CN-122024542-A - Education scene digital robot interaction system based on multi-mode dynamic perception

Abstract

The invention relates to the field of intelligent robots, in particular to an education scene digital robot interaction system based on multi-mode dynamic perception, which comprises a teaching content storage module, a teaching content analysis module and a teaching process feedback module, wherein the teaching content storage module is used for storing corresponding teaching courses, the teaching content analysis module is used for splitting and re-associating teaching videos, and the teaching process feedback module is used for collecting feedback data in a teaching process and calling or modifying a teaching video clip to be played. Through adopting above-mentioned technical scheme, through the facial expression of student in the teaching process, pupil focus data of eyes and the dialect word degree adjustment teaching content and the progress of giving lessons in the inquiry, make teaching robot can produce timely in depth interaction with the student under teaching system's help through such a mode, avoid the student to compare the exclusive sense of principal department.

Inventors

• LI HONGPING

Assignees

• 上海豪派数码科技有限公司

Dates

Publication Date

20260512

Application Date

20260316

Claims (8)

1. 1. An educational scene digital robot interactive system based on multi-modal dynamic perception, characterized by comprising: the teaching content storage module is used for storing corresponding teaching courses; The teaching content analysis module is used for splitting and re-associating the teaching videos; and the teaching process feedback module is used for collecting feedback data in the teaching process and calling or modifying the to-be-played teaching video clip.
2. 2. The education scene digital robot interaction system based on multi-mode dynamic perception according to claim 1, wherein the teaching content analysis module comprises a splitting unit, an analysis unit and a re-association unit, the splitting unit is used for splitting according to chapter content of a course file, the analysis unit is used for reading chapter content part keywords of the course file, and the re-association unit is used for sequentially arranging according to the extracted keyword relevance.
3. 3. The system for digital robot interaction of educational scenario based on multi-modal dynamic perception according to claim 2, wherein the reassociation unit is provided with an iteration subunit, the iteration subunit is used for collecting the questions sent by the user when learning the course of the chapter, and associating the chapter content capable of solving the questions with the chapter with the number of times of the questions.
4. 4. The education scene digital robot interactive system based on multi-mode dynamic perception according to claim 1, wherein the teaching process feedback module comprises a pupil analysis unit, a facial expression analysis unit, a word analysis unit and a selection analysis unit, wherein the selection analysis unit is used for generating whether to continue playing, whether to skip three options, and when the selection is selected, the skipped course carries out playing learning when the user learns keywords of the chapter triggered by other courses, after the user selects the selection needing to accelerate playing, the pupil analysis unit, the facial expression analysis unit and the word analysis unit judge the acceptance degree of the user, if the acceptance degree is lower than a set value, the playing is stopped, if the acceptance degree is higher than the set value, the playing is continued, and if the selection needs to continue playing, the user needs to judge whether to continue playing by learning duration, and when the single continuous learning duration exceeds the set value, the playing is stopped automatically.
5. 5. The system for digital robot interaction in educational scenes based on multi-modal dynamic perception of claim 4, wherein the through-hole analysis unit is configured to determine whether the user's line of sight looks at the display screen, if so, make facial expression determination, if not, send a prompt, and simultaneously stop playing temporarily, avoiding invalid playing.
6. 6. The system for digital robot interaction in educational scenes based on multi-modal dynamic perception according to claim 4, wherein the facial expression analysis unit comprehensively judges whether wrinkles exist in the center of forehead and radian of mouth angle or not through the bending angle of eye corners.
7. 7. The system for digital robot interaction in educational scenes based on multi-modal dynamic perception of claim 4, wherein said means for analyzing word of speech is configured to perform status judgment based on word of speech interacted by user, and is divided into a restless status and an acceptable status, and stop playing when in the restless status.
8. 8. The system for digital robot interaction in educational scenes based on multi-modal dynamic perception according to claim 4, wherein the facial expression judging unit is used for classifying the facial surface of the user into five states of confusion, interest, impatience, gas and happiness according to the micro-expression judging information, and stopping the teaching progress when the impatience state occurs.

Description

Education scene digital robot interaction system based on multi-mode dynamic perception Technical Field The invention relates to the field of intelligent robots, in particular to an education scene digital robot interaction system based on multi-mode dynamic perception. Background Learning generally refers to the process of obtaining knowledge or skills through reading, listening, speaking, thinking, research, practice, and the like. Education is a teaching of thinking, and the thinking modes of different people are generally different, so that education should be different from person to person, and an education method which is most suitable for individuals is found from the differences of different individuals. The students are learning knowledge, and the teacher needs to teach the students of one class at the same time, so the methods taught by the teacher are generally indiscriminate, and the students cannot absorb the knowledge taught by the teacher well. The family teacher is also a way to cultivate the individual thinking of students, but the family teacher cannot guarantee to grow along with the students, if the family teacher is replaced, the teacher and the students are required to be familiar again, and meanwhile, the way generally consumes more manpower and financial resources, and not all students can have the ability to ask the family teacher for the students. With the development of scientific technology, robot technology is mature more and more, and home robots are a member of robot families, and the development speed is rapid. The existing floor sweeping robots, old man nursing robots, infant early education accompanying robots and entertainment robots in the market at present belong to household robots, wherein the infant early education accompanying robots are generally aimed at children of 0-12 years old, and are used for enlightenment education and safety accompanying of infants. However, as children age and learning difficulty increase, such robots often cannot continue to play a role in helping children learn. With the development of scientific technology, robot technology is mature more and more, and home robots are a member of robot families, and the development speed is rapid. The existing floor sweeping robots, old man nursing robots, infant early education accompanying robots and entertainment robots in the market at present belong to household robots, wherein the infant early education accompanying robots are generally aimed at children of 0-12 years old, and are used for enlightenment education and safety accompanying of infants. However, as children age and learning difficulty increase, such robots often cannot continue to play a role in helping children learn. Disclosure of Invention The invention aims to provide an education scene digital robot interaction system based on multi-mode dynamic perception, which solves the problems existing in the prior art. The technical aim of the invention is realized by the following technical scheme: An educational scene digital robot interactive system based on multi-modal dynamic perception, comprising: the teaching content storage module is used for storing corresponding teaching courses; The teaching content analysis module is used for splitting and re-associating the teaching videos; And the teaching process feedback module is used for collecting feedback data in the teaching process and calling or modifying the to-be-played teaching video clip. Through adopting above-mentioned technical scheme, it is noted here that the teaching content refers to the audio-video file of all courses from enlightenment to the senior stage, the teaching content that stores need split according to corresponding age bracket earlier, then carry out the dismantlement back reassociation according to the chapter content of each course, this step is the front-back association that is used for reinforcing corresponding problem, avoid the acquisition content of fragmentation to be irrelevant around, be used for through the mode of associative memory reinforcing student to the understanding and the memory of course, and through the facial expression of student in the teaching process, pupil focus data of eyes and the degree adjustment of the spirit word light and heavy degree in asking teaching content and teaching progress, through this mode makes teaching robot can produce timely deep interdynamic with the student under teaching system's help, avoid the student to take care the exclusive sense of department. In a further embodiment, the teaching content analysis module comprises a splitting unit, an analysis unit and a re-association unit, wherein the splitting unit is used for splitting according to chapter content of the course file, the analysis unit is used for reading chapter content part keywords of the course file, and the re-association unit is used for sequentially arranging according to the extracted keyword relevance. By adopting the technical scheme,