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

Reducing errors introduced by model updates

A model and original model technology, applied in the direction of computing model, database model, computer system based on knowledge mode, etc., can solve the problem of inaccurate population assignment, etc., to reduce effective downtime, improve efficiency, high efficiency and Effects of an efficient model update process

Pending Publication Date: 2020-09-22
GOOGLE LLC
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Variations in paths between different models and the resulting outputs can lead to inaccurate model-based population assignments

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
  • Reducing errors introduced by model updates
  • Reducing errors introduced by model updates
  • Reducing errors introduced by model updates

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] This document describes methods, systems, and apparatus for improving output consistency between analytical models. In some cases, model updates result in different outputs for the same unique input, and the difference between the results of the updated model and the original model can lead to inefficiencies. If a decision tree model provides output that represents the allocation of resources, differences between the results of the previous model and the new model may cause resources to be reallocated. For example, if a decision tree model receives an input representing a seat in a conference room in building A and provides an output representing a unique person to be assigned to a seat in building A, but that unique person has already been assigned to Seats in different meeting rooms in building B, moving people to meeting rooms in different buildings will cause inconvenience to people and inefficiency in scheduling. In another example, if a model receives input repre...

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

Methods, systems, and computer readable medium for reducing inconsistencies in output between an original model and a new model. The method includes receiving an original model and a new model, mapping structures of the new model to structures of the original model, classifying each structure of the new model as belonging to a group of the original model, an unused group not in the original model,a subset of a group of the original model, or a merged set of a first and a second, different group of the original model, generating a merged model based on the mapping and classifying, and classifying a unique entities, using the merged model, by applying consistent hashing to each of the unique entities.

Description

Background technique [0001] This document is concerned with providing a model generation process that reduces variance in output introduced by changes in the analytical model. For a particular input, the updated model can use a different decision path to determine the output for that particular input than the previous version of the model. Variations in paths between different models and the resulting outputs can lead to model-based inaccurate population assignments. Contents of the invention [0002] In general, an innovative aspect of the subject matter described in this specification can be implemented in a method comprising receiving as input at one or more data processing devices an original model and a new model, the new model being generated from the original model but different from the original model is different; the structure of the new model is mapped to the structure of the original model by one or more data processing devices; each structure of the new model i...

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): G06F16/28G06N5/00
CPCG06F16/28G06N5/022G06N5/01G06F16/285G06N20/20G06F16/2246G06F16/2255
Inventor Z.C.弗雷泽A.乌尔布里奇T.A.沃恩Z.王蔡昇甫E.斯科沃尔佐夫
Owner GOOGLE LLC
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