96 results about "Semantic mining" patented technology

The invention relates to a ship user behavior self-learning recommendation system based on a large model, and relates to the technical field of ship informatization. According to the system, through collection and fusion of multi-source heterogeneous ship user behavior data, a large-scale pre-training language model (large model) is utilized to carry out deep understanding and semantic mining on massive ship field text information and user behavior sequences, and a ship field knowledge graph or semantic vector space is constructed. The large model can identify and predict potential demands, behavior patterns and preference changes of ship users, and generates highly personalized, accurate and prospective ship service, product, route or information recommendations in combination with real-time operation data and external environment factors. Besides, a user feedback self-learning mechanism is introduced into the system, recommendation strategies and model parameters are continuously optimized according to interaction behaviors and explicit evaluation of the users in modes of reinforcement learning or continuous learning and the like, and intelligent iteration of the system and continuous improvement of the recommendation effect are achieved. According to the method, the challenges of a traditional recommendation system in the aspects of data complexity, semantic gaps and dynamic demand adaptability in the ship field are effectively solved, and the ship operation efficiency and the user satisfaction degree are remarkably improved.

The invention discloses an enterprise type identification method fusing multi-source data. The method comprises the following steps: acquiring map POI point of interest information, enterprise registration information and enterprise business brief introduction information; matching the POI name with the enterprise registration name to obtain matched enterprise data; cleaning the brief introduction information of the enterprise business and the matched enterprise data to obtain cleaned data; performing semantic information extraction on brief introduction information in the cleaned data to obtain extracted data; fusing the enterprise data in the cleaned data with the extracted data to form a fused data set; and clustering the fused data set to obtain theme distribution of each enterprise. According to the method, semantic mining, LDA topic modeling, keyword recognition and regional clustering analysis can be combined, so that accurate subdivision of enterprise types and intelligent recognition of regional dominant industries are realized, and regional industry strategy making and industrial park planning layout are supported.

The invention relates to a multi-mode large model and light-weight small model collaborative road surface ice condensation state prediction method, and belongs to the field of road traffic safety monitoring and prediction. The method aims at solving the problem that real-time early warning and accurate prevention and control are difficult in the prior art. According to the invention, a multi-modal data coding system is constructed, road surface monitoring images, meteorological time sequence data and historical ice condensation text cases are integrated, and feature fusion is realized by adopting visual-physical feature joint coding, meteorological time sequence feature enhancement and text semantic mining; a pseudo label is generated through large model zero sample reasoning, and a lightweight small model is trained through cross-modal knowledge distillation; and finally, on the basis of a dynamic trigger type double-model reasoning framework, calling a cloud large model for fine judgment when the small model is low in confidence coefficient or high in scene complexity, and outputting the icing starting moment and thickness through confidence coefficient weighted fusion. According to the method, the prediction accuracy and real-time performance are improved, the model generalization ability is enhanced, and reliable support is provided for road traffic control in winter.

The invention relates to the technical field of form construction, in particular to a form construction method and system based on dragging operation and a storage medium. The method comprises the following steps: identifying a target form dragged by a mouse of a user, and performing form content structure deep analysis to obtain a form information structure identification result; obtaining a user historical form operation data set to perform operation behavior semantic mining, and performing historical page layout behavior clustering analysis on a form information structure identification result to obtain form layout preference features; performing layout demand prediction according to the form layout preference features, and performing feasibility evaluation to obtain an accurate layout demand prediction result; and identifying an affiliation page to which the user drags the target form, performing spatial layout constraint analysis, and performing available space size evaluation, thereby obtaining the available space of the current page. According to the method, efficient and convenient form self-adaptive construction is realized, the user development efficiency is improved, and multi-terminal operation is adapted.

The invention provides a deep-buried tunnel dynamic disturbance field three-dimensional positioning method based on multi-source heterogeneous sensing, and relates to the technical field of data analysis. The method comprises the following steps: firstly, obtaining a plurality of disturbance monitoring data, and determining three-dimensional coordinate data of a sensor; secondly, performing multi-level semantic mining on frequency domain information of the disturbance monitoring data to form a target disturbance semantic vector; then, fusing semantic information corresponding to the three-dimensional coordinate data of the sensor and semantic information corresponding to the disturbance start / end time data into a target disturbance semantic vector to form a target monitoring semantic vector; further, semantic information association fusion is carried out on the multiple target monitoring semantic vectors, and a global monitoring semantic vector is formed; and finally, performing positioning output based on the global monitoring semantic vector to obtain three-dimensional coordinate data of the disturbance field. On the basis of the content, the problem that in the prior art, the precision of three-dimensional positioning of the dynamic disturbance field of the deep-buried tunnel is relatively low can be solved.

