Method for extracting attribute words from commodity reviews based on ontology thesaurus
A technology of ontology thesaurus and product reviews, applied in the field of product reviews
Inactive Publication Date: 2017-11-28
无锡中科泛在信息技术研发中心有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0016] The purpose of the present invention is to provide a product review attribute word extraction method based on ontology thesaurus based on the characteristics of the current mainstream e-commerce website product reviews, which is more efficient than the traditional text processing method for extracting attribute words
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
[0031] The present invention will be further described below in conjunction with specific drawings and embodiments.
[0032] The invention is used for extracting attribute words for new commodity reviews based on the existing constructed attribute word ontology thesaurus.
[0033] In the product review text, each part separated by punctuation or blank characters in a review text is called a clause. For example, "the screen of the mobile phone is very clear and the workmanship is good" contains two clauses separated by commas.
[0034] This method of extracting attribute words from product reviews based on ontology thesaurus includes the following steps:
[0035] Step 1, preprocessing the comment text: first, divide each comment text into different clauses; secondly, for each clause of each comment, combined with the attribute word ontology thesaurus, use the forward maximum matching method for word segmentation, and then Perform part-of-speech tagging, remove stop words, and ...
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 commodity review property word extracting method based on a noumenon lexicon. The commodity review property word extracting method comprises the following steps that 1, preprocessing on review texts: firstly, dividing each review text into different clauses, secondly, word participating is conducted on each clause of each review combining with the property word noumenon lexicon, thirdly, part-of-speech tagging is conducted, stop words are removed, and then nouns are searched in each clause and are used as a property word candidate set in that review; 2, classification is conducted on property words in the property word candidate set; 3, combining synonym parts of speech of property words is conducted in each property word candidate set; 4, after the combining operation is conducted on each property word candidate set, a head-word of each synonym parts of speech is affirmed as the property word of the corresponding clause in the property word candidate set. Compared with a traditional text processing property word extracting method, the commodity review property word extracting method based on the noumenon lexicon is of higher efficiency.
Description
technical field [0001] The invention relates to commodity reviews of Internet e-commerce, in particular to a method for extracting attribute words of commodity reviews. Background technique [0002] Global Internet data in 2011 shows that as of December 2011, the total number of global websites has reached 555 million, and the number of global Internet users has exceeded 2 billion. The increase in the popularity of the Internet has led to the development of e-commerce, a network activity. More and more online messages are spread all over our network platforms, especially product reviews on shopping websites. [0003] In 2012, Alipay's transaction volume on the day of "Double Eleven" achieved rapid growth, reaching 19.1 billion yuan, including Tmall Mall 13.2 billion yuan, Taobao 5.9 billion yuan, and the number of orders reached 105.8 million; in 2013, on November 11, Alipay The total transaction volume of the Baba platform was 35.019 billion; in 2014, on November 11, the t...
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): G06F17/30
CPCG06F16/35
Inventor 马睿周晓锋潘福成
Owner 无锡中科泛在信息技术研发中心有限公司