Information processing device, information processing method, and program

Patent metadata

Field	Value
Publication number	US-9285235-B2
Application number	US-201214005648-A
Country	US
Kind code	B2
Filing date	Mar 16, 2012
Priority date	Mar 25, 2011
Publication date	Mar 15, 2016
Grant date	Mar 15, 2016

Abstract

The present technique relates to an information processing device, an information processing method and a program which can accumulate sufficient movement history data with a little power consumption. A similarity search unit searches for a past route similar to the immediate movement history which is acquired by a position sensor unit and which has time series position data, from the search data stored in a past history DB. A fitness determination unit determines whether or not goodness of fit of the past route searched by the similarity search unit and the immediate movement history is a predetermined threshold or more. A sensor control unit controls an acquisition interval of the position data of the position sensor unit according to a determination result of the fitness determination unit. The technique of this disclosure is applicable to a prediction device which, for example, acquires position data and predicts a predicted route.

First claim

The invention claimed is:

1. An information processing device comprising:
one or more processors configured to:
acquire, from a position sensor, an immediate movement history which comprises time series position data;
receive, from a memory, search data which comprises past time series position data;
calculate a similarity, as a goodness of fit, between the immediate movement history and the past time series position data,
wherein the goodness of fit is calculated based on distances between a first plurality of positions including a current position and at least one position preceding the current position in the immediate movement history and a second plurality of positions corresponding to the first plurality of positions, in the past time series position data and
wherein the second plurality of positions are obtained by tracking back a number of positions from a predetermined position in the past time series position data;
determine whether or not the goodness of fit calculated for the past time series position data and the immediate movement history is a predetermined threshold or more; and
control an acquisition interval of the position sensor to acquire the time series position data according to the determination of the goodness of fit.

2. The information processing device according to claim 1 , wherein, when the goodness of fit is the predetermined threshold or more, the acquisition interval of the time series position data becomes longer than when the goodness of fit is less than the predetermined threshold.

3. The information processing device according to claim 1 , wherein the one or more processors are further configured to:
predict a departure time which is a time to depart from a current position,
wherein, when the goodness of fit is the predetermined threshold or more and the predicted departure time comes after a predetermined time, the acquisition interval of the time series position data becomes longer than when the goodness of fit is less than the predetermined threshold.

4. The information processing device according to claim 3 , wherein the one or more processors are configured to predict the departure time as one of an absolute time and a relative time.

5. The information processing device according to claim 1 , wherein
the search data is stored as a past movement history in the memory, and
the similarity is calculated using a distance between the past movement history and the immediate movement history as the goodness of fit.

6. The information processing device according to claim 1 , wherein
the search data is stored in the memory, as a parameter obtained when a past movement history, which is the past time series position data, is learned according to a stochastic transition model, and
the similarity is calculated between the past movement history and the immediate movement history using a likelihood of the stochastic transition model calculated for the immediate movement history as the goodness of fit.

7. The information processing device according to claim 1 , wherein the one or more processors are configured to calculate the similarity by searching for a status node of a stochastic transition model corresponding to the immediate movement history.

8. The information processing device according to claim 7 , wherein the one or more processors are configured to calculate the similarity by searching for the status node with a maximum status probability corresponding to a current position in the immediate movement history.

9. The information processing device according to claim 1 , wherein the one or more processors are further configured to:
generate a sequence using a part of the past time series position data, wherein the goodness of fit of each of the positions in the part of the past time series position data is the predetermined threshold or more; and
calculate an average of the generated sequence and the immediate movement history.

10. The information processing device according to claim 9 , wherein the goodness of fit of each of the positions in the part of the past time series position data is the predetermined threshold or more and a number of positions in the part of the past time series position data is same as a number of positions in the immediate movement history.

11. The information processing device according to claim 9 , wherein the goodness of fit of each of the positions in the part of the past time series position data is the predetermined threshold or more and a number of positions in the part of the past time series position data is different from a number of positions in the immediate movement history.

12. The information processing device according to claim 9 , wherein the calculated average is a weighted average.

13. The information processing device according to claim 9 , wherein the one or more processors are further configured to set first weight for the generated sequence and second weight for the immediate movement history, wherein the first weight is higher than the second weight.

14. The information processing device according to claim 1 , wherein the one or more processors are configured to correct the immediate movement history based on the immediate movement history and the past time series position data when the goodness of fit is the predetermined threshold or more.

15. The information processing device according to claim 1 , wherein the goodness of fit is calculated as a total sum of the distances between the first plurality of positions and the corresponding second plurality of positions.

16. An information processing method comprising:
in one or more processors:
acquiring, from a position sensor, an immediate movement history which comprises time series position data;
receiving, from a memory, search data which comprises past time series position data;
calculating a similarity, as a goodness of fit, between the immediate movement history and the past time series position data,
wherein the goodness of fit is calculated based on distances between a first plurality of positions including a current position and at least one position preceding the current position in the immediate movement history and a second plurality of positions corresponding to the first plurality of positions in the past time series position data, and
wherein the second plurality of positions are obtained by tracking back a number of positions from a predetermined position in the past time series position data;
determining whether or not the goodness of fit calculated for the past time series position data and the immediate movement history is a predetermined threshold or more; and
controlling an acquisition interval of the position sensor to acquire the time series position data according to the determination of the goodness of fit.

17. A non-transitory computer readable medium having stored thereon, a set of computer-executable instructions, for causing a computer to perform steps comprising:
acquiring, from a position sensor, an immediate movement history which comprises time series position data;
receiving, from a memory, search data which comprises past time series position data;
calculating a similarity, as a goodness of fit, between the immediate movement history and the past time series position data,
wherein the goodness of fit is calculated based on distances between a first plurality of positions including a current position and at least a position preceding the current position in the immediate movement history and a second plurality of positions corresponding to the first plurality of positions in the past

Assignees

• Ide Naoki
• Kobayashi Yoshiyuki
• Ito Masato
• Sabe Kohtaro
• Sony Corp

Inventors

• Ide Naoki
• Kobayashi Yoshiyuki
• Ito Masato
• Sabe Kohtaro

Classifications

• G01C21/3617 Primary

  using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement · CPC title

• G01C21/3484

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title