Patent Issued for Methods And Systems For Ranking Leads Based On Given Characteristics (USPTO 10,860,593)

2020 DEC 22 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- Massachusetts Mutual Life Insurance Company (Springfield, Massachusetts, United States) has been issued patent number 10,860,593, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Ross, Gareth (Amherst, MA); Walker, Tricia (East Hampton, MA).

This patent was filed on July 9, 2019 and was published online on December 21, 2020.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Leads generation or acquisition is one of the most important tools for boosting sales in a company. The use of leads allows buyers to request information from businesses that offer a product or service they are interested in acquiring while enabling companies to offer their products or services to individuals with a higher propensity to close a transaction.

“Although sales leads offer an opportunity to create value for a company, there are some challenges for its efficient utilization by a business. For example, when companies generate leads from a variety of sources, often the sources providing the leads do not provide enough information about the quality of the leads generated. This can result in an agent to wasting time, effort, and financial resources by establishing contact with a lead that may not be financially ready or interested in purchasing a service and/or product.

“For the aforementioned reasons, there is a need for a method and system that provides a company with insight about the quality of leads so that the company can focus its efforts and resources on the most promising leads.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “A method for ranking and appraising leads according to their quality is disclosed. In one embodiment, a system architecture allowing the method to operate is disclosed. The system architecture includes one or more client computing devices, an analytical engine, an external data sources database, an internal database and a network connection. In this embodiment, the analytical engine is a software module implemented in one or more computing devices. Further to this embodiment, the analytical engine includes a ranking module and a price modeling module. In one embodiment, the ranking module retrieves information related to a set of leads in order to rank them based on their quality. Afterwards, the price modeling module determines a floor price based on said ranking and based on internal and external valuation information. In some embodiments, the analytical engine stores the solutions derived from the aforementioned software modules in the internal database for it to be available to other software modules operating within a systems’ architecture configured to rank and auction leads. Additionally, the results stored at the internal database are employed for future analysis using a client computer device.

“In one embodiment, a computer-implemented method for ranking leads, comprises collecting, by a computer, lead information related to one or more leads; classifying, by the computer, lead information into categories of lead information; receiving, by the computer, from a computer of an agent a selection of a first category of lead information and an attribute of the first category; filtering, by the computer, the lead information to obtain a set of filtered lead information comprising only the lead with the selected attribute; determining, by the computer, a set of attributes associated with the lead from the filtered lead information; assigning, by the computer, a score to each attribute associated with the lead from the filtered lead information based on a measure of how each attribute satisfies a predetermined set of criteria; calculating, by the computer, a quality score by computing the mean score for each lead based on the each scored attribute; ranking, by the computer, each lead based on the quality score; and associating, by the computer, the lead information with the ranked leads and the quality score.

“In another embodiment, a system for ranking leads comprises a computer processor; a memory containing a program that, when executed by the computer processor, is configured to perform an operation comprising collecting, by the computer processor, lead information related to one or more leads; classifying, by the computer processor, lead information into categories of lead information; receiving, by the computer processor, from a computer of an agent a selection of a first category of lead information and an attribute of the first category; filtering, by the computer processor, the lead information to obtain a set of filtered lead information comprising only the lead with the selected attribute; determining, by the computer processor, a set of attributes associated with the lead from the filtered lead information; assigning, by the computer processor, a score to each attribute associated with the lead from the filtered lead information based on a measure of how each attribute satisfies a predetermined set of criteria; calculating, by the computer processor, a quality score by computing the mean score for each lead based on the each scored attribute; ranking, by the computer processor, each lead based on the quality score; and associating, by the computer processor, the lead information with the ranked leads and the quality score.

“In one embodiment, a computer-implemented method for leads appraisal, comprises collecting, by a computer, lead information related to one or more leads; filtering, by the computer, the lead information to obtain a set of filtered lead information comprising a ranking associated to the one or more leads, internal valuation information, and external valuation information; determining, by the computer, one or more categories defined by the ranking associated to the one or more leads; defining, by the computer, a floor price for the set of leads associated to each rank category based on internal and external valuation information.

“In another embodiment, a system for leads appraisal comprises a computer processor; a memory containing a program that, when executed by the computer processor, is configured to perform an operation comprising collecting, by the computer processor, lead information related to one or more leads; filtering, by the computer processor, the lead information to obtain a set of filtered lead information comprising a ranking associated to the one or more leads, internal valuation information, and external valuation information; determining, by the computer processor, one or more categories defined by the ranking associated to the one or more leads; defining, by the computer processor, a floor price for the set of leads associated to each rank category.

“Numerous other aspects, features and benefits of the present disclosure may be made apparent from the following detailed description taken together with the drawing figures.”

