30 results about "Topic model" patented technology

The present disclosure relates to a system, a method, and a product for topic discovery. The system includes a memory storing instructions; and a processor in communication with the memory. When the processor executes the instructions, the instructions are configured to cause the processor to: obtain text data, conduct pre-processing on the text data to obtain pre-processed text data, extract an entity list and a keyword list based on the pre-processed text data, generate an entity embedding list based on the entity list, clusterize the entity list based on the entity embedding list to obtain a plurality of entity clusters, each entity cluster comprising at least one entity, retrieve a co-occurring keyword list based on the plurality of entity clusters, the entity list, and the keyword list, and obtain a topic for each entity cluster of the plurality of entity clusters based on the co-occurring keyword list.

The embodiment of the application discloses a kind of theme model updating method, system and storage medium and server, apply to the information processing technical field based on artificial intelligence.Theme model system will obtain the first label semantic feature and the second label semantic feature corresponding respectively to multiple old theme labels in the first theme model and multiple new theme models in the second theme model, and based on the first label semantic feature and the second label semantic label, mapping relationship is established between old theme label and new theme label, and then the old theme label in the first theme model is updated based on the mapping relationship.The updating of the first theme model existing in the system is realized automatically, the efficiency of the theme model is improved, and the theme model with larger dimensionality can also be updated, and the updating of the first theme model is not limited by the theme model acquisition method.

The invention discloses a long text abstract generation method based on hierarchical graph comparison themes, which comprises the following steps of: 1, preprocessing an original document, dividing sentence sequences, and obtaining global context-aware sentence and document representation through a hierarchical encoder network; 2, deducing document-level and sentence-level topic distribution by using a neural topic model; and 3, constructing a supervision graph based on a standard abstract to perform graph comparison learning so as to close the topic representation of a document and a key sentence and push redundant information. According to the method, the deep semantic structure of the long document can be effectively captured, so that the theme consistency and the information coverage degree of the abstract can be improved, and the redundancy is reduced.

A method for technical issue resolution. The method includes: receiving, from a user, a text query concerning a technical issue; obtaining query-related context relevant to the text query; and processing, through a large language model (LLM), the text query and the query-related context to produce a multimodal query response used by the user to address the technical issue. More specifically, embodiments described herein utilize text topic and zero shot classification models to translate multimodal technical documentation (e.g., including text and images) into topic relevant metadata; and process queries, pertaining to technical issues, using a multimodal LLM provided with query-related text and image context derived from said topic relevant metadata.

Certain aspects of the disclosure provide a method for providing user support by generating recommended response for a customer verbatim with an ensemble of machine learning models. The method includes processing a customer verbatim with a topic model trained to identify a topic associated with the customer verbatim. The method further includes processing the customer verbatim with a sentiment model trained to determine a sentiment of the customer verbatim. The method further includes processing the customer verbatim with an actionability model trained to assign an actionability score to the customer verbatim. The method includes processing the topic, the sentiment, and the actionability score with a recommendation model to generate the recommended response to the customer verbatim.

The invention discloses a multi-modal co-situation prediction method based on supervision text assistance. The method comprises the following steps: 1, obtaining text, audio and video data and carrying out feature extraction; 2, calculating fused multi-modal features through an attention mechanism and a long-short-term memory network; 3, learning topic distribution of supervised texts by using a hidden Dirichlet topic model LDA; 4, network parameters are trained through a common situation level of a given training scene and theme distribution of a corresponding supervision text; and 5, calculating and predicting the common situation level of the multi-modal scene by using the trained network parameters. According to the method, the multi-modal data and the supervision text are comprehensively utilized as privilege information, so that the model prediction performance in a complex condition-sharing scene is enhanced, the condition-sharing level in a multi-modal scene can be predicted more meticulously, the accuracy and generalization of condition-sharing prediction are remarkably improved, and the mental health support effect is effectively improved.

