Patent Application Titled “Media Forked Application System In Call Centers” Published Online (USPTO 20190260873)

2019 SEP 06 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Jayapalan, Vijay (San Antonio, TX); Yarbrough, Greg (San Antonio, TX); Smith, Eric J. (Helotes, TX), filed on May 6, 2019, was made available online on August 22, 2019.

The assignee for this patent application is United Services Automobile Association (San Antonio, Texas, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Call centers are used to provide, among other services, customer support, technical support, and product/service ordering services to callers. A call center may receive on the order of hundreds of millions of calls per year and employ thousands of customer service representatives (CSR). To provide quality services to callers, a call center must be capable of protecting the personal information of its customers and providing proper training to its CSRs.”

In addition to obtaining background information on this patent application, NewsRx editors also obtained the inventors’ summary information for this patent application: “This specification relates to analytical analyses performed on forked media streams of call center calls.

“Implementations of the present disclosure generally determine one or more call center operations to be performed based on analytical analysis of forked media streams from a call to a call center. More particularly, implementations of the present disclosure are directed to receiving results of one or more analytical analyses performed on a forked media stream, and directing further operations of call center systems in response to the results. In some implementations, the analysis results include one or more metrics indicating the likelihood that a call center call is fraudulent, and based on the metrics, the call center systems can continue forking the media stream from the call for further analysis, and process the call as a fraudulent or non-fraudulent call, as applicable. In some implementations, the analysis results indicate that a context of the call is valuable for agent (e.g., CSR) training, and the call can be recorded and stored with agent training records.

“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that include actions of sending a forked media stream of an electronic communication between a customer and an agent to an analysis system for a duration, receiving analysis results obtained from one or more analytics performed on the forked media stream, and determining whether to perform one or more operations in response to the analysis results. Other implementations of this aspect include corresponding systems, apparatus, and computer programs, configured to perform the actions of the methods, encoded on computer storage devices.

“These and other implementations can each optionally include one or more of the following features. The operations may include selectively extending the duration for sending the forked media stream. The analysis system may be a fraud detection system, and the analysis results may include voice analytic results. The operations may include extending the duration based on one or more metrics included in the analysis results. Metrics may include a fraud risk level score. The duration may be extended in response to the fraud risk level score exceeding a threshold.

“The operations may include storing the forked media stream in association with training records. Analytics may include identifying the absence or presence of one or more keywords spoken by the agent. The operations may include sending a notification for display on a computing device assigned to the agent. The analysis results may identify a topic discussed during the electronic communication, and the operations may include generating a notification including one or more training reminders relevant to the topic for display on a computing device assigned to the agent.

“Particular implementations of the subject matter described in this specification can be implemented so as to realize one or more of the following advantages. Implementations may make more efficient use of call center bandwidth and resources, provide improved security for call center customers, help CSRs (e.g., customer service representatives (CSR)) improve their communication skills, and save valuable training time for call centers.

“The details of one or more implementations of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.”

The claims supplied by the inventors are:

“1.-19. (canceled)

“20. A computer-implemented method executed by at least one processor, the method comprising: sending, by the at least one processor, a forked media stream of an electronic communication between a customer and an agent to an analysis system, the electronic communication comprising an agent media stream associated with speech from the agent and a customer media stream associated with speech from the customer, the forked media stream being a separate media stream that replicates only the agent media stream from the electronic communication and is sent to the analysis system during the electronic communication between the customer and the agent; receiving, from the analysis system and during the electronic communication, analysis results that indicate a topic being discussed between the customer and the agent during the electronic communication; identifying, based on the analysis results of the forked media stream, content for a training notification, the content being relevant to the topic being discussed between the customer and the agent; and providing, during the electronic communication and for display on a computing device assigned to the agent, the training notification.

“21. The method of claim 20, further comprising storing the forked media stream in association with training records.

“22. The method of claim 20, wherein the analysis results include a token indicating one or more keywords spoken by the agent.

