Destination prediction apparatus

• US 9,400,185 B2
• Filed: 01/21/2013
• Issued: 07/26/2016
• Est. Priority Date: 01/21/2013
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Tanaka, Kouhei, Akihara, Masaya, Shimotani, Mitsuo, Kawagishi, Toshio, Shimizu, Naoki
• Primary Examiner(s): Marc, McDieunel
• Assistant Examiner(s): Stroud, James E
• Application Number:
  US14/760,898
• Publication Number:
  US 20150345970A1
• Time in Patent Office: 1,282 Days
• Field of Search: 701/521
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/36 Input/output arrangements for on-board computers
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement

Abstract

It is an object of the present invention to predict a destination easily, and a destination display method for displaying a predicted destination. The destination prediction apparatus of the present invention includes: a behavior history acquiring unit that acquires, the behavior history; a visit history acquiring unit that acquires the visit history; a similar behavior date-and-time extractor that performs a similarity determination between a behavior within a predetermined period prior to a present date and time and a behavior in another period with reference to the behavior history and that extracts a date and time of the behavior in another period determined to be similar as a similar behavior date and time from the behavior history; and a destination candidate extractor that extracts, as a destination candidate, a location visited within a predetermined period before or after the similar behavior date and time from the visit history.

Claims

1. A destination prediction apparatus, comprising:

a behavior history receiver to receive, from a behavior history database in which a behavior history associating a behavior of a user with a date and time is recorded, said behavior history;

a visit history receiver to receive, from a visit history database in which a visit history associating a visit location of a mobile body with a date and time is recorded, said visit history;

a processor configured to execute a program; and

a memory to store the program which, when executed by the processor, results in performance of steps comprising,

performing a similarity determination between a behavior within a predetermined period prior to a present date and time and a behavior in another period with reference to said behavior history,

extracting a date and time of said behavior in another period determined to be similar as a similar behavior date and time from said behavior history, and

extracting, as a destination candidate, a location visited within a predetermined period before or after said similar behavior date and time from said visit history.

2. The destination prediction apparatus according to claim 1, further comprising said visit history database in which said visit history is recorded,

wherein said visit history receiver receives said visit history from said visit history database included in said destination prediction apparatus.

3. The destination prediction apparatus according to claim 1, further comprising said behavior history database in which said behavior history is recorded,

wherein said behavior history receiver receives said behavior history from said behavior history database included in said destination prediction apparatus.

4. The destination prediction apparatus according to claim 1, further comprising:

said visit history database in which said visit history is recorded; and

said behavior history database in which said behavior history is recorded, wherein

said visit history receiver receives said visit history from said visit history database included in said destination prediction apparatus, and

said behavior history receiver receives said behavior history from said behavior history database included in said destination prediction apparatus.

5. The destination prediction apparatus according to claim 1, wherein said behavior history includes at least one of a scheduler, a history of keyword search on the Web, a web page browsing history, a history of incoming and outgoing calls, a history of transmission and reception of e-mail messages, a life log, and a history of SNS transmission.

6. The destination prediction apparatus according to claim 1, wherein said performing performs said similarity determination again by extending said predetermined period or lowering standards for similarity determination in a case where the number of extractions of said similar behavior date and time is less than a threshold value.

7. The destination prediction apparatus according to claim 1, wherein said performing performs said similarity determination again by shortening said predetermined period or raising standards for similarity determination in a case where the number of extractions of said similar behavior date and time is more than or equal to a threshold value.

8. The destination prediction apparatus according to claim 1, wherein

said program, when executed by said processor, results in performance of steps further comprising generating display information for displaying said destination candidate on a display device,

said extracting a destination candidate counts the number of extractions in a case where the same location is extracted as said destination candidate a plurality of times, and

said generating generates said display information in which a plurality of said destination candidates are arranged in order of said number of extractions.

9. The destination prediction apparatus according to claim 1, wherein

said program, when executed by said processor, results in performance of steps comprising,

predicting a destination or its type from said destination candidate extracted in said extracting, and

generating display information for notifying a user of said destination or said type predicted in said predicting.

10. The destination prediction apparatus according to claim 9, wherein

said extracting a destination candidate counts the number of extractions in a case where the same location is extracted as said destination candidate a plurality of times, and

said predicting predicts said destination candidate as a destination when said total number of extractions of all of said destination candidates is more than or equal to a first threshold value and a percentage of said number of extractions in said total number of extractions of all of said destination candidates is more than or equal to a second threshold value.

