Position recall method and device based on large language model and electronic equipment

Abstract

The invention discloses a position recall method and device based on a large language model and electronic equipment. The method comprises the following steps: inputting a first instruction fine tuning template filled with resume information and position information of historical delivery positions into a large language model so as to perform fine tuning on the large language model; inputting the position information of a plurality of currently recruitment positions into the fine-tuned large language model, wherein the fine-tuned large language model is used for encoding the position information of the plurality of positions to obtain a plurality of position vectors; inputting the resume information of the target job seeker into a fine-tuned large language model which is used for converting the resume information of the target job seeker into a target resume vector, calculating the similarity between the target resume vector and each position vector, and screening out K position vectors with relatively high similarity; carrying out secondary recall rearrangement on the K position vectors; and ranking the positions corresponding to the plurality of rearranged position vectors according to the similarity to obtain a position recall result. According to the invention, the position recall accuracy and efficiency can be improved.

Images