26 results about "Semantic learning" patented technology

The invention discloses a cross-modal pedestrian re-identification method and system based on a multi-scale joint learning network, and relates to the technical field of pedestrian re-identification, and the method comprises a four-flow network architecture which enables a model to extract diversified semantic features through a mode of separating an application data enhancement branch from an original branch. Random channel selection and self-adaptive graying are respectively applied to the data enhancement branch, so that the robustness of the model to color change and the adaptive capacity of the model to different thermal imaging conditions are improved. Important channels are enhanced through a channel attention mechanism, irrelevant channels are inhibited, and two substreams are guided to internally enhance modal specific features. Richer semantic information is reserved through features extracted by a four-flow network, a joint semantic learning module is designed, a group of learnable vectors are defined and spatial position codes are added, global features of original branches and color invariant features of channel data enhancement are fully learned under the guidance of loss, and the overall feature of the original branches is optimized; and the features among different modes have higher semantic consistency.

The invention discloses a semantic-guided lightweight three-dimensional reconstruction method based on three-dimensional Gaussian, and the method comprises the steps: inputting a multi-view two-dimensional image, and extracting two-dimensional semantic features; projecting the two-dimensional semantic features to the three-dimensional Gaussian primitives; learning three-dimensional semantic distribution in a knowledge distillation mode, and predicting three-dimensional semantic embedding features; dividing a large scene into a plurality of sub-regions, and performing divide-and-conquer three-dimensional Gaussian optimization and semantic learning; performing semantic-guided lightweight modeling on the three-dimensional Gaussian primitives in each sub-region; executing sub-scene fusion, and performing quantitative compression on the three-dimensional data in the fused scene; and a rasterization renderer is used to carry out efficient real-time rendering under any visual angle, and a lightweight large-scene three-dimensional reconstruction result is output. According to the method provided by the invention, the real-time rendering performance of a complex scene can be remarkably improved, the model volume is effectively compressed, meanwhile, the model training process is accelerated, and the method is suitable for efficient three-dimensional visual reconstruction tasks.

This invention relates to the field of natural language processing technology, specifically to a method and system for matching the intent of intelligent NPC dialogues in multimodal interaction. The method involves real-time acquisition of multimodal data, generating multimodal semantic features through submodal preprocessing; integrating the semantic features of each modality using a cross-modal fusion module based on semantic association, generating a candidate intent set based on semantic context representation and combined with a semantic parsing module and predefined intent templates; tracking changes in user intent in real time through a continuous semantic learning mechanism and an interactive memory module, combined with a Bayesian update method, dynamically adjusting the confidence level of each intent in the candidate intent set, and filtering the final intent; constructing an NPC semantic cognition model, and performing semantic consistency analysis to perform semantic checks on user input and NPC dialogue state; combining the final intent and a decision engine to generate a dialogue strategy and output synchronized response content; this invention improves the accuracy of dynamic matching of intelligent dialogue intents.

The application relates to a multi-dimensional time sequence recognition method, device and equipment based on time-frequency semantic learning. The method comprises the following steps: constructing a task-oriented segmented basic unit, performing semantic segmentation sampling on an input multi-dimensional time sequence to obtain a plurality of initial segments, obtaining a basic segment after weighting by a weight calculation network, constructing a time domain and frequency domain component generation unit based on the basic unit, inputting multi-dimensional time sequence data monitored by different sensors in the same scene and time period into the two units for parallel processing to obtain time-frequency domain segments, inputting the time-frequency domain segments into a downstream sequence recognition model for prediction, calculating time-frequency domain consistency loss and classification loss, adjusting parameters of the two units until the loss converges, completing training, extracting time-frequency domain segments of a multi-dimensional time sequence by using the trained unit, and inputting the time-frequency domain segments into the model for recognition. The method can effectively improve the classification accuracy of multi-dimensional time sequence.

The invention relates to a method of performing a map learning via a unified framework comprising the steps on a computing device (10): - Retrieving data comprising features that are geospatially referenced and / or localized with respect to geospatially referenced; (S1) - Arranging the features in relation to each other on the basis of their localization and / or their geospatially referenced features, whereby a lane is determined and / or aligned; (S2) - Aggregate and / or cluster geometric features; (S3) - Determine a lane divider and / or lane segments based on the geometric features and / or based on lanes traveled; (S4) - Deriving a lane topology based on a connectivity of the lane segments; (S5) and - Semantic learning based on the lane topology, whereby features are assigned a function and the map is thus created or expanded. (S6) Furthermore, the invention relates to computer program and a computing device (10).

