1081 results about "Semantic association" patented technology

The invention discloses an intelligent planning method and system for a weak current system in a smart park, and belongs to the technical field of weak current intelligent design. The method comprises the steps of performing feature extraction on the weak current multi-source data of the smart park to form a weak current feature set; a multi-dimensional semantic space is constructed, semantic association features are obtained, and node features, topological relations and constraint rules of the weak current system are determined; generating a weak current knowledge graph based on the information, and performing semantic alignment on the basic information of the park to obtain a final scene demand representation; performing graph reasoning and constraint calculation according to the representation to obtain a feasible region and constraint satisfaction condition, and generating a candidate construction scheme; and screening out an optimal construction scheme from the candidate schemes according to a preset comprehensive optimization strategy and sending the optimal construction scheme to a control center. According to the scheme, the weak current scheme is promoted from demand understanding to scheme optimization, and a coherent and verifiable automatic process is formed; therefore, the manual intervention is less, the design judgment is more accurate, and the finally output construction scheme has higher engineering reliability.

The invention discloses an automobile wire harness process rule automatic matching method based on a knowledge graph, and the method comprises the following steps: collecting wire harness design data, and carrying out the standardization processing; analyzing the process rule base, extracting key attribute fields and generating a process rule metadata set; semantic modeling and structured fusion are carried out, and a process knowledge graph is constructed; performing semantic association analysis, causal constraint fusion and feasibility judgment processing by utilizing a semantic retrieval enhancement module; carrying out provable retrieval, risk assessment and conflict resolution based on the candidate process rule set; converting the target process rule set into a process instruction, and driving a design system to perform synchronous updating and rule labeling; and updating the process knowledge graph based on system feedback data, and outputting an optimized process verification report and updating a design version. The method is based on the knowledge graph and the semantic causal fusion technology, intelligent matching of the wire harness process rules is achieved, and the method has the advantages of being high in matching precision, high in interpretability and capable of achieving self-adaptive optimization.

The invention discloses an indoor three-dimensional point cloud semantic segmentation method based on a super voxel Transform architecture, and belongs to the technical field of map making. The method comprises the following steps: acquiring point cloud data of different scenes, preprocessing the point cloud data, and constructing a training sample set; constructing a neural network for indoor three-dimensional point cloud semantic segmentation; training the neural network; and obtaining indoor three-dimensional point cloud data to be segmented, preprocessing the point cloud data, inputting the point cloud data into the trained neural network, outputting a super-voxel category probability and confidence, mapping a super-voxel label back to the original point cloud, and completing semantic segmentation of the indoor three-dimensional point cloud. According to the method, efficient dimension reduction and local feature aggregation of the point cloud are realized through a hierarchical structure of the super voxels, global semantic association is modeled in combination with a self-attention mechanism of Transform, semantic segmentation can be better performed on the indoor three-dimensional point cloud, and various indoor application requirements are met.

The invention relates to the technical field of artificial intelligence, and discloses an enterprise-level large-model agent application system supporting multi-modal collaboration, and the system comprises a user interaction terminal, an agent engine server, a knowledge engine server, a plug-in integration center, and a distributed storage unit. The agent engine server is responsible for intention recognition and task arrangement of a multi-modal input signal, and dynamically loads a differential reasoning strategy based on an environment isolation mechanism. And the knowledge engine server constructs a cross-modal semantic anchor point, analyzes an unstructured document into a tetrad knowledge unit, and realizes accurate recall of images and texts by using a hybrid retrieval algorithm. And the plug-in integration center executes outbound replacement and inbound restoration of the sensitive data through the context-aware dynamic desensitization gateway. According to the method, through a multi-modal semantic association and closed-loop verification mechanism, the problems of low complex document retrieval precision and leakage of external calling data are solved, and the service processing capacity and safety of the system are improved.

