139 results about "Semantic clustering" patented technology

The invention provides an intelligent SQL generation method and system for business query, and belongs to the technical field of artificial intelligence. Related data of query statements are acquired, and a corresponding query intention knowledge graph is constructed by semantic clustering; the method comprises the following steps: analyzing a historical SQL statement structure, extracting a natural language template and an SQL template, and expanding through a large language model to generate a feed-shot example set; and constructing a composite cue word template by combining task setting guidance, a feed-shot example and CoT chain thinking reasoning guidance. An intention completion module is arranged in a large language model, a natural language query statement of a user is combined with a composite cue word template context, a structured query statement is generated through entity recognition, semantic completion, parameter filling and fuzzy intention training, and the structured query statement is converted into a standard SQL statement through a knowledge graph and a template. According to the method, the use threshold of business personnel is remarkably reduced, and efficient conversion from natural language questions to SQL statements is realized.

The invention relates to the field of government affair work order intelligent processing, in particular to a government affair work order intelligent processing method and system based on space-time semantic clustering and a large language model. According to the scheme, unified data feature modeling is conducted on a work order to be processed, an improved DBSCAN clustering algorithm is executed on the work order through a weighted space-time semantic three-dimensional distance measurement formula, and combined clustering of space, time and semantic features is achieved; calculating priority scores of the work orders, and dynamically allocating scheduling resources according to the clustering scale and the priority of the work orders; based on a retrieval enhancement generation technology of an RAG framework and an FAISS vector retrieval library, historical similar work orders are matched, a few-sample learning case is generated, and two sets of differential treatment schemes are generated by controlling temperature parameters of a large language model; visual display and interactive analysis of work order clustering are realized through an interactive GIS platform; and establishing a quality feedback closed loop of work order reconstruction. The method is suitable for intelligent government affair work order processing.

The invention discloses an automatic flow chart layout method fusing semantic analysis, which relates to the technical field of automatic flow chart layout, and comprises the following steps of: inputting a node set with a business ring dependence condition into a time sequence conflict analysis engine, and combining a semantic vector and a time sequence vector to obtain a time sequence conflict analysis result; calculating a time sequence conflict index of the annular dependency set by adopting a weighted path consistency check algorithm so as to determine a time sequence conflict degree under the condition that the nodes have service annular dependency, and generating corresponding conflict description data; and inputting the conflict description data and the semantic vector into a conflict perception clustering optimizer, introducing a time sequence conflict penalty term into a clustering objective function, and performing cluster boundary adjustment on the annular dependency set through a spectral clustering algorithm so as to adjust a semantic clustering structure according to a determination result. According to the method, the problem that a semantic clustering structure cannot be optimized in combination with a time sequence conflict under business annular dependence is solved, and the effects of conflict accurate identification, clustering boundary dynamic adjustment and layout saliency enhancement are achieved.

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

The invention relates to the technical field of artificial intelligence in the education industry, in particular to an intelligent composition quality evaluation method and system based on a large language model, and the method comprises the steps: carrying out the text normalization and semantic unit segmentation of a composition, extracting a semantic vector through a first large language model in combination with a context enhancement strategy, and positioning a semantic fracture risk position; recognizing composition core elements through a second large language model, and mapping the composition core elements back to the semantic unit sequence; constructing a demonstration logic diagram, extracting a core demonstration path and abstracting the core demonstration path into a logic role topological graph; in combination with a pre-constructed writing specification knowledge graph, comparing structural compliance, connection strength and an expected support relationship, identifying and demonstrating logic defects, and generating a global deduction item list; semantic clustering is carried out on illegal items to form an error label set, comprehensive weight is calculated in combination with historical data of students, and core weak items are positioned; according to the application, the logic analysis depth of intelligent evaluation of the argument is remarkably improved, and the pertinence and practicability of teaching feedback are improved.

