Patent Application Titled “Intelligent Prediction Systems And Methods For Conversational Outcome Modeling Frameworks For Sales Predictions” Published Online (USPTO 20220012667): Allstate Insurance Company

2022 FEB 01 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Fiddler, Garrett (Northbrook, IL, US); Pripstein, Eric (Northbrook, IL, US), filed on July 13, 2020, was made available online on January 13, 2022.

The assignee for this patent application is Allstate Insurance Company (Northbrook, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Customer services representatives may attempt to sell a product and/or service through virtual signal recordable conversations such as text-based (e.g., text-messaging, email, etc.) and/or telephonic conversations. For example, insurance companies or other businesses may utilize human sales representatives to sell policies, services, or other goods. Natural language models may be employed to guide virtually engaging users to appropriate personnel and/or to generate a natural language output of the virtual signal recordable conversation such as an amount of times a particular word was used in the conversation. However, it may be difficult to determine an impact of any type of sale strategy used in the course of the conversation.”

In addition to obtaining background information on this patent application, NewsRx editors also obtained the inventors’ summary information for this patent application: “Embodiments of the present disclosure are directed to intelligent prediction systems and methods that predict the likelihood that a conversation will have a desired outcome (e.g., result in a binding sale indicative of a successful sale attempt) and provide the impact of each individual turn of the conversation at a point in time relative to the desired outcome and based on the overall conversation to the point in time. Accordingly, outputs of the intelligent prediction systems and methods described herein may allow customer service representatives to determine sale strategies based on analyzed conversations that aid in directing a conversation to a successful result of a binding sale.

“For example, according to an embodiment of the present disclosure, an intelligent prediction system may include one or more processors, one or more memory components communicatively coupled to the one or more processors, and machine-readable instructions stored in the one or more memory components. The machine-readable instructions cause the intelligent prediction system to perform at least the following when executed by the one or more processors: receive text data comprising a plurality of speaker turn segments of a transcription of a conversation between two or more individuals regarding a sale offer, each speaker turn segment of the plurality of speaker turn segments of the transcription representative of a turn in the conversation defined by associated with speech data of one of the two or more individuals, the plurality of speaker turn segments collectively representative of the conversation up to a point of time; vectorize each speaker turn segment of the text data to assign an associated numerical value to each speaker turn segment; generate, via a neural network prediction model, a point in time a bind probability representative of a likelihood of a successful outcome of the sale offer at the point in time based on (i) a speaker turn bind probability of a speaker turn segment at the point in time and (ii) memory data associated with the plurality of speaker turn segments up to the point in time; and generate, via the neural network prediction model, a speaker turn segment impact score at the point in time by subtracting an immediately preceding point in time bind probability from the point in time bind probability.

“According to another embodiment of the present disclosure, an intelligent prediction system may include one or more processors, one or more memory components communicatively coupled to the one or more processors, and machine-readable instructions stored in the one or more memory components. The machine-readable instructions cause the intelligent prediction system to perform at least the following when executed by the one or more processors: receive text data comprising a plurality of speaker turn segments of a transcription of a conversation between two or more individuals regarding a sale offer, each speaker turn segment of the plurality of speaker turn segments of the transcription representative of a turn in the conversation associated with speech data of one of the two or more individuals, the plurality of speaker turn segments collectively representative of the conversation up to a point of time; vectorize each speaker turn segment of the text data to assign an associated numerical value to each speaker turn segment; apply a loss function configured to minimize error to each speaker turn segment post vectorization; generate, via a neural network prediction model, a point in time bind probability representative of a likelihood of the successful outcome of the sale offer at the point in time based on (i) a speaker turn segment bind probability for each speaker turn segment at the point in time and (ii) memory data associated with the plurality of speaker turn segments up to the point in time; and generate, via the neural network prediction model, a speaker turn segment impact score at the point in time by subtracting an immediately preceding point in time bind probability from the point in time bind probability.

“In yet another embodiment, a method of conversational outcome prediction using an intelligent prediction system may include receiving, with one or more processors of the intelligent prediction system, text data comprising a plurality of speaker turn segments of a transcription of a conversation between two or more individuals regarding a sale offer, each speaker turn segment of the plurality of speaker turn segments of the transcription representative of a turn in the conversation associated with speech data of one of the two or more individuals, the plurality of speaker turn segments collectively representative of the conversation up to a point of time; vectorizing, with the one or more processors, each speaker turn segment of the text data to assign an associated numerical value to each speaker turn segment, generating, with a neural network prediction module; generating, via a neural network prediction model, a point in time bind probability representative of a likelihood of the successful outcome of the sale offer at the point in time based on (i) a speaker turn segment bind probability at the point in time and (ii) memory data associated with the plurality of speaker turn segments up to the point in time; and generating, via the neural network prediction model, a speaker turn segment impact score at the point in time by subtracting an immediately preceding point in time bind probability from the point in time bind probability.

“Although the concepts of the present disclosure are described herein with primary reference to insurance sales, it is contemplated that the concepts will enjoy applicability to any setting for purposes of intelligent prediction solutions, such as alternative business settings or otherwise, including and not limited to, non-insurance related sales (e.g., other service and/or product sales), such as through telephonic, web-based, and/or other voice-based transmission technologies.”

