JP6540040B2 - Moving direction prediction device, moving direction prediction method, and moving direction prediction program - Google Patents

Moving direction prediction device, moving direction prediction method, and moving direction prediction program Download PDF

Info

Publication number
JP6540040B2
JP6540040B2 JP2015011501A JP2015011501A JP6540040B2 JP 6540040 B2 JP6540040 B2 JP 6540040B2 JP 2015011501 A JP2015011501 A JP 2015011501A JP 2015011501 A JP2015011501 A JP 2015011501A JP 6540040 B2 JP6540040 B2 JP 6540040B2
Authority
JP
Japan
Prior art keywords
movement
direction
destination
information
moving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2015011501A
Other languages
Japanese (ja)
Other versions
JP2016136344A (en
Inventor
卓也 尾山
卓也 尾山
真介 松本
真介 松本
亜耶 吉澤
亜耶 吉澤
洋一 橋本
洋一 橋本
康二 林
康二 林
成祥 熊膳
成祥 熊膳
福田 竜也
竜也 福田
知史 會見
知史 會見
圭佑 石本
圭佑 石本
Original Assignee
株式会社インテック
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社インテック filed Critical 株式会社インテック
Priority to JP2015011501A priority Critical patent/JP6540040B2/en
Publication of JP2016136344A publication Critical patent/JP2016136344A/en
Application granted granted Critical
Publication of JP6540040B2 publication Critical patent/JP6540040B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to a movement direction prediction device, a movement direction prediction method, and a movement direction prediction program.

  Conventionally, a technique has been proposed for the purpose of automatically infering the action purpose of the user even if the user does not input the action purpose, and presenting guidance information (for example, Patent Document 1). In the related art, in the navigation device, it is assumed that the user's action purpose is estimated based on information of a person existing in a car, information of an object, and the like.

  There is also proposed a technique for predicting the destination of a vehicle by referring to the travel route up to a certain point of the moving vehicle and the accumulated travel information history (for example, Patent Document 2).

  In addition, the driving start point and the driving end point, the date and time when they occurred, and the travel distance are accumulated and stored in the driving history storage means, and the driving history information is retrieved based on the information regarding the driving start date and current position. There has also been proposed a technique for predicting the name of the vehicle and the required time (for example, Patent Document 3). In the related art, when the specific motion detection means further detects a specific operation or motion of the driver, information on the name of the destination or information on the time required to reach the destination is output.

  There is also proposed a technique of selecting a movement history similar to the current route recorded by the current route recording means from among a plurality of movement histories stored (for example, Patent Document 4). In this technology, the movement history and the current route are indicated by a series of nodes specifying the position on the map, and the movement route is selected based on the weight given to the nodes included in the movement history and the current route in common. And

Patent No. 4925082 Patent No. 3527505 gazette Patent No. 3449199 gazette Patent No. 4495620 gazette

  Conventionally, techniques for estimating the destination of the user have been proposed. However, if you know where you are heading even if you do not know the final destination, you can provide information such as peripheral information and congestion status of the place you will pass later. However, there has been no technology for estimating the destination of the user. Then, an object of this invention is to provide the technique which predicts the direction of the moving destination of a user.

A moving area prediction apparatus according to the present invention includes history information including a route through which a moving object has passed in the past, which is expressed using a position information acquiring unit that acquires information indicating the position of the moving object and information indicating the position. A movement destination prediction unit that acquires history information similar to a route related to the current movement from a storage unit to be stored, and predicts the movement destination of the moving body and the probability of moving to the movement destination based on the acquired history information. And a direction having a predetermined width based on the current movement destination predicted by the movement destination prediction unit,
And a direction prediction unit for obtaining a direction in which the mobile body is predicted to move.

  In this way, it is possible to predict not the final destination but the destination of the movement based on the similarity with the route related to the past movement.

  Further, the history information may include, as a route, information indicating transition between meshes using a mesh that divides an area into a mesh shape of a predetermined size. The use of such a mesh can reduce the cost of maintaining and managing map information (road information). Moreover, processing load can be reduced and made uniform by using a mesh.

  Also, the destination prediction unit acquires, from the storage unit, history information in which a predetermined number of meshes that the mobile body has passed most recently in the current movement share the history information, and the movement destination and the destination are based on the acquired history information. The probability of moving to the side may be calculated. Specifically, the destination can be predicted based on the identity of the latest travel route.

  Also, the direction is represented by a region obtained by equally dividing the surrounding direction around the current location of the moving object, and the direction prediction unit calculates the movement probability to the movement destination calculated by the movement destination prediction unit for each direction to which the movement destination belongs. In order to predict the direction in which the mobile unit moves, the Specifically, the direction can be predicted by such processing.

