284 results about "Semantics encoding" patented technology

The invention provides a multi-agent task collaboration method, device and equipment and a storage medium, and the method comprises the steps: carrying out the deep fusion and unified semantic coding of a collected multi-modal data set through a multi-modal large language model, and obtaining a high-dimensional cross-modal feature embedding and semantic representation file, the task requirement mapping module is used for enabling local task requirements of multiple agents to correspond to cross-modal semantics to obtain task requirement semantic mapping, and task division and time arrangement are carried out; when multiple agents execute tasks, key data and operation results are sampled in real time and compared with high-dimensional semantic representation, a concept offset detection result is obtained, and when it is detected that the concept drifts progressively, the multi-modal large language model is dynamically adjusted. According to the method, the communication and cooperation efficiency among multiple agents is enhanced by using a large language model, and task allocation and collaborative decision are optimized through task demand semantic mapping; and concept drift detection and a dynamic adjustment mechanism are introduced, so that the long-term adaptability in a complex dynamic environment is improved.

Disclosed in the present application are a knowledge graph construction method and apparatus, and a storage medium, an electronic device and a computer program product. The method comprises: acquiring first natural language text; using an extraction model to perform entity extraction on the first natural language text, so as to obtain a first entity and a first entity relationship, and determining a corresponding first entity type and first relationship type; using a semantic encoder to determine a first semantic vector and a second semantic vector respectively corresponding to the first entity type and the first relationship type; on the basis of calculated first distances between the first semantic vector and cluster centers of a plurality of entity types and calculated second distances between the second semantic vector and cluster centers of a plurality of relationship types, determining a target entity type for the first entity type and a target relationship type for the first relationship type; and on the basis of the first entity, the first entity relationship, the target entity type and the target relationship type, constructing a target knowledge graph.

The invention belongs to the technical field of natural language processing and information retrieval. The invention provides a bidding document multi-modal duplicate checking method and system based on a large model, and the method comprises the steps: carrying out the structural analysis and multi-modal feature extraction of an input bidding document, and generating the feature representation of semantic blocks and non-text elements; performing deep semantic coding on text blocks by using a dynamic context-aware large language model, and retaining logic relevance of a long text in combination with hierarchical position coding; efficient matching of massive semantic vectors is achieved through a mixed retrieval framework, and calculation efficiency is optimized in combination with a distributed calculation framework and a hardware acceleration instruction; and finally, performing structured feature reconstruction on non-text contents such as tables, charts and the like to realize cross-modal semantic association analysis.

The invention provides a multi-round dialogue intention recognition method and system based on self-adaptive semantic understanding, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a natural language dialogue text of a current round of a user, and taking the natural language dialogue text as original input data; based on original input data, multi-level semantic features are extracted through a dynamic semantic coding algorithm, and semantic vector representation of a current round of dialogue is generated; setting three fixed anchor points in a semantic vector space based on a current round semantic vector and a historical dialogue state vector to form a triangular analysis structure; performing gridding segmentation on the triangular analysis structure, and generating a feature adjustment value according to distribution characteristics of segmented grids; and dynamically correcting the extraction process of the context-related features by using the feature adjustment value to obtain the corrected context-related features. According to the method, end-to-end optimization is realized in multiple rounds of interaction scenes such as customer service and intelligent assistants through full-process design.

The invention discloses a laboratory quality management document intelligent generation method and system based on retrieval enhancement, and relates to the technical field related to data processing.The method comprises the steps that semantic coding is conducted on a preset standard text, and a vector knowledge base is constructed; retrieving associated standard terms according to the document theme, and extracting structured data from a laboratory business system; embedding the standard terms and the business data into a Prompt template, and calling a preset large language model to generate a text; and performing paragraph splicing and hierarchical control on the generated text, automatically checking compliance by utilizing term consistency of rule model fusion and a numerical value comparison algorithm, and outputting a quality management document. The technical problems that in the prior art, standard term retrieval and matching are not accurate, laboratory business data fusion is difficult, and consequently document compiling efficiency and quality are poor are solved, and the technical effects that minute-level automatic generation of laboratory quality management documents is achieved, and document compiling efficiency, quality and compliance are improved are achieved.

