Systems and methods of natural language processing to rank users of real time communications connections
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10097692-B2
Publication Date
2018-10-09
Expiration Date
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.
Core Innovation
The invention provides a real time communication connection architecture in which a connection server is coupled with a data store to establish real time communication connections between telephonic devices. Communication connections are established between second users and selected ones of first users using communication references stored in the data store, and communication records of the communication connections established by the connection server are stored for later processing.
The invention performs natural language processing on transcripts of communications to generate input vectors. Ranking scores of the second users are generated from the communication records, and the input vectors are correlated with the ranking scores to establish a predictive model of ranking score.
After the connection server provides a communication connection between a telephonic device of a user and a telephonic device of selected ones of the first users, a transcript of a communication between the user and the selected ones of the first users is stored, natural language processing is performed on the transcript to generate first input vectors, and the predictive model is applied to generate a ranking score of the user.
Claims Coverage
The relevant set includes three independent claims: a method claim, a non-transitory computer storage medium claim, and a computing system claim. Across these independent claims, the coverage centers on storing communication transcripts and records, performing natural language processing to generate input vectors, correlating those input vectors with ranking scores to establish a predictive model of ranking score, and using the predictive model to generate ranking scores for a user after a communication connection is provided.
Storing transcripts and communication records for connection-server communications
Storing transcripts of communications over communication connections established by a connection server between second users and selected ones of first users, and storing communication records of the communication connections established by the connection server.
Generating NLP input vectors from communication transcripts
Performing natural language processing on the transcripts to generate input vectors, including performing natural language processing on a transcript of a communication between a user and selected ones of the first users to generate first input vectors.
Predictive ranking model correlated to ranking scores
Generating 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.
Applying predictive model to generate user ranking score after a communication connection
After the connection server provides a communication connection between a telephonic device of a user and a telephonic device of selected ones of the first users, applying the first input vectors in the predictive model of ranking score to generate a ranking score of the user.
Connection-server established communication between telephonic devices
In response to requests received from the second users identifying the selected ones of the first users, establishing 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 in the data store.
Computing system implementing transcript, NLP, and predictive ranking
A computing system in which a computing apparatus having a processor and a memory stores instructions configured to instruct the computing apparatus to perform a method comprising generating transcripts of communications, storing communication records, performing natural language processing on the transcripts to generate input vectors, generating ranking scores correlated to establish a predictive model of ranking score, and after a communication connection is provided, storing a transcript, performing natural language processing to generate first input vectors, and applying the predictive model to generate a ranking score of the user.
The independent claims collectively require connection-server established real time communication between telephonic devices, storage of transcripts and communication records, natural language processing to generate input vectors from transcripts, generation of ranking scores correlated with the input vectors to establish a predictive model of ranking score, and application of that predictive model to generate a ranking score for a user after a communication connection is provided.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?