The invention discloses a financial user portrait analysis method and system based on a knowledge graph, and the method comprises the steps: recognizing a financial entity through an FNER algorithm, carrying out the relation embedding through employing a TransFinE algorithm, integrating the time weight attenuation and risk propagation constraints, constructing a financial knowledge graph, calculating the user influence distribution through employing a FinRank algorithm, and carrying out the analysis of the financial user portrait. And finally carrying out semantic clustering and grouping to obtain a user portrait classification result. The technical problems that an existing financial user portrait analysis method cannot effectively process a multi-dimensional semantic association relationship, lacks a user network influence quantification mechanism and neglects time sequence evolution characteristics are solved.

The invention belongs to the technical field of natural language processing, provides a multi-dimensional confidence fusion large language model uncertainty evaluation method and system, designs a multi-dimensional confidence modeling mechanism, and can perform multi-dimensional confidence modeling on the basis of internal information in a large language model generation process without depending on an external knowledge base. And the reliability of the output content is effectively judged. According to the system, on the basis of a semantic clustering mechanism, a Token-level multi-dimensional confidence modeling method is innovatively introduced, a scoring system fusing factors such as probability centrality, context disturbance sensitivity, generation consistency and language rationality is constructed, the confidence structure of each part of content in model output can be evaluated from the Token level, and the evaluation efficiency is improved. And the discrimination capability of the system on the uncertainty difference in the generation process is obviously improved.

The invention relates to the technical field of artificial intelligence, in particular to a news viewpoint evolution trend tracking system based on artificial intelligence, which comprises a collector, an extractor, an aggregator, a modeler, a detector and a presenter. A disturbance sample generation and consistency detection mechanism is combined, so that the clustering process is more robust, and the recognition precision of the viewpoint cluster semantic center is remarkably improved; according to the method, a black hole detection mechanism based on density estimation and multi-point similarity joint modeling, an anti-fact intervention mechanism and a dynamic graph density-structure joint estimation model are adopted, a node disturbance situation can be constructed, the influence of the node disturbance situation on a semantic structure can be inferred, and through fusion of semantic consistency, density offset and energy anti-fact scoring, the dynamic graph density-structure joint estimation model is obtained. High-confidence screening of abnormal nodes is realized, and the purity of a viewpoint atlas structure and the reliability of semantic evolution modeling are effectively improved.

The invention relates to a manufacturing system risk control knowledge matching method based on semantic embedding and clustering analysis, and the method comprises the following steps: collecting and preprocessing risk control text data: collecting unstructured text data of a manufacturing system history record, and obtaining preprocessed risk control text data, constructing a professional corpus for a discrete manufacturing scene; text semantic embedding generation; semantic clustering modeling: performing unsupervised clustering modeling on all semantic vectors, mining semantic association and potential structures between texts, obtaining semantic representations of risk control knowledge through a clustering algorithm, and assisting in generating clustering tags; and a risk knowledge matching mechanism.

The invention discloses an archive content semantic clustering method based on a graph neural network, and the method comprises the following steps: S1, carrying out the word segmentation, denoising and vector expression of an archive text, and generating a text feature vector set; s2, constructing a semantic graph structure model according to the semantic similarity and the reference relationship between the texts; s3, generating a division result with a balanced structure on the semantic graph by adopting a graph division algorithm; s4, performing double-layer node merging on each graph division cluster, and generating a graph structure coarsening result and a mapping relation; s5, inputting the original graph and the coarsened graph into the graph neural network model, and calculating and fusing each layer of semantic representation; s6, cross-layer consistency constraint optimization node semantic representation is introduced, and a unified embedded vector set is generated; and S7, inputting the embedded vector into the clustering model, and outputting a semantic clustering category of the archive text. According to the invention, semantic recognition and automatic grouping of archive contents are realized.

The invention provides a large-scale knowledge graph visualization method and system, and relates to the field of knowledge graph visualization. The method comprises the following steps: acquiring knowledge graph data, and clustering the knowledge graph data through a modularity-based discovery algorithm; obtaining each sub-graph corresponding to the clustered knowledge graph data, and for each sub-graph, selecting a representative node based on a PageRank algorithm or a Leader Rank algorithm; carrying out force-oriented layout on the clustered knowledge graph data through a tree diagram space filling technology; and for the knowledge graph data subjected to the force-oriented layout, distributing priorities and use times of a Barnes-Hut algorithm and a random vertex sampling algorithm according to a preset mode, and dynamically displaying a visualization result in a layered manner through an affine transformation technology. According to the method and the device, the problem that the structural expression clarity of the drawn knowledge graph is greatly reduced due to the fact that semantic clusters and hierarchical organizations in the graph are difficult to accurately present in a traditional visualization method is solved.

