Patent Issued for Natural language processing platform for automated training and performance evaluation (USPTO 11861540): Allstate Insurance Company

2024 JAN 18 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Dunn, Ryan (Grayslake, IL, US), LaVigne, Michael A. (Prospect Heights, IL, US), Phillabaum, Ben (Lafayette, IN, US), filed on February 17, 2020, was published online on January 2, 2024.

The patent’s assignee for patent number 11861540 is Allstate Insurance Company (Northbrook, Illinois, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Aspects of the disclosure relate to enhanced processing systems for performing natural language processing. Many organizations and individuals evaluate employee performance to identify strong and/or weak performers, provide training, and drive revenue. In many instances, however, such performance evaluations may be subjective, and may result in generic best practices that are not tailored to the individual. Furthermore, use of such generic evaluations results in technical challenges of identifying, in real time, root causes of performance differences and identifying feedback to improve deficient performance accordingly.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “Aspects of the disclosure provide effective, efficient, scalable, and convenient technical solutions that address and overcome the technical problems associated with performance evaluation and training. In accordance with one or more arrangements discussed herein, a computing platform having at least one processor, a communication interface, and memory may determine, based on one or more of a plurality of audio transcription files, each associated with one of a plurality of individuals, a model for dynamic performance evaluation and training. In these arrangements, the model may be dynamically updated as additional audio transcription files are received. The computing platform may receive an additional audio transcription file associated with a first individual of the plurality of individuals. The computing platform may analyze the additional audio transcription file using natural language processing and the model, which may result in one or more proficiency scores, each corresponding to an event in the additional audio transcription file. Based on the one or more proficiency scores, the computing platform may calculate an overall proficiency score. Based on the one or more proficiency scores, the computing platform may identify one or more areas for improvement associated with the first individual. Based on the one or more areas for improvement, the computing platform may determine performance feedback tailored to the first individual. Using the performance feedback tailored to the first individual, the computing platform may generate a feedback interface and may send, to a user device associated with the first individual, the feedback interface.

“In one or more instances, the computing platform may receive, prior to calculating the overall proficiency score, a second plurality of audio transcription files corresponding to the first individual. In these instances, the computing platform may calculate the overall proficiency score by analyzing the second plurality of audio transcription files using natural language processing and the model. In these instances, the one or more proficiency scores may be based, at least in part, on the analysis of the second plurality of audio transcription files.

“In one or more examples, the computing platform may analyze the additional audio transcription file and the second plurality of audio transcription files by analyzing one or more of: words spoken by the first individual, a total duration of silence, an average sentence length, or an amount of time the first individual spoke in comparison to a second individual. The computing platform may analyze the one or more of the plurality of audio transcription files, which may result in one or more additional proficiency scores, each corresponding to an event in the one or more of the plurality of audio transcription files. In addition, the computing platform may compare the proficiency scores to the one or more additional proficiency scores to determine a performance comparison between the first individual and the plurality of individuals.

“In one or more instances, the computing platform may generate, using the one or more proficiency scores and the overall proficiency score, a manager dashboard interface. The computing platform may send, to a user device associated with a manager of the first individual, the manager dashboard interface.

“In one or more arrangements, the computing platform may generate one or more feedback interface commands and one or more manager dashboard interface commands. The computing platform may send, to the user device associated with the first individual, the one or more feedback interface commands, which may cause the user device associated with the first individual to display the feedback interface. The computing platform may send, to the user device associated with the manager of the first individual, the one or more manager dashboard interface commands, which may cause the user device associated with the manager of the first individual to display the manager dashboard interface.”

The claims supplied by the inventors are:

“1. A computing platform, comprising: at least one processor; a communication interface communicatively coupled to the at least one processor; and memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: determine, based on one or more of a plurality of audio transcription files, each associated with one of a plurality of individuals, a model for dynamic performance evaluation and training, wherein the model is a machine learning model that is dynamically updated as additional audio transcription files are received; receive an additional audio transcription file associated with a first individual of the plurality of individuals; analyze the additional audio transcription file using natural language processing and the machine learning model, wherein the analysis results in one or more proficiency scores for one or more events in the additional audio transcription file, wherein: the one or more events include at least one of: asking for a sale, making a multiline offering, handling a sales objection, or closing a sale, the one or more proficiency scores for the one or more events indicate a proportion of occurrences of the one or more events in audio transcription files for the first individual, the one or more proficiency scores for the one or more events is adjusted when a successful outcome is determined from the analysis of the additional audio transcription file, and one or more weights are assigned to the one or more proficiency scores for the one or more events, wherein a first weight of the one or more weights is assigned to a first event of the one or more events in a first geographic region and a second weight is assigned to the first event in a second geographic region, the first weight is greater than the second weight; calculate, based on the one or more proficiency scores and the one or more weights assigned to the one or more proficiency scores, an overall proficiency score; identify a learning style of the first individual based on the analysis using the natural language processing and the machine learning model; identify, based on the one or more proficiency scores, one or more areas for improvement associated with the first individual; determine, based on the one or more areas for improvement, performance feedback tailored to the first individual, wherein the performance feedback is based on the learning style of the first individual; generate, using the performance feedback tailored to the first individual, a feedback interface; send, to a user device associated with the first individual, the feedback interface; and dynamically modify the machine learning model for subsequent performance evaluation and training.

