95 results about "Semantic knowledge base" patented technology

The invention discloses a multi-modal index knowledge base and a construction method thereof. The construction method comprises the following steps: processing a heterogeneous document to obtain a semi-structured document; identifying a title hierarchical relationship of the document to construct a document logic structure; carrying out minimum chapter blocking on the text of the semi-structured document to obtain logic blocks; performing semantic segmentation on each logic block to obtain text blocks; the method comprises the following steps: constructing text block nodes by meta-information of text blocks, constructing non-text block nodes by meta-information of non-text elements, extracting document nodes, chapter nodes and chapter-chapter inclusion relationships according to a document logic structure, respectively extracting semantic information from the text blocks and the non-text elements, and storing the semantic information in a database; recording the corresponding relationship between the text block nodes and the semantic information and between the non-text block nodes and the semantic information; constructing a knowledge graph based on each node and relationship and storing the knowledge graph into a graph database; and constructing semantic knowledge based on the semantic information and storing the semantic knowledge into a vector database. According to the scheme, lossless retention of multi-modal information and structured organization of document logic are realized, and efficient indexing and accurate recall are facilitated.

The invention relates to a multi-class archive knowledge question and answer agent based on a large language model, and belongs to the technical field of artificial intelligence and archive information management. The intelligent agent comprises a data preparation module, a semantic knowledge base construction module, a perception and analysis module, a decision and matching module, an execution and retrieval module, a cognition and reasoning module and an interaction and generation module. According to the method, the complex query intention of the user can be accurately understood, automatic association and semantic reasoning across archive categories are achieved, and the semantic splitting problem of a traditional retrieval mode in cross-category and multi-level query is effectively solved.

The invention provides an attack link restoration method and system based on a large language model and a traditional AI model, and effectively solves the problem that attack link restoration is incomplete and inaccurate when a current attack link restoration scheme faces complex factors such as network address translation. The method comprises the following steps: acquiring an attack semantic knowledge base containing an attack context knowledge matrix, wherein the knowledge base is generated by processing an attack framework, a security log and a traceability report by a generative large model; obtaining an asset access relation graph generated by analyzing the metadata of the target network infrastructure by the large model and reasoning in combination with an attack semantic knowledge base; regularly acquiring security alarm logs in a first time window and scoring, and acquiring context logs if the security alarm logs exceed a threshold value; based on a time sequence diagram attention network model, determining the confidence degree that edges in an asset access relation graph corresponding to logs containing access pairs in the alarm logs and the context logs belong to attack links; and performing sub-graph extraction in the atlas to obtain candidate sub-graphs, and then determining a target attack link.

The invention discloses a historical building digital modeling method based on structural semantic feature extraction, and relates to the technical field of cultural heritage digitization, and the method comprises the steps: obtaining laser point cloud data, panoramic image data, infrared thermal imaging data and text data of a building, carrying out the fusion preprocessing of the obtained data, and generating an RGB-D point cloud model; based on the generated RGB-D point cloud model, a three-level feature extraction model is adopted to extract structural semantic features of the building, the extracted structural semantic features are stored, and a structural semantic knowledge base is generated; the method comprises the steps of constructing a knowledge graph, automatically matching a component template according to the knowledge graph, generating a BIM model, carrying out model optimization processing on the generated BIM model, and obtaining an interactive WebGL lightweight model and a structured attribute table. According to the method, automatic semantic modeling of historical buildings is realized, manual intervention is reduced, modeling is more accurate, and the efficiency is higher.

The invention provides a channel state information feedback enhancement method and system based on bidirectional channel correlation, and the method is executed at a base station end, and comprises the steps: receiving a downlink channel state information semantic vector which is coded, compressed and quantized by a user end through a deep joint source channel; carrying out inverse quantization on the semantic vector to obtain an intermediate semantic vector; based on the intermediate semantic vector, retrieving a related historical uplink semantic vector from an uplink channel semantic knowledge base; performing fusion enhancement on the intermediate semantic vector and the retrieval result through an attention mechanism to generate an enhanced semantic vector; inputting the enhanced semantic vector into a decoder, and outputting a reconstructed downlink channel state information matrix; wherein the encoder, the enhancement module and the decoder perform end-to-end joint training optimization by minimizing a reconstruction error. According to the method, the semantics is enhanced at the receiving end by utilizing the correlation of the uplink and downlink channels, the feedback precision and the system robustness are remarkably improved, and the method is suitable for a frequency division duplex system.

