Subjective question scoring method, device, readable storage medium and electronic device
A technology for subjective questions and score values, applied in semantic analysis, electronic digital data processing, instruments, etc., can solve the problems that the automatic evaluation technology of subjective questions does not meet the requirements of application, cannot be fully processed, and is difficult to be practical, etc. Correcting efficiency, avoiding inaccurate corrections, and promoting the effect of development and progress
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0087] Such as figure 1 As shown, the present embodiment provides a method for scoring subjective questions, the method comprising:
[0088] S1. Word vectorization step: use the Chinese news corpus to train the word2vec model, vectorize the words, and obtain a function for calculating the similarity between two words;
[0089] S2. Text preprocessing step: preprocessing the reference answer and the score point text in each student's answer respectively, and obtaining the list of words and parts of speech in the preprocessed reference answer and each student's answer respectively.
[0090] In this step, specifically include:
[0091] S21. The standard answer and the student's answer are stored in the xlsx file, and the Chinese text is read from the xlsx file. The standard answer is segmented by the special identifier "()", and the student's answer is segmented by the special identifier "()";
[0092] S22. The segmented text conforms to the set {,.! ? :;~,. ! ? :;~} clause...
Embodiment 2
[0163] Such as figure 2 As shown, corresponding to Embodiment 1, this embodiment provides a subjective question scoring device, which includes:
[0164] The word vectorization module is used to train the word2vec model through the Chinese news corpus, and vectorize the words to obtain a function for calculating the similarity between two words;
[0165] The text preprocessing module is used to preprocess the reference answers and the score point texts in the answers of each student respectively, and obtain the list of words and parts of speech in the reference answers after preprocessing and the answers of each student respectively;
[0166] Build a pyramid bag-of-words module, which is used to build a pyramid-style bag of words based on the word and part-of-speech list of the preprocessed reference answer;
[0167] The search matching algorithm module is used to find out the subsequence with the highest matching coefficient between each student's answer and the reference an...
Embodiment 3
[0173] Such as image 3 As shown, this embodiment provides an electronic device, including at least one processor; and at least one memory communicated with the processor, wherein the memory stores program instructions that can be executed by the processor, so The processor calls the program instructions to execute the above-mentioned scoring method for subjective questions.
[0174] During specific implementation, when the program instructions are executed by the processor, any implementation manner in Embodiment 1 may be implemented.
[0175] Since the electronic device introduced in this embodiment is the device used to implement a subjective question scoring method in Embodiment 1 of this application, based on the method described in Embodiment 1 of this application, those skilled in the art can understand this implementation. The specific implementation manner of the electronic device of the example and its various variations, so how the electronic device implements the ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More