CONTENT-BASED ROUTING AND RATING OF MESSAGES IN A TELECOMMUNICATIONS NETWORK

• US 20180352391A1
• Filed: 05/31/2018
• Published: 12/06/2018
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: Inteliquent, Inc. (Sinch AB)
• Original Assignee: Inteliquent, Inc. (Sinch AB)
• Inventors: Wright, Chris, Pratt, Lyle
• Granted Patent: US 10,798,534 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: H04L 45/306 Route determination based on the nature of the carried application
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context
• CPC Class Codes: H04M 15/8088 involving increased rates, e.g. spam messaging billing differentiation
• CPC Class Codes: H04M 15/8221 Message based
• CPC Class Codes: H04M 2203/158 Call-type dependent routing route determination based on the nature of the carried application in packet switching networks H04L45/306
• CPC Class Codes: H04M 2215/22 Bandwidth or usage-sensitve billing
• CPC Class Codes: H04M 2215/32 Involving wireless systems
• CPC Class Codes: H04M 2215/7826 Message based
• CPC Class Codes: H04W 4/12 Messaging; Mailboxes; Announcements
• CPC Class Codes: H04W 4/24 Accounting or billing

Abstract

Systems and methods for automated routing and rating of communication data.

Claims

1. A system for automated routing and rating of communications data comprising:

a computing device configured to;

receive from a source element, a message destined for a destination element, wherein the message comprises a service category;

determine whether to classify the message;

determine a message class, wherein determining the message class comprises;

applying, to the message, a deep learning algorithm generated based on a plurality of messages each having a payload, time stamp, source address, and destination address; and

determining the message class based on the deep learning algorithm;

compare the service category to the determined message class;

determine a rating for the message based on the comparison; and

deliver the message to the destination element.

2. The system of claim 1, wherein the destination element is associated with a commercial mobile radio service (CMRS) entity.

3. The system of claim 1, wherein the source element is associated with an over-the-top (OTT) entity.

4. The system of claim 1, wherein the deep learning algorithm utilizes at least one of the message payload, time stamp, source address, and destination address associated with the message to determine the message class.

5. The system of claim 1, wherein the deep learning algorithm utilizes a message velocity to determine the message class.

6. The system of claim 1, wherein the message class comprises one of a person to person (P2P) communication;

an application to person (A2P) communication; and

SPAM.

7. The system of claim 6, wherein the A2P communication comprises one of a notification message;

an activation message;

a validation message;

a marketing message; and

a voting message.

8. A system for automated routing and rating of communications data comprising:

a computing device configured to;

receive a message from a source element, wherein the message comprises a service category;

determine whether to classify the message;

determine a message class, wherein determining the message class comprises;

applying, to the message, a deep learning algorithm generated based on a plurality of messages having respective payloads, time stamps, source addresses, and destination addresses; and

determining the message class based on the deep learning algorithm;

compare the service category to the determined message class; and

determine a rating for the message based on the comparison.

9. The system of claim 8, wherein the source element is associated with an over-the-top (OTT) entity.

10. The system of claim 8, wherein the deep learning algorithm utilizes at least one of the message payload, time stamp, source address, and destination address associated with the message to determine the message class.

11. The system of claim 8, wherein the deep learning algorithm utilizes a message velocity to determine the message class.

12. The system of claim 8, wherein the message class comprises one of a person to person (P2P) communication;

an application to person (A2P) communication; and

SPAM.

13. The system of claim 12, wherein the A2P communication comprises one of a notification message;

an activation message;

a validation message;

a marketing message; and

a voting message.

14. The system of claim 8, wherein the rating comprises a numerical value.

15. The system of claim 8, wherein the rating is determined based on a comparison of one or more of an initial service category;

a source identity;

a source score; and

a ranking.

16. A method for automated routing and rating of communications data via a computing device within a telecommunications network, the method comprising the steps of:

at the computing device, receiving from a source element, a message destined for a destination element, wherein the message comprises a service category;

determining at the computing device whether to classify the message;

determining at the computing device a message class, wherein determining the message class comprises;

applying, to the message, a deep learning algorithm generated based on a plurality of messages each having a payload, time stamp, source address, and destination address; and

determining the message class based on the deep learning algorithm;

comparing at the computing device the service category to the determined message class;

determining at the computing device a rating for the message based on the comparison; and

delivering the message to the destination element.

17. The method of claim 16, wherein the destination element is associated with a commercial mobile radio service (CMRS) entity.

18. The method of claim 16, wherein the source element is associated with an over-the-top (OTT) entity.

19. The method of claim 16, wherein the deep learning algorithm utilizes at least one of the message payload, time stamp, source address, and destination address associated with the message to determine the message class.

20. The method of claim 16, wherein the deep learning algorithm utilizes a message velocity to determine the message class.