Word Classification Method in Text, Speech Creativity Evaluation Method and System
A classification method and creative technology, applied in text database clustering/classification, natural language data processing, unstructured text data retrieval, etc., can solve problems such as inability to apply language creative thinking, and achieve friendly interface and accurate classification of results. , the effect of improving classification accuracy or accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] Such as figure 1 As shown, it is a flow chart of the word classification method in the text disclosed by the present invention, including the following steps:
[0035] Step 1. Read the text by line, divide each line of text data in a regular way, filter punctuation marks and numbers, and obtain phrases and words;
[0036] Split each line of text data in a regular way, including defining specific characters and combinations of specific characters to form a rule string; search for text matching one or more rule strings, and filter text data;
[0037] Punctuation marks such as ",", ".", and ";" between phrases in the text are automatically converted into spaces to obtain the corresponding phrases.
[0038] Step 2, further segmenting the phrases and words obtained in step 1, and filtering stop words to obtain simple words, assuming that a total of L simple words are obtained; the word frequency of each simple word is counted;
[0039] In the present invention, phrases and...
Embodiment 2
[0049] Usually, the classification result in Embodiment 1 can meet the requirements, and the user does not need to process it. In some cases where high accuracy is required, in order to obtain a more accurate classification effect, the user can manually intervene in the classification. After the preliminary classification in step 3, this embodiment also includes the user's self-improvement of the classification accuracy. The user's self-improvement of the classification accuracy is: designing similar word texts and similar word texts, merging the M-type words after the preliminary classification, and obtaining N categories, N≤M; thus step 4 operates on the result of the user's self-improvement of the classification accuracy, and the step (4) is: for the result of the user's self-improvement of the classification accuracy, select the word with the highest word frequency in each class Words serve as the subject of this class.
[0050] In this embodiment, the similar word text i...
Embodiment 3
[0054] The present invention also discloses a verbal creativity evaluation method using the word classification method in the above text, which is based on the empathy evaluation technology or consensus evaluation principle of the creativity test, and scores from three aspects: fluency, originality and flexibility , including the following steps:
[0055] (S1) Acquiring the speech text input by the user;
[0056] (S2) adopting the word classification method in the above-mentioned text to classify the speech text;
[0057] (S3) Calculate the statistical results of originality, fluency, and flexibility according to the speech text classification results, and obtain the creativity evaluation results of the user; the frequency of occurrences of words entered by the user group;
[0058] The fluency is the sum of the number of words of all categories in the speech classification result;
[0059] The flexibility is the number of categories in the speech classification results.
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More