Distributed group intelligent system

A swarm intelligence and distributed technology, applied in transmission systems, resource allocation, program control design, etc., can solve problems such as insufficient data sets, and achieve the effect of reducing difficulty, improving adaptability and processing capacity

Active Publication Date: 2019-09-24
王静逸
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] (4) Multi-agent game and training evol...

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
  • Distributed group intelligent system
  • Distributed group intelligent system
  • Distributed group intelligent system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] Such as Figure 15 As shown, this architecture belongs to a typical HLA architecture, in which federation 1 computing center 1 and federation 2 computing center 2 are the federation central nodes of the two federations respectively; in federation 1, organizational computing unit 1 and organizational computing unit 2 belong to As a member of the federation, the camera belongs to the object as a physical computing unit, and each distributed intelligent node is connected and interacted with each other by installing this system. The system uses different surveillance cameras to form its own small network, and then forms a larger organizational network through network combination. The organization network and the centralized cloud platform are combined to give full play to the computing power of the camera. The system recognizes tasks through parallel computing, shares machine learning models, video codec computing resources and shared data through networking, and then indu...

Embodiment 2

[0099] Such as Figure 16 As shown, this is a typical DDS model, a flat terrain environment, coordination of multi-entity (multi-person, multi-vehicle, etc.) calculations, including AI simulation, AI coordination (traffic coordination) and other methods of architecture.

[0100] The architecture divides the entire terrain into 4 areas. Different areas publish different DDS topics. The computing platform unit in each area is the topic, and the non-stop entity computing unit is the publisher or subscriber. The related computing entities (vehicles) can pass their respective The theme of the area, the synchronization of distributed data, model calculation.

[0101] Furthermore, because the distributed intelligent system also supports other systems, it is also possible to realize distributed group AI decision-making through the synchronization and parallel computing of the distributed intelligent system and other topics.

Embodiment 3

[0103] In the distributed swarm intelligence system, through the combination of the software development kit (SDK) and the agent computing layer, it supports the coordinated operation of multi-computing entities and agents, and uses distributed intelligent nodes as Multi-Agents to share computing models and data messages routing channel.

[0104] The distributed swarm intelligence system will support asynchronous computing and data synchronization mechanisms between tensorflow and agents, support distributed machine learning, and achieve a collaborative mechanism among multiple agents. Specific distributed machine learning system structure diagram, such as Figure 17 Shown:

[0105] Among the commonly used machine learning algorithm categories, such as inductive learning, analogy learning, reinforcement learning, analytical learning, genetic algorithm, etc., each algorithm is processed by an agent. work independently, and the data and computational models coordinate with eac...

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 distributed swarm intelligence system comprises an underlying protocol layer used for adapting to a network protocol; a core software platform layer, used for calling computing resources of an external system platform and supporting a distributed system, a consistency algorithm and a computing model; an open software layer, used for providing an open source system framework. The distributed system at least comprises one or more of an HLA system, a DDS system and a Multi-Agent system. According to the system, the problems of large-scale calculation, calculation model splitting, cooperation of multiple intelligent expert systems, swarm intelligence decision making, intelligent system decision making flexible organization and the like are solved.

Description

technical field [0001] The patent of the present invention relates to the field of computer distributed systems, especially to the field of distributed artificial intelligence group decision-making systems under different distributed systems. Background technique [0002] In recent years, with the breakthrough of neural network, artificial intelligence has been greatly developed, especially in the fields of image, analysis, recommendation and so on. With the rapid development of artificial intelligence, problems such as the continuous expansion of computing scale, too single expert system, the flexibility of neural network models, and the complexity of application fields are also constantly escalating. In such an environment, the development of distributed artificial intelligence is put on the agenda by research institutions and large enterprises. The existing more popular distributed systems mainly include the following three types. [0003] 1. Distributed solution of Ten...

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
IPC IPC(8): H04L29/08G06F9/50H04L29/06
CPCH04L67/10H04L67/1059H04L67/1095G06F9/5083H04L69/162H04L67/56
Inventor 王静逸
Owner 王静逸
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