4 results about "Behavioural state" patented technology

The invention relates to a classroom abnormal behavior intelligent detection and teaching intervention system, and the system comprises a data collection layer which is used for obtaining multi-modal data in a student classroom; the multi-modal data comprises a student classroom performance image set and sound signals of corresponding time; the data standardization layer is used for carrying out preprocessing and time synchronization on the multi-modal data to obtain standardized multi-modal data; the abnormal behavior detection layer is used for inputting the standardized multi-modal data into a behavior state classification model to obtain a behavior classification result; the behavior classification result comprises a behavior type, behavior duration and an intervention level label; the intervention decision-making layer is used for generating a teaching intervention instruction by utilizing the behavior classification result based on intervention decision-making logic; the teaching intervention instruction comprises a system prompting instruction and a teacher intervention reminding instruction. By adopting the system, behaviors of students can be identified and classified, targeted intervention is performed, the classroom teaching efficiency is improved, and the system assists in reminding the students to quickly return to a normal learning state.

This application provides a game behavior planning method, apparatus, computer device, and medium. The method includes: acquiring the current state information and target task planning of a non-player character in the game, wherein the current state information includes the current behavior and the current behavior state, and the target task planning includes the target behavior state; quantifying the current behavior state and the target behavior state, and calculating the distance between the quantified current behavior state and the target behavior state; acquiring behavior route information from an action library based on the distance, using the current behavior as a reference; and performing behavior planning on the non-player character based on the behavior route information, so that the non-player character completes the target task planning. The method proposed in this application can acquire the behavior route of the non-player character according to a given target task planning, and then control it to complete the target planning. This method improves the development speed of the non-player character, and the behavior range of the non-player character is wide, which can improve the player's user experience.

The invention discloses a student management system and method based on classroom behavior recognition, and belongs to the field of education and teaching, and the system obtains classroom video data based on the multi-angle visual collection and microphone array signal collection technology, obtains classroom audio signal data at the same time, and achieves the student management based on target detection, key point posture recognition and time sequence behavior recognition. The method comprises the steps of extracting spatial trajectory and behavior state information of students in a classroom, obtaining audio feature parameters of student emotion activeness and classroom participation degree based on voice signal framing analysis, voice signal feature extraction and a deep emotion recognition network, and obtaining association between the students and teaching based on audio and video feature fusion and a student behavior right reconstruction model. Student groups are subjected to grouping analysis through a clustering algorithm, a teaching mode is recommended in a personalized manner based on attraction characteristics, and real-time evaluation and intelligent improvement of classroom teaching quality are realized.