Patent Issued for Intelligent agent for interactive service environments (USPTO 11133010): United Services Automobile Association
2021 OCT 18 (NewsRx) -- By a
The patent’s inventors are Fujimoto, Yuibi (
This patent was filed on
From the background information supplied by the inventors, news correspondents obtained the following quote: “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.”
Supplementing the background information on this patent, NewsRx reporters 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: monitoring, via the at least one processor, communications in a service representative application during a service session; identifying, via the at least one processor, a plurality of topics associated with at least one of the communications; determining, via the at least one processor, a plurality of topic confidence scores for the plurality of topics; composing, via the at least one processor, at least one message for each topic of the plurality of topics having a topic confidence score of the plurality of topic confidence scores above a threshold topic confidence score; determining, via the at least one processor, a message confidence score for each message of the at least one message; presenting, via the at least one processor, each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, the at least one message for each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, and the message confidence score for each message of the at least one message, through a first portion of the service representative application; receiving, via the at least one processor, an indication of a selected message of the at least one message; determining, via the at least one processor, that the selected message is identical to a previous message selected during the service session; modifying, via the at least one processor, the selected message to be different from the previous message to generate a modified selected message; and presenting, via the at least one processor, the modified selected message through a second portion of the service representative application during the service session.
“2. The system of claim 1, wherein the instructions, when executed by the at least one processor, cause: retrieving, via the at least one processor, additional data associated with each topic of the plurality of topics; and based on the additional data, composing, via the at least one processor, a plurality of candidate messages related to each topic of the plurality of topics, wherein the plurality of candidate messages comprises the at least one message.
“3. The system of claim 1, wherein: the service session is a text chat session; and the selected message is presented as text in the text chat session.
“4. The system of claim 1, wherein the selected message is presented with an indication that the selected message has been auto-generated.
“5. The system of claim 1, wherein presenting, via the at least one processor, each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, the at least one message for each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, and the message confidence score for each message of the at least one message, through the first portion of the service representative application during the service session is performed autonomously by the system.
“6. The system of claim 1, wherein: each topic of the plurality of topics comprises a question of a plurality of questions provided during the service session; and each message of the at least one message comprises an answer to the question.
“7. The system of claim 1, wherein identifying, via the at least one processor, the plurality of topics includes: parsing, via the at least one processor, text of the communications to determine one or more tokens included in the text; and determining, via the at least one processor, the plurality of topics based on the one or more tokens.
“8. The system of claim 7, wherein identifying, via the at least one processor, the plurality of topics includes: providing, via the at least one processor, the one or more tokens as input to a model that has been developed, using machine learning, to identify the plurality of topics based on one or more input tokens; and receiving, via the at least one processor, the plurality of topics that is identified by the model based on the one or more tokens.
“9. The system of claim 1, wherein the first portion of the service representative application comprises a user interface configured to enable interaction by a service representative, and wherein the second portion of the service representative application comprises a chat window configured to enable viewing of the communications by the service representative and another user.
“10. The system of claim 1, wherein the topic confidence score for a respective topic is indicative of a degree of confidence that the respective topic is present in the communications.
“11. The system of claim 1, comprising identifying, via the at least one processor, one or more messages of the at least one message having a message confidence score above a threshold message confidence score, wherein presenting, via the at least one processor, each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, the at least one message for each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, and the message confidence score for each message of the at least one message, through the first portion of the service representative application comprises presenting, via the at least one processor, each topic of the plurality of topics having the topic confidence score above the threshold topic confidence score, the one or more messages having the message confidence score above the threshold message confidence score, and the message confidence score for each message of the one or more messages through the first portion of the service representative application, and wherein the one or more messages comprise the selected message.
“12. A computer-implemented method performed by at least one processor, the method comprising: monitoring, by the at least one processor, communications of a user in a service representative application during a service session; identifying, by the at least one processor, a main inquiry in the communications; identifying, by the at least one processor, a main topic associated with the main inquiry; identifying, by the at least one processor, one or more side inquiries in the communications, wherein each side inquiry of the one or more side inquiries is introduced in the communications subsequent to introduction of the main inquiry; identifying, by the at least one processor, one or more side topics associated with the one or more side inquiries based on demographic characteristics of the user, wherein each side topic of the one or more side topics is associated with a side inquiry of the one or more side inquiries; determining, by the at least one processor, a confidence score for each side topic of the one or more side topics; composing, by the at least one processor, at least one message, wherein each message of the at least one message is related to a side topic of the one or more side topics having a confidence score above a threshold confidence score; presenting, by the at least one processor, the one or more side topics and the at least one message through a first portion of the service representative application; receiving, by the at least one processor, an indication of a selected message of the at least one message; and presenting, by the at least one processor, the selected message through a second portion of the service representative application during the service session.
“13. The method of claim 12, comprising: receiving, by the at least one processor, a command to present the selected message through the second portion of the service representative application, the command entered through the first portion of the service representative application; and presenting, by the at least one processor, the selected message through the second portion of the service representative application in response to receiving the command.
“14. The method of claim 12, comprising: retrieving, by the at least one processor, additional data associated with each side topic of the one or more side topics; based on the additional data, composing a plurality of candidate messages related to each side topic of the one or more side topics, wherein the plurality of candidate messages comprises the at least one message; and selecting, by the at least one processor, the at least one message to be presented from the plurality of candidate messages.
“15. The method of claim 14, wherein selecting, by the at least one processor, the at least one message includes: presenting, by the at least one processor, the plurality of candidate messages through the first portion of the service representative application; and receiving, by the at least one processor, a command provided through the service representative application to select the selected message from the plurality of candidate messages.
“16. The method of claim 12, wherein: the service session is a text chat session; and the selected message is presented as text in the text chat session.
“17. The method of claim 12, wherein presenting, by the at least one processor, the selected message through the second portion of the service representative application during the service session is performed autonomously by the at least one processor.”
There are additional claims. Please visit full patent to read further.
For the URL and additional information on this patent, see: Fujimoto, Yuibi. Intelligent agent for interactive service environments.
(Our reports deliver fact-based news of research and discoveries from around the world.)
Researchers Submit Patent Application, “Free Text De-Identification”, for Approval (USPTO 20210303791): Patent Application
CLASS ACTION ALERT: Kessler Topaz Meltzer & Check, LLP Reminds Waterdrop Inc. Shareholders of Securities Fraud Class Action Lawsuit
Advisor News
- Goldman Sachs, others weigh in on what’s ahead for the market in 2025
- How is consumers’ investing confidence impacting the need for advisors?
- Can a balance of withdrawals and annuities outshine the 4% rule?
- Economy ‘in a sweet spot’ but some concerns ahead
- Trump, Capitol allies likely looking at quick cryptocurrency legislation
More Advisor NewsAnnuity News
Health/Employee Benefits News
- Ask the Medicare Specialist
- Murphy, safely re-elected, attacks medical insures
- Office of Medicaid Policy and Planning Director to step down
- 5 of the most frustrating health insurer tactics and why they exist
- The business case for selling LTC insurance to small-business owners
More Health/Employee Benefits NewsLife Insurance News