CN-121999653-A - Test question explanation video generation method and system and electronic equipment

CN121999653ACN 121999653 ACN121999653 ACN 121999653ACN-121999653-A

Abstract

The application provides a test question explanation video generation method, a system and electronic equipment, wherein the method comprises the steps of analyzing test questions, generating an explanation video script in a parallel flow mode, wherein the explanation video script comprises script identifications, and the script identifications are used for identifying test question explanation stages and/or explanation video elements in the explanation video script; identifying a cut-off symbol from the generated explanation video script in the process of generating the explanation video script in a streaming mode; and when any cut-off symbol is identified from the generated explanation video script, generating a test question explanation video frame according to the explanation video script before the identified cut-off symbol. The method can improve the instantaneity and efficiency of generating the test question explanation video.

Inventors

ZHAO DAN
SUN MEI
LI SONG
SHA JING
SHENG ZHICHAO
WANG SHIJIN

Assignees

科大讯飞股份有限公司

Dates

Publication Date: 20260508
Application Date: 20251222

Claims (10)

1. The test question explanation video generation method is characterized by comprising the following steps of: analyzing the test questions, and generating an explanation video script in parallel, wherein the explanation video script comprises script identifications, and the script identifications are used for identifying explanation stages and/or explanation video elements of the test questions in the explanation video script; Identifying a cut-off symbol from the generated explanation video script in the process of generating the explanation video script in a streaming mode, wherein the cut-off symbol comprises a preset script mark and/or punctuation mark for indicating the end of the explanation step; When any cut-off symbol is identified from the generated explanation video script, a test question explanation video frame is generated from the explanation video script preceding the identified cut-off symbol.
2. The method of claim 1, wherein in the event that any truncated symbol is identified from the generated narrative video script, the method further comprises: Generating a video rendering data frame according to the explanation video script before the identified cut-off symbol, wherein the video rendering data frame comprises a plurality of fields and field contents corresponding to the fields, and the fields comprise a test question explanation stage, a mouth playing content, a screen display content, an interaction action and an interaction problem; the generating of the test question explanation video frame according to the explanation video script before the identified cut-off symbol comprises the following steps: And generating a test question explanation video frame according to the video rendering data frame.
3. The method of claim 2, wherein generating the video rendering data frame from the interpreted video script preceding the identified truncated symbol comprises: And intercepting the explanation video script which is positioned after the explanation video script intercepted last time and positioned before the cut-off symbol recognized at the time from the generated explanation video script, and generating a video rendering data frame based on the intercepted explanation video script.
4. The method of claim 2, wherein generating the question explanation video frame from the video rendering data frame comprises: Generating video explanation audio based on the mouth cast content and/or the interaction problem, generating a screen display image based on the screen display content, and rendering a virtual human figure based on the interaction action.
5. The method of claim 1, wherein parsing the questions and generating the interpretation video script in parallel flow comprises: Inputting the test questions into a large language model, so that the large language model analyzes the test questions and outputs an explanation video script in parallel.
6. The utility model provides a test question explanation video generation system which characterized in that includes: The test question analysis unit is used for analyzing the test questions and generating an explanation video script in a parallel flow mode, wherein the explanation video script comprises script identifications, and the script identifications are used for identifying test question explanation stages and/or explanation video elements in the explanation video script; The script processing unit is used for identifying a cut-off symbol from the generated explanation video script in the process of generating the explanation video script in a streaming manner by the test question analyzing unit, wherein the cut-off symbol comprises a preset script mark and/or punctuation mark for indicating the end of the explanation step; And the video generation unit is used for generating a test question explanation video frame according to the explanation video script before the identified cut-off symbol when any cut-off symbol is identified from the generated explanation video script.
7. The system of claim 6, wherein the question parsing unit parses the questions and generates the interpretation video script in parallel, comprising: Inputting the test questions into a large language model, so that the large language model analyzes the test questions and outputs an explanation video script in parallel.
8. The system of claim 6, wherein the script processing unit is further configured to: Under the condition that any cut-off symbol is identified from the generated explanation video script, generating a video rendering data frame according to the explanation video script before the identified cut-off symbol, wherein the video rendering data frame comprises a plurality of fields and field contents corresponding to the fields, and the fields comprise a test question explanation stage, a mouth broadcasting content, a screen display content, an interaction action and an interaction problem; The video generating unit generates a test question explanation video frame according to the explanation video script before the identified cut-off symbol, and the method comprises the following steps: and the video generating unit generates a test question explanation video frame according to the video rendering data frame.
9. The system of claim 8, wherein the script processing unit generates a video rendering data frame from the interpreted video script preceding the identified cut-off symbol, comprising: And intercepting the explanation video script which is positioned after the explanation video script intercepted last time and positioned before the cut-off symbol recognized at the time from the generated explanation video script, and generating a video rendering data frame based on the intercepted explanation video script.
10. An electronic device comprising a memory and a processor; the memory is connected with the processor and used for storing programs; the processor is configured to implement the method for generating a test question interpretation video according to any one of claims 1 to 5 by running a program in the memory.

