CN-122021924-A - Method, apparatus, storage medium and program product for reading a drawing

CN122021924ACN 122021924 ACN122021924 ACN 122021924ACN-122021924-A

Abstract

The application discloses a method, equipment, a storage medium and a program product for reading a drawing book, which relate to the technical field of artificial intelligence and comprise the steps of outputting questioning data associated with a target drawing book by electronic equipment in the process of reading the target drawing book if questioning conditions are met, obtaining reply content input by a user, carrying out quality assessment on the reply content to determine which of three quality grades the reply content belongs to, wherein the three quality grades comprise a first quality grade representing that the reply content is completely correct, a second quality grade representing that the reply content is partially related to questioning data but not completely correct, a third quality grade representing that the reply content is completely incorrect or not related to the questioning data, and feeding back the reply content based on an assessment result. The application improves the intelligence of drawing and reading.

Inventors

LI SHOUYI
GAO CHUANG
LIU QINGSHENG

Assignees

安徽淘云科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260213

Claims (11)

1. A method for reading a drawing book for an electronic device, comprising: Outputting questioning data associated with the target drawing if questioning conditions are met in the process of reading the target drawing; Obtaining reply content input by a user; The quality of the reply content is evaluated to obtain an evaluation result, wherein the evaluation result at least comprises the quality grade of the reply content, and the quality grade of the reply content is one of a first quality grade which characterizes the reply content to be completely correct, a second quality grade which characterizes the reply content to be partially related but not completely correct with the questioning data, and a third quality grade which characterizes the reply content to be completely incorrect or not related with the questioning data; and feeding back the reply content based on the evaluation result.
2. The method of claim 1, wherein outputting the question data associated with the target transcript if the question condition is satisfied comprises: When reading each page of the target drawing book, if the currently read page is any one of a plurality of preset target pages, screening a plurality of questions related to the target read data stored in a drawing book library and adapting to the user as question data based on target read data of the user and user information, wherein the target read data comprises read data of the current page and/or read data of historical read pages; And outputting the questioning data.
3. The method of claim 2, wherein the codebook library further stores standard answers corresponding to the question data, quality level assessment criteria, and feedback suggestions corresponding to different quality levels; Performing quality evaluation on the reply content, and feeding back the reply content based on the evaluation result, wherein the method comprises the following steps: performing quality assessment on the reply content based on the quality grade assessment standard; And generating feedback content based on the evaluation result and feedback suggestions corresponding to the quality level of the reply content, and outputting the feedback content.
4. The method of claim 1, wherein outputting the question data associated with the target transcript if the question condition is satisfied comprises: When reading each page of the target drawing book, judging whether the current page is suitable for asking questions through a large model based on target reading data and user information of a user, and generating asking data suitable for asking questions and standard answers and quality grade evaluation standards corresponding to the asking data, wherein the target reading data comprises reading data of the current page and/or reading data of historical reading pages; And outputting the questioning data.
5. The method of claim 3, wherein each quality level corresponds to feedback content that includes forward positive content corresponding to the quality level, and wherein the forward positive content corresponding to different quality levels is different.
6. The method of claim 5, wherein the feedback content corresponding to the third quality level further comprises: the questions re-asked to the user, wherein the re-asked questions are different from the contents of the questioning data and have the same semantics; Generating prosody expression modes corresponding to the quality grades based on the evaluation results and feedback suggestions corresponding to the quality grades of the reply contents; the prosody expression corresponding to the third level is different from the prosody expression corresponding to the non-third quality level.
7. The method of claim 6, wherein outputting the feedback content comprises: And outputting the feedback content in voice according to the prosody expression mode.
8. The method of claim 2 or 4, further comprising, prior to outputting the question data: After the reading of the current page is completed, monitoring whether the user turns the page within a preset time length; Correspondingly, if the user does not turn pages when the preset duration is reached, outputting the questioning data.
9. A computer program product comprising computer readable instructions which, when run on an electronic device, cause the electronic device to implement the method of drawing a book as claimed in any one of claims 1 to 8.
10. An electronic device comprising at least one processor and a memory coupled to the processor, wherein: the memory is used for storing a computer program; The processor is configured to execute the computer program to enable the electronic device to implement the method for drawing a book as claimed in any one of claims 1 to 8.
11. A computer storage medium carrying one or more computer programs which, when executed by an electronic device, enable the electronic device to implement the method of drawing a book as claimed in any one of claims 1 to 8.

Description

Method, apparatus, storage medium and program product for reading a drawing Technical Field The present application relates to the field of artificial intelligence technology, and in particular, to a method, apparatus, storage medium, and program product for reading a drawing book. Background The painting is a kind of books mainly painted with a small amount of characters. The drawing book not only tells stories and learns knowledge, but also can comprehensively help children to build the mental world, and becomes an important book for enlightenment education of the children. The current parents accompany the children in limited time, and the painting reading is very important for the study of the young children, based on the fact, the reading robot is generated, the children directly take the painting in front of the painting reading robot, and the painting reading robot can read the painting, and the children accompany the painting. However, the current drawing reading robot only outputs story contents in the drawing mechanically, lacks interaction with a user, and has low intelligence in drawing reading. Disclosure of Invention In view of the foregoing, the present application provides a method, apparatus, storage medium and program product for reading a drawing, so as to improve the intelligence of the drawing reading. The specific scheme is as follows: The first aspect of the application provides a method for reading a drawing, which is used for electronic equipment and comprises the following steps: Outputting questioning data associated with the target drawing if questioning conditions are met in the process of reading the target drawing; Obtaining reply content input by a user; The quality of the reply content is evaluated to obtain an evaluation result, wherein the evaluation result at least comprises the quality grade of the reply content, and the quality grade of the reply content is one of a first quality grade which characterizes the reply content to be completely correct, a second quality grade which characterizes the reply content to be partially related but not completely correct with the questioning data, and a third quality grade which characterizes the reply content to be completely incorrect or not related with the questioning data; and feeding back the reply content based on the evaluation result. In one possible implementation, the outputting the question data associated with the target script if the question condition is satisfied includes: When each page of the target drawing book is read, if the currently read page is any one of a plurality of preset target pages, screening a plurality of questions related to the target reading data stored in a drawing book library and adapting to the user as question data based on target reading data of the user and user information, wherein the target reading data comprises reading data of the current page and/or reading data of historical reading pages, and the user information comprises names, ages, sexes, characters, current emotion, school age information and historical drawing book reading conditions. And outputting the questioning data. In one possible implementation, the codebook library further stores standard answers, quality level evaluation standards and feedback suggestions corresponding to different quality levels, wherein the standard answers, the quality level evaluation standards and the feedback suggestions correspond to the questioning data; Performing quality evaluation on the reply content, and feeding back the reply content based on the evaluation result, wherein the method comprises the following steps: performing quality assessment on the reply content based on the quality grade assessment standard; And generating feedback content based on the evaluation result and feedback suggestions corresponding to the quality level of the reply content, and outputting the feedback content. In one possible implementation, the outputting the question data associated with the target script if the question condition is satisfied includes: When reading each page of the target drawing book, judging whether the current page is suitable for asking questions through a large model based on target reading data and user information of a user, and generating asking data suitable for asking questions and standard answers and quality grade evaluation standards corresponding to the asking data, wherein the target reading data comprises reading data of the current page and/or reading data of historical reading pages; And outputting the questioning data. In one possible implementation, the feedback content corresponding to each quality level includes forward positive content corresponding to the quality level, and the forward positive content corresponding to the different quality levels is different. In one possible implementation, the feedback content corresponding to the third quality level further includes: the questions re-asked to the user, wherein