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

A model training and a prediction method and a device based on the model training

A technology of model training and training modules, applied in the field of big data science, can solve the problem of low prediction accuracy of the model and achieve the effect of improving the prediction accuracy

Inactive Publication Date: 2019-01-18
北京鑫毅数字科技有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a model training and prediction method and device based on model training to solve the problem of low accuracy of model prediction in the prior art

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
  • A model training and a prediction method and a device based on the model training
  • A model training and a prediction method and a device based on the model training
  • A model training and a prediction method and a device based on the model training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] figure 1 It is a schematic diagram of a model training process provided by an embodiment of the present invention, and the process includes:

[0040] S101: For each layer of sub-models of the model to be trained, identify whether the layer of sub-models is the last layer of sub-models of the model to be trained, if not, go to S102, if yes, go to S103.

[0041] The data quality detection method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device may be a device such as a mobile phone, a personal computer (PC), or a tablet computer, or may be a device such as a server or a server cluster.

[0042] In the embodiment of the present invention, the model to be trained includes at least two layers of sub-models, and the algorithms corresponding to each layer of sub-models can be the same or different, for example: the model to be trained includes three layers of sub-models, and each layer of sub-models can correspon...

Embodiment 2

[0052] In order to ensure the effect of training each layer of sub-models, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, each sample data that has contained positive or negative sample labels in the training set is input to the layer of sub-models In, before training the layer sub-model, the method also includes:

[0053] Judging whether the number of sample data in the training set is greater than a set number threshold;

[0054] If yes, proceed to the next steps;

[0055] If not, a warning message is issued.

[0056] Specifically, if the number of sample data for training the sub-model is too small, the accuracy of the sub-model will be reduced. In the embodiment of the present invention, in order to prevent the number of sample data for training the sub-model from being too small, the Before the sub-model is trained, it is judged whether the number of sample data in the training set is greater than the set number threshold; i...

Embodiment 3

[0058] image 3 A schematic diagram of a prediction process based on the above-mentioned model training process provided by an embodiment of the present invention, the process includes:

[0059] S301: Input the data to be detected into the trained model.

[0060] S302: Based on the trained model, output a result of predicting whether the data to be detected is positive sample data.

[0061] Specifically, after the model training is completed through the training set containing a large number of positive sample data and negative sample data, the data to be tested is input into the training model, and the trained model is based on each layer of sub-models that have been trained, and is completed according to the training Each sub-model of each layer determines the confidence of the data to be detected corresponding to the positive sample data, and when the confidence of the data to be detected corresponding to the positive sample data determined by the sub-model is greater than...

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 model training and a prediction method and a device based on the model training. The method comprises the following steps: identifying whether the layer sub-model is the lastlayer sub-model according to each layer sub-model of the model to be trained which includes at least two layer sub-models in turn; If not, inputting each sample data in the training set containing positive or negative sample tags into the layered sub-model to train the layered sub-model; And updating the sample data in the training set by using the sample data whose confidence level of the corresponding positive sample data in the training set is greater than the confidence level threshold value corresponding to the layer sub-model based on the confidence level of each sample data corresponding to the positive sample data in the training set output by the layer sub-model after training; If yes, inputting each sample data in the training set containing positive or negative sample tags intothe layered sub-model, and training the layered sub-model to improve the prediction accuracy of the model.

Description

technical field [0001] The invention relates to the field of big data science and technology, in particular to a model training and a prediction method and device based on model training. Background technique [0002] With the rapid development of economy and informatization, big data emerges as the times require. Big data refers to a collection of data whose scale exceeds the capabilities of traditional database software tools in terms of acquisition, storage, management, and analysis. Data analysis and prediction can provide strong support for business and decision-making of enterprises. In the face of massive data in the era of big data, traditional manual data analysis and data value mining are no longer applicable, and the emergence of artificial intelligence technology provides a better solution for big data data analysis and data value mining . [0003] The application of the existing artificial intelligence model usually requires the user to select appropriate trai...

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): G06Q10/04G06Q40/02G06N3/04G06K9/62
CPCG06Q10/04G06N3/045G06Q40/03G06F18/214
Inventor 曾伟雄
Owner 北京鑫毅数字科技有限公司
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