The claims supplied by the inventors are:

“What is claimed is:

“1. A server-implemented method comprising: periodically scanning, by a server, one or more databases to extract lead information associated with a set of leads; upon receiving a lead attribute from a computer of an agent, filtering, by the server, the lead information to obtain a set of filtered lead information comprising a first subset of leads from the set of leads containing the lead attribute; executing, by the server, a machine-learning model to calculate a score for each lead within the subset of leads based on a learning dataset comprising the lead information, the score corresponding to a likelihood of each lead converting to a customer; periodically querying, by the server, the one or more databases to receive modified data associated with each lead; iteratively updating, by the server, the learning dataset of the machine-learning model based on the modified data associated with each lead, wherein the machine-learning model is configured to use an updated learning dataset each time the machine-learning model is executed after the learning dataset is updated; determining, by the server, a second subset of leads from the first subset of leads having the score that satisfies a threshold; and calculating, by the server, a minimum auction price for the second subset of leads based on previous auctions; updating, by the server, a graphical user interface of a computer of an agent with the minimum auction price and ranking information associated with the second subset of leads, wherein each lead of the second subset of leads is ranked based on their corresponding score.

“2. The server-implemented method of claim 1, further comprising determining, by the server, the second subset of leads from the first subset of leads that imply a highest potential value of each lead based on their corresponding score.

“3. The server-implemented method of claim 2, further comprising triaging, by the server, each ranked lead of the second subset of leads that imply the highest potential value of each lead based on the score.

“4. The server-implemented method of claim 1, wherein the machine-learning model utilizes a naive bayes technique to calculate the score for each lead.

“5. The server-implemented method of claim 1, wherein the machine-learning model utilizes a support vector machine to calculate the score for each lead.

“6. The server-implemented method of claim 1, wherein the machine-learning model utilizes a random forest technique to calculate the score for each lead.

“7. The server-implemented method of claim 1, wherein the machine-learning model utilizes a logistic regression technique to calculate the score for each lead.

“8. The server-implemented method of claim 1, further comprising scanning, by the server, one or more social networking web documents associated with the set of leads within the one or more databases.

“9. The server-implemented method of claim 8, further comprising extracting, by the server, the lead information from the one or more social networking web documents.

“10. The server-implemented method according to claim 9, wherein the lead information comprises at least one of: identity, age, ethnicity, place of residence, number of dependent persons, identity of dependent persons, expenditure, savings, approximate market value of assets and their composition, education, professional situation, contact information, shopping preferences, travel preferences, hobbies, social activities, active lifestyle, online behavioral patterns, medical and health records.

“11. A system comprising: a server configured to: periodically scan one or more databases to extract lead information associated with a set of leads; upon receiving a lead attribute from a computer of an agent, filter the lead information to obtain a set of filtered lead information comprising a first subset of leads from the set of leads containing the lead attribute; execute a machine-learning model to calculate a score for each lead within the subset of leads based on a learning dataset comprising the lead information; periodically query the one or more databases to receive modified data associated with each lead; iteratively update the learning dataset of the machine-learning model based on the modified data associated with each lead, wherein the machine-learning model is configured to use an updated learning dataset each time the machine-learning model is executed after the learning dataset is updated; determine a second subset of leads from the first subset of leads having the score that satisfies a threshold; and calculate a minimum auction price for the second subset of leads based on previous auctions; update a graphical user interface of a computer of an agent with ranking information associated with the second subset of leads, wherein each lead of the second subset of leads is ranked based on their corresponding score.

“12. The system of claim 11, wherein the server is further configured to determine the second subset of leads from the first subset of leads that imply a highest potential value of each lead based on their corresponding score.

“13. The system of claim 12, wherein the server is further configured to triage each ranked lead of the second subset of leads that imply the highest potential value of each lead based on the score.

“14. The system of claim 11, wherein the machine-learning model utilizes a naive bayes technique to calculate the score for each lead.

“15. The system of claim 11, wherein the machine-learning model utilizes a support vector machine to calculate the score for each lead.

“16. The system of claim 11, wherein the machine-learning model utilizes a random forest technique to calculate the score for each lead.

“17. The system of claim 11, wherein the machine-learning model utilizes a logistic regression technique to calculate the score for each lead.

“18. The system of claim 11, wherein the server is further configured to scan one or more social networking web documents associated with the set of leads within the one or more databases.

“19. The system of claim 18, wherein the server is further configured to extract the lead information from the one or more social networking web documents.

“20. The system according to claim 19, wherein the lead information comprises at least one of: identity, age, ethnicity, place of residence, number of dependent persons, identity of dependent persons, expenditure, savings, approximate market value of assets and their composition, education, professional situation, contact information, shopping preferences, travel preferences, hobbies, social activities, active lifestyle, online behavioral patterns, medical and health records.”

For the URL and additional information on this patent, see: Ross, Gareth; Walker, Tricia. Methods And Systems For Ranking Leads Based On Given Characteristics. U.S. Patent Number 10,860,593, filed July 9, 2019, and published online on December 21, 2020. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,860,593.PN.&OS=PN/10,860,593RS=PN/10,860,593

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