Behavior estimation apparatus, threshold calculation apparatus, behavior estimation method and non-transitory computer readable medium thereof

• US 8,924,324 B2
• Filed: 08/30/2013
• Issued: 12/30/2014
• Est. Priority Date: 11/20/2012
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Sakamoto, Yoshiyuki, Sakamoto, Hideo, Koiso, Takashi, Imahara, Shuuichiro, Shingaki, Ryusei, Yano, Toru, Takeuchi, Ryosuke, Umeno, Shinya
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US14/015,547
• Publication Number:
  US 20140142862A1
• Time in Patent Office: 487 Days
• Field of Search: None
• US Class Current: 706/42
• CPC Class Codes: A63F 13/70 Game security or game management aspects
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: H02J 3/00 Circuit arrangements for ac mains or ac distribution networks
• CPC Class Codes: H02J 3/003 Load forecast, e.g. methods or systems for forecasting future load demand
• CPC Class Codes: H02J 4/00 Circuit arrangements for mains or distribution networks not specified as ac or dc
• CPC Class Codes: H04B 17/26 using historical data, averaging values or statistics
• CPC Class Codes: H04B 17/318 Received signal strength

Abstract

According to one embodiment, a behavior estimation apparatus includes a storage unit, a first calculation unit, a second calculation unit, and an estimation unit. The storage unit stores first data collecting power values consumed by a consumer in a period. The first calculation unit calculates second data representing a frequency of each power value by using the first data. The second calculation unit calculates a first threshold to divide a first power value from a second power value which is larger than and next to the first power value, among power values corresponding to maximal values of frequencies included in the second data. The estimation unit obtains a power value consumed by the consumer in an estimating period, and estimates the consumer'"'"'s behavior status in the estimating period by using the power value and the first threshold.

Claims

1. An apparatus for estimating behavior status, comprising:

a storage unit to store first data collecting power values consumed by a consumer in a period;

a first calculation unit configured to calculate second data representing a frequency of each power value by using the first data;

a second calculation unit configured to calculate a first threshold to divide a first power value from a second power value which is larger than and next to the first power value, among power values corresponding to maximal values of frequencies included in the second data; and

an estimation unit configured to obtain a power value consumed by the consumer in an estimating period, and to estimate the consumer'"'"'s behavior status in the estimating period by using the power value and the first threshold.

2. The apparatus according to claim 1, wherein

the second calculation unit calculates a second threshold to divide a third power value which is the smallest from a fourth power value which is smaller than and next to the third power value, and

the estimation unit estimates whether a person is in the consumer or absent from the consumer by comparing the power value consumed by the consumer in the estimating period with the second threshold.

3. The apparatus according to claim 1, wherein

the estimation unit estimates whether a behavior related to the person'"'"'s power consumption in the consumer is a short term behavior or a long term behavior by comparing the power value consumed by the consumer in the estimating period with the first threshold.

4. The apparatus according to claim 1, wherein

the second calculation unit comprises

a third calculation unit configured to calculate a plurality of probability distributions each including a maximal value by fitting a probability model to the second data;

and

a fourth calculation unit configured to calculate a power value corresponding to an intersection point of adjacent probability distributions as the first threshold.

5. The apparatus according to claim 4, wherein

the probability model is Gaussian mixture model.

6. The apparatus according to claim 1, wherein

the second calculation unit comprises

a fifth calculation unit configured to calculate an approximation curve of the frequency by using the second data;

and

a sixth calculation unit configured to calculate a power value corresponding to a minimal value of the approximation curve as the first threshold.

7. The apparatus according to claim 6, wherein

the approximation curve is an approximation curve by moving average.

8. The apparatus according to claim 1, wherein

the second calculation unit comprises

a classifying unit configured to classify the first data into a plurality of clusters, based on the frequency;

and

a seventh calculation unit configured to calculate a power value corresponding to a maximal value of the frequency in each of the plurality of clusters as a representative value of the cluster, and to calculate a power value to divide two representative values of adjacent clusters as the first threshold.

9. The apparatus according to claim 1, wherein

the power value includes an instantaneous power used at a timing or an accumulated electric energy used in an interval.

10. The apparatus according to claim 1, wherein

the frequency includes an occurrence frequency or a probability density of the power value.

11. The apparatus according to claim 1, wherein

the estimating period is an arbitrary period including the present time or an arbitrary period in the past.

12. An apparatus for calculating a threshold, comprising:

a storage unit to store first data collecting power values consumed by a consumer in a predetermined period;

a first calculation unit configured to calculate second data representing a frequency of each power value by using the first data; and

a second calculation unit configured to calculate a first threshold to divide a first power value from a second power value which is larger than and next to the first power value, among power values corresponding to maximal values of frequencies included in the second data.

13. A method for estimating behavior status, comprising:

by using first data collecting power values consumed by a consumer in a predetermined period, calculating second data representing a frequency of each power value;

calculating a first threshold to divide a first power value from a second power value which is larger than and next to the first power value, among power values corresponding to maximal values of frequencies included in the second data;

obtaining a power value consumed by the consumer in an estimating period; and

estimating the consumer'"'"'s behavior status in the estimating period by using the power value and the first threshold.

14. The method according to claim 13, wherein

the calculating a first threshold comprises

calculating a second threshold to divide a third power value which is the smallest from a fourth power value which is smaller than and next to the third power value;

and

the estimating comprises

estimating whether a person is in the consumer or absent from the consumer by comparing the power value consumed by the consumer in the estimating period with the second threshold.

15. The method according to claim 13, wherein

the estimating comprises

estimating whether a behavior related to the person'"'"'s power consumption in the consumer is a short term behavior or a long term behavior by comparing the power value consumed by the consumer in the estimating period with the first threshold.

16. A non-transitory computer readable medium for causing a computer to perform operations for estimating behavior status, the operations comprising:

by using first data collecting power values consumed by a consumer in a predetermined period, calculating second data representing a frequency of each power value;

calculating a first threshold to divide a first power value from a second power value which is larger than and next to the first power value, among power values corresponding to maximal values of frequencies included in the second data;

obtaining a power value consumed by the consumer in an estimating period; and

estimating the consumer'"'"'s behavior status in the estimating period by using the power value and the first threshold.

17. The non-transitory computer readable medium according to claim 16, wherein

the calculating a first threshold comprises

calculating a second threshold to divide a third power value which is the smallest from a fourth power value which is smaller than and next to the third power value;

and

the estimating comprises

estimating whether a person is in the consumer or absent from the consumer by comparing the power value consumed by the consumer in the estimating period with the second threshold.

18. The non-transitory computer readable medium according to claim 16, wherein

the estimating comprises

estimating whether a behavior related to the person'"'"'s power consumption in the consumer is a short term behavior or a long term behavior by comparing the power value consumed by the consumer in the estimating period with the first threshold.