The invention discloses an unsupervised domain adaptive method based on a cascade learning strategy, and aims to decouple the training process of a source domain and a target domain, prevent semantic information confusion and realize fine-grained adaptation to the target domain. Specifically, the proposed two-stage cascade learning framework mainly comprises two stages of learning processes, in the first stage, a low-rank adaptation fine tuning module is used for performing fine tuning of a source field on a visual language pre-training model so as to learn feature information which is related to categories and invariable in field; and in the second stage, learning knowledge of a target domain by freezing the fine-tuned visual language pre-training model and a low-rank adaptive fine-tuning module and introducing text prompt, and refining a pseudo tag by means of knowledge of a source domain. According to the method, semantic learning and a domain-specific adaptation process are effectively decoupled, so that the performance of the target domain is improved.

The application provides an embedding generation method and device of a binary function, electronic equipment and a medium, and relates to the technical field of computers. The method comprises the following steps: inputting a target binary function into a pre-trained control flow semantic learning model to obtain a control flow semantic embedding, wherein the control flow semantic learning model is used for converting a relationship control flow graph corresponding to the binary function into a vector and outputting; inputting the target binary function into a pre-trained global sequential semantic learning model to obtain a global sequential semantic embedding, wherein the global sequential semantic learning model is used for converting machine code corresponding to the binary function into a vector and outputting; and integrating the control flow semantic embedding and the global sequential semantic embedding, and taking the integration result as an embedding corresponding to the target binary function. The scheme of the application can make the embedding of the binary function retain code information to the greatest extent, has good generalization performance, and improves the quality of the binary function embedding.

The application relates to a pedestrian attribute recognition method based on attribute semantic similarity matching, and relates to the technical field of computer vision. First, an adaptive semantic query module is designed, adaptive queries combined with visual features are used to learn attribute-specific spatial distribution, and semantic information of each attribute is captured. In addition, pedestrian attribute recognition is reconstructed as a semantic matching task, attribute text features are used as semantic anchors, and the distance between the semantic information of the query and the anchors is used to predict the pedestrian attribute. Finally, a dynamic negative semantic learning strategy is proposed, the spatial prior information of the attribute is combined with the learnable parameters to generate the negative semantic information of the attribute, the attention area of the semantic query module to the attribute is constrained, and more accurate pedestrian attribute recognition is realized.

The invention provides a task planning method, a control device and a storage medium, and belongs to the technical field of long-range planning. The method comprises the following steps: constructing a corresponding rich semantic learning graph according to a target planning problem of a PDDL problem format; and inputting the rich semantic learning graph into the trained hybrid planning network, calculating a heuristic value corresponding to each state, guiding to search a transfer solution from an initial state to a target state, obtaining a planning action sequence of a target planning problem, and constructing the hybrid planning network based on node attention and a relational graph neural network. According to the method, semantic information is extracted by adopting a large language model, and a rich semantic learning graph and a hybrid planning network which are used for fully capturing PDDL problem information to assist task planning are constructed; the success rate of the planning problem can be improved by utilizing the rich semantic learning graph and the hybrid network architecture, and the reliability and the high efficiency of long-range planning are effectively guaranteed.

The invention belongs to the technical field of data processing and generation, and particularly relates to a federal cross-domain retrieval entity recommendation method and system for mineral resource retrieval, and the method comprises two stages of federal cross-domain semantic learning and behavior prediction based on a large language model. The method comprises the following steps: firstly, locally extracting semantic features of texts of knowledge entities from each data domain, encrypting the semantic features and uploading the encrypted semantic features to a server, and mining a cross-domain public semantic structure by the server through clustering to generate a shared semantic vector and issuing the shared semantic vector; and obtaining the user and entity representation of the ID modal based on the user-entity interaction sequence, and embedding and fusing the issued shared semantic vector and the ID modal entity through knowledge distillation to obtain an enhanced local representation. And projecting the user and enhanced entity representation into a soft prompt which can be understood by a large language model through a mapping network, forming a mixed prompt in combination with a task instruction, inputting the mixed prompt into the large language model for reasoning, and recommending a next possible retrieval entity to the user. And on the premise of protecting user privacy, knowledge migration and fusion among non-overlapping fields are realized.