The claims supplied by the inventors are:

“1. An intelligent prediction system for conversational outcome prediction, comprising: one or more processors; one or more memory components communicatively coupled to the one or more processors; and machine-readable instructions stored in the one or more memory components that cause the intelligent prediction system to perform at least the following when executed by the one or more processors: receive text data comprising a plurality of speaker turn segments of a transcription of a conversation between two or more individuals regarding a sale offer, each speaker turn segment of the plurality of speaker turn segments of the transcription representative of a turn in the conversation associated with speech data of one of the two or more individuals, the plurality of speaker turn segments collectively representative of the conversation up to a point of time; vectorize each speaker turn segment of the text data to assign an associated numerical value to each speaker turn segment; generate, via a neural network prediction model, a point in time bind probability representative of a likelihood of a successful outcome of the sale offer at the point in time based on (i) a speaker turn segment bind probability of a speaker turn segment at the point in time and (ii) memory data associated with the plurality of speaker turn segments up to the point in time; and generate, via the neural network prediction model, a speaker turn segment impact score at the point in time by subtracting an immediately preceding point in time bind probability from the point in time bind probability.

“2. The intelligent prediction system of claim 1, further comprising: a display communicatively coupled to the one or more processors; wherein the machine-readable instructions further cause the intelligent prediction system to generate a point in time bind probability plot to graphically display the point in time bind probability at each turn of the conversation, and display the point in time bind probability plot on the display.

“3. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: identify one or more flag events corresponding to a predetermined sale technique; and analyze each speaker turn segment to identify the one or more flag events corresponding to the predetermined sale technique.

“4. The intelligent prediction system of claim 3, further comprising: a display communicatively coupled to the one or more processors, wherein the machine-readable instructions further cause the intelligent prediction system to: generate a point in time bind probability plot to graphically display the point in time bind probability at each turn of the conversation on the display; generate one or more markers associated with the one or more flag events that are identified at each turn in which the one or more flag events occurred; and provide a visual output on the display of the one or more markers on the point in time bind probability plot.

“5. The intelligent prediction system of claim 3, wherein the one or more flag events comprise at least one of: a customer service representative asking for a sale; a customer asking for a sale; and the customer service representative offering a discount.

“6. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: receive, via an audio capture module, audio data of the conversation; transcribe the audio data of the conversation from the audio capture module into the text data for each speaker turn segment.

“7. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: receive customer data from one or more customer information sources; determine a starting bind probability based on the customer data; and generate the point in time bind probability representative of the likelihood of the successful outcome of the sale offer at the point in time based on the starting bind probability.

“8. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: determine an average bind probability based on one or more stored conversations; and determine a set of performance metrics of a participant in the conversation, each performance metric of the participant determined based on a participant performance score in the conversation at each turn associated with the participant relative to the average bind probability; generate a feedback performance metric for the participant based on the set of performance metrics; compare in a comparison the average bind probability to the feedback performance metric of the participant in the conversation; and generate a positive participant performance score when the comparison is positive such that the feedback performance metric is above the average bind probability.

“9. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: apply a padding function to each speaker turn segment with the vectorization such that each speaker turn segment comprises an equivalent segment length, wherein the padding function comprises addition of zeros to adjust each speaker turn segment to the equivalent segment length.

“10. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: apply a loss function to each speaker turn segment post vectorization such that each speaker turn segment comprises a weight adjustment to achieve a weight adjustment value, wherein the loss function comprises adjusting each speaker turn segment based on the weight adjustment to achieve the weight adjustment value.

“11. The intelligent prediction system of claim 1, wherein the machine-readable instructions further cause the intelligent prediction system to: train the neural network prediction model based on a plurality of data sets of pre-stored conversations, wherein the neural network prediction model is trained to generate the point in time bind probability for the conversation based on the plurality of data sets of pre-stored conversations.

“12. An intelligent prediction system for conversational outcome prediction, comprising: one or more processors; one or more memory components communicatively coupled to the one or more processors; and machine-readable instructions stored in the one or more memory components that cause the intelligent prediction system to perform at least the following when executed by the one or more processors: receive text data comprising a plurality of speaker turn segments of a transcription of a conversation between two or more individuals regarding a sale offer, each speaker turn segment of the plurality of speaker turn segments of the transcription representative of a turn in the conversation associated with speech data of one of the two or more individuals, the plurality of speaker turn segments collectively representative of the conversation up to a point of time; vectorize each speaker turn segment of the text data to assign an associated numerical value to each segment; apply a loss function configured to minimize error to each speaker turn segment post vectorization; generate, via a neural network prediction model, a point in time bind probability representative of a likelihood of a successful outcome of the sale offer at the point in time based on (i) a speaker turn segment bind probability of a speaker turn segment at the point in time and (ii) memory data associated with the plurality of speaker turn segments up to the point in time; and generate, via the neural network prediction model, a speaker turn segment impact score at the point in time by subtracting an immediately preceding point in time bind probability from the point in time bind probability.

“13. The intelligent prediction system of claim 12, wherein the machine-readable instructions further cause the intelligent prediction system to: apply a padding function to each speaker turn segment with the vectorization such that each speaker turn segment comprises an equivalent segment length, wherein the padding function comprises addition of zeros to adjust each speaker turn segment to the equivalent segment length.

“14. The intelligent prediction system of claim 12, wherein the machine-readable instructions further cause the intelligent prediction system to: apply the loss function to each speaker turn segment post vectorization such that each speaker turn segment comprises a weight adjustment to achieve a weight adjustment value, wherein the loss function comprises adjusting each speaker turn segment based on the weight adjustment to achieve the weight adjustment value.

“15. The intelligent prediction system of claim 12, wherein the machine-readable instructions further cause the intelligent prediction system to: train the neural network prediction model based on a plurality of data sets of pre-stored conversations, wherein the neural network prediction model is trained to generate the point in time bind probability for the conversation based on the plurality of data sets of pre-stored conversations.”

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

For more information, see this patent application: Fiddler, Garrett; Pripstein, Eric. Intelligent Prediction Systems And Methods For Conversational Outcome Modeling Frameworks For Sales Predictions. Filed July 13, 2020 and posted January 13, 2022. Patent URL: https://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220220012667%22.PGNR.&OS=DN/20220012667&RS=DN/20220012667

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