The disclosure provides a method and an apparatus for processing an image, an electronic device, and a storage medium, which relates to the field of artificial intelligence technologies, and particularly to a technical field such as computer vision, deep learning, and large-scale models. The solution includes: obtaining an input content adapted to an image processing task, in which the input content includes at least one of: a first text token sequence, a first image token sequence, or an image-text fusion sequence; obtaining a joint feature representation including multimodal semantic information by performing cross-modal semantic modeling on the input content, in which the multimodal semantic information indicates a semantic correlation relationship of the input content in different modalities; and generating an output content adapted to the image processing task based on the joint feature representation.

The invention relates to the technical field of data analysis, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a multi-agent traceable analysis method, device, equipment and medium, and the method comprises the steps: receiving a target theme and a data source list, collecting a multi-source document, and carrying out the preprocessing of the multi-source document to generate a preprocessing document set; configuring an analysis agent based on a semantic clustering result, and setting an analysis direction to form an analysis agent set; generating a structured note and index data table, and executing cross-document comparison to form an analysis output set; and receiving a feedback instruction to adjust the analysis agent set, triggering incremental processing to update the analysis output set, generating a theme research and judgment report, and keeping mapping consistency. According to the method, the multi-source document is fused through semantic clustering and a multi-agent cooperation mechanism, semantic association and traceable analysis are achieved, agent configuration is optimized in combination with interactive feedback, and the accuracy and the intelligent level of report generation are improved.

The invention discloses an unmanned aerial vehicle multi-task collaborative planning method based on a large language model, and particularly relates to the technical field of path planning. Obtaining a task natural language description and extracting a task semantic vector; constructing a task semantic association graph and performing clustering to form a task cluster; collecting unmanned aerial vehicle state information to generate a state vector; calculating a task-unmanned aerial vehicle matching score based on a large language model, and constructing an initial task allocation matrix; introducing feasibility constraints and generating a feasible task allocation scheme through an optimization algorithm; combining an A * algorithm and a large language model to generate an initial path, and performing iterative optimization on the path through a semantic constraint loss function; in the task execution process, if task or communication changes are detected, task allocation and paths are dynamically reconstructed; the method has the technical advantages of strong semantic understanding, high planning robustness and excellent path adaptability, and is suitable for multi-unmanned aerial vehicle cooperative task execution in a complex dynamic environment.

The invention discloses a software development result traceability analysis system based on version control, and relates to the technical field of intelligent software analysis. According to the method, the non-tampering property of code submission records is ensured through a block chain technology, a credible basis is provided for traceability, the code semantic analysis module generates a data set containing semantic association in combination with a clustering algorithm and weighted calculation, and the function influence positioning module constructs a function association graph by applying a graph neural network algorithm, so that the traceability is improved. An influence path of code change on system functions is automatically identified, the time cost of complex project function influence positioning is remarkably reduced, an evolution path generation module analyzes and tracks a code evolution path in combination with a time sequence, and a core module identification module clusters key nodes and positions a core function module. And the time-tracing source data storage module generates a visual relation graph and a queried data set, so that the whole-process management from code submission to result tracing is realized.

The invention relates to the technical field of robot control, and discloses an industrial robot adaptive control method and system based on multi-modal sensor fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the time-space alignment; capturing space-time semantic association of visual textures, tactile pressure distribution and force sense fluctuation in the multi-modal data through a multi-head attention mechanism guided by a physical model, and performing space-time registration; a CNN-LSTM hybrid model is adopted to extract visual texture features and time sequence tactile features in the physical information enhanced multi-modal feature matrix; and carrying out dynamic weight distribution on the fusion feature vectors with physical consistency by utilizing a weight distribution model driven by element reinforcement learning to generate dynamic weighted fusion features. According to the method, the spatial positioning precision of the industrial robot in a precise assembly scene is greatly improved, the contact force control stability is greatly improved, and the control robustness in a complex operation scene is remarkably enhanced.

