Urban road network link prediction method, system and storage medium
A link prediction and urban road network technology, applied in the field of urban transportation, can solve the problem of unoptimistic scalability of the single-layer linear limitation model, and achieve the effect of preventing over-fitting
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0028] This embodiment discloses a method for predicting urban road network links.
[0029] For ease of description, some terms used in this embodiment are explained as follows:
[0030] [Link Prediction]: Define graph G=(V, E) as an undirected connected graph, V is the set of all nodes in G, and E is the set of edges. Define n=|V|, n is the number of nodes in graph G, m=|E| is the number of edges in graph G, then there are n(n–1) / 2 node pairs in the network, and U is the total number of node pairs Set, |U|=n(n–1) / 2,. Given the state of each pair of nodes in graph G at time δ, the link prediction problem can be formally described as inferring a subset of missing links in the current state or that will be formed at time H+t.
[0031] [Adjacency matrix]: Define matrix A as the adjacency matrix of graph G. Matrix A satisfies the following conditions,
[0032]
[0033] The adjacency matrix A is a symmetric matrix, the diagonal elements are all 0, and each row sum (column su...
Embodiment 2
[0119] This embodiment discloses a system for predicting urban road network links, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps of the above method are realized. .
Embodiment 3
[0121] This embodiment discloses a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.
[0122] In summary, the urban road network link prediction method, system and storage medium disclosed in the above-mentioned embodiments of the present invention have the following beneficial effects:
[0123] On the one hand, there is no derivation calculation of the Sigmoid function in the loss function used. The weight update of the weight matrix depends on the error. The larger the error, the faster the update, and the smaller the error, the slower the update, thus avoiding the existing cost of variance. When the function is a loss function, the weight matrix update is too slow due to the nature of the Sigmoid function.
[0124] On the other hand, in the loss function adopted, the limitation of local linear embedding is added, so that after the network performs represent...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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