Methods and systems for representing a degree of traffic congestion using a limited number of symbols

• US 10,140,254 B2
• Filed: 06/09/2014
• Issued: 11/27/2018
• Est. Priority Date: 06/07/2013
• Status: Active Grant

• Current Assignee: Direct Cursus Technology LLC
• Original Assignee: Yandex Europe AG (Yandex N.V.)
• Inventors: Karpov, Victor Vladimirovich
• Primary Examiner(s): Roni, Syed A
• Application Number:
  US14/896,573
• Publication Number:
  US 20160124906A1
• Time in Patent Office: 1,632 Days
• Field of Search: None
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G08G 1/012 from other sources than vehicle or roadside beacons, e.g. mobile networks
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination

Abstract

Method of creating a computerized model for computing values representative of traffic congestion in respect of a geographic area for use in representing a degree of traffic congestion in the geographic area using a limited number of symbols, comprising: retrieving, in respect of roads within geographic area, historical traffic data and values representative of traffic congestion; deriving a computerized model for computing values representative of traffic congestion in respect of roads within the geographic area based on the retrieved information. Method of representing a degree of traffic congestion in a geographic area using a limited number of symbols, comprising: receiving recent traffic and weather data including one of recent average vehicle speed and recent average vehicle transit time and two of temperature, relative humidity, barometric pressure, and cloud cover; and computing a value representative of traffic congestion using the recent traffic and weather data and a trained artificial neural network.

Claims

1. A method of presenting traffic congestion to a user of a client device, the method executable by a server, the method comprising:

inputting, by the server at a given time, into a first artificial neural network, a first set of data as input, the first set of data including traffic data in respect of roads within a geographical area and preceding the given time, the geographical area including a plurality of road segments, the first artificial neural network being one of a plurality of artificial neural networks,

each artificial neural network of the plurality of artificial neural networks having been trained to generate a symbol representative of traffic congestion in an entirety of the geographical area for one specific time interval of a plurality of time intervals, the symbol being one of a limited number of symbols,

the one specific time interval for which the first artificial neural network had been trained being a first time interval;

receiving, by the server in response to the input, from the first artificial neural network, the symbol representative of the traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval; and

sending, by the server to the client device for displaying to the user in respect of the first time interval, the symbol for the first time interval; and

wherein the symbol for the first time interval is a combination of a number and a color representative of the traffic congestion in the entire geographical area for the first time interval.

2. The method of claim 1, wherein each artificial neural network of the plurality of artificial neural networks had been trained to output the symbol for the one specific time interval for which that artificial neural network had been trained, by having received, during a training phase associated therewith:

a plurality of second sets of data and a plurality of training-phase single values as training input,

each second set of data of the plurality of second sets of data including traffic data in respect of roads within the geographical area and preceding the one specific time interval for which that artificial neural network had been trained, and

each single value of the plurality of training-phase single values corresponding to that second set of data and being representative of traffic congestion in the entire geographical area during the one specific time interval for which that artificial neural network had been trained.

3. The method of claim 1, wherein the number is a whole number between zero and ten inclusive.

4. The method of claim 1, wherein the first set of data includes weather data within the geographical area preceding the given time.

5. The method of claim 1, wherein each of the plurality of time intervals is an hour.

6. The method of claim 1, wherein the first time interval includes the given time.

7. A method of presenting traffic congestion to a user of a client device, the method executable by a server, the method comprising:

inputting, by the server at a given time, into a first artificial neural network, a first set of data as input, the first set of data including traffic data in respect of roads within a geographical area and preceding the given time, the geographical area including a plurality of road segments, the first artificial neural network being one of a plurality of artificial neural networks,

each artificial neural network of the plurality of artificial neural networks having been trained to generate a symbol representative of traffic congestion in an entirety of the geographical area for one specific time interval of a plurality of time intervals, the symbol being one of a limited number of symbols,

the one specific time interval for which the first artificial neural network had been trained being a first time interval;

receiving, by the server in response to the input, from the first artificial neural network, the symbol representative of the traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval; and

sending, by the server to the client device for displaying to the user in respect of the first time interval, the symbol for the first time interval; and

wherein;

the first artificial neural network comprises a set of artificial neural networks, each artificial neural network of the set of artificial neural networks generating in response to the input, a respective value for the first time interval; and

the symbol outputted by the first artificial neural network comprises an average of the respective values of the set of artificial neural networks.

8. The method of claim 7, wherein:

the set of artificial neural networks includes at least three artificial neural networks generating at least three respective values,

the at least three respective values include,

a first value representative of a minimum degree of traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval,

a second value representative of an average degree of traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval, and

a third value representative of a maximum degree of traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval; and

the symbol outputted by the first artificial neural network comprises an average of the first, second and third respective values of the set of artificial neural networks.

9. The method of claim 8, wherein the symbol outputted by the first artificial neural network includes a value representative of traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval.

10. The method of claim 9, wherein the symbol outputted by the first artificial neural network includes a color representative of traffic congestion in the entirety of all of the plurality of road segments within the geographic area for the first time interval.

11. The method of claim 7, wherein the first set of data includes weather data within the geographical area preceding the given time.

12. The method of claim 7, wherein each of the plurality of time intervals is an hour.

13. The method of claim 7, wherein the first time interval includes the given time.