Method and system for performing machine learning process

A machine learning and machine learning model technology, applied in the field of executing machine learning process, can solve the problems of modeling scheme or achievement and model separation, unable to effectively realize the production and application of machine learning model, etc.

Pending Publication Date: 2020-02-07
THE FOURTH PARADIGM BEIJING TECH CO LTD
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even though there are already some platform products for machine learning modeling, the existing machine learning platforms only focus on completing the investigation of machine learning models, that is, how to train a machine learning model based on accumulated historical data. model, but cannot effectively realize the subsequent production and application of the machine learning model (for example, it is difficult to use the machine learning model to provide online services), in other words, there is a severe separation between the modeling scheme or the results and the model application process in the existing technology question

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
  • Method and system for performing machine learning process
  • Method and system for performing machine learning process
  • Method and system for performing machine learning process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] figure 1 A block diagram of a system 100 for performing a machine learning process according to an exemplary embodiment of the present application is shown. The system 100 includes a data collection unit 110 , a real result collection unit 120 , an automatic model training unit 130 and a service providing unit 140 .

[0085] Specifically, the data collection unit 110 can continuously collect prediction data. Here, the prediction data may be the data that the user (for example, an information service provider for recommending information) expects to obtain related prediction results. Here, the data collection unit 110 continuously receives the prediction data from the user or through other paths. For example, when a user wants to know the prediction result of whether the information recommended to his customers (such as end consumers) will be accepted (that is, whether it will be clicked or read by consumers), the data collection unit 110 can collect prediction data , ...

Embodiment 2

[0148]

[0149] Figure 9 A schematic flowchart showing a method for executing a machine learning process according to another embodiment of the present disclosure. The method can be executed by at least one computing device, and the at least one computing device can be constructed entirely as a local device, or as a cloud device (for example, a cloud server), and can also include both a local device and a cloud device (for example, a local both client and cloud server).

[0150] Step S9100, providing a first operation entry and a second operation entry that are independent of each other.

[0151] The first operation entry is used to collect behavior data that is the basis of model prediction, and the second operation entry is used to collect feedback data that is the real result of the behavior data.

[0152] Behavior data involves the characteristic part of the training data, which can be imported by users through different paths, such as uploading locally stored data to...

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

There is provided a method and system for performing a machine learning process. The system comprises: a data collection unit for continuously collecting prediction data, a real result collection unitfor continuously collecting real results of the prediction data, a model automatic training unit for generating an updating training sample based on the collected prediction data and a correspondingreal result according to a configured model updating scheme and continuously obtaining an updated machine learning model by utilizing the updating training sample, and a service providing unit which is used for selecting an online machine learning module for providing an online prediction service from the machine learning models according to the configured model application scheme, and in responseto a prediction service request including the prediction data, providing a prediction result for the prediction data included in the prediction service request using the online machine learning model.

Description

technical field [0001] The present application relates generally to the field of artificial intelligence, and more particularly to a method and system for performing a machine learning process. Background technique [0002] With the emergence of massive data, artificial intelligence technology has developed rapidly, and machine learning is an inevitable product of the development of artificial intelligence to a certain stage. It is committed to mining valuable potential information from large amounts of data through computing means. In computer systems, "models" can be generated from historical data through machine learning algorithms, that is, historical data is provided to machine learning algorithms, and machine learning models can be obtained by modeling based on these historical data. [0003] However, in the process of machine learning, it involves the processing of data, features, algorithms, parameter tuning, etc., which requires a lot of machine learning knowledge a...

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): G06N20/00
CPCG06N20/20G06N20/00G06N5/04
Inventor 王敏李瀚乔胜传陶雪军孙越唐继正徐昀
Owner THE FOURTH PARADIGM BEIJING 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