JP2012133712A - Spot recommendation device and method therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a spot recommendation device and a method therefor which, based on visit histories of a plurality of users, among all spots visited by respective users in the past, can recommend other users a so-called little-known good spot which is rarely visited by other users.SOLUTION: A spot recommendation device 1 comprises: a spot visit history acquisition unit 11 for, based on a transition history of a predetermined user within a predetermined period, acquiring at least a visit history of the predetermined user that includes a frequency of visits of each spot; an activity range spot number acquisition unit 12 for, based on the transition history, determining an activity range of the predetermined user within the predetermined period to acquire the number of spots included in the activity range; and a spot feature degree calculation unit 13 for calculating a value of a feature degree by multiplying the frequency of visits of each spot by the number of activity range spots to divide by the number of visitors of the spot within the predetermined period.

Description

  The present invention relates to a spot recommendation device and a method for recommending a spot based on a visit history of a user.

2. Description of the Related Art In recent years, an apparatus that provides a recommended store by inputting conditions such as the number of participants, a fee, and cooking has been known. As such an apparatus, there is provided a usage history information storage unit that stores usage history information indicating a usage history of a user, and a selection unit that selects a store that is less used by the user based on the usage history information. Is known (see, for example, Patent Document 1). According to the invention described in Patent Literature 1, since a store that is not normally visited by the user is recommended, the pleasure of visiting a new store is born.
On the other hand, it is possible to recommend a store or restaurant that other users visit frequently, but this method recommends a store or restaurant that is a so-called classic spot that many users frequently visit. .

JP 2010-033484 A

  However, it is highly likely that users are already familiar with stores that have become so-called classic spots and are already introduced in various media such as magazines and televisions, and the value of introducing them again is often low. Therefore, based on the visit histories of a plurality of users, out of destinations visited by each user in the past (hereinafter referred to as “spots” in this specification), so-called spot spots where other users rarely visit are selected. There is a need to provide a spot recommendation device and method that can be recommended to other users. However, the conventional techniques including the invention described in Patent Document 1 cannot provide any means for solving such problems.

  According to the present invention, based on the visit histories of a plurality of users, out of spots visited by each user in the past, so-called spot spots that are rarely visited by other users can be recommended to other users. An object of the present invention is to provide a spot recommendation device and a method thereof.

  The present invention provides the following solutions.

  (1) A spot recommendation device for recommending a spot based on a visit history of a user, the visit including at least the number of visits of each spot of the predetermined user based on a movement history of the predetermined user within a predetermined period Based on the spot visit history acquisition means for acquiring the history and the movement history of the predetermined user within the predetermined period, the action range of the predetermined user within the predetermined period is specified, and the spot included in the action range The number of spots in the action range for acquiring the number of spots, and the spot feature degree indicating the feature degree of each spot of the predetermined user as the number of visits of each spot acquired by the spot visit history acquisition means, the action range By multiplying the number of spots acquired by the number of spots acquisition means, and dividing by the number of visitors of spots within the predetermined period. Spot recommendation apparatus and a spot characteristic calculation means for calculating.

  According to the invention described in (1), the spot visit history acquisition means acquires a visit history including the number of visits of each spot of at least a predetermined user based on a movement history of the predetermined user within a predetermined period. The behavior area spot number acquisition means identifies a behavior range of the predetermined user within the predetermined period based on a movement history of the predetermined user within the predetermined period, and acquires the number of spots included in the behavior range. To do. Then, the spot feature degree calculation means acquires the spot feature degree indicating the feature degree of each spot of the predetermined user by the spot number in the action range acquisition means to the number of visits of each spot acquired by the spot visit history acquisition means. It is calculated by multiplying the number of spots and further dividing by the number of visitors of the spots within a predetermined period. Based on the visit histories of a plurality of users, so-called spot spots that other users rarely visit among the spots visited by each user in the past without requiring the user to input impressions and the like can thereby be obtained. It is possible to provide a spot recommendation device that can be recommended to other users.

  (2) The spot recommendation device according to (1), comprising a spot feature adjustment unit that decreases the spot feature as the number of spots visited by each user during the predetermined period increases.

  According to the invention described in (2), the smaller the number of spots visited by each user, the higher the performance that each user has visited can be reflected in the spot feature. Therefore, it is possible to provide a spot recommendation device capable of calculating a spot feature degree for extracting a hole spot more accurately.