The invention provides an environment-friendly public toilet equipment state monitoring method, device and equipment, and relates to the technical field of equipment state monitoring. The method comprises the following steps: firstly, acquiring multi-dimensional state time sequence data of target environment-friendly public toilet equipment; secondly, performing cross-dimensional state time sequence semantic mining on the multi-dimensional state time sequence data to form multi-dimensional state time sequence features corresponding to the multi-dimensional state time sequence data; and then, network state prediction is carried out based on the multi-dimensional state time sequence characteristics, and a target network state prediction result is obtained. On the basis of the content, the problem that in the prior art, the reliability of equipment state monitoring is relatively low can be solved.

The invention discloses an industrial Internet of Things production line safety analysis method, system and device and a medium, and relates to the technical field of industrial Internet of Things, and the method comprises the steps: obtaining the operation environment time sequence data of a target production line and the corresponding fault record data; through a semantic mining model included in a target production line data analysis network, respectively performing semantic coding on the operation environment time sequence data and the fault record data to obtain corresponding operation environment features and fault features; performing cross-domain association semantic coding on the operating environment features and the fault features through the semantic analysis model to obtain corresponding environment fault association features; and performing safety situation assessment on the target production line according to the environment fault correlation features through a safety assessment model to obtain a corresponding operation safety assessment result. The method has the effect of improving the accuracy of safety analysis of the production line.

The invention provides a distribution network equipment operation state evaluation method and system based on data analysis, and relates to the technical field of data analysis. The method comprises the following steps: firstly, acquiring state data of a plurality of pieces of distribution network equipment; secondly, for each piece of distribution network equipment state data, extracting time domain state characteristics of the distribution network equipment state data, and converting the distribution network equipment state data into equipment state frequency domain data; then, based on semantic information of the time domain state features, semantic mining is carried out on the semantic information of the equipment state frequency domain data, and a first state semantic vector is formed; further, fusing the first state semantic vector corresponding to each piece of distribution network equipment state data to form a second state semantic vector; and finally, performing state evaluation based on the second state semantic vector to obtain a running state evaluation result. Based on the above content, the problem that the reliability of the operation state evaluation of the distribution network equipment is relatively low in the prior art can be improved.

The invention provides a risk identification method and system based on video data and mobile phone signaling analysis, and relates to the technical field of data analysis. The method comprises the following steps: firstly, acquiring monitoring video data and mobile phone signaling data formed in a target time interval in a target area, and determining motion trail data of each mobile phone user based on the mobile phone signaling data; secondly, performing video semantic mining on the monitoring video data to form a video semantic vector; secondly, track semantic mining is carried out on the motion track data, track semantic vectors are formed, and in the track semantic mining process, different track complexities have different mining modes; further, aggregating the video semantic vector and the track semantic vector to form a video track aggregation vector; and finally, performing risk identification based on the video trajectory aggregation vector to obtain a risk identification result. Based on the method, the problem that the reliability of risk identification is relatively low in the prior art can be improved.

The application relates to the technical field of artificial intelligence, in particular to a retrieval method and device based on multiple agents, equipment and a medium. Applied to a financial scene, the application realizes the intellectualization and dynamicization of the retrieval process through a multiple-agent cooperative working mechanism. The retrieval core elements are accurately extracted and a dynamic cognitive graph is updated by analyzing the agents, deep semantic mining and correlation expansion are carried out based on the cognitive seeds of semantic agents, the dependence on keywords in traditional retrieval is effectively broken, and the breadth and depth of semantic understanding are improved. The query statement is optimized by combining the extended semantics and the dynamic cognitive graph of the context agent, so that the query is more in line with the real intention and context of the user. The retrieval agent efficiently retrieves the candidate path in the updated dynamic cognitive graph, the recommendation agent filters the optimal result through cognitive consistency scoring, and the accuracy, relevance and logical coherence of the retrieval result are ensured, and the accuracy of the complex information retrieval task is significantly improved.

