CN-122018668-A - Teaching data processing method and device, storage medium and electronic equipment

CN122018668ACN 122018668 ACN122018668 ACN 122018668ACN-122018668-A

Abstract

The embodiment of the specification discloses a teaching data processing method, a device, a storage medium and electronic equipment, wherein the method comprises the steps of detecting a hand-drawing action of a host user in a teaching conference scene, collecting hand-drawing action data corresponding to the hand-drawing action, acquiring reference teaching scene information, carrying out hand-drawing content identification based on the hand-drawing action data and the reference teaching scene information to obtain target hand-drawing content, and synchronizing the target hand-drawing content to a participant user side so as to enable the participant user side to display the target hand-drawing content.

Inventors

LIU PENGKUN
LI MIN
LIU YANQING
LIU XIANQI
Cui ao

Assignees

北京三六零智领科技有限公司

Dates

Publication Date: 20260512
Application Date: 20241108

Claims (10)

1. A method of teaching data processing, the method comprising: In a teaching conference scene, detecting a hand-drawing action of a main speaking user, collecting hand-drawing action data corresponding to the hand-drawing action and obtaining reference teaching scene information; Performing hand-drawing content identification based on the hand-drawing action data and reference teaching scene information to obtain target hand-drawing content; And synchronizing the target hand-drawn content to the participant user side so that the participant user side displays the target hand-drawn content.
2. The method of claim 1, wherein the obtaining the reference teaching context information comprises: extracting hand-drawing action change characteristics of the hand-drawing action data, and determining target hand-drawing recognition difficulty aiming at a hand-drawing recognition model based on the hand-drawing action change characteristics; And determining a target auxiliary identification data combination based on the target hand-drawing identification difficulty, and acquiring reference teaching scene information corresponding to the target auxiliary identification data combination.
3. The method of claim 2, wherein the determining auxiliary recognition data combinations based on the target hand-drawn recognition difficulty comprises: Inquiring auxiliary recognition data combinations corresponding to the target hand-drawing recognition difficulty in a preset difficulty combination mapping relation, wherein the preset difficulty combination mapping relation comprises a plurality of auxiliary recognition data combinations corresponding to the hand-drawing recognition difficulty.
4. The method of claim 1, wherein the identifying the hand-drawn content based on the hand-drawn motion data and the reference teaching context information to obtain the target hand-drawn content comprises: Determining a hand-drawn recognition task prompt for the hand-drawn action data and the reference teaching scenario information; Inputting the hand-drawing action data, the reference teaching scene information and the hand-drawing recognition task prompt word into a hand-drawing recognition large model, and carrying out hand-drawing content recognition through the hand-drawing recognition large model to obtain target hand-drawing content.
5. The method of claim 4, wherein the performing the hand-drawn content recognition by the hand-drawn recognition large model to obtain the target hand-drawn content comprises: Performing action recognition on the hand-drawing action data through the hand-drawing recognition large model to obtain initial hand-drawing content, determining hand-drawing content description information of the initial hand-drawing content, and performing hand-drawing associated information mining processing on the reference teaching scene information based on the hand-drawing content description information to obtain teaching demonstration associated information; And carrying out hand-drawing content adjustment on the initial hand-drawing content based on the teaching demonstration association information to obtain target hand-drawing content.
6. The method of claim 5, wherein performing the hand-drawn content adjustment on the initial hand-drawn content based on the instructional presentation related information to obtain a target hand-drawn content comprises: determining a plurality of teaching demonstration related contents from the teaching demonstration related information; Determining target teaching presentation associated content matching the initial hand-drawn content from the plurality of teaching presentation associated content; and carrying out content correction processing on the initial hand-drawn content based on the target teaching demonstration related content to obtain target hand-drawn content.
7. The method of claim 6, wherein performing content modification processing on the initial hand-drawn content based on the target teaching presentation associated content to obtain target hand-drawn content comprises: determining content structure information and knowledge point standard content in the target teaching demonstration related content, and performing structural optimization on the initial hand-drawn content based on the content structure information; Performing content detail optimization on the first hand-drawn content based on the knowledge point standard content to obtain second hand-drawn content; and performing visual display enhancement processing based on the second hand-drawn content to obtain target hand-drawn content.
8. A teaching data processing apparatus, said apparatus comprising: The data acquisition module is used for detecting the hand-drawing action of the main speaking user in a teaching conference scene, acquiring hand-drawing action data corresponding to the hand-drawing action and acquiring reference teaching scene information; the content identification module is used for carrying out hand-drawing content identification based on the hand-drawing action data and the reference teaching scene information to obtain target hand-drawing content; And the content synchronization module is used for synchronizing the target hand-drawn content to the participant user side so as to enable the participant user side to display the target hand-drawn content.
9. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any one of claims 1 to 7.
10. An electronic device comprising a processor and a memory, wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-7.

