and adds a water balance constraint term in the loss function to explicitly inject the hydrological physical law into the neural network; finally, the model is trained by using historical data and features are completed and dynamically optimized in the real-time data stream combined with the knowledge graph to output the water level prediction value at the future time.