JP2007257374A - Traffic condition prediction program, device, and method, and recording medium for recording traffic condition prediction program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To predict a traffic condition easily and accurately. <P>SOLUTION: An arbitrary link is detected from a plurality of links for composing a road network by a detection section 2002, and result information related to a first period up to current time and that related to a second period, excluding the current time are acquired from the result information for relating travel speeds in the detected arbitrary link for each date/time by an acquisition section 2004. Then, the similarity between the acquired result information related to the first period and that related to the second period is calculated by a calculation section 2005, and the result information related to the third period after the lapse of the second period is determined to be the predicted value of the travel speed from the current time by a determination section 2006, based on the calculated similarity. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a traffic situation prediction program for predicting a traffic situation, a recording medium recording the program, a traffic situation prediction apparatus, and a traffic situation prediction method.

  Conventionally, various attempts have been made to predict traffic conditions such as the location and scale of traffic jams. For example, based on a counter value by a traffic counter embedded in a road, a vehicle passing speed at a specific point and a time required for passing a link including the specific point are calculated, and a traffic situation is predicted using the calculation result. There is such a technique.

  Further, in Patent Document 1 below, on the basis of traffic jam correlation data with other links for a predetermined link created based on past road traffic information for each link and current road traffic information for each link, The congestion occurrence probability of each link is calculated based on the congestion pattern data for a given link created based on the past road traffic information for each link and the current road traffic information for each link. A technique is disclosed in which traffic condition prediction data for each link is calculated using the calculated traffic jam persistence probability and traffic jam occurrence probability.

JP 2004-272408 A

  However, in the conventional technique described in Patent Document 1 described above, it is possible to calculate the congestion occurrence probability and the congestion persistence probability for each link, but since the time to reach each link is not known, There is a problem that it is difficult to accurately predict traffic conditions.

  The present invention eliminates the above-described problems caused by the prior art, a traffic situation prediction program capable of easily and accurately predicting a traffic situation, a recording medium storing the program, a traffic situation prediction apparatus, and a traffic The purpose is to provide a situation prediction method.

  In order to solve the above-described problems and achieve the object, a traffic situation prediction program, a recording medium storing the program, a traffic situation prediction apparatus, and a traffic situation prediction method according to the present invention include a plurality of links constituting a road network. From the record information that detects an arbitrary link from among the record information that associates the movement speed of the detected link at every date and time, the record information about the first period up to the present time, and the present time The actual information on the second period not included is acquired, the similarity between the acquired actual information on the first period and the actual information on the second period is calculated, and based on the calculated similarity, The moving speed in the performance information regarding the third period after the second period has elapsed is determined as a predicted value of the moving speed from the current time.

  According to the present invention, it is possible to determine the predicted value of the moving speed in an arbitrary link after a predetermined time has elapsed from the current date and time without newly providing a physical infrastructure facility. Can be predicted with accuracy.

  In the above invention, the area including the arbitrary link is identified from the areas constituted by a part of the plurality of links, and the moving speed of the links constituting the identified area is determined by date. It is good also as acquiring the performance information regarding the said 1st and 2nd period from the performance information linked | related for every time.

  According to this invention, since the predicted value of the moving speed can be determined for each area, it is possible to easily and accurately predict a traffic situation having a high utility value when moving within the area.

  Moreover, in the said invention, it is good also as specifying the area containing the link from which the moving speed in the said 1st period fell below the predetermined speed threshold value.

  According to the present invention, since the predicted value of the moving speed can be determined for each area where traffic congestion is assumed, it is possible to easily and accurately predict a traffic situation with higher utility value when moving within the area. can do.

  Moreover, in the said invention, it is good also as acquiring the performance information regarding the said 1st and 2nd period based on the increase / decrease number per unit time of the link which fell below the said predetermined speed threshold value in the said area.

  According to the present invention, it is possible to determine the predicted value of the moving speed in consideration of the traffic jam pattern that is expected to occur in the area. Predictions can be made easily and with high accuracy.

  Moreover, in the said invention, it is good also as acquiring the performance information regarding the said 1st and 2nd period based on the number per unit time of the link which fell below the said predetermined speed threshold value in the said area.

  According to the present invention, since the predicted value of the moving speed can be determined in consideration of the size of the traffic jam that is expected to occur in the area, the traffic situation with higher utility value can be simplified when moving in the area. In addition, it can be predicted with high accuracy.

  Further, in the above invention, the record information that the movement speed in the second period falls below a predetermined speed threshold is acquired from the record information that associates the movement speeds in the links constituting the area for each date and time. It is good as well.

  According to the present invention, since the predicted value of the moving speed can be determined in consideration of the actual traffic jam that has occurred in the area, it is possible to easily and accurately determine the traffic situation with higher utility value when moving within the area. Can be predicted.

  Also, in the above invention, a record in which one link is specified from among the plurality of links, and the moving speed of the specified one link and a link having a predetermined correlation with the one link is associated for each date and time. It is good also as acquiring the performance information regarding the said 1st and 2nd period from information.

  According to the present invention, it is possible to determine the predicted value of the moving speed for each unit using one link and the correlated link as one unit. In addition, it can be predicted with high accuracy.

  Further, in the above invention, the first information may be selected from among the performance information in which the correlation speed established between the link speed of the one link is within a predetermined range and the movement speed in the correlation link is associated for each date and time. And it is good also as acquiring the performance information regarding the 2nd period.

  According to the present invention, it is possible to determine the predicted value of the moving speed in one link using the past link information having a clear correlation with one link based on the existing correlation coefficient. Therefore, it is possible to easily and accurately predict a traffic situation having high utility value when moving one link.

  In the above invention, the first information can be obtained by using the Euclidean distance between the performance information related to the first period and the performance information related to the second period in the Euclidean space having the same number of dimensions as the number of links acquired. It is good also as calculating the similarity of the performance information regarding the period and the performance information regarding the second period.

  According to this invention, since the predicted value of the moving speed in the target link can be determined using the actual information having clear similarity, the traffic situation having high utility value can be easily and easily obtained when moving each link. Predict with high accuracy.

  Further, in the above invention, the record information relating to the third period after the period with the highest similarity in the second period may be determined as the predicted value of the moving speed from the current time. .

  According to this invention, since the predicted value of the moving speed in the target link can be determined based on the record information most similar to the record information related to the first period, it is highly useful when moving each link. Traffic conditions can be predicted easily and with high accuracy.

  Moreover, in the said invention, it is good also as determining the moving speed from the date time when the said 2nd period is completed to the predicted value of the moving speed from the said present time.

  According to the present invention, the date time when the second period is completed and the current date time are made relative to each other, and the moving speed from the date time when the second period is completed is determined as the predicted value of the moving speed from the current time. Therefore, it is possible to predict traffic conditions easily and with high accuracy.

  According to the traffic situation prediction program, the recording medium storing the program, the traffic situation prediction apparatus, and the traffic situation prediction method according to the present invention, it is possible to easily and accurately predict the traffic situation.

(Embodiment 1)
Exemplary embodiments of a traffic situation prediction program, a recording medium recording the program, a traffic situation prediction apparatus, and a traffic situation prediction method according to the present invention will be explained below in detail with reference to the accompanying drawings. In the first embodiment, a traffic situation prediction system that calculates a predicted value of a link speed in each link constituting an arbitrary area on a map will be described.

