DETECTIVE METHOD AND SYSTEM FOR ACTIVITY-OR-BEHAVIOR MODEL CONSTRUCTION AND AUTOMATIC DETECTION OF THE ABNORMAL ACTIVITIES OR BEHAVIORS OF A SUBJECT SYSTEM WITHOUT REQUIRING PRIOR DOMAIN KNOWLEDGE

• Format: Patent
• Language: English
• Published: 28.12.2017

According to one embodiment of the invention, a detective method, applied in a detective system comprising a activity-or-behavior model constructor, for activity-or-behavior model construction and automatic detection of activities of a subject system, comprising steps of: using an unsupervised machine learning technique to preprocess and analyze raw sensor data obtained from the monitored subject system to generate post data; with the post data as input, using a Natural Language Processing technique (NLP) to discover the activities or behaviors performed by the subject system; and with output data from the NLP technique as input, using a surprised machine learning technique to build an activity-or-behavior model for predicting the future behaviors of the subject system and automatically detecting abnormal activities or behaviors of the subject system; wherein the activity-or-behavior model is capable to handle multidimensional sensor data input from a plurality of sensor data streams and incorporate the sensor data values and a selected temporal information about at least one sensor data stream and between different sensor data streams.