  In addition, an information output unit may be further provided which outputs information related to the area based on the predicted area. For example, if you want to stop at a toilet, parking lot, gas station or so-called charging station, restaurant etc. at a certain point in time, it will be a route from the current location to the destination rather than the nearest store etc. It may be preferable even if the existing store etc. is farther. Direction prediction can be used to present appropriate information.

  Further, when the prediction of the area is repeatedly performed, the area prediction unit may calculate the probability that the mobile body moves in the area by multiplying the previous prediction result. In this way, abrupt prediction switching can be suppressed.

  The contents described in the means for solving the problems can be combined as much as possible without departing from the problems and technical ideas of the present invention. Further, the contents of the means for solving the problems can be provided as a system including a device such as a computer or a plurality of devices, a method executed by a computer, or a program executed by a computer. In addition, a recording medium holding a program may be provided.

  According to the present invention, it is possible to provide a technique for predicting the destination of a user.

It is a figure which shows an example of a system configuration. It is a figure for explaining an area mesh code. It is a functional block diagram showing an example of a move direction prediction device. It is a schematic diagram for demonstrating a movement history. It is a movement history table which shows an example of a record format of movement history. It is a schematic diagram for explaining a field. It is an apparatus block diagram which shows an example of a computer. It is a processing flow figure showing an example of movement history generation processing. It is a figure which shows an example of the recording format of coordinate information. It is a processing flow figure showing an example of field prediction processing. It is a schematic diagram which shows an example of a field. It is a schematic diagram which shows an example of a field. It is a schematic diagram which shows an example of a field.

  Hereinafter, embodiments of the present invention will be described using the drawings. The following embodiment is an illustration of the present invention, and the present invention is not limited to the following embodiment.

<System configuration>
FIG. 1 is a diagram showing the configuration of a system according to the present embodiment. The system includes a movement direction prediction device 1, a network 2, and mobile bodies 3 (3a, 3b,...). The mobile body 3 is a passenger car, a motorcycle, etc., and carries out with the mobile device 3b such as a vehicle 3a provided with a navigation device, a mobile phone, a smartphone, a tablet (slate PC (Personal Computer)), and a laptop PC. It is a user etc. shown with a broken line. And a navigation apparatus and a mobile apparatus are provided with the sensor which can acquire the information (coordinate information) which shows positions, such as a GPS (Global Positioning System) receiver. In addition, predetermined application software is installed in the navigation device and the mobile device, and the application software continuously transmits information indicating the position to the moving direction prediction device 1 via the network 2. On the other hand, the movement direction prediction device 1 performs processing of predicting the direction of the movement destination as the mobile body 3 moves. Note that the movement direction prediction device 1 may transmit information on stores or facilities existing in the direction to which the mobile unit 3 moves, information indicating the degree of congestion, etc. to the device that the mobile unit 3 has. . Further, in the present embodiment, the position is specified using a mesh that divides the area into a mesh shape of a predetermined size.

  FIG. 2 is a diagram for explaining the area mesh code. In this embodiment, as an example of the mesh described above, a regional mesh code defined in JIS X0410 of Japanese Industrial Standard is used. Further, in the present embodiment, coordinate information including latitude and longitude is converted into, for example, a region mesh code, and a prediction model is generated from a movement history representing the transition of the region mesh code. Here, the area mesh code is a first mesh (also referred to as a "first area section") and a second mesh (a "second area section" and a "integrated area mesh") different in the degree of detail (resolution). Standard area mesh such as called) and third order mesh (also called "third area division", "reference area mesh"), and half area mesh, quarter area mesh and eighth area mesh Represent the position with a mesh of multiple step sizes.

The first-order mesh is a region divided into approximately rectangular areas each having a side length of about 80 km, and the first-order mesh code is a lower two numbers representing the upper two digits representing latitude and the longitude. Represented by a four-digit number consisting of digits. The second mesh is the first mesh divided equally into eight in the east-west direction and the north-south direction, and the second mesh code is the upper one digit representing the latitude direction and the lower one digit representing the longitude direction It is expressed in a form in which a 2-digit number consisting of the numbers of is concatenated after the primary mesh code. The third mesh is obtained by equally dividing the second mesh in the east-west direction and the north-south direction by 10, and the third mesh code is the upper one digit representing the latitude direction and the lower one digit representing the longitude direction It is expressed in a form in which a 2-digit number consisting of the numbers of is concatenated after the second mesh code. The half area mesh is the third mesh divided equally in the east-west direction and the north-south direction, and the half area mesh code is 1 in the southwest area, 2 in the south-east area The 3rd region and the 4th region of the north-east region are represented in the form of connecting either one after the third mesh code. The quarter area mesh is a half of the half area mesh divided in the east-west direction and the north-south direction, and the quarter area mesh code is 1 in the southwest area and 2 in the south-east area. It is expressed in a form in which the northwest region is 3 and the northeast region is 4 and either is connected after a half area mesh code. 1/8 area mesh is 4
One-half area mesh divided into two in the east-west direction and north-south direction, the one-eighth area mesh code is 1 in the southwest region, 2 in the south-east region, 3 in the north-west region, northeast It is expressed in a form in which the area is 4 and one is connected after a quarter area mesh code.