The application discloses a robot cognitive development method based on ontology semantics, and comprises the following steps: constructing a robot article identification professional knowledge base based on attribute function and ontology information representation of article definition; information determination based on attribute discrimination and semantic search; and robot cognitive development based on attribute information addition. The application simulates the process of human memory, learning and cognition of articles based on an ontology semantic knowledge base, and through machine learning and sensor attribute information, the robot can actively cognize, learn, expand and accumulate learned knowledge and experience according to information data; the robot can continuously develop its cognitive ability through learning, automatically construct a robot article identification professional knowledge base of unknown articles, and based on a semantic structure of triplets, share knowledge and exchange operation logic between man and machine, so that the cognitive level of the robot is improved and the operation experience of an operator is improved.

The invention discloses an intelligent data question and answer method and system based on index semantic enhancement, and relates to the technical field of intelligent data question and answer. The method comprises the following steps: acquiring a data analysis demand in a natural language form; the method comprises the following steps: performing information extraction on a data analysis demand by utilizing an index semantic enhanced large language model, generating a query statement according to the extracted information, recalling and rearranging most relevant indexes and elements in an index semantic knowledge base by utilizing a knowledge retrieval enhancement layer according to the data analysis demand and a historical session on the basis of mixed retrieval, and generating a query statement according to the query statement. Generating a prompt template according to a retrieval result of the index semantic injection layer by utilizing the index semantic injection layer, and performing semantic understanding reasoning according to the prompt template to obtain corresponding information; and checking compliance according to the query statement, and returning a query result. The method aims at achieving efficient mapping, dynamic modeling, intelligent SQL generation and optimization, authority safety management and control and multi-round intelligent interaction of natural languages and enterprise-level index assets.

The invention discloses a single photon target recognition method and device based on a semantic knowledge base, and belongs to the technical field of data recognition. The method comprises the following steps: firstly, training a neural network model adopting a probability step variational auto-encoder structure, mapping a single photon time histogram into a mean vector and a standard deviation vector, and constructing an initial semantic knowledge base according to the mean vector and the standard deviation vector; during recognition, semantic features of a to-be-detected target are extracted, and whether the semantic features of the target are known relative to the semantic knowledge base or not is judged through unknown detection. If yes, semantic matching is carried out to output categories; and if the information is unknown, dynamically adding the characteristics of the information into the knowledge base to realize online learning and self-updating of the system. According to the method, the robustness of noise signals is enhanced through probabilistic modeling, open world recognition is realized through unknown detection, and the problems that a traditional method misjudges an unknown target and is difficult to adapt to a new environment are solved.

The invention provides a semantic knowledge base recognition method based on heuristic features, which belongs to the technical field of intelligent communication, and comprises the following steps: a base station has n versions of semantic knowledge bases, the semantic knowledge bases comprise corresponding receiving end knowledge bases and sending end knowledge bases, the base station respectively calculates a feature vector set corresponding to the receiving end knowledge base and a feature vector set corresponding to the sending end knowledge base, and when a user needs to perform downlink semantic communication with the base station, the feature vector of the receiving end knowledge base is calculated and sent to the base station in a traditional communication mode; and the base station calculates Euclidean distances between the received feature vectors and the feature vectors, selects a receiving end knowledge base corresponding to the feature vector with the minimum Euclidean distance, and matches a sending end knowledge base corresponding to the receiving end knowledge base with a user receiving end knowledge base to complete semantic knowledge base recognition. According to the invention, accurate identification and matching of the semantic knowledge base can be realized.

