Prediction method and method based on multi-source heterogeneous data

A multi-source heterogeneous data and prediction method technology, applied in the field of multi-source heterogeneous data-based prediction methods and devices, can solve the problems of ineffective prediction of game results, less information, poor prediction accuracy, etc., and achieve real-time and the effect of stabilizing the predicted results

Active Publication Date: 2014-12-10
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main defect of this technical solution is that due to the relatively sparse time distribution of the games of each team, there are also changes in the players of the teams, the state fluctuations of the players themselves, and the contingency of the game, etc., so the prediction model obtained based on this is very difficult. It is difficult to m

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 method based on multi-source heterogeneous data
  • Prediction method and method based on multi-source heterogeneous data
  • Prediction method and method based on multi-source heterogeneous data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] figure 1 It is a flow chart of the prediction method based on multi-source heterogeneous data provided by Embodiment 1 of the present invention. The embodiment of the present invention is suitable for predicting the outcome of an event, specifically including the following:

[0022] S110. For a set type of event, obtain at least two types of historical data that can reflect the result of the event;

[0023] The set-type event refers to an event that can be predicted by the method of the embodiment of the present invention, generally an event whose result conforms to a certain probability distribution, typically such as a football match or a basketball match. Historical data refers to historical outcome data for such events. The result of an event can often be expressed from multiple angles, and the result data from each angle can be regarded as one category. For example, for a football game, the score data can be regarded as a type of data that can reflect the result...

Embodiment 2

[0033] figure 2 It is a flow chart of the prediction method based on multi-source heterogeneous data provided by Embodiment 2 of the present invention, image 3 It is a schematic diagram of the relationship between the model and the parameters applicable to Embodiment 2 of the present invention. This embodiment provides a specific implementation plan, specifically taking game prediction as an example for illustration. The method specifically includes:

[0034] S210. For the game, obtain historical scores and historical odds that can reflect the result of the game as two types of historical data;

[0035] This operation takes the historical results of multiple games. Each of the multiple games can be recorded as a game m, m is the serial number of the game, and the value of m ranges from 1 to M. The score of m in each game is recorded as the home team score s m,1 vs away score m,2 , the odds of m in each game are recorded as the main bet p m,1 , P m,2 and customer compen...

Embodiment 3

[0082] Figure 4 A schematic structural diagram of a prediction device based on multi-source heterogeneous data provided by Embodiment 3 of the present invention, the device includes: a data acquisition module 410 , a model estimation module 420 and a result prediction module 430 . Among them, the data acquisition module 410 is used to obtain at least two types of historical data that can reflect the result of the event for the set type of event; the model estimation module 420 is used to establish the attribute data of the set type of event and the at least two types of historical data The joint likelihood model, and determine the optimal estimate of the attribute data according to the maximum a posteriori principle; the result prediction module 430, for the event to be predicted belonging to the set type of event, based on the joint likelihood model A probability distribution associated with the attribute data, and parameters in the probability distribution are determined as...

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 provides a prediction method and method based on multi-source heterogeneous data. The prediction method comprises the steps that at least two categories of historical data which can reflect an event result are obtained according to a set type of events; a joint likelihood model of attribute data of the set type of events and the historical data is built, and optimal estimation of the attribute data is determined according to the maximum posteriori principle; parameters of probability distribution related with the joint likelihood model in the attribute data are determined and used as a prediction result of a to-be-predicted event belonging to the set type of events. According to the prediction method and method based on the multi-source heterogeneous data, the hierarchical model is used, data from difference sources are introduced into different data layers, the heterogeneous data are unified in the same joint likelihood model to be analyzed, and therefore more accurate, real-time and stable prediction result can be obtained through effective fusion.

Description

technical field [0001] Embodiments of the present invention relate to data processing technologies, and in particular to a prediction method and device based on multi-source heterogeneous data. Background technique [0002] In the prior art, predicting event results based on historical data and models is a common prediction method. A typical application scenario is to predict the results of various competitions. [0003] The prediction model based on historical game data mainly estimates the team's offensive and defensive capabilities by analyzing the performance of each team in the historical game data, and uses this as a basis to predict the results of subsequent games. [0004] The main defect of this technical solution is that due to the relatively sparse time distribution of the games of each team, there are also changes in the players of the teams, the state fluctuations of the players themselves, and the contingency of the game, etc., so the prediction model obtained...

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): G06F19/00
CPCG06F17/18G07F17/3288G06Q50/34G06F17/00G06Q50/10G06N7/01G06N5/04
Inventor 王擎胡伟沈志勇
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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