  The conversion from coordinate information including latitude and longitude to a regional mesh code can be performed using an existing algorithm. Further, in the present embodiment, for convenience, the primary mesh side is relatively referred to as the upper mesh, and the 1⁄8 area mesh side is relatively referred to as the lower mesh. Further, not limited to the existing area mesh code, a mesh that divides an area into a mesh shape of a predetermined position and size may be uniquely defined and used.

For example, unlike a method that requires map information such as the case of representing movement history with a series of position information with intersections as nodes, using area mesh codes reduces the cost of updating and managing map information. be able to. Also, store the mesh code in association with commercial facilities, sightseeing spots, and other landmarks (for example, POI (Point Of Interest)), and associate the mesh code series with traffic information such as traffic congestion or construction. By storing the data, it is possible to output appropriate information from the mobile direction prediction device 1 to the mobile 3. In addition, the area mesh code can represent the position information with a plurality of levels of detail. By changing the degree of detail according to the movement distance of the mobile unit 3, the processing load of the movement direction prediction apparatus 1, and the like, it is possible to improve the accuracy of the prediction or improve the processing speed.

<Functional configuration>
FIG. 3 is a functional block diagram showing an example of the movement direction prediction device 1. The movement direction prediction apparatus 1 includes a storage unit 11, a position information acquisition unit 12, a movement history generation unit 13, a movement destination prediction unit 14, a movement direction prediction unit 15, and an information output unit 16.

  The storage unit 11 is a so-called main storage device or auxiliary storage device, and holds information temporarily or permanently. The position information acquisition unit 12 continuously acquires coordinate information including latitude and longitude from the moving object 3 via the network 2 and specifies a region on the map with a predetermined resolution (the mesh code according to the present embodiment Converted to position information and stored in the storage unit 11. In addition, the movement history generation unit 13 reads the position information stored in the storage unit 11 and generates history information indicating a movement route. In the present embodiment, a log having one unit from the departure of the mobile unit 3 to the arrival at the destination based on a predetermined condition is called history information. Further, a set of logs indicating a plurality of movements is referred to as a movement history.

  FIG. 4 is a schematic view for explaining the movement history according to the present embodiment. FIG. 4 shows a total of 100 square regions of 10 horizontal and 10 vertical showing the area mesh. In addition, the letters A to J are attached to the mesh in FIG. 4 from left to right in the horizontal direction for convenience, and numbers from 1 to 10 are attached from the top to the bottom in the vertical direction. In this embodiment, as a schematic mesh code, position information is represented as “E2” or “I5” by a code combining characters and numbers in the horizontal direction and the vertical direction. Further, the arrow from E2 to I5 in FIG. 4 indicates the moving path of the moving body 3. A user's home is present at E2, and a mobile 3 is present at I5. The history information includes position information from the departure point to the arrival point in the order in which the mobile body 3 passes.

FIG. 5 is a movement history table showing an example of a storage format of movement history according to the present embodiment. The table of FIG. 5 includes columns of “history ID” and “path”, and a record represented by one row corresponds to history information. The history information corresponding to the movement shown in FIG. 4 is a record in which "013" is registered in the field of the history ID, and in the field of the path, a row of position information indicated by arrows from E2 to I5 passes It is registered by joining in comma in order. Such history information may be newly added, for example, when it is determined that new movement has started when the time spent in one mesh is equal to or more than a predetermined threshold.

  In addition, while the mobile unit 3 is moving, the movement destination prediction unit 14 predicts the movement destination after this based on the transition of the latest position information. For example, based on position information for a predetermined number of objects immediately before transition to the current location, history information in which the same route is transitioned is extracted from the movement history. Then, position information ahead by a predetermined number in the extracted history information is summed up, and the probability of moving to each mesh is statistically predicted. As described above, the destination prediction unit 14 predicts not a final destination of the mobile body 3 but a position at which it moves a predetermined distance ahead or after a predetermined time, and its probability.