  (3) A spot recommendation method in which a computer including a control unit and a storage unit recommends a spot based on a visit history of a user, wherein the control unit includes at least a movement history of a predetermined user within a predetermined period. Based on the spot visit history acquisition step of acquiring the visit history including the number of visits of each spot of the predetermined user and the movement history of the predetermined user within the predetermined period, the predetermined user within the predetermined period An action range spot number acquisition step of specifying an action range and acquiring the number of spots included in the action range, and a spot feature degree indicating a feature degree of each spot of the predetermined user, the spot visit history acquisition step Multiply the number of visits to each spot acquired in step 1 by the number of spots acquired in the spot number acquisition step in the action range. Further, by dividing the number of visitors spots within the predetermined period, a method for performing a spot characteristic calculation step of calculating.

  According to the method described in (3), the same effect as in (1) can be expected by implementing the invention according to the method.

  According to the present invention, based on the visit histories of a plurality of users, out of spots visited by each user in the past, so-called spot spots that are rarely visited by other users can be recommended to other users. Possible spot recommendation devices and methods can be provided.

It is a figure showing the whole composition for explaining spot recommendation device 1 concerning a 1st embodiment of the present invention. It is a figure which shows the GPS log database 31 which concerns on the 1st and 2nd embodiment of this invention. It is a figure which shows the spot database 21 which concerns on the 1st and 2nd embodiment of this invention. It is a figure which shows the spot visit history table 22 which concerns on 1st Embodiment of this invention. It is a figure for demonstrating the function of the spot number acquisition part 12 in the action range which concerns on the 1st and 2nd embodiment of this invention. It is a figure which shows the spot characteristic database 23 which concerns on 1st Embodiment of this invention. It is a flowchart of the spot recommendation apparatus 1 which concerns on 1st Embodiment of this invention. It is a figure which shows the whole structure for demonstrating the spot recommendation apparatus 101 which concerns on 2nd Embodiment of this invention. It is a figure which shows the spot visit history table 122 which concerns on 2nd Embodiment of this invention. It is a figure which shows the spot characteristic database 123 which concerns on 2nd Embodiment of this invention. It is a flowchart of the spot recommendation apparatus 101 which concerns on 2nd Embodiment of this invention.

<First Embodiment>
A first embodiment of the present invention will be described with reference to the drawings.

[overall structure]
FIG. 1 is a diagram showing an overall configuration for explaining a spot recommendation device 1 according to the first embodiment. The spot recommendation device 1 is connected to an external device 2 that stores a user's movement history and the like via a network. The spot recommendation device 1 includes a control unit 10 that comprehensively controls each function related to the spot recommendation device 1, and a storage unit 20 in which information necessary for the operation of the control unit 10 is stored.

  The control unit 10 includes a spot visit history acquisition unit 11 that acquires a visit history including the number of visits of each spot of the predetermined user based on the movement history of the predetermined user within a predetermined period. A “predetermined user” refers to a user who is expected to have some or all of the action range overlapping, such as being in the same municipality or having a common hobby. The “spot” refers to a point determined in advance by the administrator of the spot recommendation device 1, and examples thereof include places that can be widely visited by the public, such as sightseeing spots, theme parks, museums, art galleries, restaurants, and the like. Further, in this specification, a description is given assuming that the period between December 11 and 15 is the “predetermined period”, but the length of the predetermined period can be arbitrarily determined.

  A movement history of a predetermined user within a predetermined period is referred to by a GPS log database 31 provided in the external device 2. The storage unit 20 is provided with a spot database 21, and the visit history is acquired by specifying the travel history information specified by the latitude and longitude acquired from the GPS log database 31 with the spot stored in the spot database 21. This is done by replacing the information with the movement history information. The storage unit 20 is provided with a spot visit history table 22, and the visit history acquired by the spot visit history acquisition unit 11 is stored in the spot visit history table 22. The spot visit history acquisition unit 11, the spot database 21, and the spot visit history table 22 function as spot visit history acquisition means.

  The GPS log database 31 is illustrated in FIG. In the GPS log database 31, information for specifying a point where the user exists at a certain date and time is stored in advance. The location is specified by receiving radio waves emitted from a mobile terminal held by the user.

