Information processing system, information processing method, and program

Patent metadata

Field	Value
Publication number	US-2016196175-A1
Application number	US-201414916007-A
Country	US
Kind code	A1
Filing date	Mar 11, 2014
Priority date	Sep 9, 2013
Publication date	Jul 7, 2016
Grant date	—

Abstract

An information processing system, an information processing method, and a program capable of satisfactory data analysis are provided. The information processing system includes a frequency conversion unit 205 which converts a plurality of pieces of time-series data obtained through detection carried out by a plurality of sensing units 201 into pieces of frequency data 208, respectively, a model construction unit 211 which generates a correlation model 213 using pieces of the frequency data 208 for at least two sensing units 201 from among the plurality of sensing units 201 and calculates a correlation strength 214 of the correlation model 213, and an error detection unit which determines whether an error has occurred based on the correlation strength 214.

First claim

1 . An information processing system comprising:
a conversion unit which converts a plurality of pieces of time-series data obtained through detection carried out by a plurality of sensors into pieces of first frequency data, respectively; a first model generation unit which generates a first correlation model using pieces of the first frequency data for at least two sensors from among the plurality of sensors; a first calculation unit which calculates a correlation strength of the first correlation model based on the first correlation model and the first frequency data obtained from the sensor by which the data used to generate the first correlation model has been measured; and a determination unit which determines whether an error has occurred based on the correlation strength.

2 . The information processing system according to claim 1 , wherein the first model generation unit generates the first correlation model using a combination of pieces of the first frequency data for two sensors from among the plurality of sensors.

3 . The information processing system according to claim 1 , wherein the first model generation unit generates the first correlation model using average frequency data representing an average of a plurality of pieces of the first frequency data for the plurality of sensors, and a piece of the first frequency data from among the plurality of pieces of the first frequency data.

4 . The information processing system according to claim 1 , further comprising:
a conversion unit which converts pieces of time-series data obtained through detection carried out by the plurality of sensors into pieces of second frequency data; a second model generation unit which generates a second correlation model using pieces of the second frequency data; and a second calculation unit which calculates a correlation strength of the second correlation model, wherein the determination unit determines whether an error has occurred based on a comparison between the correlation strength of the first correlation model and the correlation strength of the second correlation model.

5 . The information processing system according to claim 4 , wherein the second model generation unit generates the second correlation model using a combination of pieces of the second frequency data for two sensors from among the plurality of sensors.

6 . The information processing system according to claim 4 , wherein the second model generation unit generates the second correlation model using average frequency data representing an average of a plurality of pieces of the first frequency data for the plurality of sensors, and a piece of the second frequency data.

7 . The information processing system according to claim 4 , wherein the pieces of time-series data for the pieces of first frequency data and the pieces of time-series data for the pieces of second frequency data are detected at different timings by the plurality of sensors.

8 . The information processing system according to claim 4 , wherein the pieces of time-series data for the pieces of first frequency data and the pieces of time-series data for the pieces of second frequency data are detected by different sensors from among the plurality of sensors.

9 . The information processing system according to claim 1 , wherein the pieces of frequency data used in generating the first correlation model is applied to the first correlation model to generate a threshold used to determine whether an error has occurred.

10 . An information processing system comprising:
a conversion unit which converts a plurality of pieces of time-series data obtained through detection carried out by a plurality of sensors into pieces of first frequency data, respectively; a model generation unit which generates a correlation model using pieces of the first frequency data for at least two sensors from among the plurality of sensors; and a determination unit which determines whether an error has occurred based on a difference between a predicted value of a piece of second frequency data and an actual measured value of the piece of second frequency data, the predicted value of the piece of the second frequency data being obtained by applying the piece of the second frequency data to the correlation model, the piece of the second frequency data being obtained by converting another piece of time-series data obtained from a sensor with respect to the correlation model.

11 . The information processing system according to claim 10 , wherein the model generation unit generates the correlation model using a combination of pieces of the first frequency data for two sensors from among the plurality of sensors.

12 . The information processing system according to claim 10 , wherein the model generation unit generates the correlation model using first average frequency data representing an average of a plurality of pieces of the first frequency data for the plurality of sensors, and a piece of the first frequency data from among the plurality of pieces of the first frequency data.

13 . The information processing system according to claim 12 , wherein the determination unit determines whether an error has occurred based on a difference between the predicted value of the piece of second frequency data and the actual measured value of the piece of second frequency data, the predicted value of the piece of the second frequency data being obtained by applying, to the correlation model, the piece of the second frequency data with respect to the correlation model and second average frequency data representing an average of a plurality of pieces of the second frequency data for the plurality of sensors.

14 . The information processing system according to claim 10 , wherein the pieces of frequency data used in generating the correlation model is applied to the correlation model to generate a threshold used to determine whether an error has occurred.

15 . An information processing method performed by an information processing system comprising:
converting a plurality of pieces of time-series data obtained through detection carried out by a plurality of sensors into pieces of first frequency data, respectively; generating a first correlation model using pieces of the first frequency data for at least two sensors from among the plurality of sensors; calculating a correlation strength of the first correlation model based on the first correlation model and the first frequency data obtained from the sensor by which the data used to generate the first correlation model has been measured; and determining whether an error has occurred based on the correlation strength.

16 . An information processing method performed by an information processing system comprising:
converting a plurality of pieces of time-series data obtained through detection carried out by a plurality of sensors into pieces of first frequency data, respectively; generating a correlation model using pieces of the first frequency data for at least two sensors from among the plurality of sensors; and determining whether an error has occurred based on a difference between a predicted value of a piece of second frequency data and an actual measured value of the piece of second frequency data, the predicted value of the piece of the second frequency data being obtained by applying the piece of the second frequency data to the correlation model, the piece of the second frequency data being obtained by converting another piece of time-series data obtained from a sensor with respect to the correlation model.

17 . A non-transi

Assignees

• Nec Corp

Inventors

• Kasahara Shinji
• Ochiai Katsuhiro

Classifications

• G06F11/0706 Primary

  the processing taking place on a specific hardware platform or in a specific software environment · CPC title

• G06F11/079 Primary

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/076

  by exceeding a count or rate limit, e.g. word- or bit count limit · CPC title

• G06F11/0751

  Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06) · CPC title