Description

Teaching data processing method and device, storage medium and electronic equipment Technical Field The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for processing teaching data, a storage medium, and an electronic device. Background With the rapid development of computer technology, remote video conference teaching is becoming popular. However, in video teaching, hand-drawn content (such as formulas, graphics, structural drawings, etc.) as a presenter-teacher becomes an important part of knowledge delivery. Especially in the disciplines requiring graphic and formula expression, such as mathematics, physics, chemistry, etc., the hand-drawn content can effectively help students understand complex concepts. However, the conventional video teaching lacks the function of intelligently identifying and processing the hand-drawn content, and the hand-drawn content of a teacher usually depends on capturing by a camera and is easily affected by factors such as video definition, hand-drawn accuracy, transmission delay and the like, so that students cannot clearly and accurately acquire knowledge points, thereby affecting the teaching effect. Disclosure of Invention The embodiment of the specification provides a teaching data processing method, a device, a storage medium and electronic equipment, wherein the technical scheme is as follows: in a first aspect, embodiments of the present disclosure provide a method for processing teaching data, where the method includes: In a teaching conference scene, detecting a hand-drawing action of a main speaking user, collecting hand-drawing action data corresponding to the hand-drawing action and obtaining reference teaching scene information; Performing hand-drawing content identification based on the hand-drawing action data and reference teaching scene information to obtain target hand-drawing content; And synchronizing the target hand-drawn content to the participant user side so that the participant user side displays the target hand-drawn content. In a possible implementation manner, the acquiring the reference teaching scenario information includes: extracting hand-drawing action change characteristics of the hand-drawing action data, and determining target hand-drawing recognition difficulty aiming at a hand-drawing recognition model based on the hand-drawing action change characteristics; And determining a target auxiliary identification data combination based on the target hand-drawing identification difficulty, and acquiring reference teaching scene information corresponding to the target auxiliary identification data combination. In a possible implementation, the determining auxiliary recognition data combination based on the target hand-drawn recognition difficulty includes: Inquiring auxiliary recognition data combinations corresponding to the target hand-drawing recognition difficulty in a preset difficulty combination mapping relation, wherein the preset difficulty combination mapping relation comprises a plurality of auxiliary recognition data combinations corresponding to the hand-drawing recognition difficulty. In a possible implementation manner, the identifying the hand-drawn content based on the hand-drawn action data and the reference teaching scenario information to obtain the target hand-drawn content includes: Determining a hand-drawn recognition task prompt for the hand-drawn action data and the reference teaching scenario information; Inputting the hand-drawing action data, the reference teaching scene information and the hand-drawing recognition task prompt word into a hand-drawing recognition large model, and carrying out hand-drawing content recognition through the hand-drawing recognition large model to obtain target hand-drawing content. In a possible implementation manner, the performing the hand-drawing content recognition through the hand-drawing recognition large model to obtain the target hand-drawing content includes: Performing action recognition on the hand-drawing action data through the hand-drawing recognition large model to obtain initial hand-drawing content, determining hand-drawing content description information of the initial hand-drawing content, and performing hand-drawing associated information mining processing on the reference teaching scene information based on the hand-drawing content description information to obtain teaching demonstration associated information; And carrying out hand-drawing content adjustment on the initial hand-drawing content based on the teaching demonstration association information to obtain target hand-drawing content. In a possible implementation manner, the adjusting the initial hand-drawn content based on the teaching demonstration related information to obtain the target hand-drawn content includes: determining a plurality of teaching demonstration related contents from the teaching demonstration related information; Determining