The embodiment of the invention provides a data processing method and system for an enterprise digital transformation platform, and belongs to the field of data processing. The method comprises the steps that structured field information from all heterogeneous data sources is acquired, and preprocessing operation is executed on the structured field information; constructing the processed structured field information into an embedded input sequence, splicing the embedded input sequence into a natural language fragment according to a preset template, and inputting the natural language fragment into a fine-tuned semantic coding model to obtain a corresponding semantic embedded vector; identifying similar field groups by adopting a clustering algorithm based on density or a hierarchical structure, and classifying each group of structured field information into a semantic cluster; and generating a corresponding standard field identifier for each semantic clustering cluster, and storing the generated standard field identifier in a standard field index database of the platform after digital transformation. According to the scheme, the field unified management and cross-system data alignment capability of the enterprise digital platform is remarkably enhanced.

The invention relates to an introspection lifelong SLAM method and system based on visual language model hidden space representation, and the method comprises the steps: extracting a semantic tag based on an RGB-D image through a semantic encoder, and generating a scene map and a semantic topological graph based on the RGB-D image and the semantic tag; generating a dynamic mask based on the scene map, obtaining a dynamic mask coverage rate, and screening key frames with high static confidence values based on the coverage rate; calculating camera pose estimation corresponding to the key frame in real time, sampling the key frame to realize layering of the key frame, and performing layering rendering by using a NeRF model to obtain a virtual view; the hidden space difference degree of the virtual view and the corresponding real image is calculated, whether error introspection needs to be carried out or not is judged based on the hidden space difference degree, and the system is used for achieving the method. Compared with the prior art, the method has the advantages that open semantic reasoning of VLM, high-precision reconstruction of NeRF and real-time positioning of SLAM are combined, and positioning and mapping accuracy is improved.

The invention discloses a Tibetan language multi-dialect real-time semantic conversion method based on a cross-language BERT model, and the method comprises the following steps: S1, collecting original text corpora of each dialect of the Tibetan language, and constructing a standardized training corpus set; s2, performing parameter initialization on the mBERT model, and preliminarily training the mBERT model; s3, constructing a semantic modeling model, and performing fine adjustment on the semantic modeling model; s4, receiving to-be-converted text input, and encoding; s5, obtaining an intermediate semantic representation vector of the text through a semantic coding sub-module; s6, inputting the intermediate semantic representation vector into a semantic generation sub-module, and generating target text output; and S7, executing syntactic consistency correction and language fluency correction. According to the method, mBERT modeling and an adversarial optimization mechanism are fused, real-time semantic consistency conversion of multiple dialects of the Tibetan language is achieved, and the method has the advantages of being high in accuracy, high in robustness and low in response delay.

The invention discloses a security reinforcement learning-driven large language model security decision agent, and the decision agent comprises a high-level semantic planner which is used for receiving a target and constraint instruction in a text form, receiving a language or visual observation signal of an environment at the same time, and outputting text formatted security risk information and suggested action planning; the low-layer action actuator is used for receiving low-dimensional observation and semantic codes of the environment, and the semantic codes are output by the high-layer semantic planner after text embedding conversion; the strategy network of the low-layer action actuator outputs a final safety action; the training alignment module is used for optimizing the strategy network and the value network; a high-level semantic planner is fed back and prompted through reward and cost signals collected through environment interaction, and parameters of a strategy network and a value network are trained through a security reinforcement learning algorithm. According to the method, the decision cannot violate the given text security constraint while the decision of the given text target is completed.

The invention discloses an intelligent document duplicate checking system and method based on a vector database and a large language model, and the method comprises the following steps: S1, collecting document data in various formats, and carrying out the preprocessing of the document data; s2, semantic coding is carried out through a large language model, and a document semantic vector is generated; s3, storing the document semantic vector into a vector database, constructing a vector index and recording historical query data; s4, carrying out preliminary candidate document retrieval, and carrying out approximate nearest neighbor retrieval based on outlier identification; s5, calculating the similarity between the candidate document and the document to be subjected to duplicate checking, and screening a final high-similarity document; s6, generating a duplicate checking report, and recording user operation behaviors; and S7, receiving user feedback, and dynamically updating the document semantic vector and the vector index. According to the method, efficient and accurate intelligent document duplicate checking is realized by utilizing the large language model and the vector database, the semantic matching capability is improved, the duplicate checking efficiency is optimized, and the intelligence and adaptability of a duplicate checking system are improved.

