Patent Issued for Systems and methods for electronic request routing and distribution (USPTO 11463585): Massachusetts Mutual Life Insurance Company

2022 OCT 26 (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 11463585, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Ahani, Asieh (Springfield, MA, US), Tracy, Michael (Springfield, MA, US), Zayac, Tara (Springfield, MA, US).

This patent was filed on September 14, 2020 and was published online on October 4, 2022.

From the background information supplied by the inventors, news correspondents obtained the following quote: “As the processing power of computers allows for greater computer functionality and the Internet technology era allows for interconnectivity between computing systems, many existing software solutions receive a high volume of electronic requests. Managing such electronic requests in an accurate and effective way to route each electronic request to the right agent/advisor is difficult. Existing software solutions, utilizing conventional methods, have encountered a new set of technical challenges. First, existing and conventional software solutions may randomly route each electronic request, which has proven to be inadequate. For instance, existing software solutions fail to consider attributes associated with the users transmitting the electronic requests and attributes associated with the agent/employees to identify a best match. As a result, existing software solutions may route the electronic requests to agents who cannot provide the best service, which may lead to negative user experience and loss of profit.

“Second, existing software solutions fail to consider the capacity of each agent. For instance, existing software solutions may route too many requests to an agent who has been proven to provide better services than other agents. This may overburden the agent and may negatively affect his or her performance. For example, one agent may receive a large number of electronic requests that is beyond the agent’s capacity. The agent may be too overwhelmed to provide the best service for each request, while other agents may not have enough work. Therefore, existing software solutions fail to consider load balancing when distributing the high volume of electronic requests, which may create inefficiencies and waste of resources.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “For the aforementioned reasons, there is a need for an accurate and efficient computer-implemented system and method for routing and distributing electronic requests to agents. There is a further need for a computer-specific set of rules to efficiently and accurately select right agents when facing a high number of electronic requests.

“Embodiments disclosed herein address the above challenges by providing accurate and efficient electronic requests routing and distribution. Specifically, an analytic server receives a plurality of requests. Aiming to route the plurality of requests to appropriate agents, the analytic server trains an artificial intelligence model for each agent based on historical data. For each request, the analytic server executes the artificial intelligence model to determine a score indicating the probability of the agent converting the request to a successful sale. The analytic server determines an entropy value for each request based on the scores and order the requests into a queue based on the entropy values. The analytic server sequentially processes the requests in the queue. The analytic server also calculates a capacity for each agent based on historical data. The analytic server routes each request in the queue to an agent based on at least one of the score and the capacity.

“In an embodiment, a method comprises executing, by the server, using an electronic request attribute and a first user’s attributes from an electronic request to match the first user with a second user, a set of artificial intelligence models to determine a score corresponding to each second user of a plurality of second users, each score being indicative of a probability of the second user satisfying the electronic request, each artificial intelligence model of the set of artificial intelligence models corresponding to historical data of each second user, and each artificial intelligence model configured to determine a relationship between a set of attributes of a second user and a set of attributes associated with the second user’s existing customers whose electronic requests have been previously satisfied by the second user; calculating, by the server, an entropy value based on the scores of the plurality of second users, the entropy value corresponding to each score for each second user in relation to the electronic request; iteratively selecting, by the server, a target second user for each electronic request based on at least one of the score and a capacity associated with the target second user; sequentially assigning, by the server, the plurality of electronic requests to corresponding target second users in an order based on a queue arranged in accordance with each electronic request’s entropy value; and transmitting, by the server in real time, each electronic request to a computing device associated with the target second user.

“In another embodiment, a computer system comprises a server having computer-readable instructions on a non-transitory computer-readable medium that when executed by a processor: execute using an electronic request attribute and a first user’s attributes from an electronic request to match the first user with a second user, a set of artificial intelligence models to determine a score corresponding to each second user of a plurality of second users, each score being indicative of a probability of the second user satisfying the electronic request, each artificial intelligence model of the set of artificial intelligence models corresponding to historical data of each second user, and each artificial intelligence model configured to determine a relationship between a set of attributes of a second user and a set of attributes associated with the second user’s existing customers whose electronic requests have been previously satisfied by the second user; calculate an entropy value based on the scores of the plurality of second users, the entropy value corresponding to each score for each second user in relation to the electronic request; iteratively select a target second user for each electronic request based on at least one of the score and a capacity associated with the target second user; sequentially assign the plurality of electronic requests to corresponding target second users in an order based on a queue arranged in accordance with each electronic request’s entropy value; and transmit in real time each electronic request to a computing device associated with the target second user.

