Patent Issued for Disclosure quality assurance (USPTO 11810042): United Services Automobile Association

2023 NOV 23 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Csabi, Rachel Elizabeth (Frisco, TX, US), King, Hollie Ilene (Frisco, TX, US), Kwak, Victor (Frisco, TX, US), Lake, Zachery C. (Aubrey, TX, US), Rai, Yogen (Plano, TX, US), Taylor, Samantha Elizabeth (Frisco, TX, US), Wheeler, Nicholas C. (The Colony, TX, US), filed on October 30, 2020, was published online on November 7, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11810042 is assigned to United Services Automobile Association (San Antonio, Texas, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “The present disclosure relates generally to disclosure statements. More specifically, the present disclosure relates to providing and/or rating context dependent disclosure statements to a customer.

“This section is intended to introduce the reader to various aspects of art that may be related to various aspects of the present disclosure, which are described and/or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. Accordingly, it may be understood that these statements are to be read in this light, and not as admissions of prior art.

“Most business organizations include a service in which a customer may contact a business agent to address their questions and concerns. The service may allow the customer to contact the business agent via multiple communication methods, such as by e-mail, telephone, text, and/or online chat. The telephone communication may involve the agent actively listening to the customer and reading one or more disclosures that correspond to the conversation. By way of example, the agent may read a default disclosure at the onset of the conversation, in which the disclosure may indicate that the conversation will be recorded. However, as the conversation progresses, the agent may read additional disclosures to the customer based on the context of the conversation. Each of the additional disclosures may be associated with one or more conversation topics. As such, improved systems and methods for efficiently and effectively determining disclosure statements to be provided to the customer based on the context of the conversation may be beneficial.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “One or more specific embodiments of the present disclosure are described above. In an effort to provide a concise description of these embodiments, all features of an actual implementation may not be described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers’ specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. Moreover, it should be appreciated that such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure.

“When introducing elements of various embodiments of the present disclosure, the articles “a,” “an,” and “the” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. Additionally, it should be understood that references to “one embodiment” or “an embodiment” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

“As mentioned above, business organizations may often offer a customer service in which a customer may communicate with a customer service agent to address questions or concerns regarding the business organization. One method of communication may include the customer calling a contact service number to speak with the agent (e.g., administrative agent and/or a computer generated intelligent virtual agent).

“During the call, the agent may read one or more disclosures to the customer. The disclosure may be generic and/or context specific. For example, regardless of the topic, the agent may initially read a disclosure indicating that the conversation may be recorded, the customer may be contacted in the future regarding the call, and so forth. However, the customer may be concerned with a particular topic of conversation and the topic may be one in which the business organization wants the agent to read a particular disclosure. Moreover, the conversation topic may include subtopics, such that additional disclosures associated with the subtopics should also be read by the agent.

“To read the particular disclosures to the customer, the agent may search through a library of disclosures. The library may be sorted by topic and/or subtopics, and as such, the agent may have to search through multiple layers or folders within the library to locate the particular disclosures. During this search time, the customer may discuss additional topics resulting in additional disclosures to be read. The search time may also be time consuming and take away from the customer-agent conversation, resulting in a less interactive conversation. Further, in some instances disclosures may be overlooked, as customer service representatives may be unaware of particular disclosures that should be provided based upon the context of the call.”

The claims supplied by the inventors are:

“1. A customer service system, comprising: an agent device associated with an agent; and a monitoring system, comprising: a memory configured to store instructions; and a processor configured to execute the instructions, wherein the instructions, when executed by the processor, cause the monitoring system to: monitor a conversation between a customer device associated with a customer and the agent device to identify a context of the conversation; identify, via a first machine learning algorithm, a disclosure notice based at least in part on the context of the conversation, wherein the first machine learning algorithm comprises a first neural network, a first Hidden Markov Model, or a combination thereof, wherein the first machine learning algorithm determines a first pattern, a first threshold number of keywords, or a combination thereof, to identify the disclosure notice as associated with the context of the conversation, wherein the first machine learning algorithm uses a first mathematical model based on training data, a first statistical model based on training data, or a combination thereof, wherein the disclosure notice comprises an indication of a disclosure to be read in light of the context of the conversation; iteratively train the first machine learning algorithm using the training data; provide a first indication of the disclosure notice to the agent device, wherein the agent device is configured to provide the first indication to the agent, by: receiving the first indication from the monitoring system; and rendering a graphical indication of the disclosure notice in a first graphical user interface (GUI) of the agent device based on the first indication; provide the disclosure notice to a second machine learning algorithm; monitor and evaluate, via the second machine learning algorithm, a disclosure provision of the disclosure notice from the agent to the customer, wherein the second machine learning algorithm uses past disclosure readings to determine a second pattern, a second threshold number of keywords, or a combination thereof, to assign a score to the disclosure provision; and provide a second indication of a disclosure provision feedback regarding evaluation of the disclosure provision to the agent, wherein the agent device is configured to provide the second indication, by: receiving the second indication from the monitoring system; and rendering the disclosure provision feedback in a second GUI of the agent device based on the second indication.

