Writing training-based statement recommendation method and system
A recommendation method and recommendation system technology, applied in natural language data processing, special data processing applications, instruments, etc., can solve problems such as limited reading volume of students, and achieve the effect of improving the level of articles and writing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0103] Please refer to figure 2 , Embodiment 1 of the present invention is: a sentence recommendation method based on writing training, which can be applied to students, especially primary school students' writing training, including the following steps:
[0104] S1: Select excellent sentences, that is, select preset sentences; you can choose from classics, world-renowned literature, award-winning articles, etc., and you can also choose poems, idioms, common sayings, etc.
[0105] S2: Preset corresponding keywords according to the excellent sentences; the keywords can be obtained from the excellent sentences, or can be obtained after summarizing the meanings of the excellent sentences. For example, an excellent sentence is "autumn flowers are bleak, autumn grass is yellow, autumn lights are long and autumn nights are long; I feel that the autumn window is endless, and the wind and rain can help the desolation! How fast does the autumn wind and rain come? The autumn window is ...
Embodiment 2
[0128] Please refer to image 3 , this embodiment is a further extension of Embodiment 1, the similarities will not be repeated, the difference is: in the step S8, if not, then execute the step S12.
[0129] S12: Mark the participle corresponding to the second tag as a new word.
[0130] S13: Obtain short sentences in the sentence; further, obtain short sentences according to punctuation marks, such as commas, full stops, question marks, exclamation marks, and the like.
[0131] S14: Obtain a second label corresponding to a participle that is not a new word in the short sentence.
[0132] S15: Obtain a first tag that matches the second tag.
[0133] S16: Arrange and combine the first tags according to the degree of matching with the second tags.
[0134] S17: Calculate the proportional weight of each of the first tags according to the total number of excellent sentences corresponding to each of the first tags.
[0135] S18: Acquire a corresponding number of excellent sente...
Embodiment 3
[0143] This embodiment is a specific application scenario corresponding to the foregoing embodiments.
[0144] The user intends to write an autumn outing composition, and enters the first sentence, "Today, I went to the park for an autumn outing with my classmates." The word segmentation "today" is obtained, and the corresponding second tag is calculated, but no matching first tag is found in the database. A label, so mark "today" as a new word. Afterwards, because the punctuation comma appeared, the short sentence "today" is obtained, but the short sentence has only one participle and is marked as a new word, so the short sentence is not recommended.
[0145] In the same way, for the second half of the sentence "I went to the park with my classmates for an autumn outing." The participle "me and my classmates", "together", "go", "park", and "autumn outing" can be obtained respectively, and the corresponding participle of each participle can be calculated respectively. The sec...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