  The movement direction prediction unit 15 predicts the movement direction of the mobile body 3 based on the predicted position information and the probability. For example, an area in which all directions are divided by a predetermined number (that is, directions having a predetermined angle width) around the current position is defined, and it is predicted which area the mobile body 3 moves. In the present embodiment, an area in which all directions are divided by a predetermined number around the current location is also referred to as "direction".

  FIG. 6 is a schematic diagram for explaining an example of the direction. The moving body 3 of FIG. 6 is present at E4 in the same mesh as that of FIG. Then, the peripheral region is divided into eight by the equally spaced radial broken lines centered on the position of the movable body 3. In addition, the code | symbol of (A)-(K) is attached | subjected to eight fields in FIG. 6 for convenience. Further, the mesh on the boundary indicated by the broken line is classified into one of the areas, for example, on the basis of handling as the area having the larger area to which it belongs.

  The information output unit 16 extracts related information from the storage unit 11 based on the predicted direction, and outputs the information to the mobile 3 via the network 2. Examples of relevant information include, but are not limited to, information on stores and facilities present in an area predicted to be a transition destination, traffic information on the area, weather forecast, and the like.

<Device configuration>
FIG. 7 is a device configuration diagram showing an example of a computer. The traveling direction prediction device 1, the navigation device of the mobile unit 3 (not shown), the mobile terminal, and the like are, for example, computers as shown in FIG. 7. A computer 1000 illustrated in FIG. 7 includes a central processing unit (CPU) 1001, a main storage device 1002, an auxiliary storage device (external storage device) 1003, a communication IF.
(Interface) 1004, an input / output IF (Interface) 1005, a drive device 1006, and a communication bus 1007 are provided. The CPU 1001 executes a program to perform processing and the like according to the present embodiment. The main storage device 1002 caches programs and data read by the CPU 1001, and expands a work area of the CPU. Specifically, the main storage device is a random access memory (RAM), a read only memory (ROM), or the like. The auxiliary storage device 1003 stores programs executed by the CPU 1001, position information, and the like. Specifically, the auxiliary storage device 1003 is an HDD (Hard-disk Drive) or S
It is a solid state drive (SD), an embedded multi-media card (eMMC), a flash memory, or the like. The main storage unit 1002 and the auxiliary storage unit 1003 work as the storage unit 11 or the like of the movement direction prediction apparatus 1. The communication IF 1004 transmits and receives data to and from another computer. The travel direction prediction device 1 is connected to the network 2 via the communication IF 1004. Specifically, the communication IF 1004 is a wired or wireless network card or the like. The input / output IF 1005 is connected to the input / output device, and receives an input from the user or outputs information to the user. Specifically, the input / output device is a keyboard, a mouse, a display, a touch panel or the like. The drive device 1006 reads data recorded in a storage medium such as a magnetic disk, a magneto-optical disk, an optical disk or the like, and writes data in the storage medium. The components as described above are connected by the communication bus 1007. A plurality of these components may be provided, or some components (for example, the drive device 1006) may not be provided. Also, the input / output device may be integrated with the computer. In addition, the program to be executed in the present embodiment can be provided via a portable storage medium readable by the drive device 1006, a portable auxiliary storage device 1003 such as a flash memory, the communication IF 1004, and the like. You may Then, the CPU 1001 executes the program to make the computer as shown in FIG. 7 work as the movement prediction device 1 etc. shown in FIG.

<Movement history generation process>
Next, details of processing of the movement direction prediction device 1 will be described. In addition, although the movement area prediction device 1 executes the movement history generation process and the area prediction process described later in parallel, in the present embodiment, the movement history generation process and the area prediction process are separately described.

  FIG. 8 is a process flow diagram showing an example of the movement history generation process. The movement history generation process is performed, for example, each time coordinate information including latitude and longitude is received from the moving body 3.

  The position information acquisition unit 12 of the movement direction prediction apparatus 1 acquires information indicating a position from the mobile 3 at an arbitrary timing via the network 2 (FIG. 8: S1). First, the mobile unit 3 measures information indicating its position by latitude and longitude, for example, by a GPS receiver. Then, the moving object 3 transmits information indicating the position to the moving area prediction device 1 at a predetermined time or every time the predetermined distance is moved. The information indicating the position may be so-called probe information. On the other hand, the position information acquisition unit 12 of the movement direction prediction apparatus 1 stores information indicating the received position in the storage unit 11.

  FIG. 9 is a view showing an example of a coordinate information table stored in the storage unit 11. As shown in FIG. In the example of FIG. 9, values corresponding to items such as mobile ID, date and time, latitude, longitude, direction, and speed are stored in one record as position information at a certain point in time of a mobile. Note that the item of the direction indicates the traveling direction of the moving body, and the value indicating the traveling direction is represented by an azimuth angle, for example, where true north is 0 degrees or 12 o'clock.

