An automatic mining method and system for e-commerce security-related entities
An automatic mining and e-commerce technology, applied in business, data processing applications, text database queries, etc., can solve problems such as difficulty in obtaining entity recognition results, insufficient research on the composition mode of named entities, and sparse entity data
Active Publication Date: 2020-11-17
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Statistical-based methods often rely on statistical models and corpus without adequately studying the compositional patterns of named entities themselves
However, in the e-commerce public opinion corpus, there is a serious problem of sparse entity data, which makes it difficult to obtain correct entity recognition results
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
[0079] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.
[0080] E-commerce security-related entities include:
[0081] (a) The e-commerce shopping platform is the center of the entire e-commerce black and gray industry chain, and it is also the entity type with the highest frequency in public opinion data;
[0082] (b) loopholes in the rules enforced by e-commerce shopping platforms;
[0083] (c) Anti-cheating algorithms in current e-commerce shopping platforms;
[0084] (d) E-commerce service platforms, including websites, software or tools that provide services within the scope of permission and that are not allowed to provide cheating information;
[0085] (e) The major communication platforms that facilitate communication between fraudulent orga...
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 discloses an automatic mining method and system for e-commerce security related entities. The method comprises the following steps of collecting public sentiment data relevant to e-commerce from Internet, wherein the public sentiment data is a text information set; performing primary screening on the public sentiment data; deleting text information with small relevancy to e-commerceblack and gray industry chains; segmenting the screened public sentiment data into sentences; performing iteration screening on the sentence set; deleting sentences which do not include e-commerce security related entities; artificially extracting a partial e-commerce security related entity set S1; performing entity extraction on the screened sentence set to obtain a candidate entity set; screening the candidate entity set to delete phrases which do not belong to the e-commerce security related entities to obtain an e-commerce security related entity set S2. The automatic mining method of thee-commerce security related entities can be used for effectively recognizing entities relevant to the e-commerce public sentiment security.
Description
technical field [0001] The invention relates to the technical fields of natural language processing and e-commerce service security, in particular to an automatic mining method and system for entities related to e-commerce security. Background technique [0002] In the era of "Internet +", e-commerce is developing rapidly. The increasingly fierce commodity competition has spawned an e-commerce black and gray industrial chain with speculation and cheating as the main mode, and false transactions, artificial traffic and spam reviews as the typical characteristics. At the same time, competition has triggered a series of illegal and criminal activities mainly involving fraud, which have seriously endangered the reputation system and market order of e-commerce. Therefore, comprehensively rectifying the network service environment and severely cracking down on the black and gray industry chain of e-commerce have become an inevitable requirement for the healthy development and hea...
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): G06Q30/00G06F16/953G06F16/33
CPCG06Q30/018
Inventor 纪守领伍一鸣陈建海刘倩君
Owner ZHEJIANG UNIV