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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