  Then, based on the information indicating the position added to the storage unit 11, the movement history generation unit 13 determines whether the moving body 3 has started a new movement (S2). The movement history generation unit 13 determines that a new movement has started, for example, when information indicating the current position is received after a predetermined time or more has passed since the information indicating the previous position is transmitted from the moving body 3. Further, it may be determined that a new movement has started when the movement distance from the previous time satisfies a predetermined condition in addition to the elapsed time from the previous time. In addition, when information indicating engine start of the vehicle can be acquired, it may be determined that a new movement has been started by engine start. In addition, the position of the user's home of the mobile unit 3 is specified by, for example, causing the user to input or performing predetermined prediction processing, and when holding in advance, new movement is started when starting movement from the position of the home. It may be determined that the movement has started.

  When it is determined that a new movement has been started (S2: YES), the movement history generation unit 13 adds new history information to the movement history table as shown in FIG. 5 (S3), and movement history generation processing Finish. That is, the movement history generation unit 13 adds a record to the movement history table, and registers position information. In addition, the movement history generation unit 13 converts the information indicating the position including the latitude and the longitude shown in FIG. 9 into position information such as a region mesh code, for example, and registers the information in the field of the route in FIG. .

On the other hand, when it is determined that the new movement is not started in S2 (S2: NO), the movement history generation unit 13 sets the field of the route of the latest history information in the movement history table as shown in FIG. Position information is added (S4), and the movement history generation process is terminated. If the mesh in which the moving object 3 indicated by the position information is present is the same as the previous mesh registered in the path of the history information, the position information may not be added. That is, position information may be added only when the moving object 3 moves to the adjacent mesh.

  By the movement history generation processing as described above, for example, as illustrated in FIG. 5, a route is stored for each past movement of the mobile body 3.

<Prediction process>
FIG. 10 is a process flow diagram showing an example of the area prediction process. The movement destination prediction unit 14 of the movement direction prediction device 1 acquires, from the movement history table of the storage unit 11, history information similar to the route related to the current movement of the moving body 3 (FIG. 10: S11). Specifically, the latest route reads the same history information. In this step, from the movement history of the same user, passage meshes for a predetermined number (temporarily set as “N” in the present embodiment) up to the current position (mesh) extract the same history information. In the present embodiment, since the latest N routes search the same history information, the direction prediction process is not performed when the number of meshes passed in the current movement is less than N. Hereinafter, it will be assumed that N is three.

  For example, it is assumed that the records having the history IDs “001” to “012” shown in FIG. 5 have already been accumulated in the movement history table, and the movement of the history ID “013” is started from now. First, at the time of E2 when the user left the home, the prediction process is not performed because the number of passing paths involved in the current movement is less than N (= 3) which is a predetermined amount. Similarly, no prediction process is performed when moving from E2 to E3. After that, when the moving object 3 moves to E4, the predetermined number of passage paths related to the current movement is N, so the movement destination prediction unit 14 sets “E2, E3, E4” in the field of the movement history table. Extract registered history information. As a result, ten pieces of history information having history IDs “001” to “010” are extracted.

  After that, the destination prediction unit 14 calculates the destination and the probability of the destination predicted based on the read history information (S12). In this step, the moving object 3 predicts the position (mesh) of the movement destination ahead of the predetermined distance or the predetermined time together with the probability. Specifically, on the basis of the history information extracted in S11, movement destinations for a predetermined number (in the present embodiment, temporarily referred to as "M") and the ratio of movement in the past are calculated.

For example, assuming that the destination ahead M times is X, the probability P (X) to reach X can be obtained by the following equation.

A case where the moving object 3 is present at E4 in the movement of the history ID “013” in FIG. Of the 10 history information extracted in S11, when the destination of M (= 3) ahead, which is a predetermined amount, and the number of times to reach the destination are totaled, the number of moves to G5 moves to 6, E7 The number of times of movement is 1 and the number of times of movement to C5 is 3. Therefore, the probability of reaching each destination is calculated as follows.
P (G5) = 6/10
P (E7) = 1/10
P (C5) = 3/10

Then, the movement direction prediction unit 15 of the direction prediction device 1 specifies the direction where the possibility of being the movement destination is high (S13). In this step, it is predicted to which direction the mobile body 3 is to move, among the areas divided into a predetermined number of areas (temporarily referred to as "K" in this embodiment) about the current position. The probability of moving to each direction can be obtained, for example, by counting the probability of reaching each moving destination calculated in S12 for each direction. Specifically, the probability of moving to each direction Di (i = 1, 2,... K) is obtained, for example, by the following equation.

