AI dynamic injection control method and device based on network data pool

A network data and dynamic injection technology, applied in the field of network artificial intelligence, to achieve good versatility, low loose coupling, and improve AI performance

Active Publication Date: 2021-09-24
FENGHUO COMM SCI & TECH CO LTD +1
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is how to realize the online high-speed re-reasoning and training of the AI ​​model based on the unified data pool of the platform layer of the network management and control system based on the AI ​​model of the network artificial intelligence application layer, so as to improve the efficiency of data acquisition and network AI model calculation, and effectively improve Overall performance of web applications

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
  • AI dynamic injection control method and device based on network data pool
  • AI dynamic injection control method and device based on network data pool
  • AI dynamic injection control method and device based on network data pool

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Embodiment 1 of the present invention provides a control method for AI dynamic injection based on a network data pool. The network application encodes the network AI model according to a unified protocol (also described as an interaction protocol), and compresses and packages the network AI model according to the unified protocol. Such as figure 1 and figure 2 As shown, the methods include:

[0052] In step 201, the network AI model is remotely injected and uploaded, and the request processing for the training and / or reasoning of the network AI model is dynamically triggered as needed.

[0053] For example: remote procedure call (Remote Procedure Call, abbreviated as: RPC) is used to realize the remote injection and upload of the network AI model, and dynamically trigger the request for reasoning and / or training of the network AI model on demand.

[0054] Among them, in dynamically triggering the reasoning and training of the network AI model, a training sandbox envi...

Embodiment 2

[0132] Such as Figure 7 As shown, it is a schematic diagram of the structure of the control device for AI dynamic injection based on the network data pool according to the embodiment of the present invention. The device for controlling AI dynamic injection based on a network data pool in this embodiment includes one or more processors 21 and a memory 22 . in, Figure 7 A processor 21 is taken as an example.

[0133] Processor 21 and memory 22 can be connected by bus or other means, Figure 7 Take connection via bus as an example.

[0134] The memory 22, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs and non-volatile computer-executable programs, such as the control of AI dynamic injection based on the network data pool in Embodiment 1 method. The processor 21 executes the control method of AI dynamic injection based on the network data pool by running the non-volatile software programs and instructions stored in th...

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 relates to the technical field of network artificial intelligence, and provides an AI dynamic injection control method and device based on a network data pool. The method comprises the following steps: performing remote injection and uploading on a network AI model, and dynamically triggering a training and/or reasoning request on the network AI model as required; acquiring real transmission parameters of current network AI model calculation and data collection from the context of the request; enabling the data pool to start a calculation process of training and/or reasoning of a network AI model; and obtaining a training state and/or a reasoning result of the network AI model. According to the control method for dynamically injecting the network AI model in the operation period and enabling the AI model to conduct reasoning and training on the near data side, the online reasoning and training performance of the AI model can be effectively improved, and meanwhile loose coupling and low intrusion among network application, the AI model and a network data pool are kept.

Description

【Technical field】 [0001] The invention relates to the technical field of network artificial intelligence, in particular to a control method and device for AI dynamic injection based on a network data pool. 【Background technique】 [0002] The application of artificial intelligence in telecom networks is diverse, and the scenarios cover the entire life cycle of network intelligent operation and maintenance, such as: intelligent analysis and positioning of network faults, intelligent optimization of network performance, intelligent prediction of network traffic, etc. In a telecom network intelligent management and control system, these upper-layer network applications often obtain data by accessing the unified network data pool provided by the management and control system platform layer, which is used for training and reasoning of various internal AI models, such as: network Topology data, configuration data, business data, operation data (alarms, performance, status, events),...

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): G06N20/00G06N5/04
CPCG06N20/00G06N5/04Y02D10/00
Inventor 毕千筠
Owner FENGHUO COMM SCI & TECH CO LTD
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