  Here, the “link” is a line segment that constitutes a road in map data representing roads throughout Japan and connects two nodes representing arbitrary points in the map data. The “link speed” is information indicating a speed when moving the above-described link. The “link speed” can be obtained, for example, by measuring the speed of a vehicle that has actually passed through an arbitrary point on the link using a traffic counter embedded in the road. Further, the “link speed” can be obtained by, for example, dividing the link distance by the time required to pass through the link.

(System configuration of traffic condition prediction system)
First, the system configuration of the traffic condition prediction system according to the first embodiment of the present invention will be described. FIG. 1 is a system configuration diagram of a traffic situation prediction system according to Embodiment 1 of the present invention. In FIG. 1, a traffic condition prediction system 100 collects road traffic information and predicts traffic conditions such as the occurrence of traffic jams, the size of traffic jams, and patterns of traffic jams based on the collected road traffic information.

  Here, the “road traffic information” is information that can specify the time required for the vehicle to move on an arbitrary section on the road and the moving speed of the vehicle at an arbitrary point. Specifically, the “road traffic information” is, for example, a point where traffic is expected to travel at a certain speed or less, such as a traffic congestion point on the road or a traffic restriction point due to work such as construction on or around the road. And information indicating the distance that traffic continues at a speed below a certain level.

  In the traffic situation prediction system 100, a traffic situation prediction apparatus 101 and a client terminal 102 are connected to a network 110 such as a LAN, WAN, or the Internet, and can communicate with each other. The traffic situation prediction apparatus 101 is a computer apparatus that calculates the link speed of each link using data stored in various tables in the database 103.

  The time required for passing through the link is the time represented by the difference between the times when an arbitrary vehicle passes through both ends of the link. Here, the time of passing through both ends of the link is not limited to the time of actually passing through both ends of the link. For example, a plurality of current position information of an arbitrary vehicle is acquired at different times, and the time estimated to have passed through both ends of the link based on the acquired current position information and the time at which the current position information was acquired May be obtained by calculation.

  The client terminal 102 is, for example, a computer device installed in a vehicle management organization that collects information such as the current location or movement status of a specific vehicle such as a bus or taxi, and manages the vehicle using the collected information. is there. The client terminal 102 transmits information collected from a specific vehicle to the traffic situation prediction apparatus 101.

(Hardware configuration of computer device)
Next, the hardware configuration of the computer apparatus (traffic situation prediction apparatus 101 or client terminal 102) shown in FIG. 1 will be described. FIG. 2 is a block diagram showing a hardware configuration of the computer apparatus shown in FIG. In FIG. 2, the computer apparatus includes a CPU 201, a ROM 202, a RAM 203, an HDD (hard disk drive) 204, an HD (hard disk) 205, an FDD (flexible disk drive) 206, and an example of a removable recording medium. An FD (flexible disk) 207, a display 208, an I / F (interface) 209, a keyboard 210, a mouse 211, a scanner 212, and a printer 213 are provided. Each component 201 to 213 is connected by a bus 200.

  Here, the CPU 201 controls the entire computer apparatus. The ROM 202 stores a program such as a boot program. The RAM 203 is used as a work area for the CPU 201. The HDD 204 controls data read / write with respect to the HD 205 according to the control of the CPU 201. The HD 205 stores data written under the control of the HDD 204.

  The FDD 206 controls reading / writing of data with respect to the FD 207 according to the control of the CPU 201. The FD 207 stores data written under the control of the FDD 206 or causes the computer device to read data stored in the FD 207.

  In addition to the FD 207, the removable recording medium may be a CD-ROM (CD-R, CD-RW), MO, DVD (Digital Versatile Disk), memory card, or the like. The display 208 displays data such as a document, an image, and function information as well as a cursor, an icon, or a tool box. As the display 208, for example, a CRT, a TFT liquid crystal display, a plasma display, or the like can be adopted.

  The I / F 209 is connected to a network 110 such as the Internet through a communication line, and is connected to other devices via the network 110. The I / F 209 controls an internal interface with the network 110 and controls input / output of data from an external device. For example, a modem or a LAN adapter may be employed as the I / F 209.

  The keyboard 210 includes keys for inputting characters, numbers, various instructions, and the like, and inputs data. Moreover, a touch panel type input pad or a numeric keypad may be used. The mouse 211 performs cursor movement, range selection, window movement, size change, and the like. A trackball or a joystick may be used as long as they have the same function as a pointing device.

  The scanner 212 optically reads an image and takes in the image data into the computer apparatus. The scanner 212 may have an OCR function. The printer 213 prints image data and document data. As the printer 213, for example, a laser printer or an ink jet printer can be employed.

  Next, the monitoring area will be described. FIG. 3 is an explanatory diagram for explaining the monitoring area. Here, the “monitoring area” is an arbitrary area on the map, and is an area to be monitored for predicting the traffic situation in the traffic situation prediction system 100. “Congestion” is a state in which the link speed is equal to or less than the congestion threshold as a predetermined speed threshold set in advance.

  Here, the “congestion threshold” is information for determining whether or not the road is congested. The traffic congestion threshold is determined as a vehicle speed such as “10 km / h or less per hour” by, for example, VICS (Vehicle Information and Communication System: registered trademark). A plurality of traffic congestion threshold values are set according to the type of road constituted by links, and the traffic congestion threshold value on an expressway is different from the traffic congestion threshold value on a general road.

  As illustrated in FIG. 3, the size of the monitoring areas e1 to e3 varies depending on the size of the traffic jam that occurs in each of the monitoring areas e1 to e3. The size of the monitoring areas e1 to e3 increases as the size of the generated traffic jam increases. In the monitoring areas e1 to e3, an arbitrary area in which it is determined by the administrator of the traffic condition prediction system 100 that the occurrence frequency of traffic congestion is high is set.

(Link structure)
Next, the link configuration in each of the monitoring areas e1 to e3 will be described. FIG. 4 is an explanatory diagram (part 1) illustrating the configuration of the link. FIG. 4 shows, as an example, a configuration of links that configure a road in the monitoring area e1. In FIG. 4, the circles represented by reference characters L101 to L112 indicate the links that constitute the road in the monitoring area. The links L101 to L112 are links with a track record of occurrence of traffic jams and links around the links. The monitoring area e1 is composed of links L101 to L112.

(Table in database 103)
Next, the table and database stored in the database 103 shown in FIG. 1 will be described. The database 103 stores a monitoring area table (see FIG. 5), a link information performance database (see FIG. 6), a traffic jam record table (see FIGS. 7 and 8), and a traffic jam incidental information table (see FIGS. 9 and 10). Yes. Hereinafter, it demonstrates in order using drawing.

  First, the monitoring area table will be described. FIG. 5 is an explanatory diagram showing a monitoring area table. The monitoring area table 500 is a data table that stores the links configuring the monitoring areas e1 to e3 described above for each area No. As shown in FIG. 5, in the monitoring area table 500, identification information of the links L101 to L112 constituting the monitoring areas e1 to e3 is stored for each area No. Here, “area No.” is identification information for identifying an area, and is unique to each of the monitoring areas e1 to e3.

  Next, the link information performance database will be described. FIG. 6 is an explanatory diagram showing a link information performance database. The link information performance database (hereinafter referred to as “DB”) is a database that stores the link speeds of links constituting a road network for each identical date and time. As shown in FIG. 6, the link information performance DB 600 stores the link speeds of all the links L1 to Ln constituting the road in the monitoring areas e1 to e3 for each date and time.

