Systems and methods of natural language processing to rank users of real time communications connections

• US 10,412,225 B2
• Filed: 10/08/2018
• Issued: 09/10/2019
• Est. Priority Date: 05/27/2015
• Status: Active Grant

• Current Assignee: Ingenio LLC
• Original Assignee: Ingenio LLC
• Inventors: Jandwani, Neeraj
• Primary Examiner(s): Addy, Thjuan K
• Application Number:
  US16/154,476
• Publication Number:
  US 20190045060A1
• Time in Patent Office: 337 Days
• Field of Search: 379 85, 37926509, 37926512, 37926505, 3792661, 37921201, 37921102, 37926511, 370352
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 7/026 Magnitude comparison, i.e. determining the relative order of operands based on their numerical value, e.g. window comparator
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 20/14 specially adapted for billing systems
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 2203/408 Customer-specific call routing plans
• CPC Class Codes: H04M 2203/551 Call history recording a computer conference H04L12/1831
• CPC Class Codes: H04M 2203/558 Databases
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15
• CPC Class Codes: H04M 7/003 : Click to dial services

Abstract

A computing apparatus configured to perform natural language processing, e.g., by comparing the words in a communication transcript of a user to a list of keywords, to generate an input vector representing a pattern of text in the communication transcript. A predictive model is generated from correlating input vectors to user ranking scores, e.g., for retention. The input vector determined from a communication transcript is applied to the computation model to compute a predicted retention score of the user. The retention score can be used, for example, to select a personalized recommendation for a communication connection to an adviser and/or a targeted offer.

Claims

1. A method, comprising:

in response to requests received from second users identifying selected ones of first users, a connection server establishes a communication connections between respective telephonic devices of the second users and respective telephonic devices of the selected ones of the first users using communication references;

storing in a computing apparatus, transcripts of communications over communication connections established by the connection server;

performing, by the computing apparatus, natural language processing on the transcripts to generate input vectors; and

generating, by the computing apparatus, ranking scores of the second users from the communication records, wherein the input vectors are correlated with the ranking scores to establish a predictive model of ranking score.

2. The method of claim 1, further comprising:

after the connection server provides a communication connection between a telephonic device of a user and a telephonic device of a selected ones of the first users;

storing, in the computing apparatus, a transcript of a communication between the user and the selected ones of the first users;

performing, by the computing apparatus, natural language processing on the transcript of the communication to generate first input vectors; and

applying, by the computing apparatus, the first input vectors in the predictive model of ranking score to generate a ranking score of the user.

3. The method of claim 2, wherein the input vectors correspond to text patterns identified via the natural language processing of the transcripts.

4. The method of claim 2, wherein the natural language processing performed by the computing apparatus is based on a list of stored keywords.

5. The method of claim 4, wherein the input vectors generated from the transcripts includes term frequencies of the list of keywords in the transcripts.

6. The method of claim 5, wherein the input vectors are correlated with the ranking scores to establish the predictive model of ranking score via a statistical analysis of correlation of the input vectors and the ranking scores.

7. The method of claim 5, wherein the input vectors are correlated with the ranking scores to establish the predictive model of ranking score includes using a machine learning technique in training the predictive model of ranking score to predict, from the input vectors, scores that match the ranking scores.

8. The method of claim 2, wherein the communication connection between the telephonic device of the user and the telephonic device of the selected ones of the first users is provided by:

establishing a first connection between the connection server and the telephonic device of the user;

establishing a second connection between the connection server and the telephonic device of the selected ones of the first users; and

bridging the first connection and the second connection.

9. The method of claim 8, wherein the generating of the transcript of the communication between the user and the selected ones of the first users includes performing voice recognition of the communication transmitted through the connection server bridging the first connection and the second connection.

10. The method of claim 9, wherein the first users provide coaching over the communication connections established by the connection server between the second users and the selected ones of the first users.

11. The method of claim 10, further comprising:

identifying, by the computing apparatus, a recommendation for a connection to one of the first users based at least in part on the ranking score of the user.

12. The method of claim 10, further comprising:

communicating, by the computing apparatus, an offer to the user based at least in part on the ranking score of the user.

13. A non-transitory computer storage medium storing instructions configured to instruct a computing device to perform a method, the method comprising:

in response to requests received from second users identifying selected ones of first users, a connection server establishes a communication connections between respective telephonic devices of the second users and respective telephonic devices of the selected ones of the first users using communication references;

storing in a computing apparatus, transcripts of communications over communication connections established by the connection server;

performing, by the computing apparatus, natural language processing on the transcripts to generate input vectors; and

generating, by the computing apparatus, ranking scores of the second users from the communication records, wherein the input vectors are correlated with the ranking scores to establish a predictive model of ranking score.

14. A computing system, comprising:

a computing apparatus having a processor and a memory storing instructions configured to instruct the computing apparatus to perform a method comprising;

in response to requests received from second users identifying selected ones of first users, a connection server establishes a communication connections between respective telephonic devices of the second users and respective telephonic devices of the selected ones of the first users using communication references;

storing in the computing apparatus, transcripts of communications over communication connections established by the connection server;

performing, by the computing apparatus, natural language processing on the transcripts to generate input vectors; and

generating, by the computing apparatus, ranking scores of the second users from the communication records, wherein the input vectors are correlated with the ranking scores to establish a predictive model of ranking score.

15. The computing system of claim 14, wherein after the connection server provides a communication connection between a telephonic device of a user and a telephonic device of a selected ones of the first users:

storing, in the computing apparatus, a transcript of a communication between the user and the selected ones of the first users;

performing, by the computing apparatus, natural language processing on the transcript of the communication to generate first input vectors; and

applying, by the computing apparatus, the first input vectors in the predictive model of ranking score to generate a ranking score of the user.

16. The computing system of claim 15, wherein the input vectors correspond to text patterns identified via the natural language processing of the transcripts.

17. The computing system of claim 15, wherein the data store further stores a list of keywords;

and the natural language processing performed by the computing apparatus is based on the list of keywords.

18. The computing system of claim 17, wherein the input vectors generated from the transcripts includes term frequencies of the list of keywords in the transcripts.

19. The computing system of claim 18, further configured to perform a statistical analysis of correlation of the input vectors and the ranking scores in correlating the input vectors with the ranking scores to establish the predictive model of ranking score.

20. The computing system of claim 18, further configured to use a machine learning technique in training the predictive model of ranking score to predict, from the input vectors, scores that match the ranking scores.