Answer scoring method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an answer scoring method and device, computer equipment and a storage medium. The method comprises the following steps that obtaining an answer of a target proposition; inputting the answer into a preset scoring model, the scoring model being a calculation model for performing polynomial regression on the feature vector according to the feature vector between the answer and a standard answer, and the feature vector representing the similarity between the answer and the standard answer; and determining the score of the answer according to the output result of the scoring model. When a polynomial regression model is established, synonym expansion is carried out on the obtained training answers, and it is ensured that the same score is obtained when the same semantics are expressed by different words. In this way, the answer is scored without depending on specific keywords or sentences, the flexibility and accuracy of paper marking and scoring areimproved, and the objectivity of scoring is effectively guaranteed.

Description

technical field [0001] The invention relates to the technical field of examination and scoring, in particular to an answer scoring method, device, computer equipment and storage medium. Background technique [0002] With the development of computer science and technology, the ability and level of automatic information processing has also been significantly improved. The emergence of the automatic marking system liberates people from heavy mechanical labor. Machine marking is not only conducive to making an objective and fair evaluation of students' grades, but also conducive to saving, counting and querying the results of marking. However, the subjective part, such as the marking of essays, can only rely on manual marking, and in order to minimize the impact of the subjective differences of different marking teachers, it is necessary to conduct various trainings for the marking teachers to unify the standards, and it may take multiple rounds Multi-person comprehensive eval...

AI Technical Summary

Problems solved by technology

However, the scoring method of subjective questions is disturbed by many factors, and it lacks flexibility when scoring only by keywords and other rules. On the other hand, although sentences are composed of words, the relationship between words also hides a lot of semantic information , keyword-based matching will cause this part of information to be lost, resulting in inaccurate scoring results

Images