Aggregation of traffic impact metrics

• US 10,055,504 B2
• Filed: 04/09/2015
• Issued: 08/21/2018
• Est. Priority Date: 04/09/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Joseph, Alex J., Nair, Raghunath E., Shivaprasad, Panibhushan
• Primary Examiner(s): Moser, Bruce M
• Application Number:
  US14/682,278
• Publication Number:
  US 20160300140A1
• Time in Patent Office: 1,230 Days
• Field of Search: None
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data

Abstract

Aggregation of traffic impact metrics is provided. Each of a plurality of holidays is associated with a holiday category of a plurality of holiday categories. The plurality of holiday categories includes a first holiday category and a second holiday category. A plurality of points of interest along a link of a transportation network is identified. At least one of the plurality of points of interest is associated with the first holiday category and at least one of the plurality of points of interest with the second holiday category. A mean category impact for each of the plurality of holiday categories is determined. An aggregated traffic impact metric is determined based, at least in part, on the mean category impact of each of the plurality of holiday categories.

Claims

1. A method for generating a graphical user interface display based on aggregation of traffic impact metrics, the method comprising:

generating, by one or more processors, a first plurality of database entries in which each of a plurality of holidays are respectively associated with a holiday category of a plurality of holiday categories, wherein the plurality of holiday categories includes a first holiday category and a second holiday category;

identifying, by one or more processors, a plurality of physical points of interest along a physical link of a transportation network;

generating, by one or more processors, a second plurality of database entries in which (i) at least one of the plurality of physical points of interest is associated with the first holiday category and (ii) at least one of the plurality of physical points of interest is associated with the second holiday category;

determining, by one or more processors, a mean category impact for each of the plurality of holiday categories;

determining, by one or more processors, an aggregated traffic impact metric based, at least in part, on the mean category impact of each of the plurality of holiday categories, wherein the aggregated traffic impact metric corresponds to a date on which a holiday of the first holiday category occurs and on which a holiday of the second holiday category occurs, and wherein the aggregated traffic impact metric is a sum of;

(i) a mean weekday volume of the date; and

(ii) the mean category impact for each of the plurality of holiday categories, wherein each mean category impact is weighted based, at least in part, on the mean category impact of each other holiday category; and

generating, by one or more processors, a graphical user interface display on a computing device, wherein the graphical user interface display includes a traffic prediction for the physical link of the transportation network based, at least in part, on one or more effects that the aggregated traffic impact metric has on (i) a traffic volume on the physical link of the transportation network and (ii) a traffic speed on the physical link of the transportation network, wherein each of the one or more effects are one or both of (i) positively correlated with the traffic volume on the physical link and (ii) negatively correlated with traffic speed on the physical link.

2. The method of claim 1, further comprising:

determining, by one or more processors, a mean weekday volume for each day of a week, wherein the mean weekday volume for each day of the week is based, at least in part, on historic traffic data for one or more previous days corresponding to the day of the week.

3. The method of claim 2, wherein the aggregated traffic impact metric is a function of:

(i) the mean category impact for each of the plurality of holiday categories;

(ii) a number of points of interest located along the link and associated with each of the plurality of holiday categories; and

(iii) a total number of points of interest along the link.

4. The method of claim 3, wherein the mean category impact for each of the plurality of holiday categories is weighted based on a ratio of the number of points of interest along a link that are associated with the holiday category to the total number of points of interest along the link.

5. The method of claim 2, wherein the mean category impact for each of the plurality of holiday categories is based on a traffic impact for each holiday of the holiday category.

6. The method of claim 5, wherein the traffic impact for each holiday is based on historical traffic data of one or more previous occurrences of the holiday and a mean weekday volume for a day of a week of each of the one or more previous occurrences.

7. The method of claim 1, the method further comprising:

determining, by one or more processors, an aggregated traffic impact metric for a given date based on a mean weekday volume and the mean category impact of each holiday category, wherein the mean category impact of each holiday category is weighted proportionally to the mean category impact of each other holiday category.

8. The method of claim 1, the method further comprising:

determining, by one or more processors, an aggregated traffic impact metric for the physical link of the transportation network, wherein the mean category impact of each of a plurality of holiday categories is weighted based on a ratio of (i) a number of points of interest along the link that belong to the holiday category to (ii) the total number of points of interest along the physical link.

