Federal learning-based prediction method and device, storage medium and remote sensing equipment

A prediction method and a technology of a prediction device, applied in the field of data processing, can solve problems such as untimeliness, inaccuracy, and delay of data analysis results, and achieve the effects of improving speed and efficiency, breaking technical bottlenecks, and realizing comprehensive utilization

Pending Publication Date: 2021-08-27
杭州煋辰数智科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technology is relatively rigid. The existing remote sensing technology is difficult and costly. The data obtained by remote sensing equipment is very precious, and it is easily affected by external factors during the normal data transmission process, such as the requirements from the

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
  • Federal learning-based prediction method and device, storage medium and remote sensing equipment
  • Federal learning-based prediction method and device, storage medium and remote sensing equipment
  • Federal learning-based prediction method and device, storage medium and remote sensing equipment

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0050]

[0051] Said (A) (n) Summarize the total value for the federated analysis model, A is the number of a single remote sensing device, the n is a fixed value to the federated learning prediction program, the i is a natural constant, the a is an uncontrollable variable, and the b is a controllable variable, The p is the number of calculations.

[0052] When i=0,

[0053] when (A) (1) The value tends to 0, indicating that the accuracy of the overall forecast data is low and does not have a large reference, and data processing needs to be re-processed.

[0054] when (A) (1) The value tends to 1, indicating that the overall prediction data is more accurate and has a greater reference value, which can be recorded and processed in a timely manner.

specific Embodiment 2

[0056]

[0057] Said (A) (n) Summarize the total value for the federated analysis model, A is the number of a single remote sensing device, the n is a fixed value to the federated learning prediction program, the i is a natural constant, the a is an uncontrollable variable, and the b is a controllable variable, The p is the number of calculations.

[0058] When i tends to 0,

[0059] when (A) (1) The value tends to 1, indicating that the accuracy of the overall forecast data is low and does not have a large reference, and data processing needs to be re-processed.

[0060] when (A) (1)The value tends to 0, indicating that the overall prediction data is more accurate and has a greater reference value, and it is recorded and processed in a timely manner.

specific Embodiment 3

[0062]

[0063] Said (A) (n) Summarize the total value for the federated analysis model, A is the number of a single remote sensing device, the n is a fixed value to the federated learning prediction program, the i is a natural constant, the a is an uncontrollable variable, and the b is a controllable variable, The p is the number of calculations.

[0064] When i is greater than 0,

[0065] when (A) (1) The value tends to 0, indicating that the accuracy of the overall forecast data is low and does not have a large reference, and data processing needs to be re-processed.

[0066] when (A) (1) The value tends to 1, indicating that the overall prediction data is more accurate and has a greater reference value, which can be recorded and processed in a timely manner.

[0067] Further, the step S3 also includes the following content:

[0068] A. Check the network: timely check the network speed during normal operation to ensure normal transmission;

[0069] B. Check delay...

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

The invention discloses a federal learning-based prediction method and device, a storage medium and remote sensing equipment, and relates to the technical field of data processing. The method comprises the following steps: S1, receiving data: receiving data collected from the outside; and S2, inputting data: inputting the data in the step S1 into a federal learning prediction program. The method has the beneficial effects that network control is carried out on the data based on federal learning prediction, so that network speed and overall fluency delay are relieved during data transmission, and normal data transmission is ensured; screening and formula calculation are carried out on the data based on federated learning prediction, a statistical result enables a part of undemanded data to be directly filtered during data summarization, occupation of a transmission channel is reduced, the transmission speed and efficiency are improved, loss of overall data caused by network disconnection is avoided; and comprehensive utilization of high-altitude data is realized based on federal learning, and the technical bottleneck of data transmission is broken.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a prediction method, device, storage medium and remote sensing equipment based on federated learning. Background technique [0002] With the development of computer technology, more and more technologies are used in the financial field, and the traditional financial industry is gradually transforming into financial technology. However, due to the security and real-time requirements of the financial industry, higher requirements are also placed on technology. At present, more and more remote sensing devices such as artificial satellites are operating at high altitudes, performing their own tasks and obtaining corresponding data. The existing technology is relatively rigid, and the existing remote sensing technology is difficult and costly. The data obtained by remote sensing equipment is very precious, and it is easily affected by external factors during the normal data tr...

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): G06N20/20G06F11/14H04L12/24H04L12/26
CPCG06N20/20G06F11/1464H04L43/0852H04L43/0894H04L41/145H04L41/147
Inventor 顾冉叶薇薇
Owner 杭州煋辰数智科技有限公司
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