The invention provides an eBPF program automatic generation method, system and device based on retrieval enhancement and thinking chain reasoning, and the method comprises the steps: constructing an eBPF semantic knowledge base, and extracting and structuring a plurality of program examples with semantic annotations; after a natural language task description input by a user is received, the natural language task description is coded into a semantic vector, and accurate retrieval of related contexts is achieved in combination with semantic indexes; based on a retrieval result, constructing a structured prompt, and guiding a language model to gradually generate an eBPF program according to stages; an eBPF verifier is used for carrying out legality check on the generated program, and behavior testing is carried out in combination with task input; when structural errors or semantic deviations are found, the model is guided to be automatically repaired based on error information. The method can be operated on a multi-language model platform, supports the output of two styles of BCC and BPFtrace, and has the advantages of controllable structure, accurate semantics, stable deployment and the like. Experimental results show that the automatic generation efficiency and accuracy of the eBPF program can be remarkably improved.

The invention provides an entity pair guided scientific and technical literature document level relation extraction method and system, and the method comprises the steps: carrying out the entity recognition of an input scientific and technical literature document, and obtaining an entity set in the scientific and technical literature document; based on an entity pair pre-screening mechanism of multiple sampling and similarity verification, screening out a candidate entity pair set from all possible entity pairs of the entity set; then generating enhanced relation description fusing corresponding entity type information and relation semantics between the entity pairs; based on a pre-constructed relation semantic knowledge base, a double-layer filtering mechanism is adopted, and a corresponding fine screening candidate relation set is retrieved for each enhanced relation description; and guiding the large language model to perform triple fact judgment by using detailed semantic description of the candidate relationship to obtain an output result. According to the method, high-precision relation extraction is ensured, and meanwhile, the calculation overhead of long text processing is remarkably reduced, so that scientific and technical literature document-level relation extraction is more accurate and efficient.

The invention relates to the technical field of computer vision and geographic information, and particularly discloses a cross-view geographic positioning acceleration method based on semantic description, which comprises the following steps of: performing instruction fine tuning on an input query image and a database image by adopting a visual language model to generate natural language description; coding the natural language description into a low-dimensional semantic vector by utilizing a word embedding model; constructing a semantic keyword association graph based on a graph embedding technology, and fusing a general semantic knowledge base and a geographic domain ontology to construct a surface feature special semantic tree; screening candidate subsets according to a preset ground feature priority and a saliency detection result of the query image; extracting global features and local key point descriptors of the images in the candidate subsets by adopting a lightweight model; constructing a visual similarity calculation model based on the state space model, and modeling a feature sequence dependency relationship; and fusing the semantic matching score and the visual similarity, outputting a final matching result by adopting a weighted sorting strategy, and cooperatively accelerating according to the matching result in combination with a lightweight model.

This disclosure relates to the field of data governance technology, and provides a method, system, apparatus, medium, and device for constructing data indicator services. The method includes: acquiring data source information and extracting indicator metadata and underlying basic data from it; inputting the indicator metadata into an indicator governance framework and the underlying basic data into an indicator calculation framework; performing semantic transformation on the indicator metadata in the indicator governance framework to obtain an indicator semantic knowledge base and generate indicator definition information; establishing a bidirectional communication channel between indicator governance and indicator calculation, and sending the indicator definition information to the indicator calculation framework through this channel; receiving indicator query requests; performing indicator calculations in the indicator calculation framework based on the request and the indicator definition information, combined with the underlying basic data, to generate indicator calculation results; outputting the calculation results to a user terminal and feeding back the calculation results to the indicator governance framework through the bidirectional channel. This embodiment improves the consistency and response efficiency of indicator services.

A semantic feature extraction method and apparatus, a device, and a communication system. The method comprises: on the basis of a local available resource, determining to perform semantic feature extraction locally or in a cloud (S202); if it is determined to perform semantic feature extraction locally, extracting a semantic feature on the basis of a local semantic knowledge base (S204); and if it is determined to perform semantic feature extraction in the cloud, sending instruction information to a server, the instruction information being used for instructing the server to extract the semantic feature on the basis of a public semantic knowledge base (S206).

