177 results about "Semantic context" patented technology

A data processing system implements receiving content and a call requesting a generative model to generate a video summary of the content; constructing a prompt including the content and instructions to the model to identify semantic context of the content, to identify a text data item, an audio data item, and / or a video data item embedded in the content to generate a text transcript of the audio data item and / or the video data item, or a textual description of the video data item, to summarize the text data item, the text transcripts, and / or the textual description as a summary of the content based on the semantic context, and to generate the video summary based on the summary and a portion of the text data item, the audio data item, and / or the video data item; providing the first prompt to the generative model; providing the video summary to a client device for presentation.

The invention relates to the technical field of natural language processing, in particular to a multi-modal interactive intelligent NPC dialogue intention matching method and system. The method comprises the following steps: collecting multi-modal data in real time, and generating multi-modal semantic features through sub-modal preprocessing; a cross-modal fusion module based on semantic association is adopted to integrate each modal semantic feature, and an intention candidate set is generated based on semantic context representation and in combination with a semantic analysis module and a predefined intention template; through a continuous semantic learning mechanism and an interactive memory module, in combination with a Bayesian updating method, tracking user intention change in real time, dynamically adjusting the confidence of each intention in the intention candidate set, and screening a final intention; constructing an NPC semantic cognition model, and performing semantic check on user input and an NPC dialogue state through semantic consistency analysis; generating a dialogue strategy in combination with the final intention and a decision engine, and outputting synchronous response content; according to the invention, the precision of intelligent dialogue intention dynamic matching is improved.

The invention discloses a camouflage target detection method based on feature selection attention and frequency domain edge guidance. According to the method, four-level features of a camouflage target image are extracted through a backbone network SMT and are respectively screened; the high-level features are input into a semantic information supplement module, and after semantic features are enhanced, the high-level features and the trunk features are sent into a spatial feature enhancement module together. And inputting the obtained fine-grained features into an edge feature sensing module, and finally fusing multi-scale features through a multi-scale jump connection technology to generate a mask pattern with higher discrimination. The method has the advantages that the network parameter quantity is reduced and key information is reserved through a feature selection mechanism; a spatial feature enhancement module is used for enhancing multi-scale feature representation and remote dependence modeling; the dilution of the semantic context is relieved by means of a semantic supplement module so as to improve the positioning precision; and an edge feature enhancement module is adopted to enhance edge semantic perception and improve boundary integrity. According to the method, the camouflage target detection performance is remarkably improved with relatively low calculation cost.

A data processing system implements receiving content and a call requesting a generative model to generate a video summary of the content; constructing a prompt including the content and instructions to the model to identify semantic context of the content, to identify a text data item, an audio data item, and / or a video data item embedded in the content to generate a text transcript of the audio data item and / or the video data item, or a textual description of the video data item, to summarize the text data item, the text transcripts, and / or the textual description as a summary of the content based on the semantic context, and to generate the video summary based on the summary and a portion of the text data item, the audio data item, and / or the video data item; providing the first prompt to the generative model; providing the video summary to a client device for presentation.

The invention discloses a personalized semantic understanding system for assisting an autonomous mobile platform, and the system comprises a user personalized word meaning library which is used for recording the mapping relation between the user habit expression and the corresponding operation; the fuzzy semantic analysis module is used for identifying fuzzy expression in a natural language instruction of a user and generating a plurality of candidate targets or operation options of semantic generalization; the multi-round context modeling module is used for establishing a semantic context based on session history and performing disambiguation and complementation on current semantics; and the intention generation module is used for converting the processed semantic information into a structured instruction. The personalized semantic understanding system is reasonable in structural design, all the modules cooperate with one another, the effect that 1 + 1 is larger than 2 can be achieved, fuzzy semantic understanding and multi-round context modeling can be conducted, the personalized requirement of a user can be met, semantic understanding precision is high, user adaptability is good, and the personalized semantic understanding system is suitable for man-machine interaction of an autonomous mobile platform.