  Here, the “date time” is information indicating the date and time when the link speeds of the links L1 to Ln are acquired. The date / time is set every predetermined unit time, for example, “every 10 minutes”. The date and time in the first embodiment is set in units of 10 minutes. For this reason, the link speed is acquired six times per hour. From FIG. 6, for example, the link speed at the date time t3 of the link Ln is vn. 3 is understood. In the link information record DB 600, the link speeds from the start of acquiring the link speeds to the present are accumulated and stored.

  In FIG. 6, for the sake of simplicity, the link information performance DB 600 in which one “link speed” is stored for one “link” is shown. There may be a plurality of link speeds corresponding to.

  For example, when a link connecting any node A and node B is a link that constitutes a road that can be face-to-face, the link information performance DB 600 includes a link speed when moving from node A to node B, Two types of link speed when moving from B to node A are stored.

  In addition, when the link connecting any node A and node B is a link constituting a road with one-way restrictions, either one of node A to node B or node B to node A is stored in the link information record DB 600. Stores the link speed.

  Further, when the link connecting any node A and node B is a link that constitutes a road that is restricted to one-way only in a specific time zone, the link information performance DB 600 includes one or Two link speeds are stored.

  The information stored in the link information result DB 600 includes a current situation table (see FIG. 11) and a traffic jam information table in addition to a traffic jam history table (see FIGS. 7 and 8) and a traffic jam information table (see FIGS. 9 and 10). (See FIG. 13). Hereinafter, in the first embodiment, each data table will be described using the monitoring area e1 shown in FIG. 4 as an example.

  First, the traffic jam record table will be described. FIG. 7 is an explanatory diagram (part 1) illustrating a traffic jam record table. Here, the traffic jam record table is a data table that stores the link speeds of the links constituting the monitoring area e1 for each identical date and time. As shown in FIG. 7, in the traffic jam record table 700, the link speeds of the links L101 to L112 in the monitoring area e1 are stored for each date and time. The date and time in the traffic jam record table 700 is from 20 minutes before the date and time at the time when the traffic jam occurs in the monitoring area e1 to 20 minutes after the date and time at the time when the traffic jam in the monitoring area e1 is resolved.

  The traffic jam record table 700 is created every time a traffic jam occurs in the monitoring area e1. Stored in the database 103. Here, “result No.” is information for identifying the traffic jam record table 700. If traffic jams occur multiple times in the same monitoring area e1, a plurality of traffic jam history tables 700 of the monitoring area e1 are stored in the database 103, and each traffic jam history table 700 has a unique track record No. Are given respectively (see FIG. 8).

  FIG. 8 is an explanatory diagram (part 2) of the traffic jam record table. As shown in FIG. 8, in the traffic jam record table 800, the link speeds of all the links L101 to L112 in the monitoring area e1 are stored for each date and time as in the traffic jam record table 700 shown in FIG. Yes.

  As can be seen from FIG. 7 and FIG. 8, the traffic jam record tables 700 and 800 are traffic jams that occurred in the same monitoring area e1, but the contents differ depending on the date and time when the traffic jam occurred. This is because, even for traffic jams occurring in the same monitoring area e1, the traffic jam patterns and scales differ depending on the situation of traffic jams, such as time of day, day of the week, or weather.

  Generally, most of the traffic jam occurs at a specific location. In general, traffic jams occurring at the same location differ depending on the conditions of the traffic jams, such as time of day and weather, but if the traffic jam conditions are similar, The pattern from the occurrence of traffic jams to the resolution is often similar.

  The traffic jam record tables 700 and 800 may store information indicating the time and weather when the traffic jam occurs, information indicating whether or not an event has been held in the surrounding area, or information indicating the contents of the event to be held.

  Next, a traffic jam accompanying information table will be described. The traffic jam accompanying information table is information representing the change state and scale of the traffic jam represented by the data stored in the traffic jam record tables 700 and 800. FIG. 9 and FIG. 10 are explanatory diagrams (No. 1) and (No. 2) showing a traffic jam accompanying information table. As shown in FIGS. 9 and 10, the traffic jam accompanying information tables 900 and 1000 store the traffic jam link increase rate, the traffic jam link reduction rate, and the traffic jam scale for each date and time.

  Here, the traffic jam link increase rate is information representing the number of traffic jam links per unit time. The traffic jam link reduction rate is information indicating the number of traffic jam links per unit time. The traffic jam scale is information indicating the number of links that are jammed in the traffic jam record table 700.

  The traffic jam incidental information tables 900 and 1000 are associated with the traffic jam history tables 700 and 800, respectively. The date and time in the traffic jam accompanying information tables 900 and 1000 are the same date and time as the date and time in the associated traffic jam record tables 700 and 800.

  Next, the current situation table will be described. FIG. 11 is an explanatory diagram showing a current situation table. Here, the “current situation table” is a data table that stores, for each date and time, the link speed related to the first period until the current time in the links L101 to L112 constituting the monitoring area e1. Hereinafter, in the first embodiment, a period corresponding to the first 20 minutes in the above-described traffic jam record tables 700 and 800 will be described as a second period that does not include the current time.

  As shown in FIG. 11, in the current situation table 1100, the link speed related to the first period in the links L101 to L112 configuring the monitoring area e1 is stored for each date and time. In the first embodiment, the time period from the current time to 20 minutes before is the first period.

  As described above, in the first embodiment, since the link speed is acquired six times per hour, the current status table 1100 includes the “current date time”, the link speed in each of the links L101 to L112. Stored is performance information in which “date and time 10 minutes before the present” and “date and time 20 minutes before the present” are associated with each other.

  Since the current date / time changes every moment, the first period described above changes as the current date / time changes. The current situation table 1100 is updated as appropriate according to changes in the current date and time. Here, FIG. 12 is an explanatory diagram for explaining the concept of creating the current situation table 1100. As shown in FIG. 12, the current status table 1100 includes dates of “current”, “t−1”, and “t−2” among the link speeds of the links L101 to L112 in the link information performance DB 600 described above. The link speed at the time is stored.

  In FIG. 12, the part surrounded by the frame line indicated by reference numeral 1201 is the current current situation table 1100, and the part surrounded by the frame line indicated by reference numeral 1202 is the current situation table 1100 40 minutes before the present.

  Next, a traffic jam accompanying information table associated with the current situation table 1100 will be described. FIG. 13 is an explanatory diagram (part 3) of the traffic jam accompanying information table. As shown in FIG. 13, in the traffic jam incident information table 1300, the traffic jam link increase rate, the traffic jam link decrease rate, and the traffic jam scale are stored for each date and time as in the traffic jam incident information tables 900 and 1000 described above. ing. The date and time in the traffic jam incidental information table 1300 is the same date and time as the date and time in the current situation table 1100 described above. The traffic jam incidental information table 1300 is a data table representing the change state and scale of the traffic jam in the current status table 1100.

  Next, a traffic jam model in the monitoring area e1 will be described. FIGS. 14 to 18 are explanatory diagrams (No. 1) to (No. 5) for explaining a traffic jam model. 14 to 18 show a traffic jam model related to the traffic jam history table 800 shown in FIG. In FIGS. 14 to 18, a link where a traffic jam has occurred is represented by a black circle. FIG. 19 is an explanatory diagram showing a traffic jam record table of traffic jams represented by the models of FIGS.