The invention relates to the technical field of computer vision, in particular to an intelligent conference video frame dynamic coding method based on multi-modal semantic understanding, which comprises the following steps: acquiring a video stream sequence and a synchronous audio stream in a conference scene in real time; performing semantic analysis and decoupling on the video stream sequence, and extracting key frames and subsequent frames; extracting a sparse motion field from a subsequent frame, and segmenting a video frame into candidate visual areas including a face, a mouth shape and a background; extracting audio semantic features, executing cross-modal semantic correlation analysis, calculating semantic correlation between the sparse motion field distribution features and the audio semantic features, and positioning a pronunciation area highly related to the voice content; and calculating a quantization offset value of each candidate visual area according to the semantic relevancy, applying the quantization offset values in different areas, and packaging the quantization offset values into a variable-code-rate video code stream. According to the invention, the multi-mode semantic understanding model is constructed to carry out deep semantic analysis on the video frame content so as to realize the dynamic coding of the conference video frame.

The invention discloses a digital human construction method and device based on a heterogeneous emotion semantic graph and long-sequence emotion modeling, and the method comprises the steps: obtaining multi-modal emotion input data of a text, voice and a visual image, extracting features, and constructing a multi-modal emotion feature set with a timestamp; constructing a heterogeneous emotion semantic graph which comprises user entity nodes, modal feature nodes and emotion concept nodes, modeling a semantic association, state transition and conflict suppression relationship through a multi-type edge structure, and introducing a dynamic evolution and conflict discrimination mechanism; performing time sequence modeling on the emotional state sequence by utilizing a local-global double-layer emotional modeling mechanism, and respectively capturing short-time fluctuation and long-time trend; performing cross-modal fusion on the emotional state and the modal features, and decoding the emotional state and the modal features into behavior parameters for controlling expressions, voices and actions of the digital human; and multi-modal emotion expression of the digital human is driven. Compared with the prior art, the emotion recognition accuracy and expression continuity and naturalness can be effectively improved.

The invention provides a passable area reasoning method and system based on a visual language model, and the method comprises the steps: obtaining the multi-modal data of a vehicle and the current position information of the vehicle; analyzing the multi-modal data, and determining visual features and traffic symbol features; performing spatial position coding on the visual object and the traffic symbol elements, and determining aerial view angle coordinate information; performing semantic alignment on the visual features and the traffic symbol features, and determining a shared embedding representation; constructing a traffic semantic map by fusing, sharing and embedding representation based on a graph neural network and bird's-eye view coordinate information of a visual object and a traffic symbol element; and according to the current position information of the vehicle, the traffic semantic map and a preset traffic rule, generating a bird's-eye view semantic map including a passable area, a no-pass area and a semantic association relationship. According to the method and the device, semantic alignment and consistency expression of visual perception and traffic symbol recognition are realized, and further feasible region reasoning of a complex traffic scene is realized.

The invention discloses an elevator intelligent operation and maintenance question-answering system based on edge computing and computing network integration. The system obtains running state data in real time through an edge data acquisition module, and performs preprocessing and dynamic sampling optimization on an edge side; the computing network fusion analysis module performs multi-dimensional comprehensive analysis on the operation state data by utilizing computing power cooperation of the edge node and the cloud node to generate an elevator health state result and a fault risk result; the knowledge graph reasoning module executes semantic association and logical reasoning in the elevator knowledge graph according to the analysis result to obtain a fault diagnosis result and a fault reason speculation result; the intelligent question and answer interaction module analyzes questions input by a user based on a natural language understanding technology, and generates question and answer responses containing running state instructions, potential risk prompts and maintenance suggestions. According to the system, a complete closed loop from data acquisition, intelligent analysis and knowledge reasoning to semantic interaction is realized, and the intelligence, real-time performance and interpretability of elevator operation and maintenance diagnosis can be remarkably improved.