  The GPS log database 31 includes a “user ID” field for identifying a user who moves between a plurality of spots, a “date and time” field indicating the date and time, a “latitude” field indicating the latitude at which the user exists, And a “longitude” field indicating the longitude of the position where the terminal exists. For example, when the user corresponding to the user ID “001” has a latitude of latitude of 34 degrees 52 minutes 10.1008 seconds north and longitude 137 degrees 52 minutes 10.1050 seconds at 12:00 on December 11 Is stored in the “user ID” field, “December 11 12:00” is stored in the “date and time” field, and “3452101008” is stored in the “latitude” field. In the “longitude” field, “137512010050” is stored.

  The spot database 21 is illustrated in FIG. The spot database 21 includes a “spot” field indicating the name of a point predetermined by the administrator of the spot recommendation device 1, a “latitude” field and a “longitude” field indicating the latitude and longitude of the center of the point, And a “radius” field for specifying the area covered by the radius from the center. For example, the latitude of the center of the spot 1 is 34 degrees 52 minutes 10.1018 seconds north latitude, the longitude is 137 degrees 52 minutes 10.0056 seconds east, and the area covered by the spot A is within a radius of 112 m from this center “Spot 1” is stored in the “Spot” field, “3452101018” is stored in the “Latitude” field, “1375120101050” is stored in the “Longitude” field, and “112” is stored in the “Radius” field. Is memorized.

  An example in which the spot visit history acquisition unit 11 acquires user visit histories from December 11 to December 15 will be described with reference to FIGS. 1 to 3. Referring to the GPS log database 31 shown in FIG. 2, the user corresponding to the user ID “001” is 34 degrees 52 minutes 10.1008 seconds north latitude at 12:00 on December 11, 137 degrees 52 minutes 10.1050 seconds east longitude. It exists in the position specified by. With reference to the spot database 21 shown in FIG. 3, this position corresponds to the spot 1. Therefore, the spot visit history acquisition unit 11 specifies that the user corresponding to the user ID “001” visited the spot 1 at 12:00 on December 11th.

  As the spot visit history acquisition unit 11 repeats the same processing, the spot visit history acquisition unit 11 visits the spot 1 at 12:00 on December 11th at 12:00 on December 11, when the user corresponding to the user ID “001”. Visited spot 4 at 00, visited spot 1 at 12:00 on the 12th, visited spot 3 at 17:00 on the same day, visited spot 5 at 12:00 on the 13th, and spot 1 at 17:00 on the same day , Visit spot 1 at 12:00 on the 14th, visit spot 3 at 12:00 on the 15th, and spot 1 at 17:00 on the same day. Note that the user corresponding to the user ID “001” exists at a location not specified in the spot database 21 at 17:00 on the 14th.

  In addition, the spot visit history acquisition unit 11 visits the spot 2 at 12:00 on December 11, 12:00, and visits the spot 2 at 12:00 on December 12, 17:00 Visited spot 3 at 12:00 on the 13th, visited spot 1 at 17:00 on the same day, visited spot 2 at 12:00 on the 14th, and visited spot 3 at 17:00 on the same day. Visit and identify spot 2 visited at 12:00 on the 15th. This user exists at a place not specified in the spot database 21 at another time.

  Then, the spot visit history acquisition unit 11 visits the spot 1 at 12:00 on December 11, 12:00 on the user corresponding to the user ID “003”, visits the spot 4 at 17:00, and 12:00 on the 12th. The spot 5 is visited, the spot 2 is visited at 12:00 on the 13th, and the spot 3 is visited at 17:00 on the 14th. This user exists at a place not specified in the spot database 21 at another time.

  Incidentally, the spot visit history acquisition unit 11 also counts the number of visitors of each spot within the predetermined period. This number of visitors is not the total number of visitors, but the actual number of visitors. That is, the user corresponding to the user ID “001” visits the spot 1 twice or more within the predetermined period, but is counted as one visitor. In this specification, it is assumed that 25 visitors have visited the spot 1, 20 visitors have visited the spot 2, and 500 visitors have visited the spot 3 within the predetermined period.

  The spot visit history table 22 is illustrated in FIG. In the spot visit history table 22, basically, a row is specified by a user ID and a column is specified by a spot. In the spot visit history table 22, a visit history including the number of visits of each spot acquired by the spot visit history acquisition unit 11 is stored. For example, if the user corresponding to the user ID “001” visited the spot 1 20 times, visited the spot 2 0 times, and visited the spot 3 twice during the predetermined period, the user ID “001” “20” is stored in the “spot 1” column of the row corresponding to “0”, “0” is stored in the “spot 2” column of the same row, and “spot 3” of the same row stores “0”. 2 "is stored.