“23. The method of claim 22, further comprising: identifying a rule associated with the token; and in response to the rule, storing a recording of the forked media stream in association with a training category indicated by the rule.

“24. The method of any of claim 20, wherein identifying the content for the training notification comprises identifying the content for the training notification by applying a set of training rules to the analysis results.

“25. The method of claim 20, wherein the content of the training notification is identified based on a training rule that is specific to the agent.

“26. The method of claim 20, wherein the content of the training notification is identified based on a training rule that is specific to a subset of agents based on at least one common attribute shared by agents in the subset of agents.

“27. A call-center agent training system comprising: at least one computer; and tangible, non-transitory media operably connectable to the at least one computer and storing instructions that, when executed, perform operations comprising: sending a forked media stream of an electronic communication between a customer and an agent to an analysis system, the electronic communication comprising an agent media stream associated with speech from the agent and a customer media stream associated with speech from the customer, the forked media stream being a separate media stream that replicates only the agent media stream from the electronic communication and is sent to the analysis system during the electronic communication between the customer and the agent; receiving, from the analysis system and during the electronic communication, analysis results that indicate a topic being discussed between the customer and the agent during the electronic communication; identifying, based on the analysis results of the forked media stream, content for a training notification, the content being relevant to the topic being discussed between the customer and the agent; and providing, during the electronic communication and for display on a computing device assigned to the agent, the training notification.

“28. The call-center agent training system of claim 27, further comprising storing the forked media stream in association with training records.

“29. The call-center agent training system of claim 27, wherein the analysis results include a token indicating one or more keywords spoken by the agent.

“30. The call-center agent training system of claim 29, further comprising: identifying a rule associated with the token; and in response to the rule, storing a recording of the forked media stream in association with a training category indicated by the rule.

“31. The call-center agent training system of any of claim 27, wherein identifying the content for the training notification comprises identifying the content for the training notification by applying a set of training rules to the analysis results.

“32. The call-center agent training system of claim 27, wherein the content of the training notification is identified based on a training rule that is specific to the agent.

“33. The call-center agent training system of claim 27, wherein the content of the training notification is identified based on a training rule that is specific to a subset of agents based on at least one common attribute shared by agents in the subset of agents.

“34. A non-transitory computer readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: sending a forked media stream of an electronic communication between a customer and an agent to an analysis system, the electronic communication comprising an agent media stream associated with speech from the agent and a customer media stream associated with speech from the customer, the forked media stream being a separate media stream that replicates only the agent media stream from the electronic communication and is sent to the analysis system during the electronic communication between the customer and the agent; receiving, from the analysis system and during the electronic communication, analysis results that indicate a topic being discussed between the customer and the agent during the electronic communication; identifying, based on the analysis results of the forked media stream, content for a training notification, the content being relevant to the topic being discussed between the customer and the agent; and providing, during the electronic communication and for display on a computing device assigned to the agent, the training notification.

“35. The medium of claim 34, further comprising storing the forked media stream in association with training records.

“36. The medium of claim 34, wherein the analysis results include a token indicating one or more keywords spoken by the agent.

“37. The medium of claim 36, further comprising: identifying a rule associated with the token; and in response to the rule, storing a recording of the forked media stream in association with a training category indicated by the rule.

“38. The medium of claim 34, wherein identifying the content for the training notification comprises identifying the content for the training notification by applying a set of training rules to the analysis results.

“39. The medium of claim 34, wherein the content of the training notification is identified based on a training rule that is specific to a subset of agents based on at least one common attribute shared by agents in the subset of agents.”

For more information, see this patent application: Jayapalan, Vijay; Yarbrough, Greg; Smith, Eric J. Media Forked Application System In Call Centers. Filed May 6, 2019 and posted August 22, 2019. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220190260873%22.PGNR.&OS=DN/20190260873&RS=DN/20190260873

(Our reports deliver fact-based news of research and discoveries from around the world.)