6 results about "Event mining" patented technology

The application discloses a hotspot event mining method, system, device and storage medium, wherein the method comprises the following steps: obtaining a government work order set of an event to be mined; determining a first work order abstract of each sub government work order according to the government work order set; determining a first semantic similarity according to the first work order abstract and a sentence coding model; the first semantic similarity is used to represent the semantic similarity of any two sub government work orders corresponding to the first work order abstract; determining a first entity similarity according to the government work order set; the first entity similarity is used to represent the entity similarity of government entities corresponding to any two sub government work orders; determining a target similarity according to the first semantic similarity and the first entity similarity; performing clustering processing on all sub government work orders in the government work order set according to the target similarity to determine a hotspot event. The method can improve the accuracy of hotspot event mining. The application can be widely applied in the technical field of data processing.

The invention relates to a perioperative period operation abnormal event mining, analyzing and labeling system and method, and belongs to the field of medical big data. The system comprises a data sampling module, an abstract syntax tree extraction module, a rule embedding module, a rule judgment module, a time sequence feature extraction module, a large model verification module, a frequency domain model verification module and a conflict resolution module. The method comprises the following steps: S1, formulating an exception rule; s2, establishing an abstract syntax tree; s3, collecting time sequence data of the perioperative period; s4, traversing the abstract syntax tree to judge an abnormal result; s5, extracting dynamic features; s6, analyzing an abnormal result by using a large model; s7, when the result conflicts, executing the step S8, and otherwise, marking and executing the step S9; s8, calling a frequency domain model to verify an abnormal result and labeling the abnormal result; and S9, repeating the steps S4-S8 until the labeling is completed. According to the method, accurate identification and labeling of the abnormal classification of the perioperative time series data can be realized, risk early warning is facilitated, and postoperative recovery analysis is facilitated.

Procedure (100,500) for detecting an event from a social stream, wherein the procedure (100,500) comprises the steps of one: Receiving a social stream from a social network, where the social stream contains at least one object; and where the object contains a text, sender information of the text and recipient information of the text (101,510); Assigning the object to a cluster based on a similarity value between the object and the cluster (102,520); Monitoring changes in at least one of the clusters (103,540); and Triggering an alarm when changes in at least one of the clusters exceed a first threshold (104,550), where at least one of the steps is performed using a computer unit, wherein the procedure further includes maintaining changes in the clusters as history data of the social stream (530), wherein in the maintenance step a sketch-supported technique is used, and wherein the sketch-supported technique is used to estimate a structural similarity value between the object and the clusters.

The invention relates to the technical field of computers, and discloses an intelligent analysis system and method for mass data, and the system comprises a threshold module which is used for obtaining text information of a current database, carrying out the clustering of all data according to the content information of the text information, and determining an abnormal parameter threshold according to a clustering result; the mining module is used for acquiring a historical data exception event, mining a strong association rule of the historical data exception event, and determining an exception parameter of the current data according to the strong association rule of the historical data exception event; and the early warning module is used for determining abnormal data in the database according to the abnormal parameters and the abnormal data threshold. The anomaly detection efficiency of the database can be effectively improved, and the abnormal data can be rapidly and accurately detected.

This invention discloses a method and system for regional and national hotspot mining and briefing generation based on complex networks and large language models, belonging to the field of natural language processing and public opinion analysis technology. The method includes: collecting, cleaning, deduplicating, and sorting multilingual public opinion data; constructing a news dissemination network based on temporal semantic similarity and using connected component algorithms to discover hotspot communities; performing quality assessment and topic consistency optimization on the communities, and selecting representative texts using an improved PageRank algorithm; and automatically generating structured briefings including event summaries, knowledge graphs, news rewriting and commentary, and hotspot extensions by combining preset prompt templates with a generative large language model. This invention can effectively capture the dynamic evolution of multilingual public opinion, improve the accuracy and completeness of hotspot event mining, achieve full automation from data collection to report generation, and significantly improve the efficiency and depth of regional and national public opinion analysis.

The invention provides a cultural heritage digital reconstruction system and method based on space narration, and the system comprises a multi-source data collection module which is used for collecting the data of a place where cultural heritage is located; the preprocessing module is used for preprocessing the collected data; the knowledge graph construction module is used for carrying out semantic segmentation on the preprocessed data by utilizing a machine learning algorithm, carrying out classified labeling on different objects or parts, and constructing a knowledge graph of the cultural heritage according to a semantic labeling result; the spatial narrative modeling module is used for performing place analysis, event mining and path planning respectively, constructing a spatial narrative three-dimensional model of the cultural heritage by adopting polygon modeling, and adding a semantic tag for each component in the three-dimensional model; and the dynamic interaction module interacts with the spatial narrative modeling module through gestures by utilizing a gesture recognition technology, breaks through the limitation that only morphological records are concerned in traditional heritage digitization, and introduces spatial narrative into digital modeling and virtual scene design, so that the heritage becomes a lecture space.