The invention discloses a content auditing abnormity monitoring and early warning method and system based on intelligent alarm suppression, and the method comprises the following steps: obtaining real-time content auditing data collected in multiple dimensions, determining multi-dimensional data, carrying out the data cleaning and standardization processing of the multi-dimensional data, and carrying out the monitoring and early warning of the content auditing abnormity. Storing the multi-dimensional data subjected to data cleaning and standardization processing into a database; and constructing a deep reinforcement learning model, determining data input of the deep reinforcement learning model based on the standardized multi-dimensional data, and driving the deep reinforcement learning model to optimize an alarm mode in a training process. According to the method, hidden violation and semantic evolution trends are recognized through semantic clustering, and the traditional detection bottleneck based on a numerical threshold value is broken through; according to the invention, by realizing cross-cycle trend evolution analysis, early signals before abnormal outbreak can be identified in advance; the method has the cross-event semantic comparison capability, and the false alarm rate and the redundant data volume are remarkably reduced.

The invention discloses a front-end cache management method, system and device for a lightweight large-model dialogue state and a medium, belongs to the technical field of front-end cache management of a large-model dialogue system, and aims at solving the technical problem of how to overcome the defects that in a traditional scheme, long context cache is low in efficiency, storage redundancy and insufficient in dynamic semantic adaptation capacity, and the large-model dialogue state cannot be managed easily. In order to realize dialogue context volume compression, improve semantic similar request hit rate and reduce cross-end synchronization delay, the adopted technical scheme is as follows: data acquisition and preprocessing: capturing user interaction behaviors in real time through front-end burying points, and performing preprocessing operation on the acquired user behavior data; semantic normalization processing: performing embedded vector conversion and semantic clustering on the text input by the user to generate a unique semantic identifier and a context vector; querying and updating the multi-level cache; and dynamic collaborative updating: dynamically adjusting the cache based on the cache hit rate, the response delay and the user feedback, and optimizing the cache effect in real time.

According to the QA-driven large-model hierarchical knowledge graph parameterization construction method provided by the invention, the unstructured document is segmented, and the structured question and answer pairs are generated in combination with the language model, so that automatic extraction from the original text to the knowledge unit is realized, and the manual participation cost is reduced; then, semantic affiliation and hierarchical relations are established between the extracted question content and entity categories, atomic nodes and intermediate nodes, systematic hierarchical organization of the knowledge graph is achieved, the structure is clear, and logic is complete. Moreover, a semantic clustering algorithm is adopted to classify bottom nodes, and intermediate nodes are automatically constructed on the premise of meeting graph structure constraint conditions, so that redundancy and repetition are avoided; and finally, through information granularity decomposition driven by question and answer pairs and in combination with atomic node construction, the fine degree of knowledge extraction and the expressive power of graph representation are remarkably improved.

The invention discloses a cross-file information summarization and new knowledge automatic summarization method and system, and belongs to the technical field of file data processing, and the method specifically comprises the steps: collecting document file data, vectorizing the document file data based on a semantic embedding model, carrying out the reconstruction and semantic clustering of the semantic vector of the document file data, and carrying out the automatic summarization of the new knowledge. The method comprises the following steps: constructing a semantic structure chart which represents a logical relationship between document file data, performing content completion on nodes which are not completely associated in the semantic structure chart, extracting structured knowledge units from the completed semantic structure chart, and generating a new knowledge text based on the structured knowledge units; according to the method, the limitation of low efficiency of knowledge splitting and manual summarization between traditional document files is solved, the automation degree of knowledge discovery is remarkably improved, and the method is suitable for scenes of knowledge base construction, domain rule extraction, domain knowledge discovery and the like.