The invention discloses a lightweight knowledge graph rapid construction method and system based on an NLP technology. The method comprises the steps of preprocessing an unstructured text and segmenting the unstructured text into semantic segments; unsupervised clustering is combined with the contour coefficient to determine the optimal clustering number, and a semantic association fragment cluster is obtained; performing word segmentation, part-of-speech tagging, NER and entity linking on the fragment cluster, extracting an entity and initial relationship, and fusing semantic similarity, TF-IDF word frequency collaboration degree and co-occurrence frequency to calculate a relationship edge weight; constructing a lightweight knowledge graph; in the question and answer stage, questions are disassembled through a process engine, related sub-graphs are retrieved, and answers with reasoning links are generated. The system correspondingly comprises a text preprocessing module, a clustering module, an entity relation processing module, a graph construction module, a question and answer reasoning module and a storage module. According to the method, the construction cost is reduced, the interpretability and the module coupling degree are improved, multiple scenes such as government and enterprise public opinions and medical assistance are adapted, and the problems of weak generalization, poor real-time performance and'black box 'in the traditional technology are solved.

The invention relates to the technical field of document processing, and discloses a document knowledge retrieval method and system, electronic equipment and a storage medium. Based on a language model, synchronously generating abstract contents and a semantic association query set for each text fragment, and aggregating the abstract contents of all text fragments corresponding to the same document to form a fragment abstract set; constructing a multi-path retrieval pool based on the text fragment, the abstract content and the semantic association query set, and respectively constructing a plurality of independent retrieval data sources; the method comprises the following steps: constructing a dual-granularity abstract index system, receiving a query request of a user, executing query routing processing based on dual-granularity abstract index and a hierarchical retrieval process based on a metadata structure, returning retrieval result data, performing fusion calculation and duplicate removal processing on the retrieval result data recalled by multiple paths, and obtaining a retrieval result. And meanwhile, the document abstract short sentence group is injected into a search suggestion function of a search engine. According to the method, the retrieval accuracy can be improved, and the user experience is improved.

The invention relates to a KV cache optimization method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: calculating a key vector and a value vector corresponding to each element in a text input sequence input into a large language model; through a multi-head potential attention mechanism, performing low-rank joint compression on the key vector and the value vector to obtain a potential vector, and storing the potential vector in a KV cache space; based on a scaling law, determining an optimal compression dimension, regenerating an adaptive potential vector and updating a KV cache space; for the same text input sequence, generating corresponding query vectors, and grouping the query vectors according to a preset grouping rule; calculating a semantic association weight between each group and the correspondingly called potential vector, and taking the semantic association weight as a group attention calculation result; in the reasoning process, potential vectors and grouping attention calculation results are calculated to calculate attention weights. By adopting the method, the storage requirement of the KV cache can be further reduced.

The invention belongs to the technical field of cloud side-end collaborative data processing, and discloses a cloud side-end collaborative heterogeneous data fusion processing system, which establishes dynamic association of data features, resource states and service priorities through a scheduling module, and adopts a reinforcement learning algorithm combining DQN and an attention mechanism to perform fusion processing on heterogeneous data. Task allocation weights are dynamically adjusted with the minimum delay, the highest precision and the maximum business value as targets; the sensing module and the preprocessing module complete lightweight processing such as feature extraction and noise reduction redundancy elimination at the edge end, and the cross-node data transmission amount is reduced. The complex fusion task dispatches cloud computing power support, and reserves resources in advance by means of an LSTM-based task urgency predictor; the cross-modal fusion module designs a double-stage fusion algorithm, in the first stage, cross-modal semantic association is enhanced through multi-head self-attention, and in the second stage, the fusion weight is adjusted according to the reliability coefficient of the sensing module.

The invention discloses a scientific and technological achievement analysis and prediction method and system based on big data, and relates to the technical field of machine learning and big data analysis, and the method comprises the steps: collecting and preprocessing multi-source scientific and technological achievement semantic data, and constructing a scientific and technological concept relation graph; the method comprises the following steps: performing training by taking a time sequence diagram convolutional network as a basic framework and taking a scientific and technological concept relation graph as a training sample, constructing a dynamic knowledge flow semantic model, performing evolution feature extraction on the scientific and technological concept relation graph by utilizing the dynamic knowledge flow semantic model, and outputting a knowledge flow feature vector; and inputting the causal enhanced space-time diagram into a space-time diagram neural network, aggregating semantic association and causal relationships among the scientific and technological achievements in a space dimension, capturing a dynamic change mode of scientific and technological achievement characteristics in a time dimension, and outputting a scientific and technological concept time sequence predicted value sequence. According to the method, the causal enhancement space-time diagram is constructed, so that trend deduction and causal traceability analysis are carried out for the time dimension, and the accuracy of scientific and technological achievement development trend prediction is improved.