The invention relates to the technical field of equipment maintenance and overhaul decision, and discloses a knowledge graph driven two-stage classification equipment condition-based overhaul decision method, which comprises the following steps: acquiring multi-source text data; performing first-stage classification on the equipment based on the equipment importance evaluation model, and performing second-stage classification on the parts based on the maintenance strategy; a device entity, a fault mode entity and a maintenance measure entity are taken as knowledge ontologies, state variable nodes are embedded, and a knowledge graph fusing state variables is constructed by using a long-short-term memory network; in combination with a semantic context sensing mechanism and a graph structure stability constraint mechanism, outputting candidate fault nodes; candidate maintenance measures corresponding to the candidate fault nodes are retrieved in the knowledge graph, candidate maintenance measure verification is carried out in combination with soft constraints and hard constraints, and a maintenance measure list is converted into an equipment maintenance decision scheme by utilizing an execution arrangement generator, so that intelligence of the maintenance decision scheme is realized in combination with the knowledge graph; and decision support is provided for maintenance personnel.

The invention discloses an attention-based context-aware sparse hybrid expert model routing method, which comprises the following steps of: encoding prompt information input by a user to obtain context vector representation of the prompt information, and introducing a multi-head attention mechanism to obtain multi-scale semantic interaction information; further, constructing a gating network based on attention output, and dynamically selecting Top-K expert networks for reasoning; by introducing a self-adaptive neighbor attention weight and a fusion gating mechanism, expert dispatching and weight fusion of a token level are realized; combining with the sub-output of each expert network, and aggregating according to the weight to obtain the final model output; according to the method, the understanding ability of the model for different semantic contexts is enhanced through a multi-expert structure and a dynamic routing mechanism, and the method is adaptive to multiple rounds of token generation processes, so that the accuracy and diversity of generated texts can be improved.

Aspects of the present disclosure relate to systems and methods for generating one or more prompts based on an input and the semantic context associated with the input. In examples, the prompts may be provided as input to one or more general ML models to provide a semantic context around the input and / or output of the model. The prompt simulates training and fine-tuned specialization of the general ML model without the need to use a fine-tuning process to actually train the general ML model into a fine-tuned state. Additionally, the model output may be evaluated for responsiveness to the input prior to being returned to the user. An advantage of the present disclosure is that it allows a general ML model to be applied to a plurality of applications without the need for expensive and time-consuming training to fine-tune the ML model.

The invention discloses an SAR directed target detection method based on multi-scale context sensing, and belongs to the technical field of remote sensing image processing and computer vision. According to the method, firstly, through a scattering characteristic guided multi-scale dynamic characteristic enhancement network, a multi-branch structure and a dynamic fusion mechanism are utilized to enhance characteristic expressions of targets of different scales; and secondly, designing a task-adaptive regional context sensing module, fusing local details and semantic contexts, and improving the target discrimination capability under a complex background. And a decoupling type progressive refining detection head is adopted to predict a target category, a directed bounding box and a direction angle, and the positioning precision is optimized through progressive regression. Semantic consistency loss is introduced in the training stage, and end-to-end optimization is achieved in combination with a multi-task joint strategy. According to the method, the problems of large target scale difference, strong background interference, changeable directions and the like in the SAR image are effectively solved, and the accuracy and robustness of directed target detection are remarkably improved.

A data processing system implements receiving a user prompt requesting a diagram representing digital content; constructing a prompt including the user prompt, the digital content, and instructions to a generative model to identify semantic context of the digital content, to identify a text data item, an audio data item, a video data item, and / or a structured file item embedded in the digital content to generate at least one of a text transcript of the audio / video / structure file item, and / or a text description of the audio / video / structure file item, to semantically analyze and extract diagram data from the text data item, the text transcripts, and / or the textual descriptions based on the semantic context, and to generate the diagram of the digital content based on the diagram data; providing the prompt to the generative model and receive the diagram; and providing the diagram to the client device for display.