A neural network compression system based on lexical attention score dynamic pruning comprises an input module, a mask generation module and a dynamic reasoning module, attention scores are directly introduced into a pruning decision to quantify the importance of an internal structure of a model, fine pruning based on real attention distribution is achieved, and the accuracy of pruning is improved. The distortion problem of a traditional weight amplitude-based method is avoided; according to the method, lexical elements are divided through semantic clustering, independent masks are generated in each class, and class-level pruning granularity is constructed, so that a model structure is more adaptive to input semantic features, performance stability is kept under a high pruning rate, lexical element classes are identified based on a KNN algorithm, and the masks are dynamically called; sparse strategy switching during reasoning is realized, reasoning efficiency and model precision are both considered, and a new dynamic control path is provided for lightweight reasoning of a large model.

The invention relates to a technology comparative analysis system and method based on standard semantic analysis and a computer readable recording medium. According to the system, dimension reduction processing is carried out on process data and standard texts through a semantic clustering module, and a semantic mapping relation between processes and standard terms is constructed; generating a contrast set by using a process operation standard threshold construction module and a convolutional network; and calculating a compliance score by adopting a contrast learning module. The system supports dynamic updating of a multi-dimensional standard knowledge graph, analyzes texts and recognizes semantic equivalent pairs through a natural language processing technology, achieves intelligent comparison and deviation recognition of process data and standard rules, automatically generates compliance reports and early warning information, and finally achieves digital management of enterprise standard full life cycles. And automation and accuracy of compliance analysis are improved.

The invention discloses a corpus construction method and system, a product, equipment and a storage medium, high-frequency reply answers are obtained by clustering reply speech term meanings of seats, on one hand, the accuracy of reply contents is ensured, on the other hand, high-quality and high-frequency replies of high-performance seats can be mined, and high utilization value of produced knowledge is ensured. Contextual information of an original dialogue is positioned through answer reverse matching, and the context is summarized and extracted into a high-quality customer question by using the semantic understanding advantage of a large model. Compared with the prior art, the method has the advantages that automatic high-frequency QA mining can be realized at low cost, meanwhile, the quality of questions and answers can be ensured, and knowledge base construction of the specific field scene FAQ is efficiently realized.

The invention discloses a river network modeling and question-answering method based on a time sequence knowledge graph, and the method comprises the steps: fusing geographic information data and hydrological and hydrodynamic data, constructing a river network ontology model with a time evolution capability, obtaining a high-frequency concept through semantic clustering, and designing a multi-granularity time relation; carrying out entity and relation joint extraction on heterogeneous data by adopting an OneRel model, designing a SelfKG-T algorithm to complete entity alignment, and constructing a complete time sequence knowledge graph; and realizing semantic question answering and dynamic response to river network knowledge in combination with an RAG architecture and a large language model. The method has the advantages of knowledge graph construction automation, knowledge expression timing, question and answer interaction intelligence and the like, and is suitable for intelligent water conservancy scenes such as flood control scheduling and water resource management.

The invention discloses a text classification method and device and a processor. A normalized text vector is obtained by preprocessing and coding an input text. Then utilizing a multi-layer structure in a pre-trained bad text recognition model, firstly carrying out first-level category classification on the input vector through a first Transform coding layer and a classification layer, and meanwhile, carrying out related semantic clustering through a first clustering layer to generate a first clustering text vector; then, a second Transform coding layer and a classification layer complete finer-grained secondary category classification based on the first clustering text vector, and continuous aggregation is performed through a second clustering layer to generate a second clustering text vector; and finally, the third Transform coding layer and the classification layer are combined with the second clustering vector to output a global classification result. And finally, all classification results are screened by setting a confidence threshold, high-confidence categories are reserved, and accurate classification results with clear levels are obtained.

The invention discloses a network security threat detection method and device, a storage medium and a processor. According to the scheme, real-time alarm data are acquired; based on a white list rule base, filtering the real-time alarm data, and performing semantic clustering de-duplication on the filtered real-time alarm data to obtain real-time alarm data after semantic clustering de-duplication; and performing context prompt generation and attack chain reasoning on the real-time alarm data after semantic clustering and duplicate removal by using a large language model to obtain a network security threat detection result corresponding to the real-time alarm data. Compared with the prior art that the manual verification alarm consumes a long time, the processing efficiency is low, a large language model API is directly called to analyze the full-amount alarm, the API calling cost per month is very high due to the fact that a huge amount of safety alarm data is used, and sustainable operation and large-scale deployment of the system are seriously limited, the method has obvious advantages.