  In the spot visit history table 22, a row is specified by the number of visitors. In the present embodiment, 25 visitors have visited the spot 1, 20 visitors have visited the spot 2, and 500 visitors have visited the spot 3 within the predetermined period. "25" is stored in the "Spot 1" column of the row corresponding to "", "20" is stored in the "Spot 2" column of the same row, and the "Spot 3" column of the same row is stored. “500” is stored.

  Returning to FIG. 1, the control unit 10 identifies the action range of the predetermined user within the predetermined period based on the movement history of the predetermined user within the predetermined period, and the number of spots included in the action range. The number-of-actions spot acquisition part 12 is acquired.

  The function of the within-behavior-range spot number acquisition unit 12 will be described with reference to FIG. The action range is identified by the spot number acquisition unit 12 within the action range by extracting the position coordinates where the user existed during the predetermined time based on the information stored in the GPS log database 31 and drawing it from the position coordinates. This is done by specifying the outer edge. This specification is performed individually for each of the predetermined users. For example, as shown in FIG. 5, for the user corresponding to the user ID “001”, the first action range 41 that is the user's action range is specified, and for the user corresponding to the user ID “002”, A second action range 42 that is a user action range is specified. For the user corresponding to the user ID “003”, the third action range which is the user action range is specified.

  Further, the acquisition of the number of spots included in the action range is obtained by positioning the position within the action range area specified with reference to the GPS log database 31 among the position coordinates of a plurality of spots stored in the spot database 21. This is done by specifying the number of coordinates. Taking FIG. 5 as an example, the acquisition of the action range of the user corresponding to the user ID “001” is specified with reference to the GPS log database 31 among the position coordinates of a plurality of spots stored in the spot database 21. This is performed by specifying the number of position coordinates located within the area of the first action range 41. Similarly, the acquisition of the action range of the user corresponding to the user ID “002” is performed by referring to the second action range specified with reference to the GPS log database 31 among the position coordinates of a plurality of spots stored in the spot database 21. This is done by specifying the number of position coordinates located within the 42 region. The action range of the user corresponding to the user ID “003” is acquired by referring to the third action range 43 specified by referring to the GPS log database 31 among the position coordinates of a plurality of spots stored in the spot database 21. This is done by specifying the number of position coordinates located inside the area. The number of spots acquired by the in-behavior-range spot number acquisition unit 12 is stored in the spot visit history table 22. The within-behavior-spot number acquisition unit 12, the spot database 21, and the spot visit history table 22 function as a within-behavior-spot number acquisition unit.

  Moving to FIG. 4, the spot visit history table 22 is specified not only by the column by the spot but also by the number of spots in the action range. For example, when there are twelve spots inside the area drawn by the position coordinates visited by the user corresponding to the user ID “001” during the predetermined period, the “action range” in the row corresponding to the user ID “001” “12” is stored in the “inner spot number” column. Similarly, when there are 250 spots inside the area drawn by the position coordinates visited by the user corresponding to the user ID “002”, the “number of spots in the action range” of the row corresponding to the user ID “002” is set. “250” is stored in the column. Further, when there are 53 spots inside the region drawn by the position coordinates visited by the user corresponding to the user ID “003”, the column “number of spots in the action range” in the row corresponding to the user ID “003” Stores “53”.

  Returning to FIG. 1, the control unit 10 sets the spot feature degree indicating the feature degree of each spot of the predetermined user to the number of visits of each spot acquired by the spot visit history acquisition unit 11, and the number of spots within the action range acquisition unit. A spot feature degree calculating unit 13 that calculates the number of spots obtained by multiplying by the number of spots acquired by 12 and divided by the number of visitors of the spot within the predetermined period is provided. The feature degree calculated by the spot feature degree calculation unit 13 is stored in the spot feature degree database 23. The spot feature degree calculation unit 13 and the spot feature degree database 23 function as spot feature degree calculation means.