11. The destination prediction apparatus according to claim 9, wherein

said extracting a destination candidate counts the number of extractions in a case where the same location is extracted as said destination candidate a plurality of times, and

said predicting predicts all of said destination candidates as destinations in a case where said total number of extractions of all of said destination candidates is less than a first threshold value.

12. The destination prediction apparatus according to claim 9, further comprising

a facility type receiver to receive a facility type of said destination candidate, wherein

said program, when executed by said processor, results in performance of steps further comprising

calculating said number of extractions of said destination candidate for each facility type,

said extracting a destination candidate counts the number of extractions in a case where the same location is extracted as said destination candidate, and

said predicting acquires said facility type of each of said destination candidates in a case where said number of extractions is more than or equal to a first threshold value and a percentage of said number of extractions of any of said destination candidates in said total number of extractions of all of said destination candidates is less than a second threshold value, and predicts said facility type as a facility type of a destination when said number of extractions for each facility type is more than or equal to a threshold value.

13. The destination prediction apparatus according to claim 9, further comprising

a facility type receiver to receive a facility type of said destination candidate, wherein

said program, when executed by said processor, results in performance of steps further comprising

calculating said number of extractions of said destination candidate for each facility type,

said extracting a destination candidate counts the number of extractions in a case where the same location is extracted as said destination candidate, and

said predicting acquires said facility type of each of said destination candidates in a case where said number of extractions is more than or equal to a first threshold value and a percentage of said number of extractions of any of said destination candidates in said total number of extractions of all of said destination candidates is less than a second threshold value, and predicts all of said facility types as facility types of destinations when said number of extractions for each facility type is less than a threshold value.

14. The destination prediction apparatus according to claim 1, wherein said program, when executed by said processor, results in performance of steps further comprising recording a current location as said visit location in said visit history database on the basis of at least any states of an engine, a gear, and a side break of said mobile body.

15. The destination prediction apparatus according to claim 1, wherein

said program, when executed by said processor, results in performance of steps further comprising extracting, as a characteristic behavior from said behavior history, a behavior having a multiplication value of a term frequency and an inverse document frequency of the behavior calculated by a TF·

IDF method more than or equal to a threshold value, and

said extracting a date and time of said behavior performs said similarity determination between said characteristic behavior within the predetermined period prior to the present date and time and said characteristic behavior in another period.

16. The destination prediction apparatus according to claim 1, wherein said extracting a date and time of said behavior for no behavior within the predetermined period prior to the present date and time in said behavior history sets, as a similar behavior period, a period in which there is no behavior for said predetermined period or more before said predetermined period prior to the present date and time in said behavior history, and extracts a specific date and time determined in said similar behavior period as said similar behavior date and time.

17. The destination prediction apparatus according to claim 1 further comprising a behavior-location database to associate behavior details of said behavior history with said destination candidate when said mobile body arrives at said destination candidate, said behavior history being a source from which said destination candidate is extracted,

wherein said predicting, in a case where the past predetermined period prior to the present date and time includes the same behavior details recorded in said behavior history as behavior details entered in said behavior-location database, predicts, as a destination, a location associated with the behavior details in said behavior-location database.

18. The destination prediction apparatus according to claim 1, further comprising:

a facility type receiver to receive a facility type of said destination candidate; and

a behavior-type database in which behavior details of said behavior history and said facility type are entered when said mobile body arrives at a location belonging to said facility type of said destination candidate, said behavior history being a source from which said destination candidate is extracted,

wherein said predicting, in a case where the past predetermined period prior to the present date and time includes the same behavior details recorded in said behavior history as behavior details entered in said behavior-type database, predicts, as a facility type of a destination, said facility type associated with the behavior details in said behavior-type database.

19. The destination prediction apparatus according to claim 1, wherein said extracting a date and time of said behavior for said behavior history that indicates each behavior in a character string performs a morphological analysis on said character string to perform said similarity determination from words or a combination of words.

20. The destination prediction apparatus according to claim 1, further comprising:

a local behavior history database in which said behavior history acquired by said behavior history acquiring unit is recorded; and

a local visit history database in which said visit history acquired by said visit history acquiring unit is recorded.