1 results about "Preference behavior" patented technology

The present application relates to the technical field of enterprise training management and personalized recommendation, in particular, the present application relates to a talent performance dynamic evaluation and training resource intelligent pushing method, the present application collects staff daily task data and active retrieval text and time stamp, adopts the dynamic model of the time decay coefficient of the forgetting curve to calculate the current ability evaluation of each skill, and generates the ability gap label set by comparing with the post benchmark, obtains the intention feature by encoding the semantic of the retrieval text, combines the interactive operation depth to calculate the active inclination intensity index, generates the learning time period preference vector according to the retrieval time period distribution, constitutes the active learning preference behavior fingerprint, matches the candidate resource by the gap label set and determines the content matching degree, weights and fuses the content matching degree, the active inclination intensity index and the time period coincidence degree of the decision time period and the preference vector, obtains the pushing priority evaluation value, reorders the resource after the value, and pushes the resource, realizes the fusion of the ability dynamic evaluation and the learning preference.