  Taking the spot visit history table 22 shown in FIG. 4 as an example, the user corresponding to the user ID “001” will be described. The number of visits of the spot 1 acquired by the spot visit history acquisition unit 11 is “20”, The number of spots acquired by the in-range spot number acquisition unit 12 is “12”. Further, the number of visitors to the spot 1 within the predetermined period is “25”. Therefore, the spot feature degree calculation unit 13 multiplies the number of visits of the spot 1 acquired by the spot visit history acquisition unit 11 by the number of spots acquired by the in-behavior range spot number acquisition unit 12, and further within the predetermined period. The value divided by the number of visitors to the spot 1, that is, 20 × 12 ÷ 25 = 9.60, is calculated as the feature degree of the spot 1 for the user corresponding to the user ID “001”.

  The spot feature database 23 is illustrated in FIG. The spot feature database 23 includes a “user ID” field that indicates a user ID and a “feature” field that indicates the feature of each spot for the user corresponding to the user ID. As a result of the calculation by the spot feature degree calculation unit 13, the feature degree of the spot 1 for the user corresponding to the user ID “001” is 9.60. When calculated in the same manner, the feature degree of the spot 2 for the user corresponding to the user ID “001” is 0.00, and the feature degree of the spot 3 is 0.05. Therefore, “001” is stored in the “user ID” field of the spot feature database 23, “9.60” is stored in the “spot 1” area of the “feature” field, and “spot 2”. “0.00” is stored in the area of “0.05”, and “0.05” is stored in the area of “spot 3”.

  Although illustration is omitted, it is preferable that the control unit 10 includes a spot recommendation unit that recommends a spot having the highest characteristic degree to another user with respect to one user. In the above example, regarding the user corresponding to the user ID “001”, the spot having the highest characteristic degree is the spot 1, and therefore the spot recommendation unit uses the user IDs “002” and “ To the user corresponding to “003”. Note that the spot recommendation unit may recommend to other users only spots having a feature level higher than a certain threshold.

[Hardware and Software Configuration of this Embodiment]
The hardware and software configurations of this embodiment will be described. The hardware of the spot recommendation device 1 includes a storage device (storage unit), a communication device (communication unit), a display device (display unit), and an input device (input unit) in addition to a CPU as a control device (control unit). included. Examples of the storage device (storage unit) include a memory (RAM, ROM, etc.), a hard disk drive (HDD), an optical disk (CD, DVD, etc.) drive, and the like. Examples of the communication device (communication unit) include various wired or wireless interface devices. Examples of the display device (display unit) include various displays such as a liquid crystal display or a plasma display. Examples of the input device (input unit) include a keyboard, a pointing device (such as a mouse), a remote control device, and the like.

  The software of the spot recommendation device 1 includes a program and data for controlling the hardware. Programs and data are stored in a storage device (storage unit), and are appropriately executed and referenced by a control device (control unit). Further, the computer program and data can be distributed by an electromagnetic method, or can be recorded and distributed on a computer-readable medium such as a CD-ROM.

[flowchart]
FIG. 7 is a flowchart of the spot recommendation device 1 according to the present embodiment.

  First, the spot visit history acquisition unit 11 executes a spot visit history acquisition process (S1). In this process, the spot visit history acquisition unit 11 includes a visit including at least the number of visits of each spot of the predetermined user based on the movement history of the predetermined user stored in the GPS log database 31 within a predetermined period. A process of acquiring the history with reference to the spot database 21 is executed. The visit history acquired by the spot visit history acquisition unit 11 is stored in the spot visit history table 22.

  Next, the in-behavior-spot number acquisition unit 12 executes an in-behavior-spot number acquisition process (S2). In this process, the number-of-behavior-spots acquisition unit 12 specifies a range of action for a predetermined user within a predetermined period based on the movement history of the predetermined user within a predetermined period stored in the GPS log database 31. And the process which acquires the number of the spots contained in the action range with reference to the spot database 21 is performed. The action range acquired by the action range spot number acquisition unit 12 is stored in the spot visit history table 22.

  Next, the spot feature degree calculation unit 13 executes a spot feature degree calculation process (S3). In this process, the spot feature degree calculation unit 13 sets the spot feature degree indicating the feature degree of each spot of the predetermined user to the number of visits of each spot acquired by the spot visit history acquisition unit 11 and the number of spots in the action range. Multiplying the number of spots acquired by the acquisition unit 12 and further dividing by the number of visitors of spots within a predetermined period is executed. That is, the spot feature degree calculation unit 13 calculates (the number of visits of each spot acquired by the spot visit history acquisition unit 11) × (the number of spots acquired by the spot number acquisition unit 12 within the action range) ÷ (spots within a predetermined period) The number of visitors) is calculated, and a process is performed in which the value obtained by this calculation is “the characteristic degree of each spot of the predetermined user”. The feature degree calculated by the spot feature degree calculation unit 13 is stored in the spot feature degree database 23.