  According to FIGS. 14 to 18 and FIG. 19, the traffic jam (see FIG. 14) that occurred on the link L110 at the date time t3 expands to the link L109 at the date time t4 (see FIG. 15) and then expands thereafter. At date time t10, it can be seen that traffic congestion has occurred in the eight links L110, L109, L107, L106, L105, L104, L103 and L108 (see FIG. 16). As a result, it can be seen that the vehicle train having the traveling direction from the link L101 side to the link L110 side is congested.

  Thereafter, the traffic congestion gradually disappears from the head side, and the number of links with traffic congestion becomes two links L104 and L103 at the date time t17 (see FIG. 17), and only the link L103 at the date time t18. (See FIG. 18).

(Functional configuration of the traffic situation prediction apparatus 101)
Next, a functional configuration of the traffic condition prediction apparatus 101 according to the first embodiment of the present invention will be described. FIG. 20 is a block diagram showing a functional configuration of the traffic condition prediction apparatus 101 according to the first embodiment of the present invention. In FIG. 20, the traffic situation prediction apparatus 101 includes a storage unit 2001, a detection unit 2002, a specifying unit 2003, an acquisition unit 2004, a calculation unit 2005, and a determination unit 2006.

  The storage unit 2001 stores the various data tables 500, 700, 800, 900, 1000, 1100, 1300 and the database 600 described above. Information transmitted from the client terminal 102 via the network 110 is stored in the storage unit 2001. Specifically, the storage unit 2001 realizes its functions by a recording medium such as the ROM 202, the RAM 203, and the HD 205 shown in FIG.

  The detection unit 2002 detects an arbitrary link among a plurality of links constituting the road network. The detection unit 2002 may detect a single link, or may detect a plurality of links according to the area areas e1, e2, or e3 specified by the specifying unit 2003 described later.

  The identifying unit 2003 identifies one of the areas e1, e2, or e3 among the plurality of monitoring areas e1 to e3. The identifying unit 2003 may identify the monitoring areas e1, e2, or e3 designated through the operation of the administrator of the traffic situation prediction system 100, or may sequentially identify all the monitoring areas e1 to e3. Good. When the monitoring unit e1 is specified by the specifying unit 2003, the acquisition unit 2004 described above acquires the record information of the links L101 to L112 that configure the specified monitoring area e1.

  The identifying unit 2003 may identify any monitoring area e1, e2, or e3 including a link whose link speed is below a predetermined speed threshold in the current situation table 1100. In this case, the acquisition unit 2004 described later can acquire the record information of the areas e1, e2, or e3 where the traffic jam occurs.

  The acquisition unit 2004 includes the track information related to the first period from the track record information that associates the movement speed on the arbitrary link detected by the detector 2002 for each date and time, and the track information that does not include the current time. And record information about the period of 2. Specifically, in the first embodiment, as described above, the time period from the current date time to 20 minutes before is set as the first period, and the time period of any 20 minutes in the past from the current time is set as the second period. Period. The lengths of the first period and the second period are the same.

  In addition, when the area is specified by the specifying unit 2003, the acquiring unit 2004 presents the current congestion based on the traffic congestion link increase rate or the traffic congestion link decreasing rate in the traffic jam incidental information tables 900 and 1000 of the monitoring area e1 specified by the specifying unit 2003. And it is good also as acquiring the past performance information.

  Further, when the area is specified by the specifying unit 2003, the acquiring unit 2004 obtains the link speed in the second period from the record information that associates the link speeds of the links constituting the specified area for each date and time. It is good also as acquiring the performance information which fell below the predetermined speed threshold value. In this case, the acquisition unit 2004 acquires the record information included in the first 20-minute time zone in the above-described traffic jam record tables 700 and 800 as the record information regarding the second period.

  The calculation unit 2005 calculates the degree of similarity between the record information related to the first period acquired by the acquisition unit 2004 and the record information related to the second period. Here, the “similarity” is information indicating the degree of similarity between the state from 20 minutes before to the present in the monitoring area e1 and the state for the first 20 minutes in the traffic jam record tables 700 and 800. The similarity is calculated by calculation using the following equation (1).

  According to the above-described equation (1), the similarity q is the number of dimensions corresponding to the number of links L101 to L112 constituting the monitoring area e1 with the link speed of the links L101 to L112 constituting the monitoring area e1 as an axis. Defined by the Euclidean distance in the space. In the first embodiment, since the number of links L101 to L112 configuring the monitoring area e1 is “112”, the similarity q is defined by the Euclidean distance in the 12-dimensional space.

  According to equation (1), the similarity q can be evaluated as “similarity is higher” as the value is closer to “0”. As a specific example, the similarity between the traffic jam record table 800 shown in FIG. 8 and the current situation table 1100 shown in FIG. 11 is calculated as shown in the following equation (2).

  The determination unit 2006 determines, based on the similarity calculated by the calculation unit 2005, the moving speed in the performance information regarding the third period after the second period has elapsed as the predicted value of the link speed from the current time. . Here, the “predicted value of the link speed” is information indicating the link speed predicted in each link from the current date time to the date time ahead, that is, the future date time. The third period is a predetermined period after the second period has elapsed. The period length of the third period is a period length from the second period to the current time at the maximum.

  In Embodiment 1, the determination part 2006 determines the predicted value of the link speed of each link which comprises the monitoring area e1. As a result, it is possible to determine the predicted value of the link speed for any link after the lapse of a predetermined time from the current date and time without newly installing physical infrastructure equipment, so traffic conditions can be predicted easily and with high accuracy. can do.

  Further, since the determination unit 2006 can determine the predicted value of the link speed in units of the monitoring area e1, it is possible to easily and accurately predict a traffic situation having a high utility value when moving within the monitoring area e1. . Thereby, for example, it is possible to select and move a road with a small amount of traffic in the monitoring area e1 or to avoid moving in the monitoring area e1.

  Further, the determination unit 2006 may determine the performance information regarding the third period after the period having the highest similarity in the second period as the predicted value of the link speed from the current time. As a result, it is possible to determine the predicted value of the link speed at the target link based on the performance information most similar to the current performance information. Can be predicted with accuracy.

  When the above-described specifying unit 2003 specifies any monitoring area e1, e2, or e3 including a link whose link speed is below a predetermined speed threshold in the current situation table 1100, the determining unit 2006 The predicted link speed can be determined in units of monitoring areas e1, e2, or e3 that are expected to occur. Thereby, it is possible to easily and accurately predict a traffic situation having a higher utility value when moving in the monitoring area e1, e2, or e3.

  Further, when the performance information regarding the first and second periods is acquired based on the congestion link increase rate and the congestion link decrease rate in the congestion incidental information tables 900 and 1000 of the monitoring area e1, the determining unit 2006 determines each monitoring The predicted value of the link speed can be determined in consideration of the traffic jam pattern expected to occur in the areas e1 to e2, so that the traffic situation with higher utility value can be easily and highly enhanced when moving within the area. Can be predicted with accuracy.

  Moreover, when the performance information included in the first 20-minute time zone of the traffic jam record tables 700 and 800 is acquired as the past track record information, taking into account the traffic jams that occurred in each of the monitoring areas e1 to e2, Since the predicted value of the link speed can be determined, it is possible to easily and highly accurately predict a traffic situation having a higher utility value when moving within the monitoring areas e1 to e2.