The application discloses a kind of unified visual and semantic learning multimodal image collaborative fusion method, it is related to infrared and visible light image fusion field. Including: based on sample scene visible light image and infrared image generate shared semantic representation;Through hierarchical interactive attention module and fusion specific enhancement module respectively to shared semantic representation and the visible light feature of visible light image is processed, generates the spatial domain feature of segmentation task and fusion task;Through frequency perception task router, shared semantic representation is processed to generate the frequency domain feature of segmentation task and fusion task;Based on the spatial domain feature and frequency domain feature corresponding to segmentation task and fusion task respectively, the task feature of segmentation task and fusion task is generated;Based on the task feature of segmentation task, preliminary segmentation image is obtained, based on the task feature of fusion task, preliminary fusion image is obtained, to realize in unified framework, visual fidelity, significant target expression and availability of high-level task are considered.

The invention relates to a fraud number recognition method and system, and the method comprises the steps: carrying out the voice abnormality recognition, text abnormality recognition and behavior abnormality recognition of the obtained multi-mode communication data of each number; weighted dynamic scoring is carried out on the voice abnormity recognition result, the text abnormity recognition result and the behavior abnormity recognition result obtained by each number through a weighted fusion mechanism, so that current case-related numbers are obtained, and each case-related number is used as a core node. Constructing a case-related association network based on a core node according to the multi-mode communication data of each case-related number, performing semantic learning on the case-related association network by adopting a GAT map attention network, and generating a fraud prediction model based on the captured fraud mode and the active period of the core node; and carrying out identification and early warning on future case-related numbers through the fraud prediction model. Therefore, according to the method and the system, the fraud number is accurately identified, and meanwhile, early warning can be performed on the occurrence of future fraud behaviors.

A method, computer system, and computer program product for leveraging semantic learning-enhanced joint learning are provided. An aggregator can receive cluster information from a distributed computing device. The cluster information may relate to identified clusters in sample data from the distributed computing device. The aggregator can integrate the cluster information to define categories. This integration may include identifying any redundant clusters among the identified clusters. The number of categories may correspond to the total number of clusters from the distributed computing device minus any redundant clusters. A deep learning model can be sent from the aggregator to the distributed computing device. The deep learning model may include an output layer with nodes that may correspond to the defined categories. The aggregator can receive the results of joint learning performed by the distributed computing device. Joint learning can train the deep learning model.

The application discloses a text classification method based on label semantic learning and attention adjustment mechanism, and mainly comprises the following steps: preprocessing text data, extracting text semantic features, text label graph embedding, using a multi-head adjustment attention mechanism to measure the semantic relationship between words and labels, then multi semantic integration and network training, thereby realizing multi-label text classification, training the model, and then using the trained model to predict the category of a text. The application proposes a multi-head adjustment attention hybrid BERT model for a multi-label text classification framework, which can effectively extract useful features from text content, establish semantic connection between labels and words, obtain label-specific word representation, and thus improve the performance of multi-label text classification.

This invention discloses a 3D point cloud analysis method and apparatus based on Transformer that enhances local semantic learning capabilities. The method constructs a deep learning model, including a local semantic self-attention learning module, which can perceive global context information and acquire finer-grained local semantic features in parallel, thereby enhancing the perception capability of the entire network framework. Local and global features of the point cloud are obtained from different modules through four local semantic learning modules, and these features are converged to obtain global joint features. The joint features obtained in the learning stage are then sent to subsequent point cloud classification and segmentation stages to obtain semantic classification results and final segmentation results. This invention can acquire key local geometric semantic information in 3D data and has significant advantages in various 3D point cloud analysis applications, such as point cloud classification, point cloud segmentation, and semantic segmentation of large indoor scenes.

The application relates to the technical field of enterprise information management systems, and discloses an enterprise information management method and an enterprise information management system, the method comprising the following steps: calculating interaction demand information of a first system in a second system in enterprise information management; constructing an interaction strategy optimization semantic learning model in an interaction module, mapping internal fields of the first system and corresponding internal fields of the second system in the interaction demand information, so as to determine a plurality of interaction nodes in the second system; establishing corresponding interaction mapping nodes in the interaction module; when it is detected that data updating exists in the interaction demand information, determining an interaction node of the interaction mapping node to which to-be-synchronized data are synchronized, synchronizing updated interaction demand information in the interaction node to the interaction mapping node, and generating feedback data sent to the first system. The application is beneficial to solving the problem of data islands existing in the current enterprise information management.