The invention discloses electronic whiteboard equipment with AI image generation and interactive drawing functions, and relates to the technical field of electronic interactive equipment. The equipment comprises an input module, a content identification module, an AI generation module, a display control module, a processor and a storage module, and a communication module can be additionally arranged to realize data synchronization and knowledge base updating. After the input module collects user sketch data, the content recognition module recognizes sketch semantics through a built-in sketch semantic knowledge base and a dynamic matching algorithm, the AI generation module calls a pre-training model based on a recognition result to generate a standardized high-quality image, and finally the display control module writes the image back to a whiteboard. And a complete interactive closed loop of hand-drawing input, semantic recognition, AI optimization and write-back display is formed. The problems that a traditional electronic whiteboard is weak in drawing intellectualization, low in creation efficiency and the like are solved, sketches can be automatically beautified, professional symbols can be accurately recognized, and the multi-scene requirements of education, commerce, engineering and the like are met.

The invention discloses an agricultural machinery label identification method based on an image, and relates to the technical field of label identification, and the method comprises the steps: obtaining an original image of an agricultural machinery label, carrying out the image enhancement preprocessing of the original image, inputting the enhanced image into a text detection network based on adaptive Bezier curve regression, and carrying out the recognition of the agricultural machinery label. And obtaining a preliminary text recognition result, performing verification, error correction and formatting conversion, generating a key-value pair data packet, and uploading the key-value pair data packet to a remote management platform. According to the method, illumination unevenness and background interference are inhibited through image enhancement preprocessing, the low-contrast character edge definition is improved, a character detection network of adaptive Bezier curve regression is adopted, a deformed text area is accurately fitted, robust detection of the agricultural machinery sign under the complex background is achieved, and the method is suitable for popularization and application. According to the method, the Bessel feature alignment and lightweight attention decoding mechanism are combined, the processing efficiency is improved while the recognition precision is ensured, then verification and error correction are performed by using a structured rule and a semantic knowledge base, the accuracy of text recognition is improved, and data are output.

The present disclosure provides a semantic communication method and apparatus, and a storage medium. In the present disclosure, a first communication device acquires first information from a second communication device, wherein the first information comprises parameter information of a first semantic knowledge base, so that matching of the parameter information of the first semantic knowledge base can be achieved between the first communication device and the second communication device, thereby improving semantic communication performance.

The invention provides a lightweight anaphora ambiguity resolution multi-task learning method, and relates to the technical field of intelligent language processing of a power system, and the method comprises the steps: S1, collecting power production command related documents to construct a lightweight power semantic knowledge base; s2, on the basis of the lightweight electric power semantic knowledge base, constructing an ultra-lightweight semantic analysis model through double-layer knowledge distillation; s3, performing lightweight deployment on the ultra-lightweight semantic analysis model based on an INT8 quantification technology to obtain a quantification model capable of running on edge equipment; s4, inputting the electric power semantic analysis task into a quantitative model obtained by lightweight deployment by adopting an end-side collaborative reasoning strategy, performing complexity evaluation and intelligent shunting processing, and outputting a semantic analysis result with high confidence; according to the method, high-precision semantic understanding under the condition of extremely low computing resources can be realized, and a practical and reliable intelligent language analysis capability is provided for a power production command system.

The invention relates to a semantic feature extraction method and device, equipment and a communication system. The method comprises the steps of determining to perform semantic feature extraction locally or in a cloud according to local available resources; if it is determined that semantic feature extraction is performed locally, semantic features are extracted based on a local semantic knowledge base; if it is determined that semantic feature extraction is performed at the cloud, sending indication information to a server; the indication information is used for indicating the server to extract semantic features based on the public semantic knowledge base. According to the method, the semantic feature extraction mode is determined according to the local available resources, and the sending end can be assisted to complete semantic feature extraction in an end-cloud cooperation mode, so that the semantic communication system can transmit information more effectively, and the quality and efficiency of the whole semantic communication process are improved.

This invention relates to the field of bridge structural safety inspection technology, and in particular to a bridge damage assessment method, system, and medium based on a visual segmentation model. The method includes: acquiring prior structural information and post-damage images of the bridge to be inspected; matching the image to be inspected generated based on the post-damage images with the prior structural information and a preset damage semantic knowledge base to generate multimodal prompts; inputting the fused multimodal prompts and the image to be inspected into a visual segmentation model with input parameters frozen, and adaptively iterating to obtain pixel-level segmentation masks for each damage candidate region; superimposing each pixel-level segmentation mask onto the image to be inspected, and inputting it along with the damage analysis prompt template into a visual language model to generate a structured damage assessment report. This invention utilizes the general segmentation capability of the visual segmentation model to achieve rapid and accurate pixel-level segmentation and recognition of sudden bridge damage, and automatically generates a structured damage assessment report.

