Multi-dimensional expansion prediction method and device for non-stationary time series data
A technology for time series and forecasting methods, applied in the field of multi-dimensional expansion forecasting of non-stationary time series data, can solve problems such as processing, incompetence in time series forecasting tasks, lack of modeling, etc., to achieve the effect of strong expression ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] The present invention is realized through the following technical solutions, as figure 1 As shown, a multi-dimensional extended forecasting method for non-stationary time series data, including the following steps:
[0035] Step S1: Collect the original meter reading data, process the original meter reading data, and expand the data dimension to construct the meter reading data set.
[0036] The original meter reading data collected by the meter is composed of two parts: the remote transmission data of the meter and the manual meter reading data. The original meter reading data has differences in time steps and belongs to a non-stationary time series. The dimension of the original meter reading data is expanded, and the dimension of the expanded original meter reading data includes meter number, meter reading time, and meter reading reading.
[0037] Perform granular processing on the meter reading time of the expanded original meter reading data, align the remote data...
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