As shown in FIG. 6, assuming that K is 8 and the probability that the mobile 3 existing in E2 moves in each direction is obtained, the following is obtained.
P (c) = 6/10
P (e) = 1/10
P (f) = 3/10

  In addition, the information output unit 16 of the direction prediction device 1 extracts related information from the storage unit 11 based on the predicted direction, and outputs it to the mobile 3 via the network 2 (S14), and the direction prediction processing Finish. As described above, as the related information, for example, information of a store or facility existing in an area predicted to be a transition destination, traffic information of the area, weather forecast and the like can be exemplified, but it is not limited thereto. Specifically, for example, an information reception unit (not shown) of the direction prediction apparatus 1 acquires various information associated with position information (for example, an area mesh code of any degree of detail) and stores it in the storage unit 11 in advance. I shall let you. For example, information on a road work schedule is registered in association with location information of a site, or information on occurrence of traffic congestion is registered in association with location information of the site. Further, information on a newly opened store, information on an advertisement, information on a sightseeing spot, and the like may be registered in association with position information. In S14, information stored in association with position information belonging to the direction in which the mobile unit 3 is predicted to move later is extracted from the storage unit 11 and transmitted to the computer of the mobile unit 3. Note that the process of this step may not be performed, and when a request is received from the user of the mobile unit 3, information may be output based on the content of the request and the predicted direction.

In addition, if the mobile body 3 moves to E5 of FIG. 4, the area prediction process is executed again. At this time, the probability of reaching the position three points ahead on the basis of the three nearest passing mesh rows in S12 is calculated as follows.
P (H5) = 6/10
P (E8) = 1/10
P (C6) = 1/10
P (B5) = 2/10

In addition, meshes belonging to eight areas change as the mobile body 3 moves. FIG. 11 is a diagram showing an example of the case where the mobile unit 3 is present at E5. Then, the probability of moving in each direction in S13 is calculated as follows.
P (c) = 6/10
P (e) = 1/10
P (f) = 1/10
P (ki) = 2/10

Similarly, when the mobile unit 3 moves to F5 in FIG. 4, the direction prediction processing is executed again. Then, the probability of reaching the position three points ahead on the basis of the latest three passing mesh rows in S12 is calculated as follows.
P (H6) = 6/6
Then, the probability of moving in each direction in S13 is calculated as follows. The direction in the case where the mobile unit 3 exists in F5 is defined around F5 as shown in FIG.
P (U) = 6/6

Next, when the mobile unit 3 moves to G5 in FIG. 4, the direction prediction processing is executed again. Then, the probability of reaching the position three points ahead on the basis of the latest three passing mesh rows in S12 is calculated as follows.
P (H7) = 6/8
P (I6) = 2/8
In this case, both H7 and I6 belong to the direction (D). Therefore, the probability of moving in each direction in S13 is summarized as follows. The direction in which the mobile unit 3 exists in G5 is defined around G5 as shown in FIG.
P (d) = 8/8
The description of the subsequent movement is omitted.

<Effect>
For example, if you want to stop at a toilet, parking lot, gas station or so-called charging station, restaurant etc. at a certain point in time, it will be a route from the current location to the destination rather than the nearest store etc. It may be preferable even if the existing store etc. is farther. In such a case, if the direction prediction of this embodiment is used, appropriate information can be presented to the user.

  Further, according to the present invention, by expressing position information by area mesh and expressing a route by a series of adjacent area meshes, it is possible to reduce the cost of maintaining and managing map information (road information). It will be. Moreover, processing load can also be reduced and equalized by using the area mesh.

  In addition, the area mesh can express position information at multiple levels of detail in stages. A prediction model may be generated with a plurality of levels of detail, and the prediction model used in the prediction process may be changed. In this way, it is possible to improve the accuracy of prediction by changing to a lower detailed mesh. Also, by changing to the upper coarse mesh, the processing load can be reduced. In addition, when the mobile transmits the position information, the position information may be specified by a coarse mesh. In this way, it is possible to provide a service that takes into account the privacy of the user because the area having a certain area is treated without specifying the home position or destination as one point.

<Modification>
In the above embodiment, the prediction of the area is performed using all of the history information accumulated in the movement history table shown in FIG. 5, but the prediction of the area is performed based on, for example, the latest part of the history information. You may do so.

  The value of N is not limited to the above-mentioned fixed value "3". Instead of a fixed value, it may be dynamically changed to, for example, about 5% of the moving distance of the moving body 3.