“2. The customer service system of claim 1, wherein the first pattern, the first threshold, or the combination thereof, is based at least in part on one or more keywords, a weight associated with the one or more keywords, spacing between the one or more keywords, a combination of the one or more keywords, or any combination thereof.

“3. The customer service system of claim 1, wherein the conversation comprises an ongoing conversation, a recorded conversation, or a combination thereof.

“4. The customer service system of claim 1, wherein the monitoring system comprises one or more audio sensors to detect audio of the conversation, one or more display sensors to detect the first GUI on a display associated with the agent device, or a combination thereof.

“5. The customer service system of claim 1, wherein the second machine learning algorithm references a database comprising a word dictionary, a thesaurus, or a combination thereof, to determine the disclosure provision feedback.

“6. The customer service system of claim 1, wherein the processor determines one or more words spoken by the agent using phonemes in a context of other phonemes, machine learning, and a library of known words, phrases, and sentences.

“7. The customer service system of claim 1, wherein the first pattern, the first threshold number of keywords, or the combination thereof, is based at least in part on one or more keywords, a weight associated with the one or more keywords, spacing between the one or more keywords, a combination of the one or more keywords, or any combination thereof.

“8. The customer service system of claim 1, wherein the second pattern, the second threshold number of keywords, or the combination thereof, is based at least in part on a specific reading speed of keywords when reading the disclosure notice, an annunciation of keywords, skipped words, or a combination thereof.

“9. The customer service system of claim 1, wherein the second machine learning algorithm comprises a second neural network, a second Hidden Markov Model, or a combination thereof, wherein the second machine learning algorithm uses a second mathematical model based on training data, a second statistical model based on training data, or a combination thereof.

“10. A method, comprising: monitoring a conversation between a customer device associated with a customer and an agent device associated with an agent in a customer service system to identify a context of the conversation; identifying, via a first machine learning algorithm, a disclosure notice based at least in part on the context of the conversation, wherein the first machine learning algorithm comprises a neural network, a Hidden Markov Model, or a combination thereof, wherein the first machine learning algorithm determines a first pattern, a first threshold number of keywords, or a combination thereof, to identify the disclosure notice as associated with the context of the conversation, wherein the first machine learning algorithm uses a first mathematical model based on training data, a first statistical model based on training data, or a combination thereof, wherein the disclosure notice comprises an indication of a disclosure to be read in light of the context of the conversation; iteratively training the first machine learning algorithm using the training data; providing a first indication of the disclosure notice to the agent device, wherein the agent device is configured to provide the first indication to the agent, by: receiving the first indication from a monitoring system; and rendering the disclosure notice in a first graphical user interface (GUI) of the agent device based on the first indication; providing the disclosure notice to a second machine learning algorithm; monitoring a disclosure provision of the disclosure from the agent to the customer; evaluating, via the second machine learning algorithm, the disclosure provision to identify whether the disclosure provision passes or fails a threshold quality level, wherein the second machine learning algorithm determines a second pattern, a second threshold number of keywords, or a combination thereof, to score the disclosure provision; and providing a second indication of a disclosure provision feedback regarding evaluation of the disclosure provision to the agent, by: receiving the second indication from the monitoring system; and rendering the disclosure provision feedback in a second GUI of the agent device based on the second indication.

“11. The method of claim 10, wherein the second pattern, the second threshold number of keywords, or the combination thereof, is based at least in part on factors comprising a reading of one or more keywords, annunciation of the one or more keywords, percentage or number of words read from a total number of words in the disclosure notice, percentage or number of substituted words that provide similar effect as original words, or any combination thereof.

“12. The method of claim 11, comprising: monitoring an action performed by the customer after the disclosure provision to identify an understanding measurement indicative of whether the customer understood the disclosure provision; and scoring the disclosure provision based upon the understanding measurement.

“13. The method of claim 10, wherein the evaluation comprises a scoring, the scoring comprising a percentage indication.

“14. The method of claim 10, wherein the disclosure provision feedback comprises a recommendation, a score detail, or a combination thereof.

“15. The method of claim 14, wherein the score detail comprises a plurality of individual scores of the disclosure provision each corresponding to a plurality of factors.”

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

URL and more information on this patent, see: Csabi, Rachel Elizabeth. Disclosure quality assurance. U.S. Patent Number 11810042, filed October 30, 2020, and published online on November 7, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11810042)&db=USPAT&type=ids

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