The embodiment of the invention provides a text classification method, electronic equipment, a storage medium and a program product. The method comprises the following steps: processing a to-be-classified text according to a lexical element division rule to obtain a lexical element sequence; according to the lexical element sequence, adopting a pre-trained unsupervised topic model to obtain a topic distribution data set corresponding to the to-be-classified text; adopting a pre-trained unsupervised clustering model to obtain a clustering distribution data set corresponding to the to-be-classified text; splicing the topic distribution data set and the clustering distribution data set to obtain a text hidden topic; obtaining a plurality of text clusters and current cluster hidden topics corresponding to the text clusters, and calculating the similarity between the text hidden topics and the current cluster hidden topics; and determining a target text cluster from the plurality of text clusters, and adding the to-be-classified text to the target text cluster. Through a cluster classification mechanism of subject distribution and cluster distribution conjoint analysis, the accuracy and result stability of text classification are improved.

The application discloses a long-text official document key information extraction agent method based on a large model, relates to the technical field of artificial intelligence, and comprises the following steps: collecting original official document long-text data; performing structural analysis and hierarchical coding on the original official document text data; performing dynamic semantic segment division based on a topic model guide; constructing a long-text official document key information extraction model based on a bidirectional semantic encoder; performing model training and trainable parameter updating; performing long-text official document key information extraction; and constructing a long-text official document key information extraction agent based on the large model. The application adopts a multi-dimensional structural coding method which fuses official document hierarchies, formats and positions, converts domain prior knowledge into computable vectors, adopts a dynamic planning text segmentation algorithm based on topic consistency and semantic density scoring, guarantees the integrity of long-text semantic segments, and introduces a structure-guided cross-segment attention mechanism in a Transformer encoder, so that precise modeling of long-distance semantic dependence is realized through structural similarity constraints.

The application discloses a news stand discrimination method and system based on a heterogeneous graph neural network, and the method comprises the following steps: step 1, using a named entity recognition technology and an LDA topic model to extract entity and topic information in news, and establishing a heterogeneous graph in association with a sentence; step 2, processing the constructed heterogeneous graph through a heterogeneous graph neural network to obtain feature vectors of all nodes in the heterogeneous graph; and step 3, fusing the feature vectors of all nodes output by the heterogeneous graph neural network to comprehensively judge the stand tendency of the news. The application can comprehensively judge the stand tendency of the news by combining important element information in the news and structural relationships between the element information, and has a high discrimination accuracy.

An analysis method for investment decision-making involves, firstly, acquiring news data, invoking a custom-trained topic model to extract entities from the news data, and creating a finite state mach

The application discloses a city functional area identification method based on POI and an improved topic model, and belongs to the technical field of geographic information systems. The city functional area identification method based on POI and the improved topic model comprises the following steps: obtaining interest point data of a target functional area, wherein the interest point data comprises spatial position data of each interest point; dividing the target functional area into a plurality of functional sub-areas according to the spatial position data; determining sub-area semantic features of each functional sub-area; and obtaining regional spatial semantic features of the target functional area according to the sub-area semantic features, so that the problems of low recognition precision and poor accuracy existing in the prior art are solved.

The invention provides a conference key information real-time extraction and knowledge pushing method based on a large language model, and relates to the technical field of artificial intelligence and conference management, and the method comprises the steps: obtaining a voice data stream in real time, carrying out the transcription and semantic analysis, and dividing semantic segments based on semantic integrity constraints; identifying key information by using the information extraction template and the conference theme model; constructing a conference discussion evolution knowledge graph; and carrying out accurate knowledge pushing according to the map and the conference process. The conference efficiency can be improved, knowledge sharing is enhanced, and the decision process is optimized.

The disclosure provides a method, device and equipment for constructing a dataset, and a storage medium, relates to the technical field of computers, in particular to the fields of natural language processing, cloud computing, deep learning and the like. The specific implementation scheme is as follows: determining a target topic according to a topic-word distribution matrix output by a topic model based on a text set; determining a target text according to a text-topic distribution matrix output by the topic model based on the text set by using the target topic, wherein the target text is derived from the text set; and constructing a dataset based on the target text. According to the scheme of the disclosure, the target text required for constructing the dataset can be quickly and accurately screened from the text set.

This application relates to an intent recognition method, apparatus, and computer device based on domain knowledge seed words. The method includes: acquiring and preprocessing a planning document corpus; calculating term importance weights to filter initial seed words; dividing the corpus into hierarchical seed words using a large language model; expanding the corpus using a dual-dimensional approach of general vocabulary similarity and domain context embedding similarity; filtering the corpus with a domain dictionary to obtain a hierarchical expanded seed word dictionary; increasing the Dirichlet prior weight of the corresponding level's expanded seed words in the topic model based on hierarchical matching relationships according to the expanded word dictionary corresponding to each level; performing topic modeling on the planning document corpus; outputting the vocabulary distribution of each topic and the topic distribution of each document; constructing a clustering tree based on topic semantic distance; filtering the optimal partition; and generating hierarchical intent results by combining the hierarchical structure. This method can effectively achieve automated and hierarchical intent recognition, ensuring that the recognition results align with domain business logic.