The embodiment of the invention discloses a log analysis method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence. One specific implementation mode of the method comprises the steps that a historical log text and domain knowledge data associated with the historical log text are acquired, the domain knowledge data is used for indicating business logic, fault association rules and system operation specifications corresponding to the historical log text; semantic analysis is conducted on the historical log texts and the domain knowledge data, semantic vector distribution is constructed, and the semantic vector distribution is used for indicating potential correlation between the historical log texts; based on semantic vector distribution, performing multi-dimensional association retrieval on the to-be-analyzed log to generate a structured cognitive guidance package; and based on the structured cognitive guide package and a preset analysis model, analyzing the to-be-analyzed log to generate a log analysis result. Deep semantic mining of the log is realized, system behaviors, business logics and causal relationships implied in the log are effectively captured, and the log analysis precision is improved.

The invention provides a control system and method for the working condition of a clean room, and relates to the technical field of data analysis. The method comprises the following steps: firstly, constructing a target adjacent matrix; secondly, performing semantic mining on the target environment data based on the target adjacency matrix to form a target environment semantic vector; performing semantic mining on the current environment data based on the target adjacency matrix to form a current environment semantic vector; further, semantic mining is carried out on the historical environment data based on the target adjacency matrix to form a historical environment semantic vector; further, fusing the historical environment semantic vector into the current environment semantic vector to obtain an enhanced environment semantic vector; and finally, determining target working condition data based on the target environment semantic vector, the enhanced environment semantic vector and the semantic vector corresponding to the current working condition data of each environment control device. Based on the method, the problem that in the prior art, the reliability of working condition control of the clean room is relatively low can be solved.

This application relates to the field of smart park management technology, and discloses a method for automatic triggering and closed-loop management of park tasks based on key semantic mining. It collects, cleans, and sorts park meeting audio and business text in real time to form a key data stream. Key semantics are extracted through lexical and syntactic analysis and converted into business feature tags through feature mapping. These tags are input into a pre-set task model for rule collision and constraint calculation to generate execution tasks. After trigger addressing and packetization, task distribution instructions are generated and delivered to vertical domain digital human agents via a collaborative distribution network to complete multi-agent collaborative execution and produce execution data. This solves the technical problem of lagging business perception and disconnected task execution in traditional park management.

The application discloses a kind of achievement transformation report intelligent generation method and system, comprising: constructing achievement transformation corpus;Based on corpus, use five-element prompt word framework to extract entity and relationship, check, implicit completion and weight update are carried out in combination with achievement transformation value evaluation model, and optimized knowledge graph is constructed;Knowledge cluster is divided to graph, and dual-mode index network of paragraph vector index and structured knowledge index is constructed;After receiving user input, core entity set is obtained by semantic coding and entity recognition;With the set as center, structured knowledge enhancement retrieval is executed, and evidence fragment is screened by fusing semantic similarity and knowledge correlation degree score;Finally, sort constructs input context, calls natural language generation model to generate structured report, simultaneously extracts reasoning path and is associated with evidence source and outputs.The application solves the problems of poor precision in manual writing, poor adaptation of general model and insufficient semantic mining, and improves the scientificity, pertinence and traceability of the report.

The application discloses a version knowledge graph reasoning method and system based on large language model enhancement, relates to the technical field of dynamic knowledge graph, and comprises the following steps: adopting a semantic drift detection and compensation mechanism, comparing the context coding differences of the same entities in different versions in an initial knowledge graph, identifying drift, dynamically adjusting entity embedding vectors, and outputting a compensation update graph; adopting a multi-hop reasoning algorithm enhanced by an LLM, performing multi-hop reasoning on the compensation update graph, performing symbolic reasoning, vector reasoning and context reasoning in parallel in each hop, and obtaining entity relationship reasoning results through dynamic weight fusion; and superimposing the entity relationship reasoning results on the compensation update graph through a cloud collaborative node, adding entity edges and automatically maintaining version history logs, and obtaining a reasoning fusion version knowledge graph. Through the multi-hop reasoning algorithm enhanced by the large language model, the deep semantic mining capability and reasoning accuracy of the cross-version entity relationship are effectively improved.

