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

A vehicle networking knowledge base representation method, device and system

A knowledge representation and Internet of Vehicles technology, applied in the field of Internet of Vehicles, can solve problems such as difficulties and shortages, and achieve the effects of fast memory operation, low space complexity, and flexible knowledge sampling methods

Active Publication Date: 2022-03-29
HUAWEI TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the lack of general and basic means applicable to the entire IOV field, there are still great difficulties in AGI-style learning in the IOV field

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 vehicle networking knowledge base representation method, device and system
  • A vehicle networking knowledge base representation method, device and system
  • A vehicle networking knowledge base representation method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0290] Example 1: SC-based IOV knowledge representation

[0291] ○Use SC as the carrier of knowledge on IOV multi-dimensional continuous space to perform discrete sampling and continuous deduction.

[0292] Represent an IOV knowledge f:R with a k-dimensional SC with a k'-dimensional function value k →R k’ (that is, a function with k input variables and k' output values: 1 ,…,x k >→1 ,…,y k’ >):

[0293] Any point in SC represents an input point of f;

[0294] ■Any point in SC has a k-dimensional coordinate, that is, the value of k input variables at this point;

[0295] ■Any point in SC has a k'-dimensional function value, that is, the k' output values ​​of f at this point.

[0296] ●Discrete sampling, continuous deduction:

[0297] ■Discrete sampling: The vertices of SC are used as sampling points, and only the coordinates and function values ​​are recorded at these points, and not at other points (non-sampling points).

[0298] ■Continuous deduction: Use SC units as ...

Embodiment 2

[0301] Embodiment 2: Import method of SC-based IOV existing knowledge

[0302] ○Designed a general method of importing knowledge into SC (that is, the initialization method of the knowledge base): first select the appropriate set of SC vertices (discrete sampling points), and calculate the function value on each vertex, and then establish SC units to seamlessly Connect the vertices.

[0303] ○ In particular, the existing knowledge also includes the knowledge from the rule-based IOV system, thereby realizing the re-expression and import of the existing rules (technical problem 1).

Embodiment 3

[0304] Example 3: SC-based IOV knowledge point fast location method

[0305] ○ Designed a method to speed up the search by attaching additional clues: the problem of directly searching for the target unit where a given target point is located is transformed into an indirect search process: first determine a starting unit and starting point for the search, and then start from the Starting from the starting element, along the ray from the starting point to the target point, the target element is searched linearly. In this way, the originally vast search space (the entire SC) can be reduced to a series of units penetrated by the rays, and an exponential search speedup can be obtained, thereby making up for the biggest shortcoming of the topological SC (technical problem 6).

[0306] ○The acquisition method of additional clues is designed: the entire SC space is structured and partitioned, and according to the continuity of multiple positioning, the proxy unit in the area where 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

An embodiment of the present invention provides a method for representing IOV knowledge of the Internet of Vehicles based on a simple complex SC, the method includes: using a k-dimensional SC with a k'-dimensional function value to represent k'-dimensional knowledge on a k-dimensional continuous space; wherein , the coordinates of the vertices of SC are the values ​​of k input variables (x 1 ,...,x k ), the function value on the vertex is the k' output value of the function (y 1 ,...,y k’ ), the relationship between the two is: (y 1 ,...,y k’ ) = f(x 1 ,...,x k’ ), where f is a correspondence function based on IOV knowledge; k and k' are natural numbers; the boundary of SC is used to represent the safety boundary of IOV knowledge, wherein, IOV knowledge includes the steering wheel angle of the autonomous vehicle, the road curvature and the autonomous vehicle The speed of the vehicle and the relationship between the parameters conform to the objective laws of vehicle dynamics, wherein the steering wheel angle of the self-driving vehicle, the curvature of the road and the speed of the self-driving vehicle are obtained through the sensors on the self-driving vehicle.

Description

technical field [0001] The invention relates to the field of Internet of Vehicles, in particular to a method, device and system for representing a knowledge base of the Internet of Vehicles. Background technique [0002] Recently, a clear development trend of the Internet of Vehicles is the transition from a rule-based approach to a learning-based approach. There are two types of transitions: split transitions and fusion transitions. In a fragmented transition, the new learning-based IOV system completely follows the learning method, from scratch, from form to content, completely abandoning the old rule-based system. That is to say, a lot of rules and experience (or knowledge) that were summarized and precipitated under the rule-based framework were also discarded and wasted. In an integrated transition, the knowledge of the rule-based system is applied to the learning-based framework to maximize the energy of the former. In other words, by replacing a rule-based system w...

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 Patents(China)
IPC IPC(8): G06F16/22
CPCG06N5/022G06N20/00G06N3/08G06N3/042B60W2552/30B60W30/08B62D15/021G06N5/025
Inventor 殷晓田李剑陶永祥
Owner HUAWEI TECH CO LTD
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