The invention provides an IPv6 full-response prefix detection method based on an autoregression model, which comprises the following steps: firstly, carrying out semantic learning by using the autoregression model, learning a complex relationship between a full-response prefix mode and related factors thereof, and finally generating the representation of the full-response prefix mode by using the learned probability model; then, in a prediction stage, according to the semantic information of the routing prefixes, predicting a possible full response prefix mode, and generating candidate full response prefixes; and finally, in a scanning stage, carrying out online scanning on the candidate full-response prefixes, collecting a detection result, judging whether the candidate full-response prefixes are real full-response prefixes or not according to the detection result, carrying out granularity correction on the real full-response prefixes to obtain a prefix set with a real length, and finally obtaining a prefix set with a real length. And a full-response prefix database which is wide in coverage range and high in accuracy is constructed.

The present application relates to the technical field of digital culture intelligent interaction, in particular to a culture communication interaction method and system based on deep learning, comprising: collecting text, image, audio and video original cultural material data, constructing a multi-modal culture knowledge graph with structured association through cross-modal alignment and semantic annotation; training a deep cross-modal understanding model supervised by the graph, learning the deep-level semantic association of different modal culture elements; receiving user interaction intention and preference, generating personalized culture exploration tasks combined with context; using the model to perform semantic retrieval and association reasoning in the graph, generating diversified culture content sequence matching the task, forming an interactive culture experience flow through narrative logic reorganization and presentation adaptation, and continuously optimizing the interaction based on user physiological feedback. Through cross-modal precise alignment, knowledge graph structured association and model deep semantic learning, the present application realizes personalized and coherent culture communication interaction.

The invention discloses an Alzheimer's disease text detection method and system based on semantic noise disturbance, and belongs to the technical field of text semantic learning. The method comprises the following steps: acquiring dialogue text transcription data; establishing an Alzheimer's disease text discrimination data set composed of a training set and a test set; developing a semantic disturbance generation and fusion module for the multi-category text features; an open source pre-training language model is used for generating text feature representations, then semantic noise disturbance is dynamically injected into the representations, and a final Alzheimer's disease detection model is formed. Through fine tuning of disturbance levels of various text features, the trained model can effectively distinguish normal texts from texts affected by the Alzheimer's disease, and fine differences in language use are identified. According to the method, the capability of accurately detecting the specific language pattern of the Alzheimer's disease by the model is greatly improved, so that the text detection performance of the Alzheimer's disease is improved.

This invention belongs to the field of large language model technology, specifically a method for constructing large language models based on DSL, SYSML, and UML constraints. The method includes: constructing a five-layer unified capability stack, embedding constraint concepts into the large language model at the architectural level; defining a unified intermediate representation (UIR) as a universal data format; injecting constraint concepts into model weights at the parameter level through a four-stage unified adjustment process of corpus immersion, graph semantic learning, inference pattern learning, and capability alignment; constructing a unified inference pattern library covering requirements analysis, architecture design, behavioral modeling, constraint verification, code generation, and document generation; and using the UIR and the inference pattern library to guide inference, achieving synchronous generation and constraint verification of multiple output types. This invention enables the large language model to form structured constraints internally, resulting in outputs that naturally meet engineering requirements, and solves the problems of easy failure of external constraints and poor cross-domain adaptability.

This invention discloses a scalable cross-modal tactile signal generation method for emergency rescue scenarios. First, audio and video signals are encoded on the device side, and contrastive learning is used to reduce inter-modal differences. Then, the edge terminal senses network bandwidth information and feeds it back to the device side in a timely manner, guiding the device to complete scalable semantic encoding. Finally, after receiving the corresponding cross-modal fused semantic information or different levels of fused semantic representation, the edge terminal uses a designed adaptive tactile signal generation strategy to generate tactile signals of the appropriate granularity. This invention effectively solves the problem of tactile signal loss caused by the difficulty in directly acquiring tactile signals and dynamically fluctuating transmission bandwidth in emergency rescue, ultimately affecting the operator experience when performing remote control. It achieves relevant semantic learning and cross-modal generation of multimodal signals, ensuring real-time and reliable acquisition of tactile signals under conditions of dynamically fluctuating network bandwidth, and ultimately improving the operator's rescue efficiency.

