2 results about "Risk category" patented technology

The invention provides a risk text extraction method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps of performing feature extraction on a to-be-processed text containing a plurality of text segments through a feature extraction layer of a risk classification model to obtain a feature value corresponding to each text segment, wherein the risk classification model is used for performing classification of at least two risk categories on a to-be-processed text; through a prediction layer of the risk classification model, based on the feature values corresponding to the text segments, determining association degrees between the corresponding text segments and the risk categories; and respectively selecting the text fragments of which the association degree with each risk category meets an association degree condition from the plurality of text fragments, and taking the selected text fragments as risk texts extracted from the to-be-processed text. Through the method and the device, the instantaneity of risk text extraction can be improved.

The invention provides a risk control method and system for bank account opening, and relates to the technical field of financial data processing, and the method comprises the steps: carrying out the classification of a customer set of a bank, and obtaining a plurality of customer categories; determining a risk category vector of the customer category; determining a risk category vector of each biological feature recognition mode; determining a biological feature recognition mode corresponding to the customer category; determining an abnormal distance vector corresponding to each account opening data; clustering the historical account opening data to obtain a plurality of historical account opening data subsets; determining a threshold value of the historical account opening data subset corresponding to each biological feature recognition mode; when a new customer opens an account in a bank, determining a customer category to which the new customer belongs and a corresponding abnormal distance vector according to customer information filled by the new customer; and determining a biological feature recognition mode and a corresponding threshold value when the new customer opens the account in the bank, and performing identity verification on the new customer by using the biological feature recognition mode and the corresponding threshold value.