The invention relates to a marketing topic key user and influence measurement method based on multi-feature fusion, and belongs to the technical field of social network analysis. According to the method, modeling is performed on text data through an LDA topic model, and meanwhile, a marketing topic set is extracted by utilizing a clustering algorithm. The topic correlation is used as an index for measuring the correlation degree between the text and the topic, and the quality and correlation of the text and the topic are effectively evaluated. Secondly, introducing a fuzzy mathematical theory, and establishing a fuzzy comprehensive evaluation model based on information entropy; various characteristics of the user are fused as evaluation indexes, and the weight is determined by using an entropy weight method, so that the interference of subjective preference is reduced. And finally, constructing a multi-dimensional heterogeneous network based on marketing topics. By fusing the attribute characteristics of each node and utilizing the random walk strategy, the user behavior and interaction information are comprehensively considered, so that the influence of the user in the marketing topic is more comprehensively evaluated.

The invention relates to an intention recognition method and device based on field knowledge seed words and computer equipment. The method comprises the steps that a planning document corpus is obtained and preprocessed, term importance weights are calculated to screen initial seed words, the seed words of all levels are obtained through hierarchical granularity division of a large language model, and two-dimensional expansion of general vocabulary similarity and domain context embedding similarity is adopted to obtain a multi-level seed word; filtering through a domain dictionary to obtain a hierarchical extension seed word dictionary, improving the Dirichlet prior weight of the extension seed word of the corresponding hierarchy in the topic model according to the extension word dictionary corresponding to each hierarchy and a hierarchy matching relationship, carrying out topic modeling on the planning document corpus, and outputting the vocabulary distribution of each topic and the topic distribution of each document. And constructing a clustering tree based on the topic semantic distance, screening the optimal division, and then combining with the hierarchical structure to generate a hierarchical intention result. By adopting the method, the automatic and hierarchical intention recognition can be effectively realized, and the recognition result fits the domain business logic.

The application discloses a context scene data recognition method and device, and the method comprises the steps: inputting the preceding data and the following data in the context text data into a single sentence topic model respectively to obtain preceding topic representation and following topic representation; inputting the context text data into a context topic model to obtain context topic representation; calculating the similarity of any two of the preceding topic representation, the following topic representation and the context topic representation; judging whether the similarity meets a threshold condition, and if yes, judging the preceding data and the following data as context scene data. The context scene data recognition method improves the sufficiency of context scene data discovery through two rounds of context data discovery process, and reduces the manpower, time and cost consumed in the context scene data labeling process.

This invention relates to the field of data processing, and more particularly to an information retrieval method for a smart city system. The method includes: acquiring historical data blocks from a business system and user interaction session data; segmenting the data to obtain a set of original words and words to be processed; calculating the topic probabilities and topic relevance of the original words and historical data blocks using a topic model; filtering candidate words and calculating their importance; generating extended words and historically perceived words, concatenating them into a dynamic sequence; calculating the semantic similarity between the sequence and historical data blocks; and sorting and displaying a preset number of data blocks to complete the retrieval. This invention calculates the topic probabilities and corresponding topic relevance of the original words and historical data blocks using a topic model, allowing candidate words to inherit the topic attributes of the original words. It also combines JS divergence metrics to quantify the consistency of the topic probability distribution between candidate words and original words to filter extended words, thus avoiding the risk of topic deviation from semantic expansion at the source and improving retrieval matching accuracy.