The invention provides an intelligent SQL question and answer mode access method. The method comprises the steps that S1, a basic environment and configuration are initialized; s2, inputting an SQL question and answer pair and constructing an original semantic knowledge base; s3, semantic analysis and feature preprocessing; s4, constructing a class ER structure storage model; s5, multi-dimensional model training is carried out; and S6, performing intelligent access execution and closed-loop updating. According to the method, full automation from natural language to SQL access is realized through an integrated process of basic configuration construction, question and answer pair input, semantic preprocessing, structured storage, multi-dimensional training, intelligent access and closed-loop updating.

The application provides an information synchronization method and device, equipment and a non-transient readable storage medium. The information synchronization method comprises the following steps: sending a synchronization request for a semantic knowledge base to a first device; the first device is a base station or an edge side device or a second terminal; the second terminal comprises a peer terminal in communication with the first terminal or a neighboring terminal of the first terminal; receiving a synchronization response sent by the first device; and synchronizing the semantic knowledge base according to the synchronization response. The scheme can support intelligent and flexible semantic knowledge base synchronization, thereby improving the efficiency and accuracy of coding and decoding in the semantic transmission process, and can also avoid the high communication overhead and the influence on system communication efficiency caused by frequent signaling interaction to a certain extent, and solves the problem that the semantic knowledge base synchronization cannot be supported in the prior art.

This invention discloses a method and apparatus for detecting harmful Chinese memes that combines relative intent reasoning and knowledge enhancement. It generates an expanded set of meme semantic keywords by training memes, and for each keyword, it searches a set of background knowledge documents in a Chinese harmful semantic knowledge base. A re-ranking model constructs prompt words for each candidate document in the background knowledge document set and its corresponding query. Based on the meme content of the trained memes, it optimizes and updates a multimodal detection model to obtain a classification multimodal detection model. The meme to be detected is input into the classification multimodal detection model to obtain the corresponding label and reason, where the label is either harmful or harmless. This invention integrates an external cultural knowledge base and possesses multi-faceted dialectical reasoning capabilities for the detection and interpretation of harmful Chinese memes, thereby improving the accuracy, robustness, and interpretability of the detection.

The invention relates to the technical field of data processing, and discloses a heterogeneous data semantic alignment method and system, electronic equipment and a storage medium, and the method comprises the steps: collecting Web front-end heterogeneous data, carrying out the type labeling according to a preset dimension, constructing a mapping relation between a data type and an extraction template, generating an extraction instruction corresponding to the data type, and carrying out the semantic alignment of the Web front-end heterogeneous data. Inputting the Web front-end heterogeneous data subjected to type labeling and a corresponding extraction instruction into a large language model, and outputting an extraction result; constructing a dynamic semantic knowledge base for supporting semantic alignment, performing field normalization, cross-data association and semantic ambiguity resolution processing on the extraction result through a large language model based on the dynamic semantic knowledge base, and outputting a semantic alignment result; and performing rule verification on a semantic alignment result, optimizing the large language model through a fine adjustment mode based on a verification result, and updating the dynamic semantic knowledge base at the same time. According to the invention, the adaptability and reliability of heterogeneous data processing can be improved.

The invention discloses a home-based care health assessment dynamic service orchestration method and system based on a large language model, and the method comprises the steps: (1) receiving a natural language health assessment request inputted by a user, and generating a structured task description tetrad through a large language model; (2) the task description tetrad is combined with a Prompt template to be input into a large language model, and an abstract evaluation plan is generated; (3) finding out a candidate service list meeting conditions in the service semantic knowledge base according to the service type required by each step in the abstract evaluation plan, and dynamically binding each step to an optimal main agent service provider and an optimal standby agent service provider; (4) deeply participating in an agent cooperation mechanism through a large language model; and (5) converting the bound task assembly line into a standard BPMN workflow, and driving an intelligent agent to orderly execute services through a workflow engine. According to the invention, the big language model is deeply integrated into the whole process of agent collaboration, and real dynamic intelligent service orchestration is realized.