9. A computer program product for generating a graphical user interface display based on aggregation of traffic impact metrics, the computer program product comprising:

a computer readable storage medium and program instructions stored on the computer readable storage medium, the program instructions comprising;

program instructions to generate a first plurality of database entries in which each of a plurality of holidays are respectively associated with a holiday category of a plurality of holiday categories, wherein the plurality of holiday categories includes a first holiday category and a second holiday category;

program instructions to identify a plurality of physical points of interest along a physical link of a transportation network;

program instructions to generate a second plurality of database entries in which (i) at least one of the plurality of physical points of interest is associated with the first holiday category and (ii) at least one of the plurality of physical points of interest is associated with the second holiday category;

program instructions to determine a mean category impact for each of the plurality of holiday categories;

program instructions to determine an aggregated traffic impact metric based, at least in part, on the mean category impact of each of the plurality of holiday categories, wherein the aggregated traffic impact metric corresponds to a date on which a holiday of the first holiday category occurs and on which a holiday of the second holiday category occurs, and wherein the aggregated traffic impact metric is a sum of;

(i) a mean weekday volume of the date; and

(ii) the mean category impact for each of the plurality of holiday categories, wherein each mean category impact is weighted based, at least in part, on the mean category impact of each other holiday category; and

program instructions to generate a graphical user interface display on a computing device, wherein the graphical user interface display includes a traffic prediction for the physical link of the transportation network based, at least in part, on one or more effects that the aggregated traffic impact metric has on (i) a traffic volume on the physical link of the transportation network and (ii) a traffic speed on the physical link of the transportation network, wherein each of the one or more effects are one or both of (i) positively correlated with the traffic volume on the physical link and (ii) negatively correlated with traffic speed on the physical link.

10. The computer program product of claim 9, wherein the program instructions further comprise:

program instructions to determine a mean weekday volume for each day of a week, wherein the mean weekday volume for each day of the week is based, at least in part, on historic traffic data for one or more previous days corresponding to the day of the week.

11. The computer program product of claim 10, wherein the aggregated traffic impact metric is a function of:

(i) the mean category impact for each of the plurality of holiday categories;

(ii) a number of points of interest located along the link and associated with each of the plurality of holiday categories; and

(iii) a total number of points of interest along the link.

12. The computer program product of claim 11, wherein the mean category impact for each of the plurality of holiday categories is weighted based on a ratio of the number of points of interest along a link that are associated with the holiday category to the total number of points of interest along the link.

13. The computer program product of claim 10, wherein the mean category impact for each of the plurality of holiday categories is based on a traffic impact for each holiday of the holiday category.

14. The computer program product of claim 13, wherein the traffic impact for each holiday is based on historical traffic data of one or more previous occurrences of the holiday and a mean weekday volume for a day of a week of each of the one or more previous occurrences.

15. A computer system for aggregation of traffic impact metrics, the computer system comprising:

one or more computer processors;

one or more computer readable storage media;

program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to generate a first plurality of database entries in which each of a plurality of holidays are respectively associated with a holiday category of a plurality of holiday categories, wherein the plurality of holiday categories includes a first holiday category and a second holiday category;

program instructions to identify a plurality of physical points of interest along a physical link of a transportation network;

program instructions to generate a second plurality of database entries in which (i) at least one of the plurality of physical points of interest is associated with the first holiday category and (ii) at least one of the plurality of physical points of interest is associated with the second holiday category;

program instructions to determine a mean category impact for each of the plurality of holiday categories;

program instructions to determine an aggregated traffic impact metric based, at least in part, on the mean category impact of each of the plurality of holiday categories, wherein the aggregated traffic impact metric corresponds to a date on which a holiday of the first holiday category occurs and on which a holiday of the second holiday category occurs, and wherein the aggregated traffic impact metric is a sum of;

(i) a mean weekday volume of the date; and

(ii) the mean category impact for each of the plurality of holiday categories, wherein each mean category impact is weighted based, at least in part, on the mean category impact of each other holiday category; and

program instructions to generate a graphical user interface display on a computing device, wherein the graphical user interface display includes a traffic prediction for the physical link of the transportation network based, at least in part, on one or more effects that the aggregated traffic impact metric has on (i) a traffic volume on the physical link of the transportation network and (ii) a traffic speed on the physical link of the transportation network, wherein each of the one or more effects are one or both of (i) positively correlated with the traffic volume on the physical link and (ii) negatively correlated with traffic speed on the physical link.

16. The computer system of claim 15, wherein the program instructions further comprise:

program instructions to determine a mean weekday volume for each day of a week, wherein the mean weekday volume for each day of the week is based, at least in part, on historic traffic data for one or more previous days corresponding to the day of the week.

17. The computer system of claim 16, wherein the aggregated traffic impact metric is a function of:

(i) the mean category impact for each of the plurality of holiday categories;

(ii) a number of points of interest located along the link and associated with each of the plurality of holiday categories; and

(iii) a total number of points of interest along the link.

18. The computer system of claim 17, wherein the mean category impact for each of the plurality of holiday categories is weighted based on a ratio of the number of points of interest along a link that are associated with the holiday category to the total number of points of interest along the link.

19. The computer system of claim 16, wherein the mean category impact for each of the plurality of holiday categories is based on a traffic impact for each holiday of the holiday category.

20. The computer system of claim 19, wherein the traffic impact for each holiday is based on historical traffic data of one or more previous occurrences of the holiday and a mean weekday volume for a day of a week of each of the one or more previous occurrences.