The invention relates to the technical field of artificial intelligence, in particular to a self-organizing knowledge base construction method, system and device based on a multi-agent system and a storage medium, and the method comprises the steps: S1, monitoring a dialogue information flow, calculating the self-reply confidence coefficient of an agent, and if the self-reply confidence coefficient exceeds a preset dynamic threshold value, judging that a potential knowledge value exists and triggering an extraction request; s2, in response to the request, performing semantic coding on a dialogue fragment, extracting knowledge elements, and generating a structured knowledge unit by utilizing graph neural network modeling and relation calibration; s3, through a pre-training semantic coding model, mapping the multi-dimensional semantic coding model into a multi-dimensional semantic vector; s4, carrying out hierarchical clustering comparison and combination, and if a threshold value is exceeded, establishing a new classification and adjusting a knowledge base index; and S5, knowledge fingerprints are generated and compared, and fusion updating is carried out based on the reputation scoring model when semantics conflict or redundancy occurs. According to the method, unstructured dialogue high-precision knowledge extraction is realized, so that the knowledge base structure is dynamically self-organized according to semantics, multi-source knowledge is coordinated, and the knowledge management automation level and quality are improved.

The invention belongs to the technical field of power equipment operation inspection auxiliary decision making, and particularly relates to a power operation inspection knowledge service method and device, equipment and a medium. The method comprises the following steps: analyzing semantics of query input of a user by utilizing a large semantic model, and determining a corresponding target sub-knowledge base in combination with an intention classification sample library and an intention set; performing sentence segmentation on the document of the target sub-knowledge base, generating document fragments containing continuous sentences through context supplementation, and enabling semantics of the document fragments to be overlapped; calculating a keyword correlation score of the query word and the document fragment; generating a text vector through a semantic coding model, and calculating a semantic correlation score of the query input and the document fragments; fusing the keyword correlation score and the semantic correlation score, and outputting each related document fragment according to a comprehensive score sequence; and inputting query input of a user and related document fragments into the large semantic model, and generating a structured answer in combination with the logic in the operation and inspection field of the power equipment. And the electric power operation and maintenance knowledge service with high accuracy and strong generalization is realized.

The invention relates to the technical field of robots, and discloses a task planning method and system for a robot, and the method comprises the steps: obtaining a user instruction; based on the large language model and the semantic coding model, retrieving in a memory bank to obtain environment perception information related to the user instruction; inputting a first cue word determined based on the user instruction and the environment perception information into the large language model, and generating an overall action sequence corresponding to the user instruction; and for each sub-action in the whole action sequence, determining a second cue word, inputting the second cue word into the large language model, and generating a detailed action plan corresponding to the current sub-action until each sub-action in the whole action sequence is traversed. According to the method, the natural language or unstructured instruction can be received, the intention of the user can be understood, and the executable overall action sequence and the detailed action plan of each sub-action in the sequence are generated, so that the task issued by the user is completed, it is ensured that the robot can execute the task, and the accuracy and efficiency of task execution are improved.

The invention relates to the technical field of artificial intelligence dialogue systems, in particular to an intention correction and optimization method and system for multi-round dialogue context memory. According to the method, joint semantic coding is carried out on user input and historical dialogues, key semantic elements are extracted to construct an intention evolution relation graph, context consistency verification is carried out on an initial intention recognition result, and an intention correction candidate set is generated when conflicts are detected; and dynamically adjusting the context coding weight of the historical dialogue based on the corrected intention recognition result. According to the method, the intention recognition accuracy and context coherence in multiple rounds of conversations are effectively improved, and the semantic migration risk is reduced.

The invention discloses a data analysis method and system based on a large model. The method comprises the steps that natural language query of a user is received; performing semantic coding and intention analysis on the natural language query based on a pre-trained large language model; based on metadata retrieval of vector similarity, obtaining metadata related to natural language query semantics from a vector database; generating corresponding structured query parameters through the large language model in combination with the obtained metadata and the natural language query; according to the structured query parameter, generating an executable structured query language statement; and executing the structured query language statement to obtain a data query result. According to the method, the problems of insufficient semantic comprehension ability, low metadata retrieval precision and poor query generation controllability in the prior art are solved.