(Processing procedure of the traffic situation prediction apparatus 101)
Next, a processing procedure of the traffic situation prediction apparatus 101 will be described. The traffic situation prediction apparatus 101 periodically performs a traffic jam record table creation process (see FIG. 21) and a traffic situation prediction process (see FIG. 22) at arbitrary timings.

(Congestion result table creation processing procedure)
Next, a traffic jam record table creation processing procedure of the traffic condition prediction apparatus 101 according to the first embodiment of the present invention will be described. The traffic jam record table creation process is periodically performed, and is performed for each monitoring area e1 when there is corresponding record information. FIG. 21 is a flowchart showing the traffic jam record table creation processing procedure of the traffic condition prediction apparatus 101 according to the first embodiment of the present invention. In the flowchart of FIG. 21, first, the monitoring areas e1, e2, or e3 that are targets for creation of the traffic jam record table are specified (step S2101).

  Subsequently, the link speed of the link constituting the monitoring area e1, e2, or e3 specified in step S2101 is extracted from the link speeds stored in the link information result DB 600 (step S2102), and the extracted link Based on the speed, a traffic jam record table is created (step S2103), and a series of processing ends.

(Traffic situation prediction processing procedure)
Next, the traffic situation prediction processing procedure of the traffic situation prediction apparatus 101 according to the first embodiment of the present invention will be described. The traffic situation prediction process is performed for each monitoring area e1. FIG. 22 is a flowchart showing the traffic situation prediction processing procedure of the traffic situation prediction apparatus 101 according to the first embodiment of the present invention. In the flowchart of FIG. 22, first, the monitoring areas e1, e2, or e3 that are targets for traffic condition prediction are specified (step S2201). In the first embodiment, a case where the monitoring area e1 is specified will be described below.

  Subsequently, based on the link speed stored in the link information result DB 600, the current status table 1100 of the monitoring area e1 is created (step S2202), and the congestion result tables 700 and 800 of the monitoring area e1 are acquired (step S2203). ).

  Subsequently, using the current situation table 1100 created in step S2202 and the traffic jam record tables 700 and 800 acquired in step S2203, the degree of similarity between the current situation table 1100 and the traffic jam record tables 700 and 800 is calculated ( Step S2204).

  Based on the similarity calculated in step S2204, the traffic jam record table 700 or 800 that most closely resembles the current state in the monitoring area e1 is specified (step S2205). Thereafter, based on the identified traffic jam record table 700 or 800, a predicted value of the link speed of each of the links L101 to L112 in the monitoring area e1 is determined (step S2206), and the series of processes is terminated.

  Next, the relationship between the link information performance DB 600 and the data tables 700, 800, and 1100 in the traffic situation prediction process described above will be described. FIG. 23 is an explanatory diagram for explaining the relationship between the link information performance DB 600 and the data tables 700, 800, and 1100 in the traffic situation prediction process. As shown in FIG. 23, the current situation table 1100 and the traffic jam record table (see FIGS. 7 and 8) are created based on the link information record DB 600.

  In the traffic situation prediction process, the traffic jam record table group 2320 of the monitor area e1 is narrowed down from the traffic jam record table group 2310 created for all the monitor areas e1 to e3, and monitoring is performed based on the above-described similarity. A traffic jam record table that most closely resembles the current state is identified from the traffic jam record table group 2320 in the area e1. Then, the predicted value of the link speed is determined using the traffic jam record table 2330 that most closely resembles the identified current state.

  Next, the calculation of similarity in step S2204 of the traffic situation prediction process described above will be described in detail. 24 and 25 are explanatory diagrams (part 1) and (part 2) for explaining the calculation of the similarity. When calculating the similarity, first, the current situation table 1100 is referred to, and a congestion actual result table of the traffic jam generated from the same link as the link of the traffic jam that occurred at the current date and time is extracted. .

  Reference numeral 2410 in FIG. 24 indicates a traffic jam incidental information table group associated with the traffic jam actual result table of the traffic jam generated from the same link as the link of the traffic jam generated at the current date and time. In calculating the similarity, each traffic congestion information table in the traffic congestion incident information table group 2410 is compared with the traffic congestion incident information table 1300. At this time, in each traffic jam information table, three traffic jam information in order from the oldest date and time is compared with the traffic jam information in the traffic jam information table 1300.

  Based on the comparison result, the traffic congestion incident information table 1300 having the traffic congestion incident information close to the traffic congestion incident information table group 2410 is extracted. When extracting the traffic jam incident information table 1300, a traffic jam incident information table in which each of the traffic jam link increase rate, the traffic jam link decrease rate, and the traffic jam size is within a predetermined threshold range is used as the traffic jam incident information table. Extract. Furthermore, a traffic jam record information table associated with the extracted traffic jam incidental information table 1300 is extracted.

  Subsequently, the degree of similarity between the extracted traffic record information table and the current situation table 1100 is compared, and the most similar traffic record table is specified. When comparing the similarities, an operation using the above-described equation (1) is performed using the extracted traffic jam record information table and the current situation table 1100, and the date and time in each of the jammed traffic record information tables 1000 extracted is old. The degree of similarity between the performance information for three items and the performance information in the current situation table 1100 is calculated.

  Then, the traffic jam record table having the calculated similarity value closest to “0” is specified as the traffic jam record table that is most similar. Hereinafter, the achievement No. The description will be made assuming that the Jm traffic jam record table 1000 is extracted as the most similar traffic jam record table.

  Next, the determination of the predicted value of the link speed in step S2206 of the traffic situation prediction process described above will be described in detail. FIG. 26 is an explanatory diagram for explaining the determination of the predicted value of the link speed. When determining the predicted value of the link speed, the current date and time in the current situation table 1100 is used as the result No. The link speed after date time tm4, which is the link speed within the range represented by the frame line 2610 in the traffic jam record table 1000, is applied to the date and time of tm3 in the jam jam record table 1000 of Jm, and the link of each link in the monitoring area e1. Determined as the predicted speed.

  In the example shown in FIG. 26, for example, the predicted value of the link speed after T time from the current date time is the time difference with respect to the date time tm3 among the times after the date time tm4 in the traffic jam record table 1000 is T. The link speed at the near date and time. If the date time having the closest time difference to the date time tm3 is Tm10, the predicted link speed of the links L102 and L107 after the T time from the current date time is the link after the T time from the date time tm3. The link speeds of L102 and L107 are determined as “v102.m10” and “v107.m10”.

  As described above, according to the first embodiment, it is possible to determine the predicted value of the link speed in an arbitrary link after the elapse of a predetermined time from the current date and time without newly providing a physical infrastructure facility. Can predict traffic conditions easily and with high accuracy.

  Further, according to the first embodiment, the traffic situation is monitored by determining, for each monitoring area e1 to e3, the predicted value of the link speed in the links constituting the monitoring links e1 to e3 where occurrence of traffic congestion is assumed. The prediction can be made in units of areas e1 to e3. As a result, it is possible to easily and accurately predict a traffic situation having a high utility value when moving within each of the monitoring areas e1 to e3.

(Embodiment 2)
Next, a second preferred embodiment of a traffic situation prediction program, a recording medium recording the program, a traffic situation prediction apparatus, and a traffic situation prediction method according to the present invention will be described in detail with reference to the accompanying drawings. In the second embodiment, a traffic situation prediction system that determines a predicted value of a link speed in a single link will be described.