The invention discloses an automatic advertisement creativity generation method and system based on natural language generation. According to the invention, through establishing a keyword and context construction module, a brand semantic modeling and control module, an industry trend extraction module, an advertisement generation engine, a diversity control module and a putting adaptation and post-processing module, automatic generation of advertisement originality is realized. The system firstly receives a keyword and a mood instruction input by an advertiser, and constructs an initial semantic context; and then, coding a brand sample text by utilizing a pre-training model, and generating a brand semantic center vector as a prompt embedding so as to guide the generated content to accord with brand tonality. Meanwhile, through a keyword reservation supervision mechanism, it is ensured that core keywords appear naturally and at high frequency in the process of generating the copywriting. In the generation process, the system also uses a sampling strategy through a diversity control module and uses a semantic vector to remove duplication, and finally outputs diversified and non-redundant high-quality advertisement copywriting.

The invention belongs to the technical field of digital image processing, and particularly relates to a knowledge distillation-based cross-modal fusion lightweight defect detection method, which comprises the following steps of S10, cross-modal fusion distillation; through a bidirectional vision-language alignment mechanism, the frozen multi-modal knowledge of a teacher model vision-language basic model VLM is migrated to a lightweight student model, and the dual-path fusion module comprises text condition region representation injected with semantic context and region anchoring semantic embedding fused with spatial vision clues; step S20, cross-header word-region alignment is carried out; embedding the fusion visual features generated by the two-way fusion module and the enhanced text to generate cross-head prediction so as to simulate the semantic-space association capability of a teacher model; s30, knowledge distillation loss is fused; according to the method, the multi-modal basic model is fused and distilled into the lightweight single-modal detection model, the detection performance in a defect detection scene can be improved, and compared with the basic model, the reasoning speed is greatly improved, and the parameter quantity is reduced.

The invention discloses a low illumination enhancement method based on event and image bidirectional collaborative guidance, and belongs to the technical field of computer vision. The method comprises an event feature extraction branch and an image-event fusion branch which are respectively provided with an image-guided event enhancement module and a Mama-based image-event fusion module; the two modules realize cross-modal interaction through bidirectional cooperative guidance. The image-guided event enhancement module suppresses event noise and compensates for context loss by using semantic context information of an image. The Mama-based image-event fusion module adjusts the global illumination and contrast of the image by using the global representation capability of Mama and the characteristics of linear space-time complexity, and fuses event data to the image in combination with a signal-to-noise ratio map to supplement structural information. According to the method, enhancement and fusion of the image and event information are realized through a bidirectional collaborative guidance mechanism, and the enhancement problems of image structure deficiency and illumination contrast degradation in a low-illumination scene are solved.

The invention discloses a power dispatching monitoring data anomaly detection method based on artificial intelligence, and relates to the field of data anomaly detection, and the method comprises the steps: firstly carrying out the multi-modal alignment and preprocessing of high-frequency time sequence monitoring data and sparse log text of power dispatching, and constructing the association mapping of heterogeneous data under a time window; a retrieval enhancement generation technology is utilized to deeply parse a log text to construct a global semantic context, and time series data is synchronously subjected to double-flow coding to extract inherent fluctuation features. Based on this, a cross-modal semantic gating feature modulation mechanism is established, and a dynamic reweighting sequential sequence is guided by using log semantics, so that when a semantic background of a specific scheduling operation is perceived, the attention on compliance data mutation is automatically reduced. And finally, performing signal reconstruction and adaptive anomaly judgment based on the feature sequence under semantic guidance. In this way, false alarms can be significantly reduced while the real fault sensing capability is guaranteed, and the intelligence and robustness of the power monitoring system are improved.

The invention discloses a file digital circulation privacy protection method and system based on a zero-trust architecture, and relates to the technical field of data security, and the method comprises the steps: building a mapping table of semantics and encryption fragments based on a semantic context tag set and a dynamic authorization intention in combination with the operation granularity in a homomorphic encryption domain, generating a homomorphic operation plan and a re-encryption credential set; according to the homomorphic operation plan and the re-encryption credential set, executing logic fragmentation and homomorphic encryption on the to-be-transferred file to form a cryptographic container set, obtaining an access commitment instance, and constructing an access commitment chain initial fragment; homomorphic cooperation operation is executed in the secret state container set, the access commitment chain initial fragment is checked in real time, node revocation and authorization reversal are executed according to the commitment chain state, and an updated access commitment chain and an instant trust reconstruction record are generated. According to the invention, the security, controllability and traceability of the file collaboration process are improved.

