Prediction method and device based on historical data

A technology of historical data and forecasting methods, applied in the field of data processing, can solve the problem that the accuracy of the regression forecast results is not ideal, and the fit regression function cannot be found.

Inactive Publication Date: 2017-06-30
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the prediction accuracy of the regression analysis method depends on the regression function. When the law of historical data is complex, it may not be possible to find a regression function with a high degree of fitting. In this case, the accuracy of the regression prediction result is not ideal.

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
  • Prediction method and device based on historical data
  • Prediction method and device based on historical data
  • Prediction method and device based on historical data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] see figure 1 , which is a flowchart of a prediction method based on historical data provided in Embodiment 1 of the present application.

[0040] The prediction method based on historical data provided in this embodiment includes the following steps:

[0041] Step S101: Obtain the historical data of the forecast item, and use the neural network system to train the historical data to obtain a forecast model.

[0042] In this embodiment, the forecast item refers to an item or items that need to be forecasted for future data, such as forecasting the number of online users, network traffic, network delay time, and the like. In this embodiment, the future data is predicted according to the historical data of the forecast item. The historical data includes the historical data of the predictive item itself and the relevant historical data of the predictive item, the historical data of the predictive item itself is the historical data of the predictive item itself, and the hi...

Embodiment 2

[0098] see Figure 4 , which is a structural block diagram of a prediction device based on historical data provided in Embodiment 2 of the present application.

[0099] The prediction device based on historical data provided in this embodiment includes: a historical data acquisition unit 101, a training unit 102, and a prediction unit 103;

[0100] Wherein, the historical data acquisition unit 101 is configured to acquire historical data of the forecast item;

[0101] The training unit 102 is configured to use a neural network system to train the historical data to obtain a prediction model, the historical data includes the historical data of the predicted item itself and the related historical data of the predicted item, and the predicted The model reflects the relationship between said own historical data and related historical data;

[0102] The forecasting unit 103 is configured to obtain relevant actual data of the forecast item, and obtain the actual data of the foreca...

Embodiment 3

[0113] Correspondingly, the embodiment of the present application also provides a terminal device, see Figure 5 As shown, the terminal equipment may include:

[0114] Processor 1001 , memory 1002 , input device 1003 and output device 1004 .

[0115] The number of processors 1001 in the terminal device may be one or more, Figure 5 Take a processor as an example. In some embodiments of the present application, the processor 1001, the memory 1002, the input device 1003 and the output device 1004 may be connected via a bus or other means, wherein, Figure 5 Take connection via bus as an example.

[0116] The memory 1002 may be used to store software programs and modules, and the processor 1001 executes various functional applications and data processing of the terminal device by running the software programs and modules stored in the memory 1002 . The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an ...

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 embodiment of the invention discloses a prediction method and device based on historical data, and the method and device effectively improve the precision of a prediction result. The method comprises the steps: obtaining the historical data of a prediction item, carrying out the training of the historical data through a neural network system, and obtaining a prediction model, wherein the historical data comprises the historical data of the prediction item and the related historical data of the prediction item, and the prediction model reflects the relation between the historical data of the prediction item and the related historical data of the prediction item; obtaining the related actual data of the prediction item, and achieving the prediction of the actual data based on the historical data of the prediction item according to the related actual data and the actual data, obtained by the prediction model, of the prediction item.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a prediction method and device based on historical data. Background technique [0002] At present, there are many application scenarios that need to predict future data based on historical data according to certain rules, such as predicting the number of online users at a certain point in the future or at certain points in time based on the historical number of online users of the application, so that the adaptability can be increased or decreased accordingly computer resources, or push certain services, etc. For another example, predict future network traffic data based on historical network traffic data, or predict future network delay data based on historical network delay data. [0003] The existing more popular forecasting method is the regression analysis method, which finds the functional expression of the historical forecast data and its related historical data t...

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 Applications(China)
IPC IPC(8): G06Q10/04G06N3/02
CPCG06N3/02G06Q10/04
Inventor 雷航洪楷刘伟
Owner TENCENT TECH (SHENZHEN) CO LTD
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