  In addition, since the traffic condition prediction apparatus in Embodiment 2 can be implemented using the same resources as in Embodiment 1 described above, the resources that can be implemented using the same resources as in Embodiment 1 are as follows: The illustration and the explanation thereof are omitted, and the same reference numerals are used for explanation.

(Link relationship)
First, a description will be given of the relationship of links that are targets for determining the predicted value of the link speed in the second embodiment. FIG. 27 is an explanatory diagram for explaining a relationship of links that are targets for determining a predicted value of the link speed. FIG. 27 shows the relationship between links L0 to L15 that constitute an arbitrary area on the map. Hereinafter, in the second embodiment, a case will be described as an example in which the link L0 is the target for determining the predicted value of the link speed among all the links L0 to Ln constituting the road network.

(Functional configuration of traffic condition prediction device)
Next, a functional configuration of the traffic condition prediction apparatus according to the second embodiment of the present invention will be described. Since the traffic situation prediction apparatus according to the second embodiment has the same functional configuration as the functional configuration shown in FIG. 20 in the first embodiment described above, it is limited here to different functions. I will explain. In the traffic situation prediction apparatus 101 according to the second embodiment, the functions of the specifying unit 2003 and the acquiring unit 2004 are different from the functions of the specifying unit 2003 and the acquiring unit 2004 of the first embodiment described above.

  The specifying unit 2003 in the second embodiment specifies one link from among a plurality of links constituting the road network. The identification unit 2003 may identify a link of an arbitrary link designated by the administrator of the traffic situation prediction system 100, or may sequentially identify all the links constituting the road network.

  The acquisition unit 2004 according to the second embodiment is configured from the track record information that associates the moving speed of one link specified by the specifying unit 2003 and a link having a predetermined correlation with the one link for each date and time. The performance information regarding the first and second periods is acquired. The second period in the second embodiment is an arbitrary period among all the past periods that do not include the current time among the periods having the record information.

  Specifically, the acquisition unit 2004 associates, for each date and time, the moving speed of the correlation link in which the correlation coefficient established between the link speed of one link specified by the specifying unit 2003 is within a predetermined range. The result information regarding the first and second periods is acquired from the information.

  Thereby, in Embodiment 2, the predicted value of the link speed in one link is determined using the past link information having a clear correlation with one link based on the existing correlation coefficient. Therefore, it is possible to easily and accurately predict a traffic situation having a high utility value when moving one link.

(Traffic situation prediction processing procedure)
Next, the traffic situation prediction processing procedure of the traffic situation prediction apparatus 101 according to the second embodiment of the present invention will be described. The traffic situation prediction process is performed when a link for which a predicted value of the link speed is determined is specified. FIG. 28 is a flowchart showing the traffic situation prediction processing procedure of the traffic situation prediction apparatus 101 according to the second embodiment of the present invention.

  In the flowchart of FIG. 28, first, until the link (here, link L0) for which the predicted value of the link speed is determined is specified (step S2801: No), if specified (step S2801: Yes). In step S2802, the correlation link of the link L0 is specified. Here, it is assumed that the links L2, L4, L9, and L13 are correlation links.

  Subsequently, based on the link speeds of the link L0 and the correlation links L2, L4, L9, and L13, a near-current record table is created (step S2803) and a target record table is created (step S2804). Here, the near-current performance table is a data table that stores the link speeds of the link L0 and the correlation links L2, L4, L9, and L13 for the first period until the current time for each date and time (see FIG. 32). ). The target performance table is a data table that stores the link speed of the link L0 and the correlation link for the second period not including the current time for each date and time (see FIG. 33).

  Subsequently, the similarity is calculated based on the created near-current table and target result table (step S2805). In step S2805, the similarity between the performance information regarding the first period and the performance information regarding the second period is calculated for each date and time using the equation (1) described in the first embodiment.

  Subsequently, based on the similarity calculated in step S2805, the performance information most similar to the performance information related to the first period is specified from the performance information related to the second period (step S2806), and the specified performance is determined. Based on the information, a predicted value of the link speed of the link L0 is determined (step S2807), and the series of processing ends.

  Next, the correlation link specifying method in step S2802 of the traffic situation prediction process described above will be described in detail. FIG. 29 is an explanatory diagram illustrating a correlation link specifying method. As shown in FIG. 29, the correlation with respect to the link L0 indicates that the link speed of the link L0 and the link speeds of all the links L1 to Ln except the link L0 are the same based on the link information performance DB 600. A correlation coefficient at each time is calculated, and a determination is made based on the calculated correlation coefficient.

  In the above equation (3), X is the average value of the variable x, and Y is the average value of the variable y. In equation (3), x is the link speed of the link L0 at a certain date and time, and y is the link speed of links L1 to Ln other than L0 at the same date and time. The correlation coefficient calculated by the above-described equation (3) can determine the strength of the correlation by setting in advance an absolute value serving as a reference for interpreting the calculated correlation coefficient. it can.

  Table 1 shows the relationship between the absolute value of the correlation coefficient and its interpretation. In Table 1, the calculated correlation coefficients are classified into four stages. When the calculated correlation coefficient is included in the range of “0.0 to 0.2”, there is “almost no correlation between the link speed of the target link L100 and the link speeds of the actual peripheral links L101 to L112. Can be interpreted. When the calculated correlation coefficient is included in the range of “0.2 to 0.4”, the link speed between the target link L100 and the link speeds of the actual peripheral links L101 to L112 is “slightly correlated. Can be interpreted.

  Further, when the calculated correlation coefficient is included in the range of “0.4 to 0.7”, the link speed between the target link L100 and the link speeds of the actual peripheral links L101 to L112 is “significantly correlated. Can be interpreted. When the calculated correlation coefficient is included in the range of “0.7 to 1.0”, a “strong correlation” exists between the link speed of the target link L100 and the link speeds of the actual peripheral links L101 to L112. Can be interpreted.

  The strength of the correlation is determined based on the number of times interpreted as “having a strong correlation”. In the second embodiment, a link whose number of times interpreted as “having a strong correlation” is a predetermined number or more is selected as a correlation link. Note that a predetermined number of links may be selected as correlation links in descending order of the number of times interpreted as “having a strong correlation”.

  Here, the explanation of the correlation link will be supplemented. FIG. 30 is an explanatory diagram showing a correlation link table, and FIG. 31 is an explanatory diagram showing the relationship between the link L0 that is a link speed calculation target and the correlation link of the link L0. The link correlation table is a data table that represents a correlation link that has a strong correlation with the link L0 that is the target of calculating the traffic situation prediction value. As shown in FIG. 30, the correlation link table 3000 stores links L2, L4, L9, and L13 that are correlation links of the link L0. In the second embodiment, the link L0 and the correlation link of the link L0 have the relationship shown in FIG.

  The link correlation table 3000 may be appropriately created every time the traffic situation prediction value is calculated. Alternatively, the link correlation table 3000 may be created in advance for each link and stored in the database 103. In this case, a plurality of link correlation tables 3000 are stored in the database 103 according to the moving direction of the link for which the traffic situation prediction value is calculated.