The invention relates to the technical field of artificial intelligence and natural language processing, in particular to a satellite communication field data retrieval enhancement generation method and device based on a large model. The method comprises the steps of data cleaning and metadata labeling, text double-layer clustering construction, double-layer knowledge graph construction, normalized user semantic input, knowledge graph retrieval and answer optimization. According to the double-layer semantic clustering structure and the double-layer knowledge graph construction mechanism, multi-granularity semantic units in the field of satellite communication can be effectively expressed, cross-document and cross-standard knowledge organization and retrieval are supported, a large language model is introduced to complement and standardize entities and relationships, the automation degree of the knowledge graph construction process is higher, and the construction efficiency is improved. And the relation extraction quality is better. According to the method, intelligent analysis, accurate retrieval and high-quality answer generation of complex natural language query in the satellite communication field can be realized, and the method has remarkable semantic understanding ability, reasoning ability and closed-loop optimization ability.

The invention discloses an electric power operation safety supervision target detection method, system and device based on semantic clustering and a medium, and belongs to the technical field of target detection and semantic analysis, and the method comprises the steps: extracting the image features of a target picture, determining candidate boxes needed by target detection through a region generation network, and unifying the sizes of the candidate boxes; extracting category semantic features of the target picture, and generating category semantic feature vectors; according to the candidate box, generating a clustering feature vector through a multi-layer sensing mechanism; calculating class decorrelation loss based on the clustering feature vector; calculating semantic clustering loss; and according to the candidate box, a target detection result is obtained through a multi-layer sensing mechanism, and classification loss and regression loss are calculated. According to the method, the wearing state of safety protection equipment and abnormal equipment can be accurately detected in a complex power grid environment, the problems of misjudgment and missing detection of unknown samples by a traditional detection model are effectively solved through semantic feature constraint and feature space reconstruction, and the intelligent safety supervision efficiency in scenes such as electric power inspection and high-altitude operation is improved.

The invention discloses a serialized recommendation method based on a large-scale language model. The serialized recommendation method comprises the following steps: A1, inputting: inputting a user set and an article set in the large-scale language model (LLM); for each user, its historical interaction sequence, each of which is an interacted item. Contextual information of an item. A2, data processing: a) performing semantic clustering based on logit representation output by candidate items in a large language model; b) estimating semantic uncertainty based on a semantic clustering result; c) according to the decoding step of the semantic uncertainty adjustment article score and / or sampling strategy, selecting the most tip article as a final recommendation result; and A3, outputting a recommended article list. According to the method, the problem that a decoding strategy of an existing large language model is not matched with a recommendation target in serialized recommendation is solved; the core idea of the method is to improve prediction of a next article by combining log-based clustering and adaptive scoring.

The invention discloses a tourism economy operation data investigation and monitoring system. The system comprises a data acquisition layer which is used for constructing a tourist behavior acquisition matrix; the graph space-time fusion layer integrates a TGN framework, defines a node type and a hyperedge type, adopts a Transform structure to capture a seasonal mode by a time encoder, integrates a meta-path knowledge injection mechanism and a CTBN space-time probability graph model, performs tourist state discretization by using an H3 hexagonal grid, and performs space-time dependency relationship capture through an Flink CEP extended dynamic geo-fencing operator; the data processing layer is used for carrying out track semantic clustering by adopting a TRACLUS + + algorithm, and automatically generating space-time cross characteristics in combination with Featuretools; the data storage layer is used for configuring InfluxDB to store space-time state chain data; and the data analysis layer is used for calling a PyG model to carry out implicit relationship mining by applying a near-graph calculation acceleration technology, and constructing a tourist volume prediction model by fusing a graph attention network and a space-time convolutional network to capture spatial dependence and time trend.

