Unlock instant, AI-driven research and patent intelligence for your innovation.

Information processing system and learning method of information processing system

A technology of an information processing system and a learning method, applied in the field of information processing systems, can solve the problems of reduced prediction accuracy and over-adaptation, and achieve the effect of avoiding the reduction of prediction accuracy

Active Publication Date: 2019-07-19
HITACHI LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for events with a low frequency of occurrence, adjusting the prediction parameters according to the occasional events that occur in a specific situation will lead to over-adaptation, which will lead to a decrease in prediction accuracy in new situations. This "over-learning" phenomenon has become big problem

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
  • Information processing system and learning method of information processing system
  • Information processing system and learning method of information processing system
  • Information processing system and learning method of information processing system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] figure 1 It is a conceptual diagram showing a specific example of the information processing system of the present invention. In this specific example, raw data (101) is input, and a predictive model with high accuracy for predicting teaching data (positive solution data) included in the raw data is output. Wherein, the prediction model specifically refers to an algorithm for prediction, that is, a predictor (106) and its parameters, that is, a prediction parameter (112).

[0052] As a specific example, prediction of financing review will be described. The original data is the information of the financing target (such as gender, age, working years, loan amount, annual income, etc., which are included in the financing application data such as housing loans, and the conditional data used to specify the conditions), and the teaching data is whether the financing case has become The data of the past actual performance (result) of bad debts is the result data. Condition d...

Embodiment 2

[0102] In another example, the figure 1 In , by changing the raw data, this same information processing system can also be used in forecasts for investment judgments. In this case, the raw data is a numerical value group (M pieces) representing management information, financial information, and the state of the target market of the investment target company. The teaching data is one piece of data on the results of investment, that is, the actual performance of returns obtained from investment targets (for example, the amount of dividends obtained). Regarding N pieces of various investment objects, information on the investment object and information on the resulting return are input, and a model of what return can be obtained when investing in an unknown investment object is output.

[0103] As the basic data, a data set of M+1 columns and N rows is set, and this is input into the raw data in the form of a table, a text, or a database (101).

[0104] In addition, it can also...

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

An information processing system and a learning method of the information processing system are provided. In conventional machine learning, there has been a problem that the prediction accuracy becomes low for an event in which data is small. In a preferred aspect of the present invention, in an information processing system for inputting original data and outputting a prediction result, at leastfirst data and second data are generated from original data. A first prediction formula for performing prediction using the first data has at least one parameter and a first learner for adjusting theparameter using a first prediction result of the first prediction formula. A second prediction formula for performing prediction using the second data has at least one parameter and a second learner for adjusting the parameter using a second prediction result of the second prediction formula. Then, there is at least one common parameter in the parameter adjusted by the first learner and the parameter adjusted by the second learner.

Description

technical field [0001] The present invention relates to an information processing system for supporting prediction or judgment using data on business, people and social activities. Background technique [0002] In order to use the data collected and accumulated every moment by companies and society, artificial intelligence technology is attracting attention. [0003] In particular, with regard to image recognition, which recognizes faces or objects from images by capturing the characteristics of data, and voice recognition, which recognizes language from the characteristics of voice, the accuracy has been greatly improved by adopting deep learning technology in recent years. [0004] With the development of machine learning and artificial intelligence technologies including deep learning, it is expected that business and social predictions can be made based on data. Forecasting technology using such data and machine learning is expected to be widely used in the forecasting ...

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): G06Q10/04G06N3/04
CPCG06Q10/04G06N3/045
Inventor 矢野和男
Owner HITACHI LTD