Patent Issued for Forecasting And Dynamic Routing For Service Environments (USPTO 10,778,846)

2020 SEP 30 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Petropoulos, Lambros (San Antonio, TX); Wisnowski, James Walter (San Antonio, TX); Karl, Andrew Thomas (Denver, CO), filed on April 23, 2019, was published online on September 28, 2020.

The patent’s assignee for patent number 10,778,846 is United Services Automobile Association (San Antonio, Texas, United States).

News editors obtained the following quote from the background information supplied by the inventors: “An organization may use any number of computing systems, communications networks, data storage devices, or other types of systems to provide services to individuals. An organization may also employ service representatives that use the various systems to assist individuals in service sessions that are conducted over the telephone, in a video conference, through text chat sessions, or over other communication channels. An organization may seek to optimize the manner in which incoming service requests are routed to service representatives to ensure optimal usage of computing resources and also to provide an appropriate level of responsiveness to the individuals.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “Implementations of the present disclosure are generally directed to forecasting and routing incoming requests to service representatives (SRs), or groups of SRs, within a service environment. More specifically, implementations are directed to using a doubly stochastic forecasting model to forecast incoming call volume and other parameters within a service environment, by simultaneously modeling based on multiple different time scales such as both intra-day and inter-day modeling.

“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that include operations for routing service requests in a service environment, including: receiving first call volume information that describes call volume in the service environment during a first period of time, providing the first call volume information as input to a doubly stochastic forecasting model and receiving, as output from the doubly stochastic forecasting model, second call volume information that includes predicted call volume during a second period of time after the first period of time, wherein the doubly stochastic forecasting model generates the predicted call volume by simultaneously modeling the call volume on multiple different time scales, and dynamically routing at least one service request that is received in the service environment based at least partly on the predicted call volume. 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. Implementations can optionally include one or more of the following features.

“In some implementations, the multiple different time scales include an intra-day time scale and an inter-day time scale.

“Some implementations include training the doubly stochastic forecasting model using training data that includes call volume information corresponding to the multiple different time scales.

“In some implementations, the first call volume information further describes call wait times and call handling times in the service environment during the first period of time, and the second call volume information further includes predicted call wait times and predicted call handling times during the second period of time.

“In some implementations, the predicted call volume is further based on at least one exogenous variable.

“In some implementations, the predicted call volume includes: a first predicted call volume for calls associated with a first skill code of service representatives (SRs) in the service environment and a second predicted call volume for calls associated with a second skill code of SRs in the service environment.

“Some implementations include attempting to predict the call volume during the second period of time using a first time scale model that is based on a first time scale of the multiple different time scales based on determining that the output of the doubly stochastic forecasting model does not converge. Some implementations include attempting to predict the call volume during the second period of time using a second time scale model that is based on a second time scale of the multiple different time scales based on determining that the output of the first time scale model does not converge. In some implementations, the first time scale is an intra-day time scale and the second time scale is an inter-day time scale.

“Some implementations include attempting to predict the call volume during the second period of time based on an overall average call volume based on determining that the output of the second time scale model does not converge.

“Other implementations of any of the above aspects include corresponding systems, apparatus, and computer programs that are configured to perform the actions of the methods, encoded on computer storage devices. The present disclosure also provides one or more computer-readable storage media coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations in accordance with implementations of the methods provided herein. The present disclosure further provides a system for implementing the methods provided herein. The system includes one or more processors, and one or more computer-readable storage media coupled to the one or more processors having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations in accordance with implementations of the methods provided herein.

“Implementations of the present disclosure provide the following technical advantages and/or technical improvements over previously available solutions. In traditional service environments, incoming call routing may involve a number of administrators who determine which particular call center (e.g., group of service representatives) and/or particular service representative is to receive and handle a particular call from a customer. Moreover, traditional call routing systems (either automatic or manual) may be prone to errors in which requests are misrouted, and subsequently require one or more rerouting operations to attempt to find the appropriate service representative to service a request. Also, traditional call routing systems may not be based on accurate forecasts of call volume, leading to an imbalance of load for call handling between individual SRs and/or different call center, thus creating inefficiencies and longer wait times than would otherwise be present. Implementations address these problems by providing a forecast (prediction) of call volumes, call wait times, and/or call handling times based on a doubly stochastic model, the forecast being more accurate than traditional techniques, and using the more accurate forecast to provide more efficient routing the incoming request(s) to a particular service representative and/or call center(s) suitable to handle the incoming request(s). By providing for more accurate routing of requests, and more efficient load balancing between call centers and/or SRs, implementations do not consume the processing power, memory, and/or other computing resources that traditional systems consume to recover from errors in routing and/or re-routing of requests following an erroneous routing decision, and to rebalance call volume. Accurate forecasts also allow for proper staffing solutions and can provide input to contact center optimization modeling efforts.

“It is appreciated that methods in accordance with the present disclosure can include any combination of the aspects and features described herein. That is, methods in accordance with the present disclosure are not limited to the combinations of aspects and features specifically described herein, but also include any combination of the aspects and features provided.

“The details of one or more implementations of the present disclosure are set forth in the accompanying drawings and the description below. Other features and advantages of the present disclosure will be apparent from the description and drawings, and from the claims.”

