Method for generating learned model, non-transitory storage medium, and traffic jam predicting device

Patent metadata

Field	Value
Publication number	US-12198542-B2
Application number	US-202218059468-A
Country	US
Kind code	B2
Filing date	Nov 29, 2022
Priority date	Jan 11, 2022
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

A method includes, by a processor, acquiring number of persons information that indicates a number of users, including users who ride in vehicles, who depart from a facility at each of a predetermined time period, weather information for each predetermined time period, and vehicle information relating to vehicles traveling in a periphery of the facility, determining traffic jam status that indicates absence/presence of a traffic jam on a road located in a vicinity of the facility in the predetermined time period, by using the vehicle information; and generating a learned model for predicting a traffic jam of a road by machine learning using, as teaching data, the number of persons information, the weather information, and the traffic jam status that is associated with the number of persons information and the weather information.

First claim

What is claimed is:

1. A traffic jam predicting device comprising:
a memory that serves as a non-transitory storage medium storing a program that causes a processor to execute processing that
acquires number of persons information that indicates a number of users, including users who ride in vehicles, who depart from a facility at each of a predetermined time period, weather information for each predetermined time period, and vehicle information relating to vehicles traveling in a periphery of the facility;
determines traffic jam status that indicates absence/presence of a traffic jam on a road located in a vicinity of the facility in the predetermined time period, by using the vehicle information;
generates a learned model for predicting a traffic jam of a road by machine learning using, as teaching data, the number of persons information, the weather information, and the traffic jam status that is associated with the number of persons information and the weather information; and
predicts the traffic jam status of a road located in a vicinity of the facility by inputting the weather information and estimated number of persons information that indicates a number of users, including users who ride in vehicles, who are estimated to have departed from the facility in each predetermined time period;
the traffic jam predicting device further comprising:
a processor coupled to the memory,
wherein the processor is configured to:
estimate the estimated number of persons information in an object time period for which prediction of the traffic jam status is to be carried out, and
predict the traffic jam status in the object time period by inputting the estimated number of persons information and the weather information to the learned model;
wherein the processor is further configured to provide a user with a road whose traffic jam status is predicted by using a map, results of predicting for each predetermined time period, being predicted in the object time period, and a traffic jam status for each predetermined period on a past same day of a past week in the object time period, on one screen in a prediction presenting screen displaying the predicted traffic jam status in the object time period, resulting from receiving an instruction from the user.

2. The traffic jam predicting device of claim 1 , wherein the number of persons information includes a number of users relating to a time period that is before a time period in which the traffic jam status is determined.

3. The traffic jam predicting device of claim 1 , wherein:
the vehicle information includes position information relating to a position of the vehicle and speed information relating to a speed of the vehicle, and
the determining of the traffic jam status uses the position information and the speed information.

4. The traffic jam predicting device of claim 3 , further comprising:
deriving a needed time that is needed in order to pass through a predetermined segment by using the position information and the speed information, and
determining the traffic jam status to be that there is a traffic jam in a case in which there exists, in continuation, a predetermined number of segments whose needed time is greater than or equal to a threshold value.

5. The traffic jam predicting device of claim 1 , wherein the learned model is a model using a random forest.

6. The traffic jam predicting device of claim 1 , wherein the processor is configured to estimate the estimated number of persons information in the object time period by using a past number of users who have visited the facility.

7. The traffic jam predicting device of claim 1 , wherein the processor is configured to present the estimated traffic jam status of each object time period.

8. The traffic jam predicting device of claim 1 , wherein the processor is further configured to provide a plurality of time numbers indicating each time for the each predetermined time period, and a plurality of square marks indicating the absence/presence of the traffic jam by different color, corresponding to the each time, in the prediction presenting screen, and wherein the plurality of square marks include a first square mark indicating the absence/presence of the traffic jam in the object time period as the results of prediction, and a second square mark indicating the absence/presence of the traffic jam on the past same day of the past week in the object time period.

Assignees

• Toyota Motor Co Ltd

Inventors

• Shiomi Ayumu
• Miyagawa Atsushi
• Takeuchi Hiroki
• Kawai Toshiyuki
• Fukaya Ryosuke
• Tokita Hiroyuki
• Ikenoue Yusuke
• Saka Naoyuki
• Kato Tsukasa
• Yoshikawa Katsuhisa
• Yamamura Shugen
• Akaishi Takayuki

Classifications

• G08G1/052

  with provision for determining speed or overspeed {(speed measuring in general G01P)} · CPC title

• G08G1/0112 Primary

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G06N20/20

  Ensemble learning · CPC title

• G06Q50/40

  Business processes related to the transportation industry (shipping G06Q10/083) · CPC title

• G06N20/00

  Machine learning · CPC title