The invention relates to the technical field of artificial intelligence and data processing, and discloses a multi-mode identity relation inference system based on a graph neural network. The system comprises a multi-modal feature extraction module, a cross-modal alignment module, a graph structure construction module, a dynamic relation reasoning module and a decision output module. According to the method, the cross-modal alignment module is introduced to project the image features and the text features to a unified public semantic space, so that the nonlinear distribution difference of heterogeneous modals in an embedding space is effectively eliminated, and cross-modal alignment errors are avoided from the source; by integrating the attention mechanism of modal perception in the graph neural network, the system can dynamically learn the semantic association strength between the nodes in different modals, adaptively adjust the weight distribution in the neighborhood information aggregation process, and significantly improve the accuracy of node characterization.

The invention discloses a cloud management and intelligent distribution method for classroom teaching resources, and relates to the technical field of cloud computing software. The classroom teaching resource cloud management and intelligent distribution method comprises the steps that S1, multi-source teaching resource data and auxiliary distribution data are acquired and preprocessed, and a knowledge content database is constructed; s2, performing semantic fusion analysis through text semantic association, structural consistency and professional term coverage data; s3, carrying out dependency evaluation by fusing pre-association, knowledge co-occurrence, sequence association and semantic fusion data; s4, performing resource adaptability distribution analysis through the maximum knowledge dependence value in combination with the learning state data and the historical feedback data; and S5, evaluating the teaching resource quality by collecting classroom feedback, teacher evaluation and resource use data, and implementing content optimization. The problems of semantic distortion, path breakage, distribution mismatching and resource updating inconsistency in the teaching resource data fusion and intelligent resource distribution process are solved.

The invention discloses a knowledge graph construction method which comprises the following steps: acquiring document data from different sources, extracting long content from the document data, and segmenting the long content into a plurality of semantic text blocks; for each semantic text block, extracting all entities from the semantic text block by using a large language model, and analyzing the relationship between the entities; constructing a global semantic association graph based on all entities and the relationship between the entities, and dividing the global semantic association graph by using a graph clustering algorithm to form a plurality of knowledge communities; and creating corresponding entity nodes for the entities, creating corresponding edges for relationships between the entities, creating corresponding community nodes for the knowledge communities, and establishing belonging relationships between the community nodes and the corresponding entity nodes to form a knowledge graph, and storing the knowledge graph in a graph database system. On the basis, the knowledge extraction precision and the cross-domain generalization ability can be improved, and a hierarchical knowledge system can be formed.

The invention discloses an industrial measurement data intelligent analysis report generation method and system based on a large language model, and relates to the technical field of industrial measurement, and the method comprises a multi-source data and abstraction module which carries out the structural processing of original data DAT output by measurement analysis software; and the large language model service and interface module is used for submitting the PCT to a selected large language model LLM through a multi-model adaptation interface to execute semantic reasoning and output a structured text TXT. Structured analysis and semantic association modeling are carried out on original measurement data through multi-source data and an abstract module, when overall alignment deviation or local feature anomaly exists in the original data, a hierarchical dependency relationship between the data can be established through a semantic graph structure, a deviation transmission path is revealed, and the accuracy of the measurement data is improved. The large language model is analyzed in a unified data context, and the utilization depth of measurement data can be effectively improved, so that the accuracy and integrity of report analysis are improved.

The embodiment of the invention provides a context construction method and device for an agent and a storage medium, and the method comprises the steps: obtaining the current input information of the agent in one interaction round, and carrying out the analysis to generate a current semantic representation; determining a semantic association degree between the current semantic representation and the context of the current dialogue task, and calculating a long-term value score of the current semantic representation; under the condition that the semantic association degree is greater than a first preset threshold value, storing the current semantic representation into a short-term memory library; under the condition that the long-term value score is greater than a second preset threshold value, storing the current semantic representation into a long-term memory library; when the intelligent agent needs to generate a response for the current input information, searching target memory content related to the semantics of the current input information from the short-term memory library and the long-term memory library; and combining the target memory content with the current input information to form prompt information, and inputting the prompt information into a large language model to generate a response for the current input information.

