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

Prediction model establishment method and system, object recommendation method and system, equipment and storage medium

A technology for forecasting models and building methods, applied in character and pattern recognition, instruments, buying and selling/lease transactions, etc., can solve the problem of low accuracy of forecasting models, and achieve the effect of reducing the sparseness of feature sample data and improving accuracy

Pending Publication Date: 2019-06-11
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defect that the accuracy of the prediction model obtained by using the model training method of the prior art is not high, and to provide a prediction model establishment, object recommendation method and system, equipment and storage medium

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
  • Prediction model establishment method and system, object recommendation method and system, equipment and storage medium
  • Prediction model establishment method and system, object recommendation method and system, equipment and storage medium
  • Prediction model establishment method and system, object recommendation method and system, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Such as figure 1 As shown, the method for establishing the predictive model of the present embodiment includes the following steps:

[0079] Step 101. Obtain user data and object data, and extract multiple user features and multiple object features from the user data and object data respectively to form a feature matrix.

[0080] In step 101, the extraction of multiple user features and multiple user features is related to the features that users ultimately need to predict (output features of the predictive model). ) have influence on all independent variable characteristics. Feature usability evaluation, including feature acquisition difficulty, feature coverage, feature accuracy, etc.

[0081] For example, in an e-commerce website, analysts can select at least one of the following characteristics as user characteristics: user gender, user level, user device address, user age, user network information (whether the mobile terminal currently used by the user is a 4G ne...

Embodiment 2

[0115] image 3 It is a schematic structural diagram of an electronic device provided by Embodiment 2 of the present invention. image 3 A block diagram of an exemplary electronic device 30 suitable for implementing embodiments of the invention is shown. image 3 The electronic device 30 shown is only an example, and should not limit the functions and scope of use of the embodiments of the present invention.

[0116] Such as image 3 As shown, electronic device 30 may take the form of a general-purpose computing device, which may be a server device, for example. Components of the electronic device 30 may include, but are not limited to: at least one processor 31 , at least one memory 32 , and a bus 33 connecting different system components (including the memory 32 and the processor 31 ).

[0117] The bus 33 includes a data bus, an address bus, and a control bus.

[0118] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache me...

Embodiment 3

[0124] This embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the method for establishing a prediction model provided in Embodiment 1 are implemented.

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 prediction model establishment and object recommendation method and system, equipment and a storage medium. The establishment method of the prediction model comprises the following steps: obtaining user data and object data, and respectively extracting a plurality of user characteristics and a plurality of object characteristics from the user data and the object data to form a characteristic matrix; Establishing an implicit vector representing the relevance between the features in the feature matrix based on a factor decomposition mechanism; Inputting the hidden vector as a training sample into a GBDT model, and performing training to obtain a prediction model of prediction object characteristics; Wherein the prediction model is used for predicting object characteristics of an object. Based on the factorization machine, the feature engineering construction is carried out. The feature sample data caused by One-hot coding is no longer sparse, and the influence of cross-term feature learning is insufficient. The hidden vector output by the factorization machine is used as the training sample to obtain the prediction model, which effectively improves. The accuracy of the model.

Description

technical field [0001] The present invention relates to the field of machine learning, in particular to a prediction model establishment and object recommendation method and system, equipment and storage medium. Background technique [0002] For the field of machine learning, the popular saying in the industry is that data and features determine the upper limit of machine learning, and models and algorithms are just methods to approach this upper limit. Therefore, if we want to pursue higher prediction accuracy, feature engineering construction is an essential step. [0003] In the prior art, feature engineering construction is implemented based on One-hot encoding (one-hot encoding), and then the coefficients of each feature are obtained through a linear regression model, and then the coefficients of these features are substituted into the linear model to obtain a feature model. However, after one-hot encoding, the features will become sparse, so that the cross-feature lea...

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): G06K9/62G06Q30/06
Inventor 王颖帅李晓霞苗诗雨
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO 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