The invention discloses a text generation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a source text, and carrying out word segmentation sorting to obtain a text sequence; converting the text sequence into word embedding representation; performing semantic feature extraction based on a global encoder, and fusing output vectors of the last plurality of encoding layers based on an attention mechanism to obtain first semantic encoding information; performing semantic feature extraction based on a local encoder to obtain second semantic encoding information; performing feature fusion and filtering based on a global gating unit to obtain a context semantic vector; and decoding the context semantic vector based on a decoder to generate a target text. The context semantic vector is obtained through semantic feature fusion and filtering, redundant features are removed, and post-processing is not needed; the global encoder carries out multi-coding-layer output vector fusion based on an attention mechanism, and the local encoder fuses features through a gating unit, so that richer key information features can be obtained.

The invention discloses a venous thrombosis risk assessment method based on a large language model, and relates to the technical field of medical artificial intelligence, and the method comprises the steps: collecting thoracic surgery diagnosis and treatment data of a patient, carrying out the space-time alignment, generating a standard diagnosis and treatment data flow, and carrying out the homomorphic encryption of the standard diagnosis and treatment data flow, and forming an encrypted patient data package; inputting the encrypted patient data packet into a multi-task large language model, performing feature extraction and semantic coding by a feature coding layer, performing time sequence modeling and risk probability calculation by a risk quantification layer, and outputting a venous thromboembolism risk level of a patient; and performing feature decoupling and potential space mapping on the encrypted patient data packet to obtain thrombus semantic potential features. Through the multi-task large language model, the dual machine learning algorithm and the homomorphic encryption, the accuracy of venous thrombosis risk early warning is improved, and the safety of the risk assessment process is enhanced.

A vulnerability detection method-mVulD-DO based on multi-modal joint distillation optimization comprises the steps that firstly, after a key code structure diagram is generated, a function name, a variable name and auxiliary representation information are extracted from the key code structure diagram, code slices are combined and input into a pre-training semantic encoder for encoding, and feature tensors of semantic modals are generated; in addition, a heterogeneous adjacency matrix is constructed by using nodes of the key code structure diagram and edges with different attributes, GAT is input for coding, and a feature tensor of the diagram structure is generated. And distilling the semantic feature tensor through a multi-head distillation network to obtain a corresponding single-peak feature, and further extracting a long-distance dependency relationship of the code through BLSTM to obtain a final semantic auxiliary feature. The distribution distance between a graph structure feature space and a semantic auxiliary feature space is calculated by using a dynamic Sinkhorn algorithm, and the features of the optimized mode are further fused by using a global attention layer to ensure the coordination of the features in the feature space. According to the invention, the detection efficiency of the model and the accuracy of vulnerability detection are improved.

The invention discloses an automatic causal structure generation method based on semantic representation and logical reasoning of a large language model. The method comprises the following steps: acquiring an input text; performing semantic coding and clustering on the obtained input text by utilizing a large language model, and establishing a candidate causal variable set; causal relationship detection is carried out on the established candidate causal variable set based on anti-fact intervention and do-calculation; performing causal direction judgment, and generating a directed acyclic causal graph meeting logic consistency; and on the basis of the generated directed acyclic causal graph, natural language interpretation is generated by using a large language model, and logic consistency closed-loop verification is carried out. According to the method, automatic generation from the natural language to the causal structure is realized, the causal variable set is automatically extracted and constructed from the unstructured natural language text, the defects that variables need to be manually defined and modeling depends on field experts in the existing causal modeling process are avoided, and the labor cost and professional threshold of causal structure construction are remarkably reduced.

The invention discloses a recommendation method based on semantic enhancement and a heterogeneous hypergraph network. The recommendation method comprises the following steps that semantic information in an explicit feedback text is coded and serves as an auxiliary signal of a recommendation task; classifying the articles into predefined categories by using LLM, constructing article-category association, and mining a potential co-occurrence relationship of the articles; constructing a heterogeneous hypergraph network; spreading and aggregating hypergraph information; performing semantic alignment and model training; and performing recommendation calculation based on the final representation of the user and the representation of the article, and outputting a recommendation result. According to the method, through technical paths of semantic coding, hypergraph modeling, information spreading and alignment supervision, comment semantics of LLM coding are aligned to the recommendation space through GAE, and the problem of degradation of LLM representation in the recommendation space is effectively solved.