The invention discloses a three-dimensional point cloud semantic segmentation method based on cross-scale feature fusion. In order to solve the problems that a decoder of an MLP-based point cloud semantic segmentation algorithm supplements features only through jump links, semantic and detail information of different levels cannot be aggregated, and features extracted by an encoder cannot be better analyzed, a cross-scale feature fusion module is provided; semantic context information of a high resolution level and geometric detail information of a low resolution level are reserved. According to the three-dimensional point cloud semantic segmentation method based on cross-scale feature fusion, features of three different scales are selected, and feature channels of the features are compressed into 1, so that the problem of information coincidence caused by direct element-by-element summation and element-by-element multiplication is solved, and the effect of unifying dimensions without convolution operation is achieved; then multiplying the high-scale features by the basic scale features element by element, adding the low-scale features by the basic scale features element by element, and finally applying the element-by-element results or the added results to the high-scale features or the low-scale features respectively, and adding the high-scale features or the low-scale features with the original basic scale features to form cross-scale features. And the decoder can obtain finer features for analysis.

The invention relates to the field of intrusion detection, and provides an APT attack detection method and system based on a dynamic multilayer semantic enhancement traceability graph. The APT attack detection method based on the dynamic multi-layer semantic enhancement traceability graph comprises the following steps: constructing the dynamic multi-layer semantic enhancement traceability graph which is sequentially subjected to layer-by-layer feature fusion of an original event layer, a behavior mode layer and a threat technology mapping layer, carrying out deep semantic enhancement on nodes and edges in the graph, and adopting an increment updating mechanism to update the threat technology mapping layer in the dynamic multi-layer semantic enhancement traceability graph; capturing an attack behavior, extracting a semantic context, and constructing a graph snapshot of the dynamic multilayer semantic enhanced traceability graph; adopting a pre-trained H-STFT model to embed all nodes in the graph snapshot into a feature space to obtain a node embedding vector set; aggregating all node embedding vectors in the node embedding vector set to obtain a graph level feature vector; based on the graph level feature vector, obtaining the probability of whether the APT attack exists in the current graph snapshot; and accurate detection of the APT attack is realized.

The invention provides a large model and retrieval enhanced intelligent gas risk studying, judging and handling method and device.The method comprises the steps that a gas over-limit alarm semantic description text is obtained, and structured risk elements are extracted through a large language model subjected to instruction fine adjustment; mapping the risk elements into standard terms based on a gas over-limit risk standardized ontology model; executing multi-dimensional weighted retrieval in the coal mine safety domain knowledge base according to a standardized result, calculating a comprehensive correlation score by combining semantics, ontology, regulations, cases and trend consistency, and screening knowledge fragments; and finally, constructing a scenario semantic context, driving the large language model to perform causal reasoning and generating a risk disposal strategy. Through ontology standardization and a multi-dimensional retrieval mechanism, the problems of insufficient specialty and illusion of a general model are solved, accurate study and judgment and scientific disposal of the coal mine gas risk are realized, and it is ensured that the finally generated risk disposal strategy has a clear regulation source and data support.

The application provides a kind of robot chat method based on knowledge enhanced empathetic reply, including dialogue context preprocessing, the construction and coding of semantic context graph and emotional context graph, dialogue context semantic and emotional modeling, reply generation of the fusion of semantic and emotional information;The application designs two stages of semantic context graph construction and coding and emotional context graph construction and coding, in the semantic context graph construction and coding stage, a new semantic knowledge screening strategy is proposed, a new semantic context graph is designed and constructed, to make the model obtain rich semantic information related to dialogue context, help the model more fully recognize user situation, in the emotional context graph construction and coding stage, a new emotional knowledge screening strategy is proposed, to help obtain external emotional knowledge closer to user emotion, so that the model can more accurately perceive user implicit emotion;The method can generate replies with better cognitive and emotional empathy effect.

