CPC G06V 10/82 (2022.01) [G06V 30/19147 (2022.01); G06V 30/19173 (2022.01); G06V 30/413 (2022.01); G09B 7/06 (2013.01); G06V 30/10 (2022.01)] | 11 Claims |
1. An answer evaluation method, comprising:
acquiring an answer image, which is an image of a test paper having been answered by a user;
classifying the answer image based on a pre-trained test question classification model, so as to obtain an objective question answer area and a subjective question answer area in the answer image;
identifying at least one objective question in the objective question answer area and an objective question answer for each of the at least one objective question;
identifying at least one subjective question in the subjective question answer area and a subjective question answer for each of the at least one subjective question; and
determining a total score value of the test paper based on the at least one objective question, the objective question answer, the at least one subjective question and the subjective question answer,
wherein, the step of identifying at least one subjective question in the subjective question answer area and a subjective question answers for each of the at least one subjective question comprises:
identifying, by using an optical character recognition, the at least one subjective question in the subjective question answer area and the subjective question answer for each of the at least one subjective question,
wherein the at least one subjective question comprises: at least one second type subjective question, and
wherein the step of determining a total score value of the test paper based on the at least one objective question, the objective question answer, the at least one subjective question and the subjective question answer comprises:
acquiring a standard objective question answer for each of the at least one objective question;
matching the objective question answer to the standard objective question answer for each of the at least one objective question, so as to obtain a first matching result, and calculating an objective question score value according to the first matching result;
pushing the subjective question answer for each of the at least one second type subjective question to a reviewer terminal, receiving a score value for each of the at least one second type subjective question fed back by the reviewer terminal, and calculating a second subjective question score value according to the score value for each of the at least one second type subjective question; and
determining the total score value based on the objective question score value and the second subjective question score value.
|