The invention discloses a language migration detection method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of obtaining a first language source code and a second language migration code, wherein the second language migration code is obtained by migrating the first language source code to a second language environment; analyzing the first language source code to obtain a first abstract syntax tree, and analyzing the second language migration code to obtain a second abstract syntax tree; respectively encoding each first node of the first abstract syntax tree and each second node of the second abstract syntax tree through a pre-trained semantic encoder to obtain a first semantic vector of each first node and a second semantic vector of each second node; and inputting the first semantic vector and the second semantic vector into a pre-trained logic detection model, and determining whether the logic of the first language source code and the logic of the second language migration code are consistent or not through the logic detection model, thereby realizing comprehensive detection of the business logic of the source code and the migration code.

The invention provides an Internet of Things equipment data acquisition method and system driven by an embedded template, and the method comprises the steps: S1, analyzing a protocol document of Internet of Things equipment, extracting key fields, and constructing a knowledge graph; performing semantic coding on the protocol text to generate a text vector, and generating a fusion feature vector in combination with graph embedding of the knowledge graph; s2, constructing a layered template library based on a protocol type, an equipment function type and an industry scene, adapting multiple protocols through a dynamic parameterization mechanism, and realizing automatic management of templates by adopting version control and test verification; s3, according to the generated fusion feature vector and a hierarchical template library, calculating and matching an optimal template through hybrid similarity, filling and generating a driver file in combination with explicit parameters and implicit parameters, and performing conflict detection and redundancy optimization; and S4, compiling the generated drive file into a cross-platform executable program, and monitoring the running state in real time. The driver development period is greatly shortened, and the compatibility is enhanced.

The invention discloses a spoken language understanding joint model method based on label attention and a window mechanism. The spoken language understanding joint model method is used for improving the effects of intention recognition and slot filling. The method comprises the following steps: firstly, performing semantic coding on a statement input by a user by adopting a self-attention mechanism and Bi-LSTM coding to generate basic semantic representation; then, dynamically adjusting attention distribution of each lexical element through a tag attention mechanism, extracting sentence-level intention and slot tag semantics, and constructing an overall semantic context, so as to form an intention tag attention module and a slot tag attention module; the intention module preliminarily predicts the intention of a statement by using a block-level sliding window, and the slot module preliminarily predicts slot position information by means of a slot classifier. And then, through a graph convolution layer, carrying out adaptive fusion on the preliminarily predicted intention and slot position information, and realizing information interaction between nodes to obtain an updated label embedding representation. And finally, decoding the embedded representation through a classifier module, and generating a final intention and slot position recognition result.

The invention provides a target-oriented video semantic communication system based on a visual model, and the system comprises a semantic extractor which is based on an SAM2 model and is used for processing an original video, generating a segmentation mask and extracting semantic information; the ViMama encoder is used for carrying out channel encoding on the output of the semantic extractor; the channel adaptation module is used for optimizing a coding sequence ViMama decoder based on the signal-to-noise ratio information of a physical channel, and is used for carrying out channel decoding to obtain a feature sequence; and the semantic reconstruction device is used for performing semantic reconstruction based on the feature sequence, recovering data and outputting a target video. According to the method, the problems of large redundant semantic information interference, insufficient deep semantic coding capability and poor communication robustness in a complex channel environment in a video are solved, efficient compression and robust transmission of video data are realized on the premise of ensuring semantic integrity, and the overall performance and adaptability of semantic communication are greatly improved.

The invention discloses a track user association method based on semantic perception and space-time coding, relates to the technical field of location service and user behavior analysis, and aims to solve the problems of excessive dependence of POI identifiers, limited space-time representation capability, insufficient cross-city generalization capability and the like of the existing TUL method in practical application. By introducing a pre-trained large language model to carry out POI category semantic coding, multi-frequency sine space-time coding and a double-flow transfer learning mechanism, the method can effectively improve the prediction precision and the model generalization ability.