The invention relates to the technical field of intelligent commerce, in particular to an AI-based cross-border e-commerce intelligent website building system, which comprises a semantic analysis module, a template generation module, an inventory linkage module, a customs clearance pre-check module and a dynamic tuning module. According to the method, a dynamic keyword library is generated through semantic clustering based on multi-language social media texts, a self-matching payment environment is established in combination with payment protocol feature fusion and mobile terminal parameter mapping, multi-warehouse inventory and logistics nodes are coordinated through a path optimization algorithm, and target market customs clearance rules are matched based on commodity material features. The dynamic adaptation capability of a cross-border e-commerce platform in multi-country operation is improved, automatic compatibility of payment interfaces is realized, the exchange rate conversion error of multi-currency settlement is reduced, the cross-border logistics resource scheduling accuracy is optimized, the commodity compliance pre-check efficiency is enhanced, and the risk of customs clearance delay and operation interruption caused by policy differences is reduced.

The invention discloses a key information extraction and analysis method suitable for foreign trade English negotiation voices, and the method comprises the steps: obtaining the historical voices of foreign trade English negotiation in multiple industries, extracting the voice features, carrying out the text transcription, and generating a first tag data set; training a round semantic clustering model to realize automatic classification of negotiation rounds and clustering of similar issues; then in combination with an intention-entity label labeled by the cross-language semantic understanding model, training an intention-entity bidirectional mapping model, and outputting associated data; training a rule-oriented conflict traceability model by combining a cross-border trade rule base, and identifying information conflict points and complementary points; constructing a key information priority evaluation model, and outputting a key information list sorted according to scores; and finally, generating a structured analysis report and dynamic negotiation strategy guidance. Through multi-model cooperation and foreign trade scene adaptation design, key information can be accurately extracted, intentions and entities can be associated, rule conflicts can be detected, negotiation information processing efficiency and risk management and control capability can be improved, local or cloud deployment can be flexibly adapted, and requirements of different foreign trade enterprises can be met.

The invention discloses a text semantic clustering analysis method, device and equipment based on a large language model. An original data set is sampled based on information entropy, a complete set is replaced by a subset, clustering is carried out in a sliding window mode, the problem that one-time processing cannot be carried out due to the fact that the size of the original data set is far larger than the context length of a model is solved, meanwhile, the calculation cost can be reduced through the sampling mode, and the data quality is improved. The treatment efficiency is obviously improved; and correcting clustering errors and verifying the consistency of clustering results by using a large language model so as to finish final clustering.

The invention discloses a follow-up visit data acquisition method and system based on strategy question and answer and retrieval enhancement, and the method comprises the steps: disassembling an original follow-up visit form into structured entries, and dividing the structured entries into a plurality of form blocks according to the types of the structured entries; and generating induction prompts based on the form blocks, and guiding the large language model to generate form description. Then, a problem clustering prompt is constructed in combination with form description, a large language model is driven to conduct semantic clustering on the problems, and a clustering entry set is formed; then, a natural language question is generated based on the set, multiple rounds of dialogues with the user are carried out, and dialogue content is obtained; and finally, driving a large language model to accurately extract user intentions by utilizing a retrieval enhancement technology and combining a clustering entry set and dialogue contents, and performing result judgment and feedback optimization by setting a marking condition until processing of all form blocks is completed, thereby realizing efficient and accurate follow-up visit data acquisition. The method effectively improves the interaction efficiency and the data quality, and is suitable for intelligent follow-up visit in a complex medical scene.

Example systems, methods, and computer-readable media are disclosed. In an example method, a first outbound text message is transmitted via a message broker of a messaging platform from a client to a plurality of recipients. In response to the first outbound message, a plurality of inbound text messages is received, via the message broker, from the plurality of recipients. A first grouping of the plurality of inbound text messages is determined, the first grouping associated with one or more recipients of the plurality of recipients. The first grouping is presented to the client. A second outbound text message is transmitted, via the message broker, from the client to the one or more recipients of the plurality of recipients. The second outbound text message is generated based on the first grouping. The message broker is in communication with a first messaging service and a second messaging service different from the first messaging service. The first outbound text message is transmitted via the first messaging service. A first inbound text message of the plurality of inbound text messages is received via the second messaging service. Each inbound text message of the plurality of inbound text message is addressed to a long-code telephone number generated by the messaging platform and uniquely associated with the client by the messaging platform.