  In addition, although illustration is abbreviate | omitted, a spot recommendation part may perform a spot recommendation process after the process of step S3. In this process, the spot recommendation unit executes a process of recommending a spot having the highest characteristic degree to another user with respect to one user.

  When the above process ends, the control unit 10 ends the series of processes.

[Example of Spot Recommendation Device 1]
Hereinafter, an embodiment of the spot recommendation device 1 will be described.

  First, the spot visit history acquisition unit 11 receives a mobile terminal corresponding to the user IDs “001”, “002”, “003”... Within a predetermined period (in this embodiment, from December 11th). The visit history including the number of visits of each spot of these users is acquired based on the travel history of the 15th). When the GPS log database 31 shown in FIG. 2 and the spot database 21 shown in FIG. 3 are taken as an example, the spot visit history acquisition unit 11 determines that the user corresponding to the user ID “001” is 12:00 on December 11th. Visited spot 1, visited spot 4 at 17:00, visited spot 1 at 12:00 on the 12th, visited spot 3 at 17:00, and visited spot 5 at 12:00 on the 13th 17:00, spot 1 was visited, spot 1 was visited at 12:00 on the 14th, spot 3 was visited at 12:00 on the 15th, and spot 1 was identified as having visited spot 1 at 17:00 To do. In the following description, it is assumed that the user corresponding to the user ID “001” visited the spot 1 20 times, visited the spot 2 0 times, and visited the spot 3 twice within a predetermined period.

  Similarly, it is assumed that the user corresponding to the user ID “002” visited the spot 1 0 times, visited the spot 2 20 times, and visited the spot 3 twice within a predetermined period, and corresponds to the user ID “003”. It is assumed that the user visits spot 1 once, visits spot 2 once, and visits spot 3 once within a predetermined period.

  The spot visit history acquisition unit 11 also counts the number of visitors to each spot within the predetermined period. In the following description, it is assumed that 25 visitors have visited the spot 1, 20 visitors have visited the spot 2, and 500 visitors have visited the spot 3 within the predetermined period.

  The visit history acquired by the spot visit history acquisition unit 11 is stored in the spot visit history table 22. The user corresponding to the user ID “001” visited the spot 1 20 times, visited the spot 2 0 times, and visited the spot 3 twice within the predetermined period, and therefore corresponds to the user ID “001”. “20” is stored in the “spot 1” column of the row to be stored, “0” is stored in the “spot 2” column of the same row, and “2” is stored in the “spot 3” column of the same row. Is memorized.

  Similarly, since the user corresponding to the user ID “002” visited the spot 1 0 times, visited the spot 2 20 times, and visited the spot 3 twice within a predetermined period, the user ID “002” “0” is stored in the “spot 1” column of the corresponding row, “20” is stored in the “spot 2” column of the same row, and “2” is stored in the “spot 3” column of the same row. Is stored. In addition, since the user corresponding to the user ID “003” visits the spot 1 once, visits the spot 2 once, and visits the spot 3 once within a predetermined period, it corresponds to the user ID “003”. “1” is stored in the “spot 1” column, “1” is stored in the “spot 2” column of the same row, and “1” is stored in the “spot 3” column of the same row. Is memorized.

  Also, since 25 visitors have visited Spot 1 within the predetermined period, 20 visitors have visited Spot 2, and 500 visitors have visited Spot 3, it corresponds to the “number of visitors” “25” is stored in the “spot 1” column, “20” is stored in the “spot 2” column of the same row, and “500” is stored in the “spot 3” column of the same row. Is memorized.

  Subsequently, the number-of-behavior-spots acquisition unit 12 specifies the range of action within a predetermined period of the predetermined user based on the movement history of the predetermined user within the predetermined period, and the number of spots included in the action range. To get. The action range is specified by extracting the position coordinates where the user existed during the predetermined time based on the information stored in the GPS log database 31 and specifying the outer edge drawn from the position coordinates. . Further, the acquisition of the number of spots included in the action range is obtained by positioning the position within the action range area specified with reference to the GPS log database 31 among the position coordinates of a plurality of spots stored in the spot database 21. This is done by specifying the number of coordinates.

