IP Library Granted Patent US 12677125
Granted Patent B2
US 12677125 · App. 18/209,118 · Granted Jul 7, 2026

Natural language processing for roadside assistance

Inventors: Anthony Banks (Matthews, NC); Todd Bucco (Lake Villa, IL); Brandon Tarvin (Upatoi, GA)
Assignee: Allstate Insurance Company
H04W4/90G10L15/1822G06F3/167
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12677125
App. No.
18/209,118
Granted
Jul 7, 2026
Kind
B2
Abstract

Implementations claimed and described herein provide systems and methods for submitting a roadside assistance request. The systems and methods use natural language communication to determine an intent. The intent is determined by the system and used to generate and submit the roadside assistance request.

Claims (61)

1 . A computer implemented method comprising:

receiving a phone call from a telephone device;

generating a greeting for communication to a user via the telephone device;

retrieving one or more of a policy and benefits associated with the user;

receiving voice inputs from the user via the telephone device while maintaining a voice connection with the telephone device during a submission of a roadside assistance request, wherein the submission of the roadside assistance request includes:

determining intent based on the voice inputs; and

determining a car location based on the voice inputs;

determining whether collected information during the submission of the roadside assistance request is sufficient, wherein:

when the collected information is not sufficient, transfer the phone call to a live agent while maintaining the voice connection, and

when the collected information is sufficient, submit the roadside assistance request to a benefit provider system to cause roadside assistance to be provided to the user.

2 . The method of claim 1 , wherein retrieving one or more of a policy and benefits associated with the user includes receiving the one or more of the policy and benefits from a benefit provider system.

3 . The method of claim 1 , wherein the voice inputs are natural language.

4 . The method of claim 1 , wherein the telephone device is one or more of a desktop computer, laptop computer, tablet computer, vehicle-based devices, a smart watch, mobile phone, and a landline phone.

5 . The method of claim 1 , wherein when intent cannot be determined from the voice inputs, the method further comprising:

generating one or more follow up questions; and

receiving additional voice inputs in response to the one or more follow up questions.

6 . The method of claim 1 , further comprising authenticating the policy.

7 . The method of claim 1 , further comprising determining car details, wherein the car details are determined based on one or more of the voice inputs and the policy.

8 . The method of claim 1 , further comprising:

determining whether a tow is needed based on the voice inputs; and

determining a tow location.

9 . The method of claim 1 , further comprising confirming contact information of the user.

10 . A call center system comprising:

a natural language processing platform comprising one or more processors configured to:

receive a phone call from a telephone device;

generate a greeting for communication to a user via the telephone device;

retrieve one or more of a policy and benefits associated with the user;

receive voice inputs from the user via the telephone device while maintaining a voice connection with the telephone device during a submission of a roadside assistance request, wherein the submission of the roadside assistance request includes:

determine intent based on the voice inputs; and

determine a car location based on the voice inputs;

determine whether collected information during the submission of the roadside assistance request is sufficient, wherein:

when the collected information is not sufficient, transfer the phone call to a live agent associated with a call center system while maintaining the voice connection, and

when the collected information is sufficient, submit the roadside assistance request to a benefit provider system to cause roadside assistance to be provided to the user.

11 . The call center system of claim 10 , wherein when intent cannot be determined from the voice inputs, the one or more processors is further configured to:

generate one or more follow up questions; and

receive additional voice inputs in response to the one or more follow up questions.

12 . The call center system of claim 10 , wherein the one or more processors is further configured to authenticate the policy.

13 . The call center system of claim 10 , wherein the one or more processors is further configured to determine car details based on one or more of the voice inputs and the policy.

14 . The call center system of claim 10 , wherein the one or more processors is further configured to:

determine whether a tow is needed based on the voice inputs; and

determine a tow location.

15 . The call center system of claim 10 , wherein the one or more processors is further configured to confirm contact information of the user.

16 . The call center system of claim 10 , wherein the telephone device is one or more of a desktop computer, laptop computer, tablet computer, vehicle-based devices, a smart watch, mobile phone, and a landline phone.

17 . One or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process comprising:

receiving a phone call from a telephone device;

generating a greeting for communication to a user via the telephone device;

retrieving one or more of a policy and benefits associated with the user;

receiving voice inputs from the user via the telephone device while maintaining a voice connection with the telephone device during a submission of a roadside assistance request, wherein the submission of the roadside assistance request includes:

determining intent based on the voice inputs;

determining a car location based on the voice inputs;

determining car details based on one or more of the voice inputs and the policy;

determining whether a tow is needed based on the voice inputs;

determining a tow location when the tow is needed;

determining whether collected information during the submission of the roadside assistance request is sufficient, wherein:

when the collected information is not sufficient, transfer the phone call to a live agent while maintaining the voice connection, and

when the collected information is sufficient, submit the roadside assistance request to a benefit provider system to cause roadside assistance to be provided to the user.

18 . The one or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing the computer process on the computing system of claim 17 , wherein the computer process further comprises confirming contact information of the user.

19 . The one or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing the computer process on the computing system of claim 17 , wherein the computer process further comprises authenticating the policy.

20 . The one or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing the computer process on the computing system of claim 17 , wherein when intent cannot be determined from the voice inputs, the computer process further comprises:

generating one or more follow up questions; and

receiving additional voice inputs in response to the one or more follow up questions.