Early warning method and system for identifying click farming shop based on e-commerce operation data

A technology of data recognition and store, applied in data processing applications, character and pattern recognition, payment systems, etc.

Inactive Publication Date: 2021-09-14
浪潮卓数大数据产业发展有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical task of the present invention is to provide an early warning method and system based on e-commerce operation data to identify shopkeepers who swipe ord

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
  • Early warning method and system for identifying click farming shop based on e-commerce operation data
  • Early warning method and system for identifying click farming shop based on e-commerce operation data
  • Early warning method and system for identifying click farming shop based on e-commerce operation data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] as attached figure 1 As shown, the present invention’s early-warning method for identifying shops that charge orders based on e-commerce operation data, the method is to collect comprehensive information on products and stores on the e-commerce platform, and through centralized analysis of the top products in the store, identify the sales volume of the products displayed on the page Whether it is a real sales volume, and an early warning will be given according to the recognition result; the details are as follows:

[0057] S1. Information crawling: by crawling the stores and product information of mainstream e-commerce platforms, obtain information on store unique identifier id, product id and product sales;

[0058] S2. Screening stores: through the established screening rules, and with the help of database tools, the scope of inspection of the shops that charge orders is narrowed down;

[0059] S3. Establish an early warning model for shop swiping orders (random for...

Embodiment 2

[0093] Taking a treasure store as an example, the specific steps are as follows:

[0094] (1) Data collection: Through the product details page, further collect the above-mentioned required store information, as attached Figure 4 shown;

[0095] (2) Full monthly store screening: use distributed data processing technology to screen out stores that are suspected of brushing orders;

[0096] Note: It is mainly judged by the sales volume of top products in the store. as attached Figure 5 As shown, in the case of extremely high sales volume, if the sales volume of the head product in a store is very close, it is considered that the store has a behavior of brushing orders.

[0097](3) Algorithm prediction output results: After the data preparation is completed and the model parameters are tuned, import the prepared data into our model to allow it to automatically learn the salient features of normal stores and abnormal store orders. Accurate identification of new store data ca...

Embodiment 3

[0099] The early warning system of the present invention based on the e-commerce operation data to identify shops that make orders, the system includes:

[0100] The crawling unit is used to obtain information on the store's unique identifier id, product id, and product sales by crawling the store and product information of mainstream e-commerce platforms;

[0101] The screening unit is used to pass the established screening rules and use database tools to narrow the inspection scope of the shop that brushes orders;

[0102] The model building unit is used to determine the high-sales products in the stores within the inspection range by establishing a store order-swiping early warning model, output whether the high-sales products in the corresponding store are the order-swiping products and whether the corresponding store is the order-swiping store, and report the results Provided for consumer reference; model building units include,

[0103] The preprocessing module is 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
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an early warning method and system for identifying a click farming shop based on e-commerce operation data, belongs to the technical field of e-commerce platform information, and aims to solve the technical problem of how to timely remind a consumer of whether a shop operator carries out farm clicking on commodities in the shop or not, and reduce the transaction risk of the consumer. According to the technical scheme, the method comprises the steps of collecting comprehensive information of commodities and shops of an e-commerce platform, carrying out centralized analysis on top commodities of the shops, recognizing whether the commodity sales volume displayed on a page is the real sales volume or not, and carrying out click farming early warning according to the recognition result. The method specifically comprises the following steps: information crawling: crawling shop and commodity information of a mainstream e-commerce platform to obtain a shop unique identifier id, a commodity id and commodity sales information; shop screening: according to the formulated screening rule, narrowing the check range of the click farming shop by means of a database tool; and establishing a shop click farming early warning model.

Description

technical field [0001] The present invention relates to the field of e-commerce platform information technology, in particular to an early warning method and system for identifying shops that charge orders based on e-commerce operation data. Background technique [0002] E-commerce is closely related to people's lives. In order to save shopping time and labor costs, and to get evaluations and references from other consumers, more and more consumers choose to shop on e-commerce platforms. On the product search list page, the platform usually displays products to consumers in descending order of sales volume, which is a very reasonable approach, because products favored by more consumers may have advantages in quality, price, etc. . At the same time, this method of recommending in descending order of sales has also made many store operators see the possibility of "cheating"-swiping orders. In order to better attract customers, some sellers will increase the sales and ranking...

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
IPC IPC(8): G06Q20/40G06N20/00G06K9/62
CPCG06Q20/4016G06N20/00G06F18/24323G06F18/214
Inventor 贾晓萌谢传家姚民伟
Owner 浪潮卓数大数据产业发展有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap