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

A model iteration updating method and device

An iterative update and model technology, applied in the computer field, can solve the problem that retraining and updating the knowledge base takes a lot of time, saving time and money costs, improving use efficiency, and reducing the amount of updates.

Inactive Publication Date: 2019-06-18
厦门快商通信息咨询有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above deficiencies in the prior art, the purpose of the present invention is to propose a model iterative update method and device, aiming at solving the problem that the prior art can solve the problem that the system spends a lot of time every time it retrains and updates the knowledge base

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 iteration updating method and device
  • A model iteration updating method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] An embodiment of the present invention provides a method for iteratively updating a model, which specifically includes the following steps:

[0029] Step S11, storing and labeling various models applied to the system. The system includes m algorithms and n sets of development data, and trains the 1st to mth algorithms respectively through the 1st to nth development data to obtain the training After the model group, the model group is marked as Md11, Md12, ..., Md1n, Md21, Md22, ..., Md2n, ..., Mdm1, Mdm2, ..., Mdmn, where n and m are positive integers and n≥1, m ≥1, m represents the serial number of the algorithm, and n represents the serial number of the development data; the first development data trains the 1st to mth algorithms respectively, and respectively obtains the model Md11, model Md12, ..., model Md1n; the second development data respectively trains the first The mth algorithm is trained to obtain the model Md21, the model Md22, ..., the model Md2n respectiv...

Embodiment 2

[0039] The embodiment of the present invention provides another method for iteratively updating the model, which specifically includes the following:

[0040] Step S21, storing and labeling various models applied to the system. The system includes m algorithms and n sets of development data, and trains the 1st to mth algorithms respectively through the 1st to nth development data to obtain the training After the model group, the model group is marked as Md11, Md12, ..., Md1n, Md21, Md22, ..., Md2n, ..., Mdm1, Mdm2, ..., Mdmn, where n and m are positive integers and n≥1, m ≥1, m represents the serial number of the algorithm, and n represents the serial number of the development data;

[0041] In the enumerated examples of the present invention, three kinds of algorithms are applied in a certain set of systems, respectively denoted as A1, A2, A3; the three kinds of algorithms are trained respectively with the first development data D1 and the second development data D2 , the tr...

Embodiment 3

[0050] The present invention also provides that the model iterative update device is applied to the model iterative update method; the model iterative update method is the same as the first and second embodiments, and will not be repeated here. The model iterative updating device has at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor A processor executes to cause the at least one processor to execute the steps of the iterative model updating method.

[0051] The model iterative updating method of the present invention can be stored in a computer-readable storage medium. The above-mentioned software functional units are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, server or network device, etc.) or a processor t...

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 iteration updating method and device, and the method comprises the steps: carrying out the storage and marking of various models for a system; When any development datain the first development data to the nth development data of the system is updated, using the first development data to the mth development data to perform training, generating a new model, and replacing the old model with the new model; Or when any algorithm of the system is improved or a new algorithm is added to the system, generating a new model to replace or add the new model; And screeninga model finally used by the system from the models of the model group by adopting a voting mechanism or a scoring mechanism. By adopting the method and the system, useless updating quantity can be effectively reduced, so that time and money cost are saved, and the use efficiency of the system is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for iteratively updating a model. Background technique [0002] The steps to implement most artificial intelligence technologies in the computer field are as follows: research algorithms, develop models, use developed data to train models, and then apply the trained mature models to actual scenarios. Due to many reasons, it is impossible to train the model to perfection before applying it. One is because of time issues, and the other is that the development data and algorithms used for training will be constantly updated. Whenever the development data and algorithm are updated, in order to make the model achieve better results, the model needs to be retrained. [0003] Multiple models (algorithm + development data) are often used in a system solution. If the development data or algorithm is updated, it is necessary to retrain all these models and update the...

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): G06N5/02
Inventor 洪国强肖龙源李稀敏蔡振华刘晓葳谭玉坤
Owner 厦门快商通信息咨询有限公司
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