  The value of M is not limited to the above-mentioned fixed value "3". Also, in the case of fixed values, one fixed value may be set for all moving bodies, or different fixed values may be set according to the type of moving body. Also, it may be changed dynamically as about 5% of the movement distance. In addition, the direction in which the moving object travels may be stored separately, and M may be reduced if the direction changes significantly during movement, and M may be increased if the direction does not change much. .

Further, in the above-described embodiment, the direction is independently predicted in each mesh, but the prediction may be performed in consideration of the prediction result of the previous mesh. For example, a predetermined weight is added to the above-described prediction result, and a value obtained by multiplying the previous prediction result is obtained. Specifically, the probability Q i (D j ) of advancing to the direction D j at the i-th time (i = 1, 2, 3...) May be obtained by the following equation. In this way, abrupt prediction switching can be suppressed.

Q 0 (D j ) can be an arbitrary value. For example, the following numbers may be used.

Also, the above-mentioned movement history table and coordinate information table exemplarily show a general table consisting of rows and columns for convenience of explanation, but the format for holding data is not limited to such an example, and the configuration is arbitrary. It can be normalized. Also, RDBMS (Relational Database Management System) may be adopted, or a management system such as a key-value type, an object database or the like called so-called NoSQL may be adopted. The same information may be stored as delimiter-delimited text data such as CSV (Comma-Separated Values).

  Further, in the example of FIG. 1, the area prediction processing is described as the movement area prediction device 1 on the network 2 performs the area prediction processing, but is not limited to such an example. For example, a configuration may be made such that a plurality of servers execute at least a part of processes in parallel, or a computer of the mobile 3 executes at least a part of the processes.

  The items described in the above-described embodiment and modification can be combined as much as possible without departing from the problems and technical ideas of the present invention.

<Others>
The present invention includes a computer program that performs the above-described processing. Furthermore, a computer readable recording medium recording the program is also within the scope of the present invention. With regard to the recording medium on which the program is recorded, the above process can be performed by causing a computer to read and execute the program of the recording medium.

  Here, the computer readable recording medium refers to a recording medium which can store information such as data and programs by electrical, magnetic, optical, mechanical or chemical action and read from a computer. Among such recording media, those removable from the computer include flexible disks, magneto-optical disks, optical disks, magnetic tapes, memory cards and the like. Further, as a recording medium fixed to the computer, there are a hard disk drive, a ROM and the like.

DESCRIPTION OF SYMBOLS 1 movement direction prediction apparatus 11 storage unit 12 position information acquisition unit 13 movement history generation unit 14 movement destination prediction unit 15 movement direction prediction unit 16 information output unit 2 network 3 (3a, 3b,...)

Claims (7)

  1. A position information acquisition unit that acquires information indicating the position of the mobile object;
    The history information obtained by acquiring history information similar to the route related to the current movement from a storage unit that stores history information including a route through which the mobile object has passed in the past, which is expressed using information indicating the position, and acquired A movement destination prediction unit that predicts the current movement destination of the moving body and the probability of moving to the movement destination based on information;
    Based on the current travel destination predicted by the travel destination prediction unit, it is represented by a region equally dividing the surrounding direction around the current location of the mobile object, and the direction prediction for which the mobile object is predicted to move is predicted Department,
    Equipped with
    The surface prediction unit, a movement probability to the destination of the destination prediction unit is calculated by summing each surface to which the destination belongs, said moving body moving direction prediction apparatus that predict the direction of movement.
  2. The movement direction prediction device according to claim 1, wherein the history information includes, as the route, information indicating transition between meshes using a mesh that divides an area into a mesh shape of a predetermined size.
  3. The destination prediction unit acquires, from the storage unit, history information in which a predetermined number of meshes that the mobile unit has passed most recently in the current movement share the history information, and the movement destination and the destination are determined based on the acquired history information. The movement direction prediction device according to claim 1 or 2, which calculates a probability of moving to a movement destination.
  4. The movement direction prediction apparatus according to any one of claims 1 to 3 , further comprising an information output unit that outputs information related to the area based on the predicted area.
  5. 5. The movement direction according to any one of claims 1 to 4 , wherein when repeatedly predicting the direction, the direction prediction unit calculates the probability that the moving body moves to the direction by multiplying the previous prediction result. Prediction device.
  6. Obtaining information indicating the position of the mobile object;
    The history information obtained by acquiring history information similar to the route related to the current movement from a storage unit that stores history information including a route through which the mobile object has passed in the past, which is expressed using information indicating the position, and acquired A movement destination prediction step of predicting the current movement destination of the moving body and the probability of moving to the movement destination based on information;
    A step which is represented by a region obtained by equally dividing the surrounding direction centering on the current location of the moving object based on the current moving destination predicted in the moving destination prediction step, and obtaining a field predicted to move the moving object When,
    The computer is running,
    In the step of obtaining the direction, the movement probability is counted for each direction to which the movement destination belongs to predict the direction in which the moving body moves.
    How to predict movement direction.
  7. Obtaining information indicating the position of the mobile object;
    The history information obtained by acquiring history information similar to the route related to the current movement from a storage unit that stores history information including a route through which the mobile object has passed in the past, which is expressed using information indicating the position, and acquired A movement destination prediction step of predicting the current movement destination of the moving body and the probability of moving to the movement destination based on information;
    A step which is represented by a region obtained by equally dividing the surrounding direction centering on the current location of the moving object based on the current moving destination predicted in the moving destination prediction step, and obtaining a field predicted to move the moving object When,
    On your computer ,
    In the step of obtaining the direction, the movement probability is counted for each direction to which the movement destination belongs to predict the direction in which the moving body moves.
    Moving direction prediction program.
JP2015011501A 2015-01-23 2015-01-23 Moving direction prediction device, moving direction prediction method, and moving direction prediction program Active JP6540040B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2015011501A JP6540040B2 (en) 2015-01-23 2015-01-23 Moving direction prediction device, moving direction prediction method, and moving direction prediction program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2015011501A JP6540040B2 (en) 2015-01-23 2015-01-23 Moving direction prediction device, moving direction prediction method, and moving direction prediction program

