Controlling in-vehicle air quality

Patent metadata

Field	Value
Publication number	US-10828959-B2
Application number	US-201715706027-A
Country	US
Kind code	B2
Filing date	Sep 15, 2017
Priority date	Sep 15, 2017
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

A method to train a machine learning model for in-vehicle air quality control in a knowledge-based system, executed by one or more computer processors, includes collecting data related to in-vehicle air quality from a plurality of probe cars where the data is collected by various on-board systems in each probe car. The method includes correlating the data related to in-vehicle air quality from each probe car with air quality measurements from each probe car, where the correlation is used to update the machine learning model. The method includes determining a situation when an in-vehicle air quality measurement of the air quality measurements is above a pre-determined in-vehicle air quality level and determining instructions for actions by one or more of the one or more on-board systems in each of the probe cars to maintain an in-vehicle air quality level at or below the pre-determined in-vehicle air quality level.

First claim

What is claimed:

1. A method, the method comprising:
training, by one or more computer processors, a machine learning model for in-vehicle air quality control in a knowledge-based system using a plurality of probe cars with one or more air quality sensors monitoring a level of particulate matter and a level of total volatile organic compounds in each of the plurality of probe cars while collecting, by one or more on-board systems in the plurality of probe cars, a plurality of data including location data, temperature data, nearby vehicle data, traffic conditions data, weather data, heating ventilation and air conditioning (HVAC) system status, information on nearby factories and nearby construction as;
downloading, by one or more computer processors, the machine learning model for in-vehicle air quality control, after training of the machine learning model using the one or more air quality sensors in the plurality of probe cars and the location data, the temperature data, the nearby vehicle data, the traffic conditions data, the weather data, the HVAC system status, the information on nearby factories and the nearby construction collected by the one or more on-board systems is complete, to a computing device in a vehicle without an air quality sensor;
retrieving, by one or more computer processors, a plurality of data collected by one or more on-board systems in the vehicle without the air quality sensor;
determining, by one or more computer processors, that an occurrence of a situation of one or more situations when an in-vehicle air quality level is predicted to be above the pre-determined in-vehicle air quality level based, at least in part, on the plurality of data collected by the one or more on-board systems in the vehicle without the air quality sensor;
determining, by one or more computer processors, instructions for one or more actions by one or more of the one or more on-board systems in the vehicle without the air quality sensor to maintain the in-vehicle air quality level at or below the pre-determined in-vehicle air quality level based, at least in part, on the downloaded machine learning model; and
sending, by one or more computer processors, the instructions for the one or more actions to one or more of the one or more on-board systems in the vehicle without the air quality sensor to maintain the in-vehicle air quality level at or below the pre-determined in-vehicle air quality level.

2. The method of claim 1 , wherein collecting the plurality of data from one or more on-board systems in the vehicle occurs in response to receiving an indication of a driver entry into the vehicle.

3. The method of claim 1 , wherein the pre-determined in-vehicle air quality level is a regulated in-vehicle air quality level that is simultaneously communicated to each of the plurality of probe cars and the vehicle without the air quality sensor-when a level of the pre-determined air quality is changed with a new regulation.

4. The method of claim 1 , wherein the pre-determined in-vehicle air quality level is a user specified level of air quality received from a user input via a user interface of a probe car of the plurality of probe cars or from a user input via a user interface of the vehicle without the air quality sensor, wherein the user specified level of air quality is based, at least in part, on a special health requirement of a user of the probe car or a user of the vehicle without the air quality sensor, and wherein the user specified air quality level includes at least one of a pollen level, the level of in-vehicle particulate matter, or a level of total volatile organic compounds.

5. The method of claim 1 , wherein collecting the plurality of data from the one or more on-board systems in the plurality of probe cars includes receiving from one or more probe cars of the plurality of probe cars an indication of one or more smokers in a vehicle from a user input via a user interface in the one or more probe cars of the plurality of probe cars.

6. The method of claim 1 , wherein collecting the plurality of data from the plurality of probe cars includes collecting a plurality of data on an environment external to each of the plurality of probe cars and a plurality of data on an interior vehicle environment of each of the plurality of probe cars.

7. The method of claim 6 , wherein the plurality of data on the external environment to each of the plurality of probe cars includes at least a probe car location, weather conditions at the probe car location, an identification of one or more vehicles nearby the probe car, traffic conditions at the probe car location, and map information associated with the probe car location.

8. The method of claim 1 , further comprises:
maintaining, by one or more computer processors, the pre-determined in-vehicle air quality level in the vehicle without the air quality sensor, wherein the pre-determined in-vehicle air quality level is maintained based, at least in part, on the plurality of data collected by one or more on-board systems in the vehicle without the air quality sensor and the downloaded machine learning model for in-vehicle air quality control in the vehicle without the air quality sensor.

9. A computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions executable by a processor, the program instructions comprising instructions to:
train a machine learning model for in-vehicle air quality control in a knowledge-based system using a plurality of probe cars with one or more air quality sensors monitoring a level of particulate matter and a level of total volatile organic compounds in each of the plurality of probe cars while collecting, by one or more on-board systems in the plurality of probe cars a plurality of data including location data, temperature data, nearby vehicle data, traffic conditions data, weather data, heating ventilation and air conditioning (HVAC) system status, information on nearby factories and nearby construction;
download the machine learning model for in-vehicle air quality control, after training of the machine learning model using the one or more air quality sensors in the plurality of probe cars and the location data, the temperature data, the nearby vehicle data, the traffic conditions data, the weather data, the HVAC system status, the information on nearby factories and the nearby construction collected by from the one or more on-board systems is complete, to a computing device in a vehicle without an air quality sensor;
retrieve a plurality of data collected by one or more on-board systems in the vehicle without the air quality sensor;
determine that an occurrence of a situation of one or more situations when an in-vehicle air quality level is predicted to be above the pre-determined in-vehicle air quality level based, at least in part, on the plurality of data collected by the one or more on-board systems in the vehicle without the air quality sensor;
determine instructions for one or more actions by one or more of the one or more on-board systems in the vehicle without the air quality sensor to maintain the in-vehicle air quality level at or below the pre-determined in-vehicle air quality level based, at least in part, on the downloaded machine learning model; and
send the instructions for the one or more actions to one or more of the one or more on-board systems in the vehicle without the air quality sensor to maintain the in-vehicle air quality level at or below the pre-determined in-vehicle air quality level.

10. The computer program product of claim 9 , wherein collecting the plurality of data from one or more on-boar

Assignees

• IBM

Inventors

• Duan Ning
• Gao Peng
• Huang Jing Chang
• Ji Peng
• Ma Chun Yang
• Sun Wei
• Wang zhi hu
• Yao Ren Jie

Classifications

• B60H1/00821

  the components being ventilating, air admitting or air distributing devices · CPC title

• B60H1/008 Primary

  the input being air quality · CPC title

• B60H1/00771

  the input being a vehicle position or surrounding, e.g. GPS-based position or tunnel · CPC title

• B60H3/00

  Other air-treating devices · CPC title