The present invention belongs to the field of natural language processing and information retrieval technology. It provides a large-scale model-based multimodal bid duplication checking method and system, which performs structured parsing and multimodal feature extraction on input bids to generate feature representations of semantic blocks and non-text elements. It uses a dynamic context-aware large language model to perform deep semantic encoding on text blocks, combining hierarchical position encoding to preserve the logical relevance of long texts. It achieves efficient matching of massive semantic vectors through a hybrid retrieval architecture, and optimizes computing efficiency by combining a distributed computing framework with hardware acceleration instructions. Finally, it reconstructs structured features of non-text content such as tables and charts, achieving cross-modal semantic association analysis.

The invention discloses a similarity comparison-based large model supply chain automatic restoration method and device, and the method comprises the steps: firstly carrying out the semantic coding of an original vulnerability code through a pre-training model, and constructing a semantic and structure parallel dual-channel representation in combination with an abstract syntax tree and other program structures; cWE type intelligent classification is performed on vulnerabilities by using a locally deployed large language model subjected to LoRA fine tuning, and meanwhile, a zero sample semantic matching mechanism is introduced, so that the recognition capability of unknown vulnerability types is improved. And searching the closest historical case from the knowledge base through similarity vector comparison, and extracting a repair abstract to construct a model to generate a prompt. Patch codes and repair instructions are generated through a large model, automatic filing and knowledge base updating are supported, and the continuously-enhanced automatic repair capacity is achieved. The method can be widely applied to automatic vulnerability repair scenes of supply chain components such as large model plug-ins, code interfaces and dependent packages, and the safety, functionality and interpretability of code repair patches are greatly improved.

The invention discloses an aspect-level sentiment analysis optimization method based on multivariate external knowledge fusion, which relates to the technical field of sentiment analysis optimization, and comprises the following steps: constructing a multivariate external knowledge source comprising a Chinese sentiment dictionary, a domain knowledge graph and a user comment prior mode library; the sentiment module is used for providing vocabulary-level sentiment polarity, entity attribute relations and high-frequency evaluation semantic modes; semantic coding is performed on the input text and the specified aspect words to generate context semantic representation, and global semantic features and local position features are extracted in combination with aspect word position information; based on a semantic coding result, converting the multivariate external knowledge sources into structured knowledge representations, and dynamically adjusting contribution weights of various types of knowledge through a gating fusion mechanism to generate fused knowledge representations; performing dependency syntactic analysis on the input text, constructing an original syntactic structure, and calculating the correlation strength of each grammatical component and aspect words in combination with context semantic representation; and pruning the original syntactic structure according to the correlation intensity.

The invention provides a semantic communication method and system, electronic equipment and a computer readable storage medium, and relates to the field of communication, in particular to the field of semantic communication and artificial intelligence. According to the specific implementation scheme, the method comprises the steps of inputting information source data into a pre-trained semantic encoder for semantic encoding, obtaining information source semantic features of the information source data, mapping the information source semantic features to a target codebook, and generating an information source index vector; transmitting the information source index vector from the transmitting end to the receiving end through the communication channel, and obtaining a channel index vector; obtaining a channel semantic feature according to the target codebook and the channel index vector, inputting the channel semantic feature into a pre-trained semantic decoder for semantic decoding, and generating reconstruction data; wherein the target codebook is determined according to the signal quality of the communication channel and an initial codebook; the initial codebook is obtained through joint training with the semantic encoder and the semantic decoder.

The invention provides a voice processing model training method, a voice processing method, a voice processing device and voice processing equipment, and belongs to the technical field of computers. According to the method, a sample voice signal and a reference voice text are processed through a voice processing model in a model training process to obtain semantic embedding representation, paragraph embedding representation and phoneme embedding representation, so that complete decoupling of acoustic coding, semantic coding and paragraph coding is realized; compared with the prior art, the method eliminates the side language residue in the semantic coding process, improves the training efficiency of the model, carries out the model training through the comparison loss and the acoustic reconstruction loss, enhances the integrity of semantic coding and the reconstruction fidelity, and improves the voice processing effect of the voice processing model obtained through training.