Method and system for providing artificial intelligence analytic (AIA) services using operator fingerprints and cloud data

Patent metadata

Field	Value
Publication number	US-10950132-B2
Application number	US-201715852346-A
Country	US
Kind code	B2
Filing date	Dec 22, 2017
Priority date	Dec 22, 2016
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

Abstract

One embodiment of the present invention discloses a process of providing a report predicting potential risks relating to an operator driving a vehicle using information obtained from various interior and exterior sensors, vehicle onboard computer (“VOC”), and cloud network. After activating interior and exterior sensors mounted on a vehicle operated by a driver for obtaining data relating to external surroundings and internal environment, the data is forwarded to VOC for generating a current fingerprint associated with the driver. The current fingerprint represents current driving status in accordance with the collected real-time data. Upon uploading the current fingerprint to the cloud via a communications network, a historical fingerprint which represents historical driving information associated with the driver is retrieved. In one aspect, the process is capable of generating a driving analysis report which predicts potential risks associated with the driver according to the current and historical fingerprints.

First claim

What is claimed is:

1. A method for providing a report predicting events relating to a group of drivers in accordance with information obtained from a plurality of interior and exterior sensors the method comprising:
activating the plurality of interior and exterior sensors mounted on a vehicle operated by a driver for obtaining data relating to external surroundings and interior of the vehicle;
forwarding the data to a vehicle onboard computer (“VOC”) to generate a current fingerprint associated with the driver representing substantially current driving status in response to the data;
uploading the current fingerprint to the cloud via a communications network;
retrieving a historical fingerprint associated with the driver representing historical driving related information associated with the driver;
partitioning a prediction model into a plurality of sub-models, where each sub-model is associated with a different combination of driver and traffic attributes;
selecting a sub-model of the plurality of sub-models based on a current driver attribute and a current traffic attribute
generating a driving analysis report predicting potential events associated with the driver at least partially based on use of the selected sub-model on the current fingerprint and the historical fingerprint.

2. The method of claim 1 , further comprising forwarding the driving analysis report to a subscriber for analyzing potential future risks.

3. The method of claim 1 , further comprising forwarding the driving analysis report to a parent for analyzing teen driving behavior.

4. The method of claim 1 , further comprising forwarding the driving analysis report to a fleet subscriber for analyzing potential company liabilities from its fleet drivers.

5. The method of claim 1 , further comprising updating the historical fingerprint in response to the current fingerprint.

6. The method of claim 1 , wherein activating at least a portion of the plurality of interior and exterior sensors includes enabling a set of outward facing cameras mounted on the vehicle for recording external surrounding images representing a geographic environment in which the vehicle operates.

7. The method of claim 6 , wherein activating at least a portion of the plurality of interior and exterior sensors include selectively enabling at least one of a set of inward facing cameras mounted in the vehicle for collecting interior images of the vehicle.

8. The method of claim 7 , wherein activating at least a portion of the plurality of interior and exterior sensors includes identifying targeted direction focused by operator eyes in accordance with the interior images managed by an artificial intelligence (“AI”) model.

9. The method of claim 1 , wherein activating at least a portion of the plurality of interior and exterior sensors includes detecting driver's response time based on a set of identified road conditions and information from a controller area network (“CAN”) bus of the vehicle.

10. The method of claim 1 , wherein activating at least a portion of the plurality of interior and exterior sensors includes activating a plurality of audio sensors for obtaining audio data and sound related metadata.

11. The method of claim 1 , wherein activating at least a portion of the plurality of interior and exterior sensors includes obtaining real-time images relating to at least one of road, buildings, traffic lights, pedestrian, and retailers.

Assignees

• Xevo Inc

Inventors

• Tong Richard Chia Tsing
• Welland Robert Victor
• Ludwig John Hayes
• Cordell John Palmer
• Mckelvie Samuel James

Classifications

• G06V10/80

  Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level (multimodal speaker identification or verification G10L17/10) · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G08G1/168 Primary

  Driving aids for parking, e.g. acoustic or visual feedback on parking space · CPC title

• G06F18/25

  Fusion techniques · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title