Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

User behavior machine learning model training method and device

A machine learning model and training device technology, applied in the computer field, can solve the problems of reducing the accuracy of user behavior prediction and ignoring the impact

Active Publication Date: 2014-12-24
ALIBABA GRP HLDG LTD
View PDF3 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both of the above situations will reduce the accuracy of user behavior prediction;
[0012] 2) Although the use of feature dimensionality reduction achieves the purpose of enhancing statistical information, it ignores the impact of removed features on statistical values
[0013] 3) Feature dimensionality reduction still cannot completely solve the problem that the "traffic number" corresponding to some special feature sets is too small, because this is a natural attribute of the sample set

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
  • User behavior machine learning model training method and device
  • User behavior machine learning model training method and device
  • User behavior machine learning model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] This embodiment introduces a method for training a machine learning model of user behavior, such as figure 1 As shown, the method includes the following steps.

[0053] Step 101: Collect historical access data of users.

[0054] Step 102: Classify and aggregate the user's historical access data according to a feature set containing one or more dimensions to form multiple samples.

[0055] Specifically, the feature set includes features of historical access data in one or more dimensions. Select one or more dimensions as the base dimension. Collect historical access data with the same feature value of the feature corresponding to the reference dimension as a sample.

[0056] Each sample contains the characteristic value corresponding to the characteristic of the user's historical access data in the reference dimension. The dimension may include the dimension of the user and the dimension of the user's access object. For example, the characteristic corresponding to the dimensio...

Embodiment 2

[0082] In this embodiment, the method in embodiment 1 is used to predict user behavior, such as Figure 4 As shown, including the following steps:

[0083] Step 401, select any sample point in the sample set as the target point P obj Calculate the statistical information of the target point, and determine whether the traffic (pv) number in the statistical information of the target point is greater than the first threshold (lowPv_th) of the traffic number, if it is greater, go to step 402, if not, go to step 403;

[0084] The function of lowPv_th is as follows: if the pv of the target point is greater than or equal to lowPv_th, it is considered that the statistical information of the target point is sufficient, and there is no need to find neighboring points, and a new sample is formed to train the machine learning model to predict user behaviors directly based on the statistical information of the target point. If the pv of the target point is less than lowPv_th, it is considered ...

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 a user behavior machine learning model training method and device, solves the data sparseness problem without feature reduction and improves the accuracy of user behavior prediction. The method includes collecting historical access data of a user; classifying and concentrating the historical access data of the user according to a characteristic set containing one or multiple dimensions, and acquiring a plurality of samples; calculating user behavior statistic information, including user's traffic quantity, corresponding to each sample; when the user's traffic quantity corresponding to a current sample is smaller than a first threshold, calculating the distance between the current sample and the other samples; selecting the samples with the distances smaller than the threshold to serve as adjacent samples of the current sample; combining the user behavior statistic information of the current sample with the user behavior statistic information of the adjacent samples and generate new samples; utilizing new samples to train the pre-established machine learning model used for predicting the user behavior according to characteristic values of different dimensions of the characteristic set.

Description

Technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for training a machine learning model of user behavior. Background technique [0002] Non-search advertisements are different from keyword advertisements placed in search engines. [0003] The information recommendation scheme includes information recommendation methods based on keywords and information recommendation methods based on user visit history. The keyword-based information recommendation method is to determine the information pushed to the user according to the keywords entered by the user in the search engine. The information recommendation method based on the user's access history pushes the user information that may be of interest to the user based on the user's historical access log. [0004] The information delivery platform is an intermediary platform that provides information delivery services for website owners and information publishers. The in...

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): G06F17/30
CPCG06F16/337G06F16/35
Inventor 何宪殷维栋孟晓楠
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com