An interpretation method and device for an embedding result

An embedding algorithm, a significant technology, applied in the field of machine learning, can solve the problems that the embedding algorithm is not explanatory and cannot meet the needs of business scenarios, so as to avoid legal risks and moral risks, and improve generalization ability and performance.

Active Publication Date: 2019-06-18
ADVANCED NEW TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the embedding algorithm is not explanato

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
  • An interpretation method and device for an embedding result
  • An interpretation method and device for an embedding result
  • An interpretation method and device for an embedding result

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present specification as recited in the appended claims.

[0039] The terms used in this specification are for the purpose of describing particular embodiments only, and are not intended to limit the specification. As used in this specification and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the t...

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 interpretation method and device of an embedding result. The method comprises: adopting an embedding algorithm to carry out embedding processing on embedded objects, obtaining an embedding result of each embedded object, wherein the embedding result comprises a plurality of dimensions of embedding values; According to the extreme value of the embedded value, extracting an embedded object with the embedded value meeting a significant condition under each dimension as a significant training sample; For each dimension, training an interpretation model by adopting the sample characteristics of the significant training samples under the dimension and the significant category tags; And based on a trained explanation model, determining the explanation characteristics ofthe significant training sample belonging to the significant category, and taking the explanation characteristics as the explanation characteristics of the embedding result under the dimension.

Description

technical field [0001] This specification relates to the technical field of machine learning, and in particular to an interpretation method and device for embedding results. Background technique [0002] Embedding mathematically represents a mapping that maps one space to another while preserving essential properties. Embedding algorithms can be used to convert some complex and difficult-to-express features into easy-to-calculate forms, such as vectors, matrices, etc., to facilitate the processing of predictive models. However, the embedding algorithm is not explanatory and cannot meet the needs of business scenarios. Contents of the invention [0003] In view of this, this specification provides an interpretation method and device for embedding results. [0004] Specifically, this specification is realized through the following technical solutions: [0005] An interpretation method for embedding results, including: [0006] Embedding the embedded object by using an em...

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): G06F16/35G06K9/62
CPCG06F16/35G06F18/00
Inventor 张晓露王力向彪周俊
Owner ADVANCED NEW TECH 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