  The number of spots in the action range acquired by the number of spots in action range 12 is stored in the spot visit history table 22. If there are twelve spots in the area drawn by the position coordinates visited by the user corresponding to the user ID “001” during the predetermined period, the “spot within the action range” in the row corresponding to the user ID “001” “12” is stored in the “number” column. Similarly, when there are 250 spots inside the area drawn by the position coordinates visited by the user corresponding to the user ID “002”, the “number of spots in the action range” of the row corresponding to the user ID “002” is set. “250” is stored in the column. Further, when there are 53 spots inside the region drawn by the position coordinates visited by the user corresponding to the user ID “003”, the column “number of spots in the action range” in the row corresponding to the user ID “003” Stores “53”.

  Subsequently, the spot feature degree calculation unit 13 sets the spot feature degree indicating the feature degree of each spot of a predetermined user to the number of visits of each spot acquired by the spot visit history acquisition unit 11 and the number of spots within the action range acquisition unit. 12 is multiplied by the number of spots acquired, and further divided by the number of visitors to the spot within a predetermined period.

  According to the spot visit history table 22 shown in FIG. 4, the feature degree of the spot 1 for the user corresponding to the user ID “001” is 9.60, the feature degree of the spot 2 is 0.00, and the spot 3 The degree of feature is 0.05. That is, the spot having the highest characteristic degree for the user corresponding to the user ID “001” is the spot 1.

  Similarly, the feature degree of the spot 1 for the user corresponding to the user ID “002” is 0.00, the feature degree of the spot 2 is 250.00, and the feature degree of the spot 3 is 1.00. That is, the spot having the highest characteristic degree for the user corresponding to the user ID “002” is the spot 2.

  Further, the feature degree of the spot 1 for the user corresponding to the user ID “003” is 2.12, the feature degree of the spot 2 is 2.65, and the feature degree of the spot 3 is 0.11. That is, the spot having the highest characteristic degree for the user corresponding to the user ID “003” is the spot 2.

  By the way, the characteristic degree is proportional to “the number of visits to each spot” and “the number of spots in the action range”, and inversely proportional to “the number of visitors to the spot within a predetermined period”. That is, the larger the value the more the same user visits the same spot, and the larger the value is when the spot is purposely selected even though the user's action range is wide. On the other hand, when the spot is a standard spot visited by many people, the value is small. Therefore, it can be said that the characteristic degree is an accurate numerical value of the degree of hole spot that is rarely visited by other users even though each user frequently visits individually. According to the invention described in the present embodiment, the spot 1 that is a secret spot for the user corresponding to the user ID “001” is recommended to the user corresponding to the user ID “002” and the user corresponding to the user ID “003”. It is possible to recommend the spot 2 which is a secret spot for the user corresponding to the user ID “002” to the user corresponding to the user ID “001” and the user corresponding to the user ID “003”. Therefore, based on the visit histories of a plurality of users, so-called spot spots that other users rarely visit among the spots visited by each user in the past without requiring the user to input an impression or the like. The spot recommendation device 1 that can be recommended to other users can be provided.

  Note that it is not always necessary to present the spot with the highest feature level for one user to other users, but only a spot having a feature level higher than a certain threshold value should be presented to other users. May be. In addition, the spot having the highest feature for one user is not presented to all of the other users, but this spot is a spot included in the action range specified by the in-action spot number acquisition unit 12. You may make it show only with respect to a certain other user.

Second Embodiment
Hereinafter, a second embodiment of the present invention will be described with reference to the drawings.

[overall structure]
FIG. 8 is a diagram showing an overall configuration for explaining the spot recommendation device 1 according to the second embodiment. In contrast to FIG. 1, the configuration with the same subscript is the same as that of the first embodiment. 1 and 8, the spot recommendation device 101 according to the second embodiment is (a) the spot visit history acquisition unit 11 and the spot visit history table 22 provided in the spot recommendation device 1 according to the first embodiment. The spot feature database 23 is different in configuration, and (a) the spot feature adjustment unit 114 which the spot recommendation device 1 does not have is different.

  The spot visit history acquisition unit 111 acquires the number of spots visited by each user within a predetermined period, in addition to the number of visits to each spot and the number of visitors to each spot. This number is stored in the spot visit history table 122.