The embodiment of the invention discloses an aluminum plastic package detection method and system based on machine vision, and the method comprises the steps: carrying out the noise reduction processing of a single-visual-angle detection image of an aluminum plastic package, obtaining a noise reduction detection image, extracting an abnormal feature region, and obtaining an initial detection result; establishing a semantic association rule of a pre-trained semantic rule mapping model and the quality detection demand label of the aluminum plastic package; a synchronous quality control instruction in the production link of the aluminum plastic package is used as a semantic adaptation trigger condition, and an adjustment strategy of a semantic weight distribution unit is calibrated and activated; inputting the initial detection result into a semantic rule mapping model to perform semantic dimension priority ranking on abnormal features in the initial detection result to obtain an abnormal feature ranking result; and in combination with the defect judgment model and a defect grading rule in a current production scene corresponding to the production link, performing matching judgment on the abnormal feature sorting result, and outputting a defect judgment conclusion adaptive to the current production scene.

The invention provides a self-adaptive cache evaluation method and device based on multi-dimensional evaluation parameters and a medium, and relates to the technical field of data storage. The method comprises the following steps: acquiring an evaluation access frequency f of to-be-cached data, evaluation semantic popularity h and evaluation space-time demand density d of the to-be-cached data by a to-be-cached terminal, and evaluation terminal performance e of the to-be-cached terminal; obtaining an access frequency evaluation weight alpha, a semantic popularity evaluation weight beta, a space-time demand density evaluation weight gamma and a terminal performance evaluation weight delta; and obtaining the cache value of the to-be-cached data in the to-be-cached terminal, wherein the cache value is equal to alpha * f + beta * h + gamma * d + delta * e. According to the method, the cache value of the to-be-cached data in the to-be-cached terminal is evaluated from the four dimensions of the access frequency, the semantic popularity, the space-time demand density and the terminal performance, deep demands such as semantic association, space-time distribution and terminal suitability are considered while high-frequency access is captured, resource mismatching is effectively avoided, and the cache content value can be evaluated more accurately.

The invention relates to the field of artificial intelligence, and discloses a multi-modal memory system and method for intelligent interaction. The system comprises a multi-modal information acquisition module, a confidence evaluation module, a scenario aggregation module, a knowledge graph construction module, a hierarchical storage module, an intelligent retrieval module, an active verification module and a memory management module. The core problems that in the long-term user interaction process of an existing artificial intelligence system, multi-modal information management is fragmented, information credibility is not quantitatively evaluated, memory organization lacks semantic association, a retrieval mode is single and passive, and memory life cycle is not adaptively managed are solved. Finally, unified collection, quantitative confidence evaluation, scenario semantic organization, associative intelligent retrieval and adaptive memory optimization of multi-modal information are realized, high-quality and high-efficiency long-term memory support is provided for scenes such as intelligent assistants, smart home, medical health and educational training, and the user experience and practical value of an artificial intelligence system are remarkably improved.

The invention discloses a power industry language model training data dynamic selection method, system and device, and the method comprises the steps: obtaining original scene corpus data based on a power industry power grid dispatching and fault handling application scene aimed at language model training, and constructing a candidate data pool and a scene verification data set; performing parallel or pipelined multi-dimensional quality evaluation on the candidate data in the candidate data pool, dynamically adjusting the weight corresponding to each dimension in the multi-dimensional quality evaluation based on an adjustment strategy, and calculating to obtain a comprehensive quality score; a failure case library is constructed, in the language model training process, the failure case library is updated regularly, semantic relevance between candidate data and the failure case library is quantified, and batch construction of training data is carried out based on the semantic relevance; and based on the batch construction result, performing language model training feedback circulation. According to the invention, the overall efficiency and utilization rate of training data are effectively improved.