Publications (2)

Publication Number Publication Date
JP2016136344A JP2016136344A (en) 2016-07-28
JP6540040B2 true JP6540040B2 (en) 2019-07-10

Family

ID=56512603

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2015011501A Active JP6540040B2 (en) 2015-01-23 2015-01-23 Moving direction prediction device, moving direction prediction method, and moving direction prediction program

Country Status (1)

Country Link
JP (1) JP6540040B2 (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1380813B1 (en) * 2001-08-06 2012-05-02 Panasonic Corporation Information providing method and information providing device
JP2004221819A (en) * 2003-01-14 2004-08-05 Seiko Epson Corp Mobile information apparatus
JP2010145116A (en) * 2008-12-16 2010-07-01 Nec Corp Destination prediction system, destination prediction method, and program
JP4743312B2 (en) * 2009-07-29 2011-08-10 株式会社デンソー Image identification device
EP2479736A4 (en) * 2009-09-18 2013-04-24 Ntt Docomo Inc Roadside portion traffic amount calculation device and roadside portion traffic amount calculation method
DE112009005414B4 (en) * 2009-12-02 2019-03-21 Mitsubishi Electric Corporation Navigation system

Also Published As

Publication number Publication date
JP2016136344A (en) 2016-07-28

Similar Documents

Publication Publication Date Title
Bierlaire et al. A probabilistic map matching method for smartphone GPS data
JP4283338B2 (en) Destination prediction apparatus, destination prediction method, navigation apparatus, and program
Castro et al. From taxi GPS traces to social and community dynamics: A survey
US8538686B2 (en) Transport-dependent prediction of destinations
US7936284B2 (en) System and method for parking time estimations
US8963740B2 (en) Crowd-sourced parking advisory
CN102667404B (en) The method of point of interest is analyzed with detection data
CN104978024A (en) Detecting driving with a wearable computing device
US9134137B2 (en) Mobile search based on predicted location
Alvarez-Garcia et al. Trip destination prediction based on past GPS log using a Hidden Markov Model
JP2014527617A (en) Route provision through information collection and extraction
JP2009036594A (en) Travel destination forecast device and method
CN105210119B (en) The location data points provided by computing device determine the number of pass cost
US10197409B2 (en) Frequency based transit trip characterizations
WO2014186199A2 (en) Providing predicted travel information
US20140222950A1 (en) Predictive Mobile Map Download
CN104167092A (en) Method and device for determining taxi pick-up and drop-off hot spot region center
Liu et al. iParking: An intelligent indoor location-based smartphone parking service
Chen et al. Nlpmm: A next location predictor with markov modeling
JP2018503920A (en) Method and system for providing on-demand service information
CN105683716B (en) Context traffic or current warning
US20150363700A1 (en) Discovering Functional Groups of an Area
CN104937375A (en) Destination prediction device, destination prediction method, and destination display method
US8797187B2 (en) Street parking availability estimation
Gong et al. Identification of activity stop locations in GPS trajectories by density-based clustering method combined with support vector machines

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20171218

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20180122

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20181130

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20181211

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20190206

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20190305

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20190410

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20190514

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20190527

R150 Certificate of patent or registration of utility model

Ref document number: 6540040

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150