A Chinese sentence similarity hierarchical calculation method and device for user query intent
A sentence similarity, user-oriented technology, applied in computing, special data processing applications, instruments, etc., can solve problems such as unsatisfactory similarity effect, unsatisfactory Chinese word segmentation effect, and large keyword differences
Active Publication Date: 2017-03-08
BEIJING INFORMATION SCI & TECH UNIV +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a Chinese sentence similarity hierarchical calculation method and device for user query intentions, aiming to overcome the problem of unsatisfactory Chinese word segmentation, and at the same time solve the problems of large differences in keywords, long lengths, and complex sentence structures The problem of the unsatisfactory effect of sentence calculation similarity, through the idea of hierarchical calculation, improves the accuracy of similarity calculation and enhances the practical value of this scheme
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0065] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0066] A hierarchical calculation method for Chinese sentence similarity oriented to user query intent, such as figure 1 with figure 2 shown, including the following steps:
[0067] S1. Use the edit distance sentence similarity algorithm that removes the punctuation at the end of the sentence to calculate the similarity of the data set, and determine a part of the sentences that meet the threshold as similar sentences
[0068] In step S1, the procedure for calculating the similarity of sentences with edit distance by removing the punctuation at the end of the sentence is as follows: image 3 As...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a user-query-intention-oriented Chinese sentence similarity hierarchical calculation method and user-query-intention-oriented Chinese sentence similarity hierarchical calculation device. A data set is subjected to similarity calculation by adopting a sentence-end-punctuation-removing editing distance sentence similarity algorithm; one part of sentences meeting a threshold value are determined as similar sentences; then, non-similar sentences in the data set are subjected to similarity calculation by adopting a sentence similarity algorithm based on keyword features and semantic features, so one part of sentences meeting the threshold value are determined as the similar sentences again; and finally, the non-similar sentences in the data set are subjected to sentence similarity calculation by adopting a user-intention-oriented sentence similarity algorithm, and one part of sentences meeting the threshold value are determined as similar sentences. Therefore all similar sentences in the data set are obtained. The method and the device provided by the invention have the advantages that the calculation is concise; the effect is good; and the problems of great keyword difference, great length, sentence structure complexity and the like can be effectively solved.
Description
technical field [0001] The invention belongs to the technical field of similarity calculation of Chinese sentences, and in particular relates to a hierarchical calculation method and device for similarity of Chinese sentences oriented to user query intentions. Background technique [0002] Similarity calculation is the basic work in the field of natural language processing, and has a wide range of application backgrounds. According to different processing objects, it can be divided into word similarity calculation, sentence similarity calculation and text similarity calculation. Among them, the efficiency of sentence similarity calculation in information retrieval, machine translation, question answering system and automatic summarization directly affects the overall performance of the application system. Therefore, there are still many scholars who are keen to continuously improve the calculation method of sentence similarity. [0003] The current sentence similarity calc...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27G06F17/30
Inventor 张仰森李景玉
Owner BEIJING INFORMATION SCI & TECH UNIV