Algorithm model detection method, apparatus, device and system

一种算法模型、模型的技术，应用在互联网领域，能够解决无法准确的检测出算法模型正确率和/或错误率、缺乏算法模型测试方法等问题，达到提高测试准确度、提高测试速度的效果

Active Publication Date: 2018-01-16
ZHEJIANG TMALL TECH CO LTD
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the data actually processed by the algorithm model is not limited to the data in these two data sets. If the correct rate and / or error rate of the algorithm model processing preset data is used as the correct rate and / or Error rate, also unable to accurately detect the correct rate and / or error rate of the algorithm model
[0004] Therefore, prior art lacks a kind of testing method of both accurate and fast algorithmic model

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] 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 the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.

[0058] With the development of Internet technology, web pages have not only become a source for users to obtain information, but also a way for users to upload information and shop online, and there are more and more advertisements on web pages. Commodity, after receiving the product, the user will enter the evaluation information in the shopping webpage in order to evaluate the product, and som...

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 provides an algorithm model detection method, apparatus, device and system. The system comprises an evaluation module used for evaluating to-be-evaluated information via an algorithm model, wherein the algorithm model comprises a to-be-measured algorithm model and a historical algorithm model, the historical algorithm model is a previous iteration model of the to-be-measured algorithm model; an algorithm model detection module used for detecting the accuracy of the to-be-measured algorithm model; and an algorithm model training module used for training the algorithm model according to a training sample set. By detecting the accuracy of the to-be-measured algorithm model for processing user evaluation information via a processing result of the user evaluation information by the historical algorithm model, the test accuracy of the algorithm model is improved, the algorithm model requires no manual test, and thus the test speed of the algorithm model is improved.

Description

technical field [0001] The present application relates to Internet technologies, and in particular to an algorithm model detection method and device. Background technique [0002] In the existing technology, the algorithm model is like the cognitive model of human beings, which needs to be constantly corrected and trained. Specifically, the algorithm model constantly changes its own parameters in the process of processing sample data, so that the algorithm model is constantly being updated. Iteration, however, if it is allowed to iterate continuously without testing the iterated algorithm model, it will not be possible to determine whether the iterated algorithm model can process the sample data according to the preset correct rate. [0003] In the prior art, there are two methods for testing the algorithm model: one is manual testing, for example, the algorithm model processes 100 sample data to obtain 100 results, and among the 100 results, there are correct results and so...

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): G06F11/36
Inventor 倪静
Owner ZHEJIANG TMALL 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

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