The invention relates to the technical field of medical information, and discloses a clinical nursing data management method and system for clinical big data. The method comprises the following steps: acquiring structured physiological signs and unstructured nursing text data; extracting weak semantic signals through a deep semantic mining model and converting the weak semantic signals into high-dimensional feature vectors; mapping the features to a medical knowledge graph, and constructing a recessive nursing risk dynamic deduction network; predicting a target risk event probability by using a graph neural network and Bayesian reasoning; and generating graded early warning and intervention suggestions based on the probability distribution. The system comprises a data acquisition module, a deep semantic extraction engine, a risk deduction network construction module, a prediction analysis engine and an early warning intervention generation module. According to the method, the NLP and the knowledge graph are fused to realize prospective identification and active intervention of the hidden risk, and the early warning timeliness and the nursing decision accuracy are improved.

This invention proposes a collaborative evolutionary classification method based on cross-view structural attribute dual-domain semantic mining, belonging to the field of multi-view semi-supervised classification. This invention acquires multi-view features from training samples, constructs K-nearest neighbor graphs for each view, and adaptively prunes based on the shared support relationships of the graph structure to obtain a purified adjacency matrix. Subsequently, structural and attribute representations are extracted through a shared graph convolutional network, and the consistency between the two in a unified space is constrained using a structure-attribute consistency loss. Simultaneously, learnable view position encoding and masked self-attention mechanisms are introduced for progressive fusion, and cross-view evolutionary patterns are learned through adjacent view mapping to form an evolutionary loss. Finally, the evolutionary representations of each view are concatenated and mapped to a sample-level fused representation, which is then input into the classifier for prediction. The model is jointly optimized by the classification loss, consistency loss, and evolutionary loss. Compared with other methods, this invention significantly improves the accuracy of classification results with a small amount of labeled data.

The invention discloses a clinical test data report management system and method, and relates to the field of data report management, and the method comprises the steps: carrying out the deep semantic analysis of original clinical test table data, and carrying out the multi-dimensional semantic mining in combination with a preset medical analysis rule set, therefore, key discovery points with remarkable clinical significance can be automatically identified and screened out. Furthermore, the discovery points are subjected to priority ranking and pruning to form a structured core discovery point sequence, and the structured core discovery point sequence is injected into a prompt template to construct accurate guidance for a large language model. And finally, converting the guide instruction into an abstract text with clear logic and highlighted key points by utilizing a large language model. In this way, automatic conversion from an original data table to a high-quality narrative abstract can be achieved, and therefore the writing efficiency and the intelligent level of a clinical test report are remarkably improved.

The application provides an artificial intelligence-based PON gateway fault prediction method, device and equipment, and relates to the technical field of artificial intelligence.In the application, first, a target device temperature matrix is constructed based on temperature data formed by a plurality of gateway hardware devices at a plurality of time points;second, a semantic mining unit is used to perform a plurality of semantic mining operations on the target device temperature matrix to form a plurality of device temperature semantic vectors corresponding to the target device temperature matrix;then, a semantic fusion unit is used to fuse the plurality of device temperature semantic vectors to form a fused device temperature semantic vector corresponding to the target device temperature matrix;finally, a fault prediction unit is used to predict and output a gateway fault prediction result corresponding to the target PON gateway based on the fused device temperature semantic vector.Based on the above, the problem of not timely handling of PON gateway hardware faults in the prior art can be improved.

The invention discloses a built environment crowd perception space mapping and quantitative evaluation method oriented to an urban green land scene. The method comprises the following steps: acquiring and processing multi-source heterogeneous data; carrying out recreation perception semantic mining and quantification on the social media comment text, and constructing perception scores for different ecosystem culture service types; mapping the perception score space to geographic grid units based on semantic association, and calculating an accumulated perception index of each unit by adopting a differential weight distribution algorithm according to spatial scale characteristics; extracting built environment characteristics of each grid unit; and training a machine learning model based on the accumulated perception indexes and the built environment features, establishing a mapping relation between the accumulated perception indexes and the built environment features, and performing perception index deduction on the blank area by using the model to generate global CES perception distribution. According to the method, fine spatial mapping of coordinate-free texts is realized, a perception prediction model based on environmental characteristics is established, and data-driven decision support is provided for fine design and management of a green land.