Description

Test question explanation video generation method and system and electronic equipment Technical Field The application relates to the technical field of artificial intelligence, in particular to a test question explanation video generation method, a system and electronic equipment. Background With the rapid rise of online education and the wide application of intelligent coaching systems, the demand of the education field for test question explanation videos presents explosive growth. At present, a technology for automatically generating test question explanation videos has advanced to some extent, but the real-time generation of the test question explanation videos needs to be improved, and the requirement of students on acquiring accurate explanation in real time is difficult to meet. For example, when students encounter problems in online working, it is expected to quickly obtain a targeted explanation video, and the existing technology cannot achieve this well. Disclosure of Invention Aiming at the technical problems, the application provides a method, a system and electronic equipment for generating test question explanation videos, which can improve the instantaneity and efficiency of generating the test question explanation videos. The first aspect of the application provides a test question explanation video generation method, which comprises the following steps: analyzing the test questions, and generating an explanation video script in parallel, wherein the explanation video script comprises script identifications, and the script identifications are used for identifying explanation stages and/or explanation video elements of the test questions in the explanation video script; Identifying a cut-off symbol from the generated explanation video script in the process of generating the explanation video script in a streaming mode, wherein the cut-off symbol comprises a preset script mark and/or punctuation mark for indicating the end of the explanation step; When any cut-off symbol is identified from the generated explanation video script, a test question explanation video frame is generated from the explanation video script preceding the identified cut-off symbol. In some implementations, in the event that any truncated symbol is identified from the generated narrative video script, the method further includes: Generating a video rendering data frame according to the explanation video script before the identified cut-off symbol, wherein the video rendering data frame comprises a plurality of fields and field contents corresponding to the fields, and the fields comprise a test question explanation stage, a mouth playing content, a screen display content, an interaction action and an interaction problem; the generating of the test question explanation video frame according to the explanation video script before the identified cut-off symbol comprises the following steps: And generating a test question explanation video frame according to the video rendering data frame. In some implementations, the generating a video rendering data frame from the interpreted video script preceding the identified truncated symbol includes: And intercepting the explanation video script which is positioned after the explanation video script intercepted last time and positioned before the cut-off symbol recognized at the time from the generated explanation video script, and generating a video rendering data frame based on the intercepted explanation video script. In some implementations, the generating the question explanation video frame according to the video rendering data frame includes: Generating video explanation audio based on the mouth cast content and/or the interaction problem, generating a screen display image based on the screen display content, and rendering a virtual human figure based on the interaction action. In some implementations, the parsing the test questions and generating the explanation video script in parallel flow includes: Inputting the test questions into a large language model, so that the large language model analyzes the test questions and outputs an explanation video script in parallel. The second aspect of the present application provides a test question explanation video generation system, including: The test question analysis unit is used for analyzing the test questions and generating an explanation video script in a parallel flow mode, wherein the explanation video script comprises script identifications, and the script identifications are used for identifying test question explanation stages and/or explanation video elements in the explanation video script; The script processing unit is used for identifying a cut-off symbol from the generated explanation video script in the process of generating the explanation video script in a streaming manner by the test question analyzing unit, wherein the cut-off symbol comprises a preset script mark and/or punctuation mark for indicating the end of