The claims supplied by the inventors are:

“The invention claimed is:

“1. A computer-implemented method for routing calls in a service environment, the method performed by at least one processor, the method comprising: receiving, by the at least one processor, first call volume information that describes call volume in the service environment during a first period of time; providing, by the at least one processor, the first call volume information as input to a doubly stochastic forecasting model and receiving, as output from the doubly stochastic forecasting model, second call volume information that includes predicted call volume during a second period of time after the first period of time, wherein the doubly stochastic forecasting model generates the predicted call volume by simultaneously modeling the call volume on multiple different time scales, wherein the doubly stochastic forecasting model determines an arrival rate parameter of one time scale based on residuals from expected values on another time scale, and wherein a residual is a difference between observed calls and predicted calls; and based at least partly on the predicted call volume, dynamically routing, by the at least one processor, at least one call that is received in the service environment.

“2. The method of claim 1, wherein the multiple different time scales include an intra-day time scale and an inter-day time scale.

“3. The method of claim 1, further comprising: training the doubly stochastic forecasting model using training data that includes call volume information corresponding to the multiple different time scales.

“4. The method of claim 1, wherein: the first call volume information further describes call wait times and call handling times in the service environment during the first period of time; and the second call volume information further includes predicted call wait times and predicted call handling times during the second period of time.

“5. The method of claim 1, wherein the predicted call volume is further based on at least one exogenous variable.

“6. The method of claim 1, wherein the predicted call volume includes: a first predicted call volume for calls associated with a first skill code of service representatives (SRs) in the service environment; and a second predicted call volume for calls associated with a second skill code of SRs in the service environment.

“7. The method of claim 1, further comprising: based on determining that the output of the doubly stochastic forecasting model does not converge, attempting, by the at least one processor, to predict the call volume during the second period of time using a first time scale model that is based on a first time scale of the multiple different time scales.

“8. The method of claim 7, further comprising: based on determining that the output of the first time scale model does not converge, attempting, by the at least one processor, to predict the call volume during the second period of time using a second time scale model that is based on a second time scale of the multiple different time scales.

“9. The method of claim 8, wherein: the first time scale is an intra-day time scale; and the second time scale is an inter-day time scale.

“10. The method of claim 8, further comprising: based on determining that the output of the second time scale model does not converge, attempting, by the at least one processor, to predict the call volume during the second period of time based on an overall average call volume.

“11. A system comprising: at least one processor; and memory storing instructions which, when executed, instruct the at least one processor to perform operations comprising: receiving first call volume information that describes call volume in a service environment during a first period of time; providing the first call volume information as input to a doubly stochastic forecasting model and receiving, as output from the doubly stochastic forecasting model, second call volume information that includes predicted call volume during a second period of time after the first period of time, wherein the doubly stochastic forecasting model generates the predicted call volume by simultaneously modeling the call volume on multiple different time scales, wherein the doubly stochastic forecasting model determines an arrival rate parameter of one time scale based on residuals from expected values on another time scale, and wherein a residual is a difference between observed calls and predicted calls; and based at least partly on the predicted call volume, dynamically routing at least one call that is received in the service environment.

“12. The system of claim 11, wherein the multiple different time scales include an intra-day time scale and an inter-day time scale.

“13. The system of claim 11, wherein the operations further comprise: training the doubly stochastic forecasting model using training data that includes call volume information corresponding to the multiple different time scales.

“14. The system of claim 11, wherein: the first call volume information further describes call wait times and call handling times in the service environment during the first period of time; and the second call volume information further includes predicted call wait times and predicted call handling times during the second period of time.

“15. The system of claim 11, wherein the predicted call volume is further based on at least one exogenous variable.

“16. The system of claim 11, wherein the predicted call volume includes: a first predicted call volume for calls associated with a first skill code of service representatives (SRs) in the service environment; and a second predicted call volume for calls associated with a second skill code of SRs in the service environment.

“17. The system of claim 11, wherein the operations further comprise: based on determining that the output of the doubly stochastic forecasting model does not converge, attempting, by the at least one processor, to predict the call volume during the second period of time using a first time scale model that is based on a first time scale of the multiple different time scales.

“18. The system of claim 17, wherein the operations further comprise: based on determining that the output of the first time scale model does not converge, attempting, by the at least one processor, to predict the call volume during the second period of time using a second time scale model that is based on a second time scale of the multiple different time scales.

“19. The system of claim 18, wherein: the first time scale is an intra-day time scale; and the second time scale is an inter-day time scale.

“20. One or more computer-readable storage media storing instructions which, when executed, instruct at least one processor to perform operations comprising: receiving first call volume information that describes call volume in a service environment during a first period of time; providing the first call volume information as input to a doubly stochastic forecasting model and receiving, as output from the doubly stochastic forecasting model, second call volume information that includes predicted call volume during a second period of time after the first period of time, wherein the doubly stochastic forecasting model generates the predicted call volume by simultaneously modeling the call volume on multiple different time scales, wherein the doubly stochastic forecasting model determines an arrival rate parameter of one time scale based on residuals from expected values on another time scale, and wherein a residual is a difference between observed calls and predicted calls; and based at least partly on the predicted call volume, dynamically routing at least one call that is received in the service environment.”

For additional information on this patent, see: Petropoulos, Lambros; Wisnowski, James Walter; Karl, Andrew Thomas. Forecasting And Dynamic Routing For Service Environments. U.S. Patent Number 10,778,846, filed April 23, 2019, and published online on September 28, 2020. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,778,846.PN.&OS=PN/10,778,846RS=PN/10,778,846

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