4 results about "Abnormal Indicator" patented technology

The invention provides a client exception collecting and processing method and system based on a large model, and the processing method comprises the following steps: obtaining exception event data when a client runs abnormally, the exception event data comprising an exception index and a user operation process; classifying the abnormal event data of the same type to obtain an abnormal event group; analyzing the abnormal event data in the abnormal event group by using a large language model to obtain a code defect root cause; generating an exception handling solution based on the code defect root cause by using the large language model; and performing exception handling according to the exception handling solution.

A vehicle information security identification method and device based on a behavior knowledge graph, the method comprising: determining a behavior knowledge graph; receiving a node abnormal event association graph from a vehicle end, the node abnormal event association graph being determined by the vehicle end through association of abnormal indicators; adding suspicious edge relationships in the abnormal event association graph to the behavior knowledge graph as preset low-confidence abnormal relationships to obtain an updated behavior knowledge graph; and based on the updated behavior knowledge graph, using a graph reasoning algorithm and a preset identification rule to analyze the connectivity of the relationships between nodes, and identifying a target attack chain that matches a known attack mode or is similar to the known attack mode. Thus, instead of simple threshold comparison, the preset identification rule analysis and the graph reasoning algorithm intelligent reasoning and automatic determination of complex attacks that match a known attack mode or are similar to the known attack mode can effectively identify complex attacks implemented across different entities or functional subsystems.

The application discloses a blockchain intelligent supervision system and method based on on-chain and off-chain data fusion, relates to the technical field of blockchains, and constructs an index linked list of cross-chain events; generates a unified cross-node time sequence data sequence, and matches the index linked list of cross-chain events to generate a structured event vector; based on cross-node log data and an event behavior feature vector, a supply chain link deviation and an abnormal index are calculated, key links such as transportation timeliness, inventory fluctuation and quality parameters are subjected to abnormal feature extraction and quantitative description; a behavior deviation feature sequence is formed through threshold value judgment and statistical analysis; based on the behavior deviation feature sequence, the confidence of a behavior feature is calculated, and combined with cross-chain correlation indexes, abnormal event tracing is realized, the supply chain full-link traceability, data credibility and intelligent abnormal identification are realized, and the safety is significantly improved.

This application discloses a data source management method, apparatus, device, and storage medium, relating to the field of data processing technology. The data source management method includes: monitoring the data source interface connected to at least one data source in a data source management platform, and storing the obtained monitoring data in the data source interface storage area; determining all indicator data within the target data source corresponding to the query instruction based on the monitoring data, and storing the indicator data in an abnormal indicator storage area, the indicator data including successful query data and report detail data; determining the indicator result based on the query instruction and the indicator data in the abnormal indicator storage area, and storing the indicator result in the data source indicator result storage area; detecting whether the indicator result in the data source indicator result storage area matches the abnormal rules in the abnormal rule storage area; if a matching abnormal rule exists, determining that there is an abnormal event in the target data source, and outputting an abnormal alarm message. This application achieves effective supervision of data sources.