The invention belongs to the technical field of livelihood service intelligent analysis, and provides a multi-service scene topic model dynamic recommendation method and system, and the technical scheme is as follows: obtaining a service scene feature vector based on obtained historical service data; quantizing the multi-source demand of the livelihood service multi-service scene to obtain a demand quantization vector; on the basis of the demand quantization vector, capturing a dependency relationship between demand information, learning deep semantic information, and obtaining a demand representation vector; designing a dynamic adaptation mechanism based on the acquired demand representation vector and the business scene feature vector, and recommending an algorithm matched with the current business scene; based on a recommendation algorithm, a business topic model is constructed, a performance index vector of the topic model is calculated, based on the difference between the performance index vector of the topic model and a demand representation vector, reinforcement learning is adopted to optimize the topic model to obtain an optimized topic model, and the optimized topic model is finally applied to downstream tasks such as service recommendation and demand analysis. Therefore, the intelligent level and the precision of livelihood service analysis are remarkably improved.

The invention relates to the technical field of data mining, and discloses a semantic analysis-combined data mining method and system. The method comprises the steps of obtaining a document instance set and performing linguistic processing to generate annotated text data; constructing a semantic feature space based on the annotation data, and representing the document as a feature vector; learning semantic topic distribution by adopting a topic modeling technology to obtain an initial topic model; multiple training iterations are executed, and in each iteration, the subordination relation between the document and the subject is evaluated again, and subject term distribution is updated; tracking document membership change of the theme in an iteration process, and marking the theme as a to-be-adjusted theme when the change exceeds a threshold value; analyzing a historical behavior mode of the to-be-adjusted theme, and calculating a compatibility index of the to-be-adjusted theme and the current model; and revising theme parameters of the theme model according to the indexes. According to the method, semantic evolution can be dynamically captured, and the accuracy and semantic consistency of the topic model are improved.

A long text official document key information extraction agent method based on a large model relates to the technical field of artificial intelligence, and comprises the following steps: collecting original official document long text data; performing structured analysis and hierarchical coding on the original official document text data; performing dynamic semantic fragment division based on topic model guidance; constructing a long text official document key information extraction model based on a bidirectional semantic encoder; model training and trainable parameter updating; extracting key information of the long text official document; and constructing a long text official document key information extraction agent based on the large model. According to the method, a multi-dimensional structure coding method fusing document levels, formats and parts is adopted, and field priori knowledge is converted into computable vectors; a dynamic programming text segmentation algorithm based on theme consistency and semantic closeness scoring is adopted, so that the integrity of long text semantic fragments is guaranteed; a structure-guided cross-segment attention mechanism is introduced into a Transform encoder, and accurate modeling of long-distance semantic dependency is realized through structural similarity constraints.

The present invention provides an analysis method, apparatus, and device for investment decision-making, and a storage medium. The method includes: extracting entities from news data by a custom-trained topic model, and creating a finite state machine to store entities identified from text and relationships between the entities; invoking a custom-trained BERT model to classify the sentiment of the text to generate sentiment types; constructing a graph structure based on the entities and the relationships between the entities, and storing optimized graph structure in a graph database; and in response to a query request from a user being detected, invoking the graph structure associated with the query request and the sentiment type in the graph database for analysis, and generating an analysis result. The present invention solves the problem that the prior art cannot provide analysis data to investors based on intricate financial news.

The application discloses a credit risk monitoring method for discredited subject behavior, comprising the following steps: obtaining discredited event data; obtaining basic types of discredited events according to the clustering of the discredited event data; determining the category label and keyword corpus of discredited public opinion according to the basic types of discredited events; training an LDA topic model by using the keywords in the keyword corpus; processing the keywords in the keyword corpus and storing them in a database; cleaning the discredited public opinion information in the database; performing natural language processing on the cleaned discredited public opinion information to generate intelligent labels. The application applies the constructed credit keyword library and machine learning crawler to intelligently crawl relevant discredited public opinion information, thereby improving the precision and breadth of the discredited public opinion information crawling. The data quality platform is used to clean the public opinion information, and the NLP text processing technology is used to generate intelligent labels required by various public opinions from the cleaned information, so that the discredited public opinion information can be quickly and accurately analyzed.

Embodiments address various deficiencies and provide technical advantages with respect to evaluating performance of topic models, particularly LLMs that perform topic modeling. Embodiments utilize a second LLM for evaluation, where the LLM is specially configured utilizing a particular evaluation rubric and domain-specific contextual data that enables accurate and automatic use of the configured LLM for topic model evaluation within particular domains.