“2. The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: receive, prior to calculating the overall proficiency score, a second plurality of audio transcription files corresponding to the first individual, wherein calculating the overall proficiency score comprises analyzing the second plurality of audio transcription files using natural language processing and the machine learning model, and wherein the one or more proficiency scores are based, at least in part, on the analysis of the second plurality of audio transcription files.

“3. The computing platform of claim 2, wherein analyzing the additional audio transcription file and the second plurality of audio transcription files comprises analyzing one or more of: words spoken by the first individual, a total duration of silence, an average sentence length, or an amount of time the first individual spoke in comparison to a second individual.

“4. The computing platform of claim 2, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: automatically analyze the one or more of the plurality of audio transcription files, wherein the analysis results in one or more additional proficiency scores, each corresponding to an event in the one or more of the plurality of audio transcription files; and compare the proficiency scores to the one or more additional proficiency scores.

“5. The computing platform of claim 4, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: generate, using the one or more proficiency scores and the overall proficiency score, a manager dashboard interface; and send, to a user device associated with a manager of the first individual, the manager dashboard interface.

“6. The computing platform of claim 5, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: generate one or more feedback interface commands and one or more manager dashboard interface commands; send, to the user device associated with the first individual, the one or more feedback interface commands, wherein sending the one or more feedback interface commands causes the user device associated with the first individual to display the feedback interface; and send, to the user device associated with the manager of the first individual, the one or more manager dashboard interface commands, wherein sending the one or more manager dashboard interface commands causes the user device associated with the manager of the first individual to display the manager dashboard interface.

“7. The computing platform of claim 6, wherein the manager dashboard interface includes: for each of the first individual and the plurality of individuals, one or more of: a representative identifier, a close rate (CR), a linked quote percentage, a benchmark CR, and a comparison of the CR to the benchmark CR.

“8. The computing platform of claim 7, wherein the benchmark CR indicates an average close rate of individuals who both: are located in a geographic area associated with the first individual, and are associated with a job title associated with the first individual.

“9. The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: determine an impact on performance caused by the performance feedback tailored to the first individual; and dynamically modify, based on the impact on performance, the machine learning model for dynamic performance evaluation and training.

“10. The computing platform of claim 1, wherein the feedback interface is generated in real time.

“11. A method comprising: at a computing platform comprising at least one processor, a communication interface, and memory: determining, based on one or more of a plurality of audio transcription files, each associated with one of a plurality of individuals, a model for dynamic performance evaluation and training, wherein the model is a machine learning model that is dynamically updated as additional audio transcription files are received; receiving an additional audio transcription file associated with a first individual of the plurality of individuals; analyzing the additional audio transcription file using natural language processing and the machine learning model, wherein the analysis results in one or more proficiency scores for one or more events in the additional audio transcription file, wherein: the one or more events include at least one of: asking for a sale, making a multiline offering, handling a sales objection, or closing a sale, the one or more proficiency scores for the one or more events indicate a proportion of occurrences of the one or more events in audio transcription files for the first individual, the one or more proficiency scores for the one or more events is adjusted when a successful outcome is determined from the analysis of the additional audio transcription file, and one or more weights are assigned to the one or more proficiency scores for the one or more events, wherein a first weight of the one or more weights is assigned to a first event of the one or more events in a first geographic region and a second weight is assigned to the first event in a second geographic region, the first weight is greater than the second weight; identifying a learning style of the first individual based on the analysis using the natural language processing and the machine learning model; identifying, based on the one or more proficiency scores, one or more areas for improvement associated with the first individual; determining, based on the one or more proficiency scores, performance feedback tailored to the first individual, wherein the performance feedback is based on the learning style of the first individual; generating, using the performance feedback tailored to the first individual, a feedback interface; sending, to a user device associated with the first individual, the feedback interface; and dynamically modifying the machine learning model for subsequent performance evaluation and training.

“12. The method of claim 11, further comprising: receiving a plurality of additional audio transcription files corresponding to the first individual, calculating, based on the one or more proficiency scores, an overall proficiency score based, at least in part, on analyzing the plurality of the additional audio transcription files using natural language processing and the machine learning model.

“13. The method of claim 12, wherein: analyzing the additional audio transcription file and the plurality of additional audio transcription files comprises analyzing one or more of: words spoken by the first individual, a total duration of silence, an average sentence length, or an amount of time the first individual spoke in comparison to a second individual.”

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

For additional information on this patent, see: Dunn, Ryan. Natural language processing platform for automated training and performance evaluation. U.S. Patent Number 11861540, filed February 17, 2020, and published online on January 2, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11861540)&db=USPAT&type=ids

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