The invention relates to the technical field of natural language processing, and discloses a Yi language speech recognition method based on self-supervision and attention feature fusion. The method comprises a feature encoder module, a comparative learning module, a mask language modeling module, a joint optimization and feature fusion module and a decoder module, the feature encoder module adopts a convolutional neural network structure and converts continuous waveform signals into feature representation suitable for subsequent modeling, and the comparative learning module performs feature fusion on the continuous waveform signals through a Gumbel-Softmax technology. The method comprises the following steps that: a mask language modeling module and a feature fusion module are integrated, deviation caused by manual definition or clustering is avoided, the mask language modeling module obviously enhances semantic understanding and tone modeling capabilities of a model in a low-resource scene, a self-attention feature fusion mechanism is introduced into the feature fusion module, continuous features, discrete unit representation and semantic context representation from an acoustic level are spliced, and a self-attention feature fusion mechanism is introduced into the self-attention feature fusion mechanism. The decoder module adopts a decoder structure based on connection time sequence classification, and the corresponding relation between the voice and the text can be achieved without strict alignment labeling.

The invention relates to the technical field of remote sensing change detection, and discloses a remote sensing change detection method and system based on boundary perception semantic context. The method comprises the following steps: extracting global spatio-temporal features of a double-temporal image pair under different scales through a boundary perception semantic context network model to obtain time-phase differential features of each scale, extracting texture and contour information from the time-phase differential features of each scale to obtain detail features, and integrating the time-phase differential features of each scale to obtain semantic features; and introducing the boundary information into a learning process, fusing the detail features and the semantic features to obtain enhanced features, and performing prediction according to the boundary information and the enhanced features to obtain a remote sensing change detection result. According to the invention, information of different scales and boundary information in the remote sensing image can be effectively utilized, and the accuracy of remote sensing change detection is improved.

The invention relates to a language decoding method and device based on electroencephalogram signals and electronic equipment, and the method comprises the steps: collecting the electroencephalogram signals of a subject, and carrying out the preprocessing of the electroencephalogram signals, and obtaining a neural feature time sequence; the neural feature time sequence is input into a parallel decoding architecture, and the parallel decoding architecture comprises at least two decoding branches and is used for decoding subunits of different orthogonal dimensions of a language from the neural feature time sequence; obtaining a subunit probability sequence output by each decoding branch through a parallel decoding architecture; performing time sequence probability accumulation and fusion on the sub-unit probability sequence of each decoding branch to obtain a stabilized sub-unit sequence; performing legality verification and combination on the stabilized subunit sequence according to a phonetic system rule to generate a legal syllable sequence; and disambiguating the syllable sequence based on the semantic context, and outputting a continuous natural language text. According to the method, effective modeling and generalization decoding are carried out on massive syllable categories under the condition of limited training data.

The invention provides a causal reasoning and confidence-driven gas overrun risk judgment method and device, and the method comprises the following steps: firstly constructing a scenario semantic context based on underground monitoring data and an equipment state, and inputting the scenario semantic context into a fine-tuned large language model to generate a risk evolution causal chain containing hidden intermediate nodes; then, respectively calculating a historical case support degree, a real-time data goodness of fit and a knowledge fragment matching degree, and obtaining a comprehensive confidence coefficient based on arithmetic average logic; and the system automatically executes a hierarchical response strategy of full-automatic confirmation, man-machine collaborative research and judgment or low-confidence suppression according to a comparison result of the comprehensive confidence and a preset threshold value, and performs model closed-loop optimization by using feedback data. According to the method, by introducing a recessive logic completion and three-dimensional confidence verification mechanism, interpretability analysis and reliability quantification of the gas over-limit risk are achieved, and the problems that a traditional method is high in false alarm rate and lacks physical basis are effectively solved.

The invention belongs to the technical field of image processing, and particularly relates to a remote sensing image compression and reconstruction method based on feature perception and potential diffusion super-division. The method comprises a coding and compression stage and a decoding and reconstruction stage, in the coding and compression stage, intelligent analysis, selective compression and data encapsulation are carried out on an original high-resolution remote sensing image, a feature region and a homogeneous background region in the image are intelligently identified and separated through a convolutional neural network, and differentiation processing is carried out on the feature region and the homogeneous background region; and performing high-precision recording on the feature region, and performing aggressive down-sampling on the homogeneous background region. In the decoding and reconstruction stage, a high-resolution reconstructed image is recovered from a compressed data packet, reconstruction is carried out through a potential diffusion super-resolution model, the model can utilize the semantic context of the image so as to generate visual natural textures, and the problems of overall blur and the like caused by traditional interpolation are effectively avoided. And therefore, the image can still excellently maintain key ground feature details under a high compression ratio.