The application relates to a deep learning-based network public opinion evolution simulation method and system, and relates to the technical field of text sentiment analysis in natural language processing. The pre-training task of a BERT model is improved, and a deep pre-training task is stacked on the basis, and a LDA topic model is also deeply fused to realize fine-grained public opinion simulation analysis in a topic perspective. A to-be-classified corpus set TC is input into a sentiment classification fine-tuning model to obtain a sentiment classification result, the to-be-classified corpus set TC is input into a BERT model for vectorization processing, the vectorized to-be-classified corpus set TC is input into a LDA topic model for iterative calculation to obtain a document distribution, then the sentiment classification result and the document distribution are fused to obtain a sentiment tendency distribution, the sentiment tendency distribution is divided according to time sequence to obtain a sentiment time sequence simulation result, and therefore more fine-grained and accurate text topic clustering and public opinion evolution simulation results are obtained.

Certain aspects of the present disclosure provide techniques for recommending trip purposes to users of an application. Embodiments include receiving labeled travel data from the application running on a remote device including a plurality of trip purposes. Embodiments include building a topic model representing words associated with a plurality of topics. Embodiments include training a topic prediction model, using the plurality of topics and one or more features derived from each of the plurality of trip records, to output a topic based on an input trip record. Embodiments include training a purpose prediction model, using the topic model and the plurality of trip purposes, to output a trip purpose based on an input topic. The trip purpose may be recommended to a user via a user interface of the application running on the remote device.

The application discloses a text correction-based topic modeling enhancement method and device, which comprises the following steps: extracting time distribution features of words, measuring the similarity between words according to the time distribution features, calculating the time expression ability index of the words, and obtaining a time special vocabulary set; extracting spatial distribution features of the words, measuring the spatial distribution difference of the words according to the spatial distribution features, generating a word distance matrix, performing vocabulary clustering based on the word distance matrix, and obtaining a spatial special vocabulary set; fusing point of interest data, extracting semantic distribution features of the words according to the point of interest data, calculating the semantic expression ability index of the words, and obtaining a semantic special vocabulary set; and modifying the text content based on the time special vocabulary set, the spatial special vocabulary set and the semantic special vocabulary set, to obtain an enhanced topic model; the application can extract spatiotemporal semantic special vocabularies and calculate expression ability indexes, and further correct the text to enhance topic modeling.

The application discloses a hot event controversial analysis method based on a heterogeneous symbolic attribute network, and relates to the technical field of data analysis.The analysis method comprises the following steps: obtaining an original data set from a social network, wherein the original data set contains attribute information; performing a data preprocessing operation, performing text summary processing on all comments of micro blogs, discovering event topics through a topic model, and completing construction of a heterogeneous graph; fusing the attribute information with text information and structure information; performing sentiment analysis according to comment information of users, constructing a symbolic network between users, and completing self-supervised training of the users under the heterogeneous network and the symbolic network; and measuring community controversy according to community differences, intermediary centrality and user propagation representation.The application predicts controversy from different angles based on community discovery results, and analyzes hot events through development of an online service platform, thereby providing convenience for users.

The application discloses a public opinion response effect measurement method based on theme migration and emotion change recognition. The method takes relevant microblog hot search blog posts and comment information of an event as basic data, performs theme analysis on the microblog text based on an LDA theme model, calculates the emotion value of the comment content according to a Bi-LSTM model, constructs a measurement model of the response effect under a sudden negative public opinion, and evaluates the response effect based on the recognition results of theme migration and emotion change. The application has the advantages of easy practice, scientific index, strong pertinence and the like, can be used for measuring the response effect in a sudden negative public opinion, evaluating the intervention effect on the evolution of the negative public opinion, analyzing the advantages and disadvantages of the response measures, and providing optimization strategies for optimizing the negative public opinion management work.

This invention discloses an intelligent alarm analysis method based on topic models and heterogeneous graphs. The method includes using a semantically related topic model to expand the topic features of alarm data, constructing a heterogeneous graph to model and extract potential semantic association features between different alarm information streams, using a neural network model to extract and process features from the alarm data, extracting text context sequence information features contained in the alarm text information, and concatenating and fusing the extracted potential semantic association features between different alarm information and the contained text context sequence information features. These features are then introduced into a self-attention model to highlight relevant features, and finally input into a fully connected layer and a Softmax layer for prediction output. This intelligent alarm analysis method based on topic models and heterogeneous graphs improves the accuracy and efficiency of intelligent alarm analysis.