ACTION HISTORY SEARCH DEVICE

• US 20120150777A1
• Filed: 09/15/2011
• Published: 06/14/2012
• Est. Priority Date: 12/13/2010
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Setoguchi, Hisao, Okamoto, Yuzo, Kawamura, Takahiro, Cho, Kenta
• Granted Patent: US 8,600,918 B2
• Time in Patent Office: Days
• US Class Current: 706/14
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

According to one embodiment, an action history search device receives an inquiry from a user and outputs a inquirty time and a target of inquiry, decides a range for searching action history information representing history of the user'"'"'s action together with a time of the user'"'"'s action using the target of inquiry, and calculates an elapsed time from the time of the user'"'"'s action within the range to the inquiry time. The device judges using the elapsed time and a narrowing-down model a probability on each response candidate to the inquiry based on the history of the action within the range. The narrowing-down model is used for judging according to the elapsed time the probability that the response candidate to the inquiry obtained from the history of the action is the user'"'"'s desired response. The device outputs the response candidate according to the probability.

Claims

1. An action history search device, comprising:

an inquiry processing unit that receives an inquiry from a user and outputs an inquiry time, at which the inquiry is received, and a target of inquiry;

a decision unit that decides a range for searching action history information, which represents history of the user'"'"'s action together with a time of the user'"'"'s action, using the target of inquiry;

a calculation unit that calculates an elapsed time from the time of user'"'"'s action, which is represented by the action history information within the range, to the inquiry time;

a judgment unit that judges, using the elapsed time and a narrowing-down model, a probability on each response candidate to the inquiry based on the history of the action represented by the action history information within the range, the narrowing-down model being used for judging according to the elapsed time the probability that the response candidate to the inquiry, which is obtained from the history of the action represented by the action history information, is the user'"'"'s desired response; and

an output unit that outputs the response candidate according to the probability.

2. The device according to claim 1, wherein the calculation unit further calculates the frequency related to the action based on the history of the action represented by the action history information within the range,

the narrowing-down model judges the probability according to the elapsed time and the frequency, and

the judgment unit judges the probability using the elapsed time, the frequency, and the narrowing-down model.

3. The device according to claim 2, wherein the action history information represents the history of the action including a place at which the action has been conducted, and

the calculation unit calculates the frequency including the frequency related to the action at the place based on the history of the action represented by the action history information within the range.

4. The device according to claim 3, wherein the calculation unit calculates the frequency including the frequency related to the action at the place using the action history information within the range and schedule information that represents a schedule of the user'"'"'s action together with a date, a time and a place.

5. The device according to claim 1, wherein the output unit outputs the response candidate and a judgment criterion used when the judgment unit judges the probability on the response candidate.

6. The device according to claim 1, further comprising an estimation unit that estimates the user'"'"'s state using at least one of schedule information that represents a schedule of the user'"'"'s action together with a date, a time and a place, profile information that represents the user'"'"'s profile, and measurement information measured by a sensor transmitted the measurement information to the action history search device,

wherein the decision unit decides the range using the target of inquiry and the state.

7. The device according to claim 1, further comprising a storage unit that stores a first narrowing-down model corresponding to an individual user,

wherein the judgment unit judges the probability using the elapsed time and the first narrowing-down model.

8. The device according to claim 7, further comprising a correction unit that corrects the first narrowing-down model to increase the probability on a response in response to the user'"'"'s operation input for determining the response among the response candidates.

9. The device according to claim 8, further comprising an acquisition unit that acquires a third narrowing-down model in which a second narrowing-down model corresponding to another user is reflected,

wherein the judgment unit judges the probability using the elapsed time and at least one of the first narrowing-down model and the third narrowing-down model.

10. The device according to claim 9, wherein the acquisition unit acquires the third narrowing-down model from an information processing device that stores the third narrowing-down model through a network.