Non-intrusive load monitoring could help ASHP load data collection for its benefits of lower cost and easier installation. This paper proposed a load dactylogram extracting method of air source heat pump (ASHP) based on load event monitoring. By capturing transit events, the key parameters ?T and ?P are obtained and transit events are classified, according to which ASHP starting state is recognized. Detecting events through adaptive learning, the load dactylogram library is formed by clustering identified load events. Accordingly, ASHP load can be identified and its electric quantity can be calculated. The running result shows that the start-stop-times of ASHP are correct and the accuracy of power consumption is above 84%.