  Next, the near-current record table and the target record table created in step S2803 and step S2804 of the traffic situation prediction process described above will be described. FIG. 32 is an explanatory diagram of a near-current record table. As shown in FIG. 32, in the near-current record table 3200, the link speeds of the link L0 and the correlation links L2, L4, L9, and L13 in a predetermined time range including the current date and time are stored for each date and time. Yes. FIG. 33 is an explanatory diagram of a target performance table. As illustrated in FIG. 33, the target performance table 3300 stores the link speed of the link L0 and the link speeds of the correlation links L2, L4, L9, and L13 of the link L0 for each date and time.

  The similarity between the performance information regarding the first period represented by the near-current performance table 3200 and the performance information regarding the second period represented by the frame line 3310 in the target performance table 3300 is expressed by the following expressions (4) to (4): It is calculated as in equation (6).

  In step S2806, the record information corresponding to the predetermined time range in which all the calculated similarities are within the very similar threshold range is specified as the record information related to the second period that is most similar to the record information related to the first period. . Here, the “severely similar threshold range” is a threshold used for specifying the record information. The very similar threshold range is arbitrarily set by the administrator of the traffic situation prediction system 100 according to the required prediction accuracy.

  Here, a supplementary explanation is given regarding the identification of the record information based on the similarity. FIGS. 34 and 35 are explanatory diagrams (No. 1) and (No. 2) showing a change state of the link speed of the link L0 to be determined for the link speed and the correlation links L2, L4, L9, and L13 of the link L0. is there. FIG. 34 and FIG. 35 are graphs showing the change state of the link speed with the passage of time represented on the horizontal axis. 34 and 35, reference numeral 3400 represents the current date and time.

  The graph in the area surrounded by the frame line 3410 in FIG. 34 shows the current link speed change state. When specifying the record information, the area 3410 is slid in the past direction, and a date / time range similar to the recent change state is searched from the past change state of the link speed. The search is not limited to the one that completely matches the current change state. Of the graphs representing past changes in the link speeds of the link L0 and the peripheral links L2, L4, L9, and L13, a portion having the highest ratio overlapping with the shape of the graph in the region 3410 is used as the most similar performance information. Identify.

  Note that the identification of the performance information is not limited to that performed based on the link speed. For example, it may be performed based on a speed difference with respect to the immediately preceding link speed (hereinafter referred to as “link speed difference”). FIG. 36 and FIG. 37 are explanatory diagrams (No. 1) and (No. 2) showing a change state of the link speed difference between the link L0 to be a link speed prediction target and the correlation links L2, L4, L9, and L13 of the link L0. It is. FIG. 36 and FIG. 37 are graphs showing the change state of the link speed difference with the passage of time represented on the horizontal axis.

  Even when the performance information is specified based on the link speed difference, similarly to the case of the link speed described above, the area 3510 is slid in the past direction, and the first period is selected from the past change states of the link speed difference. A period similar to the change state of the record information is searched, and the record information in the portion having the highest ratio overlapping with the shape of the graph in the region 3610 is set as record information related to the second period. In FIG. 37, the time range from the date time tj (j-5) to the date time tj (j) represents the second period similar to the change state of the performance information regarding the first period.

  Next, determination of the predicted link speed value in step S2807 of the traffic situation prediction process described above will be described. FIG. 38 is an explanatory diagram illustrating determination of a predicted link speed value. A reference numeral 3800 in FIG. 38 indicates a target performance table including the identified performance information. In determining the traffic situation predicted value, the current date and time in the near-current record table 3200 is applied to the start position of the target record table 3800, and the link speed after the date and time is determined as the link speed predicted value of the link L0. To do.

  In the example shown in FIG. 38, for example, when the performance information at the date time tj (j) to tj (j-5) is specified in step S2806, the traffic situation predicted value after T hours from the current date time is Among the times after the date time tj (j + 1) in the target performance table 3800, the link speed at the date time with the closest time difference to the date time tj (j) is T.

  If the date time closest to the time T with respect to the date time tj (j) is tj (j + 6), the predicted value of the link speed after the time T from the current date time of the link L0 is from tj (j + 1). It is determined as “v0.i + 6” which is the link speed of each link after T time.

  As described above, according to the second embodiment, since the link L0 and the correlated links L2, L4, L9, and L13 are used as one unit, the predicted value of the link speed can be determined for each unit. It is possible to easily and accurately predict a traffic situation having a high utility value during the movement of L0.

  As described above, according to the traffic situation prediction program, the recording medium on which the program is recorded, the traffic situation prediction apparatus, and the traffic situation prediction method according to the present invention, current physical infrastructure facilities can be provided without newly providing them. Since it is possible to calculate a predicted value of the moving speed on an arbitrary link after a predetermined time has elapsed from the date and time, it is possible to easily and accurately predict the traffic situation.

(Additional remark 1) The detection process which detects arbitrary links from the some links which comprise a road network,
Among the track record information that associates the moving speed in any link detected by the detection step for each date and time, track record information related to the first period up to the current time, and the second period that does not include the current time An acquisition process for acquiring achievement information;
A calculation step of calculating the degree of similarity between the result information related to the first period acquired by the acquisition step and the result information related to the second period;
A determining step of determining, based on the similarity calculated by the calculating step, a moving speed in the performance information related to the third period after the second period has elapsed as a predicted value of the moving speed from the current time; ,
A traffic condition prediction program for causing a computer to execute.

(Additional remark 2) Let the said computer perform the specific process which specifies the area containing the said arbitrary links from the area comprised by the one part link of these links,
The acquisition step includes
The supplementary note 1 is characterized in that the record information related to the first and second periods is acquired from the record information that associates the moving speeds in the links that constitute the area specified by the specifying step for each date and time. The traffic situation prediction program described.

(Supplementary note 3)
The traffic condition prediction program according to appendix 2, wherein an area including a link whose moving speed in the first period falls below a predetermined speed threshold is specified.

(Supplementary Note 4) The acquisition step includes:
The traffic condition prediction according to appendix 3, characterized in that actual information on the first and second periods is acquired based on the number of increases / decreases per unit time of a link that has fallen below the predetermined speed threshold in the area. program.

(Supplementary Note 5) The acquisition step includes:
4. The traffic condition prediction program according to appendix 3, wherein performance information relating to the first and second periods is acquired based on the number of links per unit time that have fallen below the predetermined speed threshold in the area. .

(Appendix 6)
The additional information is characterized in that, from the performance information that associates the movement speeds in the links constituting the area for each date and time, the performance information in which the movement speed in the second period falls below a predetermined speed threshold is acquired. The traffic condition prediction program according to any one of 3 to 5.

(Additional remark 7) Let the said computer perform the specific process which specifies one link among these links,
The acquisition step includes
The track record information related to the first and second periods from the track record information that associates the one link specified in the specifying step and the moving speed of the link having a predetermined correlation with the one link for each date and time. The traffic condition prediction program according to supplementary note 1, characterized in that

(Appendix 8) The acquisition step
The first and second periods are related to the first period and the second period from among the performance information associating the moving speed of the correlated link with the link speed of the one link within a predetermined range for each date and time. The traffic condition prediction program according to appendix 7, characterized in that results information is acquired.

(Supplementary Note 9) The calculation step includes
By using the Euclidean distance between the performance information regarding the first period and the performance information regarding the second period in the Euclidean space having the same number of dimensions as the number of links acquired by the acquisition step, the first period The traffic condition prediction program according to any one of appendices 1 to 8, wherein the similarity between the performance information related to the performance information and the performance information related to the second period is calculated.

