Abstract: An inference acceleration method relating to artificial intelligence technical fields such as a large model, deep learning, and natural language processing is provided. The inference acceleration method for large models includes: after inputting a source text to be processed into a target large model, obtaining a top-layer hidden state of the target large model for predicting a next token; obtaining action decision information corresponding to the next token according to the top-layer hidden state; in response to determining that the action decision information is a copy action, obtaining a text copy interval corresponding to the next token according to the top-layer hidden state; copying text in the source text to be processed that is located within the text copy interval, and using a copy result as the next token.

Abstract: A continuous logging method and device is provide, where the method includes obtaining drilling fragment samples and full-diameter core samples, and screening out target rock cuttings from the drilling fragment samples; performing a micro-indentation experiment on the target rock cuttings to obtain a static parameter thereof; performing a triaxial compression experiment on the full-diameter core samples to obtain a dynamic parameter and a static parameter thereof; determining a first correspondence between the static parameter of the target rock cuttings and the dynamic parameter of the full-diameter core samples; determining a second correspondence between logging data and the static parameter of the target rock cuttings based on the first correspondence; and drawing a formation mechanical property profile based on the second correspondence. The method solves the problem of conventional methods which cannot draw a continuous and complete profile of the mechanical property of the whole well section.

Abstract: A continuous logging method and device is provide, where the method includes obtaining drilling fragment samples and full-diameter core samples, and screening out target rock cuttings from the drilling fragment samples; performing a micro-indentation experiment on the target rock cuttings to obtain a static parameter thereof; performing a triaxial compression experiment on the full-diameter core samples to obtain a dynamic parameter and a static parameter thereof; determining a first correspondence between the static parameter of the target rock cuttings and the dynamic parameter of the full-diameter core samples; determining a second correspondence between logging data and the static parameter of the target rock cuttings based on the first correspondence; and drawing a formation mechanical property profile based on the second correspondence. The method solves the problem of conventional methods which cannot draw a continuous and complete profile of the mechanical property of the whole well section.