A method of managing a computer network includes: receiving, at a network port, a stream of multimodal data; obtaining, from the multimodal data, a subset of the multimodal data that corresponds to a modality; determining, using a large-language model (LLM) agent, a semantic context of the subset of the multimodal data; determining, based on the semantic context and among a plurality of network policies, a network security policy corresponding to the subset of the multimodal data; and directing the subset of the multimodal data according to the network security policy.

A method includes iteratively executing a pre-processing document processing loop using a large language model (LLM). The pre-processing document processing loop includes analyzing a raw document to obtain a modification recommendation. The raw document is modified based on the modification recommendation to obtain an improved document. A document style rule set is applied to the improved document to obtain a styled document. The styled document is augmented with a semantic context to obtain a discoverable document, until the discoverable document achieves a document readiness score greater than a document readiness threshold. The method further includes executing a post-processing document processing phase using the LLM. The post-processing document processing phase includes generating an answer to a user query from a discoverable document embedding corresponding to the discoverable document. The discoverable document is further updated by executing the pre-processing document processing loop, with the semantic context including the user chat history.

The application relates to the field of 4D radar point cloud enhancement in intelligent driving, in particular to a 4D radar point cloud enhancement method based on BEV semantic priori. The technical scheme comprises the following steps: collecting image data and 4D radar point cloud data; pre-processing the image data to obtain a BEV semantic graph and corresponding visual uncertainty; aligning the 4D radar point cloud data and the BEV semantic graph in terms of semantic context to obtain a radar point cloud enhanced in semantics; receiving the radar point cloud enhanced in semantics and classifying each point; dynamically fusing the BEV semantic graph, the corresponding visual uncertainty and the classified radar point cloud under different working conditions to generate a final perception result. The application realizes efficient and robust fusion of high-precision but weather-affected visual BEV perception and all-weather but sparse and noisy 4D radar perception. The application is suitable for intelligent driving.

The application discloses a semantic context-related auditory brain-computer interface consciousness detection system, uses a brain-computer interface and a deep learning technology to carry out consciousness detection, designs a speech context-related auditory brain-computer interface paradigm, through using animal sounds as auditory stimulation, adds a semantic context related to the stimulation to improve the attention of a subject to the paradigm, thereby improving the quality of an event-related potential induced by the paradigm and improving the performance of the brain-computer interface. Through improvement of an EEG-Inception model for feature extraction and classification, the EEG-Inception model can extract more effective electroencephalogram signal features and also has a better classification effect under a small sample size. Through innovation and improvement of the brain-computer interface paradigm and a detection and classification algorithm, the application improves the performance of the auditory brain-computer interface and solves the problem that some patients with consciousness disorders cannot use a visual brain-computer interface for consciousness detection because they cannot control eye movement.

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.

This invention discloses a method and apparatus for renewable energy power prediction based on time-series discrete labeling, belonging to the field of renewable energy power prediction; it includes: acquiring historical observation multivariate time series of target power plants; constructing and training a time-series labeling mapping, dividing the multivariate time series into blocks and encoding them to obtain a continuous latent representation; normalizing the continuous latent representation and the introduced learnable codebook respectively, and allocating discrete indices using nearest neighbor search to obtain a discrete time-series label matrix; expanding the discrete time-series labels output by the trained time-series labeling mapping and incorporating them into the unified vocabulary of a pre-trained language model to construct a conditional autoregressive generative model, and performing fine-tuning training while freezing the backbone network parameters of the pre-trained language model; given the environmental semantic context and the historical time-series label sequence obtained through the time-series labeling mapping, generating a future discrete label sequence based on the trained model in an autoregressive manner, and inputting the generated future discrete label sequence into the decoder of the time-series labeling mapping to reconstruct a prediction sequence in the continuous domain.