(Supplementary Note 10)
Note that the moving speed in the performance information related to the third period after the elapse of the period with the highest similarity in the second period is determined as a predicted value of the moving speed from the current time. The traffic condition prediction program according to any one of 1 to 9.

(Supplementary note 11)
11. The traffic situation prediction program according to appendix 10, wherein the moving speed from the date and time when the second period is completed is determined as a predicted value of the moving speed from the current time.

(Supplementary note 12) A computer-readable recording medium in which the traffic situation prediction program according to any one of Supplementary notes 1 to 11 is recorded.

(Supplementary note 13) Detection means for detecting an arbitrary link from among a plurality of links constituting the road network;
The track record information related to the first period up to the current time from the track record information associated with the moving speed in any link detected by the detection means for each date and time, and the same length as the first period Acquisition means for acquiring the record information relating to the second period not including the current time;
Calculating means for calculating the degree of similarity between the result information relating to the first period acquired by the acquisition means and the result information relating to the second period;
A determination unit that determines, based on the similarity calculated by the calculation unit, the performance information in the third period after the second period has elapsed, as a predicted value of the moving speed from the current time;
A traffic condition prediction apparatus comprising:

(Additional remark 14) The detection process which detects arbitrary links from the some links which comprise a road network,
The track record information related to the first period up to the current time from the track record information associated with the movement speed at any link detected by the detection step for each date and time, and the length of the track record is the same as the first period. An acquisition process for acquiring the performance information regarding the second period not including the current time;
A calculation step of calculating the similarity between the result information related to the first period acquired by the acquisition step and the result information related to the second period;
A determination step of determining, based on the similarity calculated by the calculation step, the performance information in the third period after the elapse of the second period as a predicted value of the moving speed from the current time;
The traffic condition prediction method characterized by including.

  As described above, the traffic situation prediction program, the recording medium storing the program, the traffic situation prediction apparatus, and the traffic situation prediction method according to the present invention are useful for predicting the traffic situation.

It is a system configuration figure of the traffic situation prediction system concerning Embodiment 1 of this invention. It is a block diagram which shows the hardware constitutions of the computer apparatus shown in FIG. It is explanatory drawing explaining a monitoring area. It is explanatory drawing (the 1) explaining the structure of a link. It is explanatory drawing which shows the monitoring area table. It is explanatory drawing which shows a link information performance database. It is explanatory drawing (the 1) which shows a traffic congestion performance table. It is explanatory drawing (the 2) which shows a traffic congestion performance table. It is explanatory drawing (the 1) which shows a traffic congestion attendant information table. It is explanatory drawing (the 2) which shows a traffic congestion attendant information table. It is explanatory drawing which shows a present condition table. It is explanatory drawing explaining the creation concept of a present condition table. It is explanatory drawing (the 3) which shows a traffic congestion attendant information table. It is explanatory drawing (the 1) explaining the model of a traffic jam. It is explanatory drawing (the 2) explaining the model of a traffic jam. It is explanatory drawing (the 3) explaining the model of a traffic jam. It is explanatory drawing (the 4) explaining the model of a traffic jam. It is explanatory drawing (the 5) explaining the model of a traffic jam. FIG. 19 is an explanatory diagram showing a traffic jam record table of traffic jams represented by the models of FIGS. 14 to 18. It is a block diagram which shows the functional structure of the traffic condition prediction apparatus concerning Embodiment 1 of this invention. It is a flowchart which shows the traffic jam record table preparation process procedure of the traffic condition prediction apparatus concerning Embodiment 1 of this invention. It is a flowchart which shows the traffic condition prediction process sequence of the traffic condition prediction apparatus concerning Embodiment 1 of this invention. It is explanatory drawing explaining the relationship between link information performance DB and each data table in a traffic condition prediction process. It is explanatory drawing (the 1) explaining calculation of a similarity. It is explanatory drawing (the 2) explaining calculation of a similarity. It is explanatory drawing explaining determination of the predicted value of link speed. It is explanatory drawing explaining the relationship of the link used as the decision object of the predicted value of link speed. It is a flowchart which shows the traffic condition prediction process sequence of the traffic condition prediction apparatus concerning Embodiment 2 of this invention. It is explanatory drawing explaining the identification method of a correlation link. It is explanatory drawing which shows a correlation link table. It is explanatory drawing which shows the relationship between the link used as the decision object of link speed, and the correlation link of the said link. It is explanatory drawing which shows a near present result table. It is explanatory drawing which shows a subject performance table. It is explanatory drawing (the 1) which shows the change state of the link speed of the link used as the decision object of a link speed, and the correlation link of the said link. It is explanatory drawing (the 2) which shows the change state of the link speed of the link used as the decision object of a link speed, and the correlation link of the said link. It is explanatory drawing (the 1) which shows the change state of the link speed difference of the link used as the decision object of a link speed, and the correlation link of the said link. It is explanatory drawing (the 2) which shows the change state of the link speed difference of the link used as the decision object of a link speed, and the correlation link of the said link. It is explanatory drawing explaining determination of the predicted value of link speed.

Explanation of symbols

DESCRIPTION OF SYMBOLS 101 Traffic condition prediction apparatus 2002 Detection part 2003 Specification part 2004 Acquisition part 2005 Calculation part 2006 Determination part

Claims (5)

A detection step of detecting an arbitrary link from a plurality of links constituting the road network;
Among the track record information that associates the moving speed in any link detected by the detection step for each date and time, track record information related to the first period up to the current time, and the second period that does not include the current time An acquisition process for acquiring achievement information;
A calculation step of calculating the degree of similarity between the result information related to the first period acquired by the acquisition step and the result information related to the second period;
A determining step of determining, based on the similarity calculated by the calculating step, a moving speed in the performance information related to the third period after the second period has elapsed as a predicted value of the moving speed from the current time; ,
A traffic condition prediction program for causing a computer to execute. Causing the computer to execute a specific step of specifying an area including the arbitrary link from an area constituted by some links of the plurality of links;
The acquisition step includes
2. The record information related to the first and second periods is acquired from record information in which movement speeds in links constituting the area specified in the specifying step are associated for each date and time. The traffic situation prediction program described in 1.   A computer-readable recording medium in which the traffic situation prediction program according to claim 1 is recorded. Detecting means for detecting an arbitrary link from a plurality of links constituting the road network;
The track record information related to the first period up to the current time from the track record information associated with the moving speed in any link detected by the detection means for each date and time, and the same length as the first period Acquisition means for acquiring the record information relating to the second period not including the current time;
Calculating means for calculating the degree of similarity between the result information relating to the first period acquired by the acquisition means and the result information relating to the second period;
Determining means for determining, based on the similarity calculated by the calculating means, the moving speed in the performance information in the third period after the second period has elapsed as a predicted value of the moving speed from the current time; ,
A traffic condition prediction apparatus comprising: A detection step of detecting an arbitrary link from a plurality of links constituting the road network;
The track record information related to the first period up to the current time from the track record information associated with the movement speed at any link detected by the detection step for each date and time, and the length of the track record is the same as the first period. An acquisition process for acquiring the performance information regarding the second period not including the current time;
A calculation step of calculating the similarity between the result information related to the first period acquired by the acquisition step and the result information related to the second period;
A determining step of determining, based on the similarity calculated by the calculating step, a moving speed in the performance information in a third period after the second period has elapsed as a predicted value of the moving speed from the current time; ,
The traffic condition prediction method characterized by including.

Images