The image information extraction method and device, the electronic equipment and the storage medium provided by the present application relate to the artificial intelligence technical field and the digital medical field. The method comprises the following steps: acquiring a first image, and acquiring a category of the first image to obtain a target image category; acquiring a second image according to the target image category; performing first segmentation on the first image according to a preset size to obtain at least two first regions; performing second segmentation on the second image according to the preset size to obtain at least two second regions; inputting the first regions and the second regions into a preset attention model for semantic learning to obtain third regions; splicing the third regions to obtain a target mask image; performing image segmentation on the first image according to the target mask image to obtain a target information region; and performing character recognition on the target information region to obtain target character information. The present application improves the extraction efficiency of image information.

The invention belongs to the field of natural language processing, and relates to an irony detection method based on global semantic perception inconsistent reasoning, and the method comprises the steps: obtaining a to-be-detected multi-mode dialogue, and inputting the to-be-detected multi-mode dialogue into a trained irony detection model, and obtaining a detection result; the training process of the irony detection model comprises the following steps: inputting a multi-modal dialogue sample into a multi-modal feature representation module to obtain a multi-modal feature topological graph; inputting the multi-modal feature topological graph into a global semantic learning module to obtain a global semantic vector; inputting the multi-modal feature topological graph and the global semantic vector into a global semantic inconsistency reasoning module to obtain an emotion and irony detection result; calculating a loss function value according to emotion and irony detection results, updating parameters of the model according to the loss function value, and obtaining a trained irony detection model when the loss function value is minimum; according to the method, difference measurement is carried out on the single-mode features and global semantics, cross-mode deep inconsistent features are effectively captured, and potential semantic conflicts behind irony are comprehensively revealed.

The application discloses a forest musk deer posture recognition method based on multi-modal semantic learning, relates to the technical field of animal behavior analysis and computer vision, and comprises the following steps: acquiring a forest musk deer clipping image and a global feature map with different resolutions of a to-be-recognized forest musk deer image; obtaining a global feature vector based on the global feature map; constructing a local feature learning model, inputting the forest musk deer clipping image into the local feature learning model, obtaining a plurality of channel heat maps, decoding the channel heat maps to obtain two-dimensional coordinates and confidence of a plurality of forest musk deer skeleton key points; obtaining a topological semantic feature vector and a multi-frame skeleton sequence based on the two-dimensional coordinates and the confidence; extracting a space-time joint feature of the multi-frame skeleton sequence, fusing the global feature vector, the topological semantic feature vector and the space-time joint feature to obtain a multi-modal feature fusion vector, obtaining a probability distribution of different actions of the forest musk deer based on the multi-modal feature fusion vector, and further obtaining a forest musk deer posture recognition result; and the problem that a backbone network of an existing forest musk deer posture recognition method is not optimized for forest musk deer biological characteristics, resulting in insufficient feature discrimination, and the problem that a heat map method is sensitive to occlusion, resulting in a high key point missing detection rate.

The present application belongs to the technical field of patent evaluation, and provides a patent value evaluation method based on depth map and semantic learning. In the index screening process, the patent transfer is combined with the construction of the patent value evaluation index system, providing an objective and fair evaluation method with strong operability for feature selection. Secondly, the novelty of the patent is calculated through text semantic learning, and the patent value is measured from the semantic angle. Further, the depth map learning is utilized to maximize the information integration node feature representation between the local representation and the global representation, and the XGBoost algorithm is combined to evaluate the patent value. The present application breaks through the shortcomings of the traditional method in the patent value evaluation problem, and introduces the patent text novelty to measure the value of the patent. The experimental results show that the method has high accuracy and reliability. The present application provides a new method for evaluating the value of the patent, and provides a new solution for the research on the value of the patent.

The application provides an IPv6 full-response prefix detection method based on an autoregressive model, which comprises the following steps: firstly, semantic learning is performed by using the autoregressive model to learn the complex relationship between the full-response prefix mode and related factors, and the learned probability model is finally used to generate the representation of the full-response prefix mode; then, in the prediction stage, the possible full-response prefix mode is predicted according to the semantic information of the routing prefix, and the candidate full-response prefix is generated; finally, in the scanning stage, the candidate full-response prefix is scanned online, the detection results are collected, and whether the candidate full-response prefix is a real full-response prefix is judged according to the detection results; the granularity correction is performed on the real full-response prefixes, the prefix set with a real length is obtained, and a full-response prefix database with wide coverage and high accuracy is constructed.