Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and a device for quickly customizing a model by multiple categories and multiple clients of e-commerce comments

A multi-customer and category technology, applied in electronic digital data processing, unstructured text data retrieval, text database clustering/classification, etc., to achieve the effect of good hierarchy, extensive use and cost saving

Pending Publication Date: 2019-06-18
上海宝尊电子商务有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, there is no report on the method and device for the multi-category multi-customer rapid customization model of e-commerce comments in the present invention.

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
  • A method and a device for quickly customizing a model by multiple categories and multiple clients of e-commerce comments
  • A method and a device for quickly customizing a model by multiple categories and multiple clients of e-commerce comments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Please refer to the attached figure 1 , 2 , with figure 1 It is an overall flow chart of the method and device for fast customization of multi-category and multi-customer models for e-commerce reviews, with attached figure 2 It is a pool table of a multi-category multi-customer rapid customization model method and device for e-commerce reviews. The realization of a multi-category multi-customer rapid customization model method for e-commerce comments provided by the present invention includes the following main steps:

[0042] First: Construction of the lowest granularity label:

[0043] S11. Split the training set into labels of the lowest granularity according to the actual situation. The labels required by any category store can be combined from the labels of the lowest granularity. If they cannot be combined, it means that they are not the lowest granularity and need to continue to split;

[0044] S12. According to the introduction of new categories, new requi...

Embodiment 2

[0060] Please refer to the attached figure 1 , 2 , with figure 1 It is an overall flow chart of the method and device for fast customization of multi-category and multi-customer models for e-commerce reviews, with attached figure 2 It is a pool table of a multi-category multi-customer rapid customization model method and device for e-commerce reviews. The main process of the present invention to realize the rapid customization model of multi-category and multi-customer of e-commerce comments is as follows:

[0061] 1. The training set should be fine enough, and different categories have splits for the same label, and the label with the lowest granularity shall prevail.

[0062] 2. Create a pool table to store the name of the mapping corresponding to the lowest granularity in each category. The two lowest granularity rows can be combined to form a category granularity label; flag is used to indicate whether the label is displayed in the category.

[0063] 3. Create a chan...

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 relates to a method and a device for quickly customizing a model by multiple categories and multiple clients of e-commerce comments. The method and the device for quickly customizing themulti-category and multi-client model for the e-commerce comments mainly comprise the following steps of: firstly, constructing a lowest granularity label; secondly, constructing a deep neural network model training module; and thirdly, constructing a deep neural network model labeling module. The method has the advantages that problems encountered when a model is customized for merchants are solved according to the method, the requirement of the merchants for customization of own brands is met, and the problems of rapid training, labeling, different tag names and the like are efficiently solved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular, to a method and device for quickly customizing models of multi-category and multi-customer for e-commerce reviews. Background technique [0002] In recent years, with the vigorous development of information technology and the Internet, my country's online shopping market has developed rapidly. More and more people use e-commerce websites to understand product information, purchase goods, and express their feelings about the process of purchasing goods through evaluation. Satisfaction and suggestions and requirements for purchased goods. On the one hand, consumers cannot directly contact actual products when shopping online, and can only understand the basic characteristics of products, businesses, and brands based on descriptive information such as text and pictures provided by e-commerce platforms and comment texts published by historical consumers. On ...

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): G06F16/35G06F17/27G06Q30/06
Inventor 李平章王航丁丁郑圆
Owner 上海宝尊电子商务有限公司