Implicit attribute extraction method and device

A technology with implicit attributes and explicit attributes, applied in the fields of instruments, data processing applications, business, etc., can solve the problem of incomplete fine-grained sentiment analysis of comments, achieve comprehensive fine-grained sentiment analysis of comments, and improve the probability of successful marketing. Improve the accuracy of your products

Active Publication Date: 2019-10-15
CHINA UNITED NETWORK COMM GRP CO LTD
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the present invention provides a method and device for extracting implicit attributes to solve the problem of incomplete fine-grained sentiment analysis of comments caused by the inability to extract implicit attributes of commodities in the prior art

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Implicit attribute extraction method and device
  • Implicit attribute extraction method and device
  • Implicit attribute extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0070] The implicit attributes in product reviews can be roughly divided into three types:

[0071] First, the implicit attribute is implied by the emotional word. For example, in the commodity Pinglu "very beautiful, but a bit expensive", the emotional word "expensive" implies the attribute "price", and the emotional word "beautiful" implies the attribute "Appearance" etc.

[0072] Second, the implicit attribute is implied by the emotional word and its contextual semantics. For example, in the product review "very fast, I ordered last night, and it was delivered at noon today", the emotional word "fast" cannot be recognized. For implicit attributes, it is nec...

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

No PUM Login to view more

Abstract

The invention discloses an implicit attribute extraction method and device. The method comprises the steps of preprocessing an original corpus to obtain an effective corpus; performing sentence segmentation on the effective corpus to obtain a short sentence set; dividing the short sentence set into an explicit sentence set and an implicit sentence set according to commodity attributes, wherein theexplicit sentence set is composed of short sentences containing commodity explicit attribute clusters, and the implicit sentence set is composed of short sentences except for the short sentences containing the commodity explicit attribute clusters; constructing a mapping relationship between a commodity explicit attribute cluster and sentiment words according to the explicit sentence set; judgingwhether sentiment words exist in implicit sentences in the implicit sentence set or not, and if not, abandoning the implicit sentences; and if so, obtaining an implicit attribute corresponding to theimplicit sentence according to the mapping relationship between the commodity explicit attribute cluster and the sentiment word. According to the method, comment fine-grained sentiment analysis can be more comprehensive, so that a user purchase strategy is more accurate, and merchants can improve own commodities more accurately.

Description

technical field [0001] The present invention relates to the technical field of computer information processing, in particular to an implicit attribute extraction method and device. Background technique [0002] Since different users tend to pay attention to different product features, when commenting on a product, even users who hold the same emotional tendency as a whole may hold different emotional tendencies to the local details of the product. In-depth mining of users' emotional tendencies towards various aspects of products, on the one hand, can help potential users understand the indicators or advantages and disadvantages of target products in various attribute dimensions, and provide reference for their purchase decisions; on the other hand, it can help merchants understand their own products To improve product design or service, improve product quality, or achieve precision marketing. [0003] In order to obtain product attributes from product reviews, it is necessa...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27G06Q30/06G06F16/33
CPCG06F16/3344G06Q30/0631G06F40/211G06F40/289G06F40/30
Inventor 霍慧
Owner CHINA UNITED NETWORK COMM GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products