Managing an installed base of artificial intelligence modules

An installation base, artificial intelligence technology, applied in computing models, biological neural network models, instruments, etc., can solve problems that cannot represent all situations expected to be processed by artificial intelligence modules, training data scarce resources, etc.

Pending Publication Date: 2021-09-03
ABB (SCHWEIZ) AG
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The training of more complex AI modules still requires a lot of effort
Specifically, for a particular application, the training data that constitutes the "ground truth" may be a scarce resource, and / or they may not be representative of all situations that the AI ​​module is expected to handle

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
  • Managing an installed base of artificial intelligence modules
  • Managing an installed base of artificial intelligence modules

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] figure 1 A flowchart of an exemplary embodiment of method 100 is shown. In this example, the different domains 1a-1d where the AI ​​modules 2a-2d are applied are the different plants where the AI ​​modules 2a-2d are located. In step 110, paired input data 21 and corresponding output data 22, and / or paired training Input data 21a and corresponding reference data 23a, and / or configuration parameters 22a. The collected data 21 , 23 , data 21 a , 23 a and / or the collected parameters 22 a relate to operating situations of the AI ​​modules 2 a - 2 d which are identical or sufficiently similar according to predetermined quantitative similarity criteria 3 . An exemplary implementation is to first collect data from all AI modules 2a, 2b, 2c, 2d according to box 111 and then select only data 21', 23', 23', Data 21a', 23a', and / or configuration parameters 22a' such that similarity criterion 3 is satisfied.

[0062] In step 120, pairs of input data 21 and corresponding output ...

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

A method (100) for managing an installed base of multiple artificial intelligence, AI, modules (2a-2d) comprising: obtaining (110), from multiple AI modules (2a-2d) and / or application domains (la- Id), pairs of input data (21) and corresponding output data (22), and / or pairs of training input data (21a) and corresponding reference data (23a), and / or configuration parameters (22a) relating to same or sufficiently similar operating situations according to a predetermined quantitative similarity criterion (3); and aggregating (120) the data (21, 23; 2 la, 23a), to form augmented training data (4) for training AI modules (2a-2d); and / or aggregating (130) the configuration parameters (22a), to form augmented configuration parameters (5) for configuring the internal processing chain (22) of AI modules (2a-2d); and / or determining (140), based at least in part on the data (21, 23), a quantitative indicator (6a-6d) for AI module (2a-2d) performance according to a predetermined quality criterion (6).

Description

technical field [0001] The invention relates to the management of an installed base of artificial intelligence modules that can be applied to different domains serving different purposes. Background technique [0002] In many industrial processes it is necessary to find a set of process parameters acting on the process in order to optimize some desired quantity, such as throughput, energy consumption or raw material usage. Most optimization solutions are built on mathematical models, and the creation of mathematical models is a skill that is largely performed manually. Mathematical models are usually associated with individual plants, so very little work can be reused when moving to a different plant. [0003] Neural networks and other artificial intelligence modules can be automatically trained for applications. Using the training input data and reference data as the "ground truth", the parameters that determine the behavior of the module are optimized so that when the tr...

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): G06N3/04
CPCG06N3/045G06N20/00
Inventor 迪尔克·舒尔茨
Owner ABB (SCHWEIZ) AG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap