Patent Issued for Intelligent agent for interactive service environments (USPTO 11776546): United Services Automobile Association

2023 OCT 23 (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 Fujimoto, Yuibi (Helotes, TX, US), Waldmeier, Michael (Helotes, TX, US), filed on September 8, 2021, was published online on October 3, 2023.

The assignee for this patent, patent number 11776546, 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 service to customers or other 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, in person, or over other communication channels. Organizations generally strive to provide a calm and productive interaction between service representatives and the individuals being serviced, while maintaining an appropriate quality level for the service provided by service representatives.”

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 providing information during a service session. More specifically, implementations are directed to an intelligent agent that monitors interactions between participants in a service session, and automatically generates appropriate information based on the communications exchanged during the session, and injects the information into the session to supplement the other information provided during the service session.

“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that includes operations of: monitoring communications sent by an individual during a service session between the individual and a service representative (SR); identifying a topic that is associated with at least one of the communications; retrieving data associated with the topic and, based on the retrieved data, composing a message related to the topic, wherein the identifying of the topic, the retrieving of the data, and the composing of the message are performed autonomously with respect to the SR and in real time with respect to the monitoring of communications during the service session; and presenting the message to the individual during the service session.

“Implementations can optionally include one or more of the following features: the operations further include presenting the message to the SR through an SR application; the operations further include receiving a command to present the message to the individual, the command entered by the SR through the SR application; the presenting of the message to the individual during the service session is in response to receiving the command; the operations further include analyzing the communications to determine one or more candidate topics associated with the communications; the operations further include retrieving data associated with each of the one or more candidate topics and, based on the retrieved data, composing a plurality of candidate messages that includes at least one candidate message related to each respective candidate topic; the operations further include selecting the message to be presented from the plurality of candidate messages; selecting the message includes presenting the plurality of candidate messages through the SR application, and/or receiving a command that is provided through the SR application to select the message from the plurality of candidate messages; the service session is a text chat session; the message is presented as text in the text chat session; the message is presented with an indication that the message has been auto-generated; the presenting of the message to the individual during the service session is performed autonomously with respect to the SR; the topic is a question that is asked by the individual during the service session; the message is an answer to the question, the answer determined based on the retrieved data; identifying the topic further includes parsing text of the communications to determine one or more tokens included in the text, and/or determining the topic based on the one or more tokens; and/or determining the topic further includes providing the one or more tokens as input to a model that has been developed, using machine learning, to identify at least one topic based on one or more input tokens, and/or receiving the topic that is identified by the model based on the one or more tokens.

“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 a computer-readable storage medium 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 a computer-readable storage medium 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 one or more of the following advantages. In a traditional service environment implemented using previously available systems, a service representative (SR) engaged in a chat session or other service session with an individual is limited to discussing topics within the purview or expertise of the particular to whom the individual has been routed. For example, in a financial services customer service environment, a particular SR may specialize in answering questions regarding investments. If a customer also has questions about the balances of other types of accounts (e.g., checking, saving, etc.), the SR would traditionally need to re-route the customer to be serviced by a different type of specialized SR, leading to a loss of time, customer frustration, and computing system inefficiencies for repeated re-routing of customers. Implementations provide an intelligent agent to monitors a service session between an SR and an individual, identifies those questions that can be readily answered based on available information (e.g., “what is my checking account balance?”), and generates and presents answers to such questions autonomously of the conversation between the SR and the individual. This autonomous generation and presentation of information allows the SR and individual to continue with their main topic of conversation while the intelligent agent handles other topics (e.g., side questions that are off the main topic) that are answerable based on available information. Accordingly, implementations avoid the customer frustration caused by repeated re-routing that can occur in a traditional support environment, and implementations also avoid the expenditure of network bandwidth, processing power, active memory, and/or other computing resources that are expended by traditional environments to re-route or otherwise accommodate side requests from an individual. Because of the above-mentioned advantages and/or other advantages described herein, implementations also provide for a shorter service level agreement (SLA) for providing service within the service environment.”

The claims supplied by the inventors are:

“1. 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: identify one or more topics associated with a service session of a service representative application; compose at least one message for each topic of the one or more topics; receive an indication of a selected message of the at least one message; determine that the selected message is identical to a previous message selected during the service session; modify the selected message to be different from the previous message to generate a modified selected message; and present the modified selected message in the service session.

“2. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause the at least one processor to: determine a message confidence score for each message of the at least one message; and present the at least one message for each topic of the one or more topics and the message confidence score for each message of the at least one message through the service representative application.

“3. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause the at least one processor to: receive a modification to the modified selected message through the service representative application; generate an additional modified selected message based on the modification; and present the additional modified selected message in the service session.

“4. The system of claim 3, wherein the instructions, when executed by the at least one processor, cause at least one processor to: generate a training set based on the modification; identify one or more additional topics associated with the service session; and compose at least one additional message for the one or more additional topics based on the training set.

“5. The system of claim 1, wherein the service session comprises a text chat session, and wherein the instructions, when executed by the at least one processor, cause at least one processor to present the selected message as text in the text chat session.

“6. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause at least one processor to present the selected message with an indication that the selected message has been auto-generated.

“7. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause the at least one processor to generate a user interface of the service representative application, the user interface comprising a first portion configured to enable interaction by a service representative and a second portion configured to enable viewing of the service session by the service representative and another user.

“8. The system of claim 1, wherein: each topic of the one or more topics is associated with a question provided during the service session; and each message of the at least one message is associated with an answer to the question.

“9. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause the at least one processor to identify the one or more topics by: parsing text of the service session to determine one or more tokens included in the text; and determining the one or more topics based on the one or more tokens.

“10. The system of claim 9, wherein the instructions, when executed by the at least one processor, cause the at least one processor to identify the one or more topics by: providing the one or more tokens as input to a machine-learning model that is configured to identify the one or more topics based on the one or more tokens; and receiving the one or more topics from the machine-learning model.

“11. A computer-implemented method performed by at least one processor, the method comprising: identifying a main topic associated with a service session of a service representative application with a user; identifying one or more side topics associated with the service session based on demographic characteristics of the user, wherein each side topic of the one or more side topics is introduced in communications during the service session subsequent to introduction of the main topic during the service session; composing at least one message for at least one side topic of the one or more side topics; and presenting the one or more side topics, the at least one message, or both, through the service representative application.

“12. The method of claim 11, comprising: determining a respective confidence score for each side topic of the one or more side topics; and composing the at least one message for each side topic of the one or more side topics having the respective confidence score above a threshold confidence score.

“13. The method of claim 12, comprising presenting each side topic of the one or more side topics and the respective confidence score for each side topic through the service representative application.

“14. The method of claim 11, comprising parsing text of the communications to determine one or more tokens included in the text, wherein identifying the one or more side topics is based on the one or more tokens.

“15. The method of claim 14, comprising: providing the one or more tokens as input to a machine-learning model that is configured to identify the one or more side topics based on the one or more tokens; and receiving the one or more side topics from the machine-learning model.

“16. The method of claim 11, wherein presenting the one or more side topics, the at least one message, or both, through the service representative application is performed autonomously by the at least one processor.

“17. One or more non-transitory, computer-readable media storing instructions which, when executed by at least one processor, cause the at least one processor to: identify a plurality of topics associated with a service session of a service representative application; compose at least one message for at least one topic of the plurality of topics; receive an indication of a selected message of the at least one message; determine that the selected message is identical to a previous message selected during the service session; modify the selected message to be different from the previous message to generate a modified selected message; and present the modified selected message in the service session.

“18. The one or more non-transitory, computer-readable media of claim 17, wherein the instructions, when executed by the at least one processor, cause the at least one processor to: retrieve additional data associated with each topic of the plurality of topics; based on the additional data, compose a plurality of candidate messages associated with each topic, wherein the plurality of candidate messages comprises the at least one message; and select the at least one message to be presented from the plurality of candidate messages.

“19. The one or more non-transitory, computer-readable media of claim 18, wherein selecting the at least one message includes: presenting the plurality of candidate messages through the service representative application; and receiving, through the service representative application, a selection of the at least one message from the plurality of candidate messages.

“20. The one or more non-transitory, computer-readable media of claim 17, wherein the instructions, when executed by the at least one processor, cause the at least one processor to present the modified selected message with an indication that the modified selected message has been auto-generated.”

For more information, see this patent: Fujimoto, Yuibi. Intelligent agent for interactive service environments. U.S. Patent Number 11776546, filed September 8, 2021, and published online on October 3, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11776546)&db=USPAT&type=ids

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