Processing System Having A Machine Learning Engine For Providing A Common Trip Format (CTF) Output

• US 20190310094A1
• Filed: 04/09/2018
• Published: 10/10/2019
• Est. Priority Date: 04/09/2018
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Navratil, Zoran, Rice, Kevin Patrick, Mohnen, Daniel Brian, Glickley, Kevin, Ponnala, Nilesh, Chandrawanshi, Rahul
• Granted Patent: US 10,900,796 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3697 Output of additional, non-guidance related information, e.g. low fuel level G01C21/3679 takes precedence
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: H04W 4/38 for collecting sensor information
• CPC Class Codes: H04W 4/44 for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Abstract

Aspects of the disclosure relate to enhanced telematics processing systems with improved third party source data integration features and enhanced customized driving output determinations. A computing platform may receive telematics data and third party source data. The computing platform may enrich the telematics data using the third party source data. After generating the enriched telematics data, the computing platform may use machine learning algorithms and datasets to validate the enriched telematics data. The computing platform may ingest, via a batch ingestion process, the enriched telematics data. For example, the computing platform may store the enriched telematics data and generate additional enriched telematics data until expiration of a predetermined period of time. The computing platform may ingest the enriched telematics data associated with each trip. Once the enriched telematics data has been ingested, the computing platform may generate a standardized common trip format output for each trip.

Claims

1. A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to;

establish a connection between the computing platform and a plurality of telematics sensors via the communication interface;

receive, from the plurality of telematics sensors and via the communication interface, telematics output data;

establish a connection between the computing platform and a plurality of third party sources via the communication interface;

receive, from the plurality of third party sources and via the communication interface, third party source data;

generate an enriched telematics output by combining the telematics output data and the third party source data;

validate the enriched telematics output based on one or more machine learning datasets;

determine a mode of ingestion for ingesting the validated enriched telematics output; and

generate a standardized common trip format (CTF) output based on the validated enriched telematics output and the determined mode of ingestion.

2. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

generate one or more commands directing a telematics output validation computing platform to validate the enriched telematics output;

transmit, to the telematics output validation computing platform and via the communication interface, the one or more commands directing the telematics output validation computing platform to validate the enriched telematics output; and

receive, from the telematics output validation computing platform and via the communication interface, an enriched telematics output confirmation comprising an indication that the enriched telematics output has been validated.

3. The computing platform of claim 2, wherein validating the enriched telematics output comprises receiving the enriched telematics output confirmation.

4. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

after the enriched telematics output has been validated, determine whether the enriched telematics output should be ingested in a streaming mode or a batch mode;

in response to determining that the enriched telematics output should be ingested in the batch mode;

determine that the enriched telematics output is associated with a first event;

store, for a predetermined period of time, the enriched telematics output along with a machine learning dataset associated with the first event; and

in response to an expiration of the predetermined period of time, generate, based on enriched telematics outputs stored along with the machine learning dataset associated with the first event, the standardized CTF output.

5. The computing platform of claim 4, wherein the first event comprises one of a first driving trip or an initial occurrence of an event within the first driving trip.

6. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

determine that the enriched telematics output comprises a high priority telematics output;

determine that another enriched telematics output comprises a low priority telematics output; and

ingest, prior to ingesting the other enriched telematics output, the enriched telematics output.

7. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

after the enriched telematics output has been validated, determine whether the enriched telematics output should be ingested in a streaming mode or a batch mode; and

in response to determining that the enriched telematics output should be ingested in the streaming mode, generate, based on the enriched telematics output, the standardized CTF output.

8. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

send, via the communication interface and to a customized driver output generation computing platform, the standardized CTF output; and

generate one or more commands directing the customized driver output generation computing platform to generate a customized driver output based on the standardized CTF output.

9. The computing platform of claim 1, wherein the standardized CTF output includes a user identifier.

10. The computing platform of claim 1, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

receive, from the plurality of telematics sensors and via the communication interface, second telematics output data;

generate a second enriched telematics output by combining the second telematics output data and the third party source data;

determine that the second enriched telematics output was not validated; and

determine that the second enriched telematics output should not be ingested.

11. A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to;

receive, from a telematics validation computing platform and via the communication interface, an enriched telematics output confirmation comprising an indication that an enriched telematics output has been validated;

after the enriched telematics output has been validated, determine whether the enriched telematics output should be ingested in a streaming mode or a batch mode;

in response to determining that the enriched telematics output should be ingested in the batch mode;

determine that the enriched telematics output is associated with a first event;

store, for a predetermined period of time, the enriched telematics output along with a machine learning dataset associated with the first event; and

in response to an expiration of the predetermined period of time, generate, based on enriched telematics outputs stored along with the machine learning dataset associated with the first event, a standardized common trip format (CTF) output.

12. The computing platform of claim 11, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

generate one or more commands directing the telematics validation computing platform to validate the enriched telematics output; and

transmit, to the telematics validation computing platform and via the communication interface, the one or more commands directing the telematics validation computing platform to validate the enriched telematics output.

13. The computing platform of claim 12, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

send, to a customized driver output generation computing platform, the CTF output;

generate one or more commands directing the customized driver output generation computing platform to generate a customized driver output; and

send, to the customized driver output generation computing platform, the one or more commands to generate the customized driver output.

14. The computing platform of claim 13, wherein the telematics validation computing platform and the customized driver output generation computing platform are integrated into the computing platform.

15. The computing platform of claim 11, wherein the predetermined period of time is configured by a user.

16. The computing platform of claim 11, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

determine a trip initiation location and a trip destination; and

determine, based on the trip initiation location and the trip destination, the predetermined period of time.

17. The computing platform of claim 11, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

determine, based on a predefined setting, that the enriched telematics output should be ingested in the batch mode, wherein the predefined setting is configurable by a user.

18. A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to;

receive, from a plurality of sensor devices and via the communication interface, telematics output data and third party source data;

validate, via machine learning algorithms and analysis, the telematics output data;

after validating the telematics output data, generate, based on the telematics output data and the third party source data, enhanced telematics output data;

ingest, prior to standardizing the telematics output data, the enhanced telematics output data;

ingest, for a predetermined period of time, additional enhanced telematics output data; and

in response to an expiration of the predetermined period of time, determine, based on the enhanced telematics output data and the additional enhanced telematics output data, a standardized common trip format (CTF) output.

19. The computing platform of claim 18, wherein the standardized CTF output comprises a JavaScript Object Notation (JSON) spreadsheet output containing the enhanced telematics output data and the additional enhanced telematics output data.

20. The computing platform of claim 18, wherein the memory further stores computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

send, to a customized driver output generation computing platform, the CTF output;

generate one or more commands directing the customized driver output generation computing platform to generate a customized driver output; and

send, to the customized driver output generation computing platform, the one or more commands to generate the customized driver output.