The invention provides an environment monitoring data evidence storage method based on a block chain, and relates to the technical field of data processing. The method comprises the following steps: firstly, performing matrix processing on target environment monitoring data to form an environment data matrix sequence; secondly, performing multi-angle semantic mining on the environment data matrix sequence to form a plurality of semantic mining vectors, and forming an environment data global vector based on the plurality of semantic mining vectors; then, performing anomaly recognition based on the global vector of the environmental data to form an environmental anomaly analysis result; on one hand, when an environment anomaly analysis result reflects that an anomaly exists, encrypted environment monitoring data and the environment anomaly analysis result are stored in a target block chain; and on the other hand, when the environment anomaly analysis result reflects that no anomaly exists, the target environment monitoring data and the environment anomaly analysis result are stored in the target block chain. Based on the method, the problem that data privacy and accessibility are difficult to effectively balance in the prior art can be improved.

This application provides a data analysis-based method, apparatus, and equipment for predicting power grid line losses, relating to the field of data analysis technology. In this application, latent semantic mining is performed on user load data to obtain a user load semantic vector; latent semantic mining is performed on voltage fluctuation data to obtain a voltage fluctuation semantic vector; based on the semantic information of the line loss-related frequency components in the voltage fluctuation data, line loss-related semantic constraints are applied to the voltage fluctuation semantic vector to obtain a voltage fluctuation constraint vector; latent semantic mining is performed on line characteristic data to obtain a line characteristic semantic vector; latent semantic mining is performed on environmental description data to obtain an environmental description semantic vector; semantic restoration is performed on the user load semantic vector, voltage fluctuation constraint vector, line characteristic semantic vector, and environmental description semantic vector to obtain power grid line loss prediction data. Based on the above, the relatively low reliability of power grid line loss prediction in existing technologies can be improved.

A human problem-solving thinking driven embedded enhancement method for logical reasoning problems, the present application relates to a multiple-choice logical reasoning question and answer problem in the field of natural language processing, which aims to solve the technical problems of unclear text structure analysis, insufficient use of problem related elements and difficult logical reasoning problem semantic mining in the existing logical reasoning question and answer problem solving method. The method mainly includes data preprocessing, arranging the sample into a text sequence suitable for neural network model processing, designing a question-based embedding update module based on human problem-solving thinking, first initializing character embedding representation, using a pre-trained language model to vectorize the characters in the sample, then using the embedding sequence of the question part to construct a logical information filtering vector, and then updating the embedding representation of the stem and options using the filtering vector, and a semantic relationship modeling module referring to human reading habits, analyzing the basic semantic unit of the neural network.

The present application relates to a kind of multi-modal large model and light small model collaborative road surface ice state prediction method, belong to road traffic safety monitoring and prediction field.The method aims to solve the real-time early warning and accurate prevention and control difficult problem caused by prior art.The present application constructs multi-modal data coding system, integrates road surface monitoring image, meteorological time series data and historical ice text case, realizes feature fusion using visual-physical feature joint coding, meteorological time series feature enhancement and text semantic mining;And use large model zero sample inference to generate pseudo label, train light small model through cross-modal knowledge distillation;Finally based on dynamic trigger type double model inference framework, call cloud big model accurate judgment when small model low confidence or high scene complexity, output ice starting time and thickness by confidence weighted fusion.The present application improves prediction accuracy and real-time, enhances model generalization ability, provides reliable support for winter road traffic control.

The application provides a posture measurement method, system, device and medium of a rotary steering system, and relates to the technical field of data processing.In the application, firstly, internal semantic mining is performed on a first acceleration component sequence and a second acceleration component sequence respectively, and the results of the semantic mining are associated and fused to form a target acceleration semantic feature; then, decoding output is performed based on the target acceleration semantic feature to obtain a third acceleration component and a fourth acceleration component; further, the first acceleration component is corrected based on the third acceleration component to form a first corrected acceleration component, and the second acceleration component is corrected based on the fourth acceleration component to form a second corrected acceleration component; finally, an inclination angle is determined based on the first corrected acceleration component and the second corrected acceleration component.Based on the above, the problem that the reliability of posture measurement is relatively low in the prior art can be improved.

