Patent Application Titled “Natural Language Processing Parsimonious Question Generator” Published Online (USPTO 20220164549): Patent Application – InsuranceNewsNet

JUNE 13, 2022 (NewsRx) — By a News Reporter – Staff News Editor at Daily Insurance News — According to reports from washington d.c.by NewsRx reporters, a patent application from inventors Bardhan, Ashok (El Cerrito, CaliforniaWe); GuptaAvaneendra (Cupertino, CaliforniaWe), filed on September 17, 2021was posted on May 26, 2022.

No assignee for this patent application has been named.

Journalists obtained the following quote from the background information provided by the inventors: “It is common for an applicant to answer many redundant questions when requesting a service (e.g. life insurance, loan, services medical, etc). For example, a life insurance application may require the user to answer dozens of questions, sometimes reaching up to a hundred. In addition to personal and physical descriptive data, questions may involve a detailed review of medical history, hobbies and activities, general lifestyle questions, as well as questions relating to family medical history, parents and relatives. Usually, any answer indicating that the applicant has suffered from an illness in the past usually leads them down whole tracks of other ancillary and supplementary questions, detailing visits to doctors, hospitals, treatments, medications, etc. The general universe of questions, the order in which I asked them, the sequencing and layout are common to most operators in this field and do not change from one candidate to another, regardless of their age, gender, health status, or any other factor that can materially affect overall health status, longevity prospects, and future health trajectory. These questions can often be asked through a computer interface such as a web browser and/or chat bot agent. As a result, improvements to the order, question types, and question reduction are desired in order to increase candidate engagement and improve the overall candidate experience. The PQG is an operational tool in a user journey of the future, saving time and friction, increasing conversion and satisfaction through a personalized set of questions on the life insurance application journey, depending on the age, gender and location of the applicant.

In addition to obtaining general information about this patent application, the editors of NewsRx have also obtained the inventors’ summary information for this patent application: “A computer-based method for natural language generation and management of a parsimonious questions includes the step of sorting all the counties in United States from high to low mortality rate by cause of death for each age group and sex to generate a set of sorted tables. For a specified subject and with an autonomous agent in natural language, the method generates a set of parsimonious questions. The parsimonious question set is based on a county, age group, and gender of an individual nominated to answer the parsimonious question set. The method sorts the set of parsimonious questions in descending order of personalized importance to the individual as described by age, gender, and location. With an autonomous natural language generator agent, the method asks the individual a subset of the set of parsimonious questions in the optimized order. The method detects that a statistical threshold has been reached. The method prevents the natural language generator autonomous agent from asking further questions in a remainder of the sparse question set when the statistical threshold has been crossed.

“The figures described above are a representative set and are not exhaustive with regard to the embodiment of the invention.”

The claims provided by the inventors are:

“1. A computerized method of natural language generation and management of a parsimonious question generator comprising: sorting all counties in United States from high to low mortality rate by cause of death for each age group and sex to generate a set of sorted tables; for a specified subject and with a natural language autonomous agent: generating a set of parsimonious questions, the set of parsimonious questions being based on a county, age group and gender of an individual designated to answer the set of parsimonious questions; sort the set of parsimonious questions in descending order of importance appropriate to the individual as described by age, gender and location; with an autonomous natural language generator agent, ask the individual a subset of the set of parsimonious questions in the optimized order; detecting that a statistical threshold has been reached; and preventing the natural language generator autonomous agent from asking further questions in a remainder of the parsimonious question set when the statistical threshold has been crossed.

A computer-based method according to claim 1, wherein the set of parsimony generated questions are asked via chatbot functionality in descending order of potential contribution to a future cause of death.

A computer-based method according to claim 1, further comprising: using a machine learning algorithm to optimize the sorting of the set of sorted tables.

“4. A computer-based method according to claim 3, wherein the machine learning algorithm comprises a sorting algorithm.

A computer-based method according to claim 4, wherein the machine learning algorithm generates a question sorting model with a training data set comprising a first historical set of county mortality data for each group of age and each gender.

A computer-based method according to claim 5, wherein the machine learning algorithm uses a second historical set of county mortality data for each age group and gender to validate the question sorting model.

A computer-based method according to claim 6, further comprising: using the question sorting mode to sort questions based on county, age group and gender of a individual designated to answer the set of parsimonious questions to maximize a maximum percentage of causes of death, which are obtained in a minimum number of questions.

A computer-based method according to claim 7, wherein the natural language autonomous agent varies a phraseology of the parsimonious set of questions to increase a commitment of the designated individual to answer the parsimonious set of questions.

“9. A computerized method according to claim 7, wherein the natural language autonomous agent adjusts a vocabulary, and a syntax of the set of parsimonious questions based on a common vocabulary for an age of the individual and a departmental dialect of a department where the individual lives.

“10. The computerized method of 7, in which the natural language autonomous agent obtains the mortality rate by cause of death for each age group and sex for each county of United States from a plurality of publicly available databases.

“11. A computerized system comprising: a processor configured to execute instructions; a memory containing instructions when executed on the processor, causes the processor to perform operations which: sort all counties in United States from high to low mortality rate by cause of death for each age group and sex to generate a set of sorted tables; for a specified subject and with a natural language autonomous agent: generating a set of parsimonious questions, the set of parsimonious questions being based on a county, age group, and gender of an individual designated to answer the set of parsimonious questions; sort the set of parsimonious questions in descending order of importance appropriate to the individual as described by age, gender and location; with an autonomous natural language generator agent, ask the individual a subset of the set of parsimonious questions in the optimized order; detecting that a statistical threshold has been reached; and preventing the natural language generator autonomous agent from asking further questions in a remainder of the parsimonious question set when the statistical threshold has been crossed.

A computerized system according to claim 11, wherein the set of parsimony generated questions are asked via chatbot functionality in descending order of potential contribution to a future cause of death.

“13. The computerized system of claim 11, wherein the memory contains instructions which, when executed on the processor, cause the processor to perform operations which: use a machine learning algorithm to optimize the sorting of the set of sorted tables.

“14. A computerized system according to claim 13, wherein the machine learning algorithm comprises a sorting algorithm.

“15. The computerized system of claim 14, wherein the machine learning algorithm generates a question sorting model with a training data set comprising a first historical set of county mortality data for each group of age and each gender.

The computerized system of claim 15, wherein the machine learning algorithm uses a second historical set of county mortality data for each age group and gender to validate the question sorting model.

“17. The computerized system of claim 16, wherein the memory contains instructions which, when executed on the processor, cause the processor to perform operations which: use the question sort mode to sort questions on the basis of a county, age group and gender of a designated individual to answer the set of parsimonious questions to maximize a maximum percentage of causes of death obtained in a minimum of questions.

The computerized system of claim 17, wherein the natural language autonomous agent varies a phraseology of the parsimonious set of questions to increase an engagement of the designated individual to answer the parsimonious set of questions.

“19. The computerized system of 18, in which the natural language autonomous agent obtains the death rate by cause of death for each age group and each sex for each county of United States from a plurality of publicly available databases.

“20. A computer system according to claim 19, wherein a statistical threshold is generated based on historical volatility, the goodness of fit of the models, and the varying nature of the leading causes of death historically.”

For more information, see this patent application: Bardhan, Ashok; Gupta, Avaneendra. Parsimonious natural language processing question generator. Class September 17, 2021 and posted May 26, 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=%2220220164549%22.PGNR.&OS= DN/20220164549&RS=DN/20220164549

(Our reports provide factual information on research and discoveries from around the world.)

Comments are closed.