This specification provides a method, computing system, and storage medium for generating a user interface. In the method, the computing system receives an interface generation request from a client. This request includes target text described by an operator in natural language. An intelligent agent group then performs an interface generation task based on the target text and a semantic knowledge base to obtain at least one user interface. The semantic knowledge base includes predefined information for multiple interface elements, each comprising multiple interface components and multiple visual attributes. The predefined information for each interface element characterizes its style and usage description.

The invention provides a semantic knowledge base adaptation method based on an intermediate layer, and relates to the technical field of intelligent communication, and the method comprises the following steps: a base station determines unmatched users and constructs an intermediate layer, and enters a step S2 to train the intermediate layer at a base station end; for each unmatched user, the base station uses the transmitting end knowledge base to encode the training data and transmits the training data through the constructed channel to obtain a first receiving signal, and after the first receiving signal is processed by the intermediate layer, the receiving end knowledge base of the unmatched user stored in the base station is used to decode the first receiving signal to obtain recovery data; taking the cross entropy of the training data and the recovery data as a loss function, and updating the parameters of the middle layer; and after training is completed, the base station sends the parameters of the trained intermediate layers to the corresponding unmatched users, and the unmatched users construct and start the intermediate layers according to the received parameters. The semantic communication performance under the condition that the knowledge base is incomplete can be effectively improved.

The invention provides a power equipment-oriented standard semantic knowledge base retrieval method, which comprises the following steps of: acquiring power equipment standard data, analyzing text information of the power equipment standard data, establishing semantic association among standard terms, equipment attributes and key indexes, and forming an equipment-standard-index knowledge graph; standard terms are calculated through a semantic vectorization technology, and matching calculation of the standard and equipment suitability is carried out based on a vector retrieval method; and according to the standard historical data and the deep learning model, carrying out evolution analysis on the standard terms, and providing suitability recommendation of the equipment standard. By establishing the semantic association between the equipment and the standard terms, efficient and accurate standard suitability recommendation and evolution analysis are realized, and efficient and accurate equipment standard suitability recommendation is provided through a semantic technology and a deep learning model.

The invention relates to the technical field of database integration, and particularly discloses a database integration method based on a standard semantic knowledge base, which comprises the following steps of: collecting data sets disclosed in different fields, randomly extracting batch data sets in a single field and inputting the batch data sets into a professional vocabulary acquisition model; determining the vocabularies of which the word frequencies accord with a preset threshold value as professional vocabularies to generate a professional vocabulary list, performing word segmentation processing on the data set of the single field based on a preset word segmentation device model to obtain a plurality of segmented vocabularies, and generating a graph neural network according to the segmented vocabularies and the data set of the field, and generating a word vector corresponding to each vocabulary according to the conduction relationship of the graph neural network, and taking the word vectors and the data set as a database corresponding to the field. According to the method, the corresponding standard semantic database is constructed according to the fields, the databases corresponding to the different fields are obtained, manpower does not need to be relied on, the database with high specialty and comprehensive content can be obtained, the precision of standard semantics is improved, and the cost is reduced.

The application relates to the technical field of natural language processing, in particular to a large model semantic representation generation method based on scene knowledge fusion, which comprises the following steps: inputting professional texts of a specified technical category into a general semantic representation framework, extracting representation of middle-layer output of semantic coding as scene knowledge representation quantity, and constructing a scene semantic knowledge base supporting semantic retrieval; setting a scene knowledge fusion unit in the middle layer of semantic coding, keeping inherent architecture and parameters of the original framework unchanged, and associating the fusion unit with the knowledge base; inputting a text to be processed into the framework, retrieving semantic related scene knowledge representation quantity from the knowledge base through the fusion unit based on basic semantic representation extracted from the middle layer of semantic coding, fusing the basic semantic representation and the scene knowledge representation quantity, and generating optimized semantic representation; and the application realizes dynamic injection and deep fusion of field knowledge without changing original parameters of the general framework.