  The spot visit history table 122 is illustrated in FIG. In addition to the configuration provided in the spot visit history table 22 according to the first embodiment, the spot visit history table 122 has a “visit spot number” field indicating the number of spots visited by each user within a predetermined period. Different. The number of spots in the predetermined period of the user corresponding to the user ID “001” is “5”, the number of spots in the predetermined period of the user corresponding to the user ID “002” is “15”, and the user ID “003” “5” is stored in the “visit spot number” column in the row of the user ID “001”, and the user ID “002” has the user ID “002”. “15” is stored in the “visit spot number” column in the row, and “25” is stored in the “visit spot number” column in the row of the user ID “003”.

  Returning to FIG. 8, the spot feature degree adjustment unit 114 functions as a spot feature degree adjustment unit. The spot feature level adjustment unit 114 decreases the spot feature level as the number of spots visited by each user within the predetermined period increases. In the present embodiment, the feature degree calculated by the spot feature degree calculation unit 13 is further described as being directly divided by “the number of spots visited by each user within the predetermined period”. However, the present invention is not limited to this. Absent.

  The feature degree adjusted by the spot feature degree adjustment unit 114 is stored in the spot feature degree database 123. The spot feature database 123 is illustrated in FIG. The spot feature database 123 stores a value obtained by dividing the value stored in the spot feature database 23 according to the first embodiment by “the number of spots visited by each user within the predetermined period”. ing.

[flowchart]
FIG. 11 is a flowchart of the spot recommendation device 101 according to the second embodiment. In contrast to FIG. 7, the process with the same subscript is the same as that of the first embodiment. 7 and FIG. 11, the spot recommendation device 101 according to the second embodiment is different in the processing contents of the spot visit history acquisition process (S1) that the spot recommendation device 1 according to the first embodiment has executed. The spot feature adjusting process (S104) that has not been executed by the spot recommendation device 1 according to the first embodiment is different.

  In the spot visit history acquisition process (S101), the spot visit history acquisition unit 111, in addition to the number of visits to each spot and the number of visitors to each spot, the number of spots visited by each user within a predetermined period. To get. This number is stored in the spot visit history table 122.

  In the spot feature adjustment process (S104), the spot feature adjustment unit 114 executes a process of reducing the spot feature as the number of spots visited by each user in the predetermined period increases.

  According to the invention described in the second embodiment, the smaller the number of spots visited by each user, the higher the performance that each user has visited can be reflected in the spot feature. Therefore, it is possible to provide the spot recommendation device 101 that can calculate the spot feature degree for extracting the hole spot more accurately.

  The effects described in the present embodiment are only the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the present embodiment. Absent.

DESCRIPTION OF SYMBOLS 1 Spot recommendation apparatus 2 External apparatus 10 Control part 11 Movement history acquisition part 12 Movement relation specific | specification part 14 Evaluation score calculation part 20 Storage part 21 Movement relation database 31 GPS log database 32 Spot geographical information database 33 Evaluation score database

Claims (3)

A spot recommendation device that recommends spots based on a user's visit history,
Spot visit history acquisition means for acquiring a visit history including the number of visits of each spot of at least the predetermined user based on a movement history of the predetermined user within a predetermined period;
Based on the movement history of the predetermined user within a predetermined period, the action range within the predetermined period of the predetermined user is specified, and the number of spots within the action range is acquired. When,
The spot feature degree indicating the feature degree of each spot of the predetermined user is set to the number of visits of each spot obtained by the spot visit history obtaining unit, and the number of spots acquired by the spot number in the action range is obtained. A spot recommendation device comprising: a spot feature degree calculating means for calculating by multiplying and dividing by the number of visitors of the spot within the predetermined period. The spot recommendation device according to claim 1,
A spot recommendation device comprising spot feature degree adjusting means for reducing the spot feature degree as the number of spots visited by each user within the predetermined period increases. A spot recommendation method in which a computer comprising a control means and a storage means recommends spots based on a visit history of a user,
The control means includes
A spot visit history acquisition step of acquiring a visit history including a visit count of each spot of at least the predetermined user based on a movement history of the predetermined user within a predetermined period;
Based on the movement history of the predetermined user within a predetermined period, the action range of the predetermined user is specified within the predetermined period, and the number of spots within the action range is acquired. When,
The spot feature degree indicating the feature degree of each spot of the predetermined user is set to the number of visits of each spot obtained in the spot visit history obtaining step, and the number of spots obtained in the action range spot number obtaining step is calculated. And a spot feature calculation step of calculating by multiplying and dividing by the number of visitors of the spot within the predetermined period.

Images