The invention discloses a marine island multi-dimensional adaptation method and system based on spatial topology and semantic mining, and belongs to the technical field of marine resource management and territorial space planning. The method comprises the following steps: receiving structural information input of a sea-used project, an island-used project and a sea-used island project; realizing dynamic combined query and result display based on multi-dimensional semantic features; automatically distributing projects and synchronizing states according to county-level administrative divisions; automatically calling a GIS service on a project detail page, superposing multiple layers to carry out spatial topology analysis, and outputting a structured conclusion; and based on a preset template, generating a PDF analysis report integrating space conformity, doubtful point and doubtful area and sea area use gold calculation results. According to the method, the problems of different data standards, low manual review efficiency and disjunction of business and spatial analysis in the prior art are solved, and scientific review and decision support of the project using the sea and the island are realized.

This application discloses a method, system, device, and medium for displaying in-game data, relating to the technical field of games. The method includes: acquiring scene state information of a target player in the current game scene, wherein the scene state information includes first state information of a target character, field-of-view parameters of a virtual camera, and second state information of multiple virtual objects within the field of view, the target character being the character controlled by the target player; performing semantic mining on the scene state information to obtain a personalized visual attention vector for the target character, and determining a standard visual attention vector corresponding to the current game scene based on the scene state information; acquiring the target player's historical scene state information, and constructing a standard visual prediction model based on the historical scene state information; and traversing a set of target rendering parameters based on the standard visual prediction model and a genetic algorithm. This application has the effect of improving the player's gaming experience.

The invention discloses an intelligent data verification method and device, electronic equipment and a storage medium, which are used for solving the problems of poor flexibility, low verification efficiency and low accuracy in the current data verification means. Obtaining a preprocessed to-be-verified text; performing grammar verification based on the grammar analysis tree on the to-be-verified text to obtain grammar verification information, and performing semantic understanding on the to-be-verified text to obtain semantic understanding information; performing context verification combined with deep semantic mining and semantic association knowledge graph enhancement on the to-be-verified text to obtain context information; performing emotional tendency analysis on the to-be-verified text to obtain emotional analysis information, and performing entity recognition on the to-be-verified text to obtain entity analysis information; performing text proofreading and error correction on the to-be-verified text to obtain text correction information; and integrating the grammar verification information, the semantic understanding information, the context information, the sentiment analysis information, the entity analysis information and the text correction information as a data verification result.

The application provides a t-SNE-based high-entropy alloy document keyword implicit semantic mining method and device, and relates to the technical field of material document clustering. The method comprises the following steps: obtaining and preprocessing an entropy alloy document data set; training a high-entropy alloy document word vector; representing a high-entropy alloy document; clustering analyzing a high-entropy alloy document vector; and mining a high-entropy alloy hotspot and development trend according to a clustering analysis result. The high-entropy alloy clustering method comprehensively considers the abstract and keyword information of the high-entropy alloy document, fully mines the implicit semantic information from the high-entropy alloy abstract, fully mines the implicit semantic information of the high-entropy alloy document keyword, and through the t-SNE visualized high-entropy alloy document clustering, the distribution and clustering effect of the high-entropy alloy document can be more intuitively observed, thereby providing technical support for mining potential information such as the development trend of the high-entropy alloy.

This invention provides a method, system, and product for automatically extracting metadata and metadata relationships, relating to the field of big data technology. The method includes: extracting table information, table field information, and foreign key relationships between tables in the current database to obtain explicit metadata; extracting multiple sample data entries from each table; assembling the explicit metadata and the sample data entries to obtain model instruction prompts; using these prompts to call a large language model to output structured table semantic descriptions and field semantic descriptions, and outputting these as metadata; extracting semantic relationships between tables based on the table semantic descriptions, and extracting semantic relationships between fields based on the field semantic descriptions; and outputting the inter-table semantic relationships and inter-field semantic relationships as metadata relationships. This invention solves the problem that existing technologies mainly focus on explicit structured information while neglecting deep semantic mining, significantly improving the efficiency and fault tolerance of data querying, integration, and modeling processes.