Network intelligent operation and maintenance knowledge graph collaborative construction and sharing method and device
A technology of knowledge graph and network intelligence, which is applied in the field of collaborative construction and sharing of knowledge graphs for network intelligent operation and maintenance, which can solve problems such as collaborative construction and achieve the effect of solving repeated judgments.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] Such as figure 1 Shown is a network intelligent operation and maintenance knowledge map collaborative construction and sharing method provided by the present invention, including:
[0053] S1. Construct a high-dimensional space unified representation model;
[0054] S2. Based on the high-dimensional space unified representation model, the knowledge graphs corresponding to different time, different manufacturers, and different network devices are expressed as knowledge graph increments, and are arranged in an orderly manner in the high-dimensional space according to dimensions to build network operation and maintenance High-dimensional collaborative model of knowledge graph;
[0055] S3. In the high-dimensional collaborative model of the network operation and maintenance knowledge graph, input the characteristics of the entity into the multi-factor weighted distance measurement formula, and output the entity semantic similarity set;
[0056] S4. Traverse the entity sem...
Embodiment 2
[0076] Such as figure 2 As shown, it is a high-dimensional collaborative representation method of network operation and maintenance knowledge graph in the embodiment of the present invention. In order to clearly describe the construction method of high-dimensional space, the present invention takes four-dimensional space as an example. The construction method of higher-dimensional space is consistent with the construction of four-dimensional space, and the dimension of space is determined by the number of entities and relationships in the knowledge map. of.
[0077] The four-dimensional collaborative representation model proposed by the patent is S=I abcd , dimension I d Specify the embedding position of different knowledge map increments in the high-dimensional space, figure 2 The knowledge graph incremental embedding on the right is in dimension I d The position corresponding to the value 1 is represented as I in the present invention abc,1 .
[0078] In the process ...
Embodiment 3
[0086] The present invention proposes a multi-factor weighted distance measurement method, which includes two coefficients ε and β. Table 3 is used to illustrate the assignment method of coefficient ε. In this embodiment, the optical network health degree of manufacturer A is defined into three categories, and the optical network health degree of manufacturer B is divided into five levels.
[0087] Table 3 Examples of optical network health classification of two manufacturers
[0088]
[0089] In the above table, by multiplying the health degrees of two manufacturers, 15 categories (3 times 5) can be obtained, and the ranking is performed according to the possibility of network degradation caused by the health degree classification product, and then assigned. In Table 2, an example of sorting is given as follows: (health, level one), (health, level two), (sub-health, level one), (sub-health, level two), (health, level three)... (unhealthy, five levels), this ranking can b...
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