Patent Issued for Predictive routing for service sessions (USPTO 11223540): United Services Automobile Association

2022 FEB 02 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Lilley, David Alexander (Schertz, TX, US), filed on October 12, 2017, was published online on January 11, 2022.

The assignee for this patent, patent number 11223540, is United Services Automobile Association (San Antonio, Texas, United States).

Reporters 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.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Implementations of the present disclosure are generally directed to routing requests in a service environment. More specifically, implementations are directed to predictive routing of requests in a service environment, in which the routing of an individual’s request is based at least partly on actions previously taken by the individual in an application.

“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that include operations of: detecting at least one action that is performed by an individual in an application executing on a user device, wherein the at least one action is performed to access information that is received from a back-end server computing device and presented in the application; storing in an activity data store, an activity record that identifies the individual and a category that corresponds to the at least one action; and receiving an indication of the service request that is submitted by the individual in the service environment after the performing of the at least one action and, in response, retrieving the activity record from the activity data store, determining a service representative (SR) associated with the category indicated in the activity record, and initiating a service session between the SR and the individual in the service environment.

“Implementations can optionally include one or more of the following features: the service environment includes an interactive voice response (IVR) interface; the service request is a call to the IVR interface; initiating the service session includes bypassing at least a portion of the IVR interface; the activity record includes a telephone number of the individual; the activity record is retrieved that corresponds to the telephone number calling into the IVR interface; the activity record includes a time-to-live (TTL) value; the service session is initiated based on determining that an elapsed time between the storing of the activity record and the receiving of the service request has not exceeded the TTL value; the TTL value is based on the category; the at least one action is a selection of the category made, by the individual, through a category selection dialog that is presented through the application; the category selection dialog provides for the indication of the category through a selection of the category from a hierarchical arrangement of categories; the category is predicted based on identifying a particular section of the application in which the individual performs the at least one action; the operations further include selecting, from a category data store that includes a plurality of categories of service requests, the category that corresponds to the at least one action, wherein the activity record includes a category identifier that is a key to the category in the category data store; and/or the plurality of categories stored in the category data store includes a hierarchical arrangement of categories.

“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, such as call centers, call routing may involve a number of administrators who determine which 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. Implementations address these problems by predicting or otherwise determining a category for the service request, based at least partly on the requesting individual’s previous action(s), and automatically routing the request to a service representative who is suitable to handle the request of the determined category. By providing for more accurate routing of requests, 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.”

The claims supplied by the inventors are:

“1. A computer-implemented method for routing service requests in a service environment, the method performed by at least one processor, the method comprising: detecting, by the at least one processor, that an individual has performed at least one action on a particular user interface of an application executing on a user device, wherein the at least one action is performed to access information that is received from a server system of a user account service environment and presented in the application; determining, by the at least one processor, a category that corresponds to the at least one action; storing, by the at least one processor, in an activity data store, an activity record that identifies the individual, the category that corresponds to the at least one action, and a time-to-live (TTL) value associated with the category of the at least one action, the TTL value indicating a period of time after which the activity record expires, wherein the period of time begins when activity record is created and is elapsed only over hours that a service corresponding with the category is available to handle service requests; and receiving, by the at least one processor, a service request from the individual after the performing of the at least one action, and, in response: retrieving, by the at least one processor, the activity record from the activity data store; determining, by the at least one processor, whether the TTL value has expired; and in response to determine that the TTL value has not expired: a) determining, by the at least one processor, a service representative (SR) associated with the category indicated in the activity record; and b) initiating, by the at least one processor, a service session between the SR and the individual in the service environment.

“2. The method of claim 1, wherein: the service request is a call received through an interactive voice response (IVR) interface; retrieving the activity record from the activity data store includes matching a telephone number of the call with a telephone number associated with the activity record; and initiating the service session includes bypassing at least a portion of the IVR interface.

“3. The method of claim 2, wherein: the service request is a text message received through an SMS or MMS system; retrieving the activity record from the activity data store includes matching a telephone number of the text message with a telephone number associated with the activity record; and initiating the service session includes sending a response text message with a link that, when executed, establishes a text chat, audio chat, or video chat session with a service representative.

“4. The method of claim 1, wherein the category is determined by a machine learning model, and wherein the method further comprises in response to determining that the service request was re-routed to a new SR within a predetermined time period, using the service request to refine the machine learning model.

“5. The method of claim 1, wherein the TTL value is selected from among multiple different time periods based on the category of the at least one action, each time period being associated with one or more different categories.

“6. The method of claim 1, wherein the at least one action is a selection of the category made, by the individual, through a category selection dialog that is presented through the application.

“7. The method of claim 6, wherein the category selection dialog provides for the indication of the category through a selection of the category from a hierarchical arrangement of categories.

“8. The method of claim 1, wherein the category is predicted based on identifying a particular section of the application in which the individual performs the at least one action.

“9. The method of claim 1, further comprising: selecting, by the at least one processor, from a category data store that includes a plurality of categories of service requests, the category that corresponds to the at least one action, wherein the activity record includes a category identifier that is a key to the category in the category data store.

“10. The method of claim 5, wherein the multiple different time periods include at least a first time period and a second time period, the second time period being longer than the first time period, and wherein the first time period is associated with at least an account fraud category and the second time period is associated with at least an account service category.

“11. A system, comprising: at least one processor; and a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising: detecting that an individual has performed at least one action on a particular user interface of an application executing on a user device, wherein the at least one action is performed to access information that is received from a server system of a user account service environment and presented in the application; determining a category that corresponds to the at least one action; storing, in an activity data store, an activity record that identifies the individual, the category that corresponds to the at least one action, and a time-to-live (TTL) value associated with the category of the at least one action, the TTL value indicating a period of time after which the activity record expires, wherein the period of time begins when activity record is created and is elapsed only over hours that a service corresponding with the category is available to handle service requests; and receiving a service request from the individual after the performing of the at least one action and, in response: retrieving the activity record from the activity data store; determining whether the TTL value has expired; and in response to determine that the TTL value has not expired: a) determining a service representative (SR) associated with the category indicated in the activity record; and b) initiating a service session between the SR and the individual in the service environment.

“12. The system of claim 11, wherein: the service request is a call received through an interactive voice response (IVR) interface; retrieving the activity record from the activity data store includes matching a telephone number of the call with a telephone number associated with the activity record; and initiating the service session includes bypassing at least a portion of the IVR interface.

“13. The system of claim 12, wherein: the service request is a text message received through an SMS or MMS system; retrieving the activity record from the activity data store includes matching a telephone number of the text message with a telephone number associated with the activity record; and initiating the service session includes sending a response text message with a link that, when executed, establishes a text chat, audio chat, or video chat session with a service representative.

“14. The system of claim 11, wherein the category is determined by a machine learning model, and wherein the operations further comprises in response to determining that the service request was re-routed to a new SR within a predetermined time period, using the service request to refine the machine learning model.

“15. The system of claim 11, wherein the TTL value is selected from among multiple different time periods based on the category of the at least one action, each time period being associated with one or more different categories.

“16. The system of claim 11, wherein the at least one action is a selection of the category made, by the individual, through a category selection dialog that is presented through the application.

“17. The system of claim 16, wherein the category selection dialog provides for the indication of the category through a selection of the category from a hierarchical arrangement of categories.

“18. The system of claim 11, wherein the category is predicted based on identifying a particular section of the application in which the individual performs the at least one action.

“19. The system of claim 11, the operations further comprising: selecting, from a category data store that includes a plurality of categories of service requests, the category that corresponds to the at least one action, wherein the activity record includes a category identifier that is a key to the category in the category data store.”

There are additional claims. Please visit full patent to read further.

For more information, see this patent: Lilley, David Alexander. Predictive routing for service sessions. U.S. Patent Number 11223540, filed October 12, 2017, and published online on January 11, 2022. 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=11223540.PN.&OS=PN/11223540RS=PN/11223540

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