“It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the disclosed embodiment and subject matter as claimed.”

The claims supplied by the inventors are:

“1. A computer-implemented method comprising: executing, by a server, using an electronic request attribute and a first user’s attributes from an electronic request to match the first user with a second user, a set of artificial intelligence models to determine a score corresponding to each second user of a plurality of second users, each score being indicative of a probability of the second user satisfying the electronic request, each artificial intelligence model of the set of artificial intelligence models corresponding to historical data of each second user, and each artificial intelligence model configured to determine a relationship between a set of attributes of a second user and a set of attributes associated with the second user’s existing customers whose electronic requests have been previously satisfied by the second user; calculating, by the server, an entropy value based on the scores of the plurality of second users, the entropy value corresponding to each score for each second user in relation to the electronic request; iteratively selecting, by the server, a target second user for each electronic request based on at least one of the score and a capacity associated with the target second user; sequentially assigning, by the server, the plurality of electronic requests to corresponding target second users in an order based on a queue arranged in accordance with each electronic request’s entropy value; and transmitting, by the server in real time, each electronic request to a computing device associated with the target second user.

“2. The method of claim 1, wherein the server initiates the selection of the target second user using a lowest corresponding entropy value.

“3. The method of claim 1, wherein the capacity is a threshold number of electronic requests the target second user can accept.

“4. The method of claim 1, wherein transmitting each electronic request further comprises directing each first user to a webpage displaying data associated with the target second user, whereby the target second user satisfies each electronic request.

“5. The method of claim 1, further comprising determining, by the server, the capacity for each second user based on a historical dataset.

“6. The method of claim 1, further comprising determining, by the server, the capacity for each second user based on a trend of a success ratio relative to a number of electronic requests assigned to the second user.

“7. The method of claim 1, further comprising determining, by the server, the capacity for each second user as a number of electronic requests of a last local maxima that is above an average success ratio of the second user.

“8. The method of claim 1, further comprising displaying, by the server on a graphical user interface, indicators of the plurality of second users, wherein the indicators are ranked based on scores of the plurality of second users.

“9. The method of claim 1, wherein at least one artificial intelligence model comprises a random forest model.

“10. The method of claim 1, wherein an electronic request with a lowest entropy value is assigned to a corresponding target second user with a highest priority.

“11. The method of claim 1, further comprising: determining, by the server, a set of second users from the plurality of second users by identifying the set of second users whose scores satisfying a second threshold; determining, by the server, a subset of second users from the set of second users by identifying the subset of second users whose electronic requests are less than their capacities; and selecting, by the server, the target second user from the subset of second users.

“12. The method of claim 11, further comprising: resetting, by the server, the second threshold when the subset of second users is empty.

“13. The method of claim 11, further comprising: selecting, by the server from the subset of second users, a second user with a score as high as the target second user.

“14. A computer system comprising: a server having computer-readable instructions on a non-transitory computer-readable medium that when executed by a processor: execute using an electronic request attribute and a first user’s attributes from an electronic request to match the first user with a second user, a set of artificial intelligence models to determine a score corresponding to each second user of a plurality of second users, each score being indicative of a probability of the second user satisfying the electronic request, each artificial intelligence model of the set of artificial intelligence models corresponding to historical data of each second user, and each artificial intelligence model configured to determine a relationship between a set of attributes of a second user and a set of attributes associated with the second user’s existing customers whose electronic requests have been previously satisfied by the second user; calculate an entropy value based on the scores of the plurality of second users, the entropy value corresponding to each score for each second user in relation to the electronic request; iteratively select a target second user for each electronic request based on at least one of the score and a capacity associated with the target second user; sequentially assign the plurality of electronic requests to corresponding target second users in an order based on a queue arranged in accordance with each electronic request’s entropy value; and transmit in real time each electronic request to a computing device associated with the target second user.

“15. The system of claim 14, wherein the server initiates the selection of the target second user using a lowest corresponding entropy value.

“16. The system of claim 14, wherein the capacity is a threshold number of electronic requests the target second user can accept.

“17. The system of claim 14, wherein transmitting each electronic request further comprises directing each first user to a webpage displaying data associated with the target second user, whereby the target second user satisfies each electronic request.

“18. The system of claim 14, wherein the server is further configured to determine the capacity for each second user based on a historical dataset.

“19. The system of claim 14, wherein the server is further configured to determine the capacity for each second user based on a trend of a success ratio relative to a number of electronic requests assigned to the second user.

“20. The system of claim 14, wherein the server is further configured to determine the capacity for each second user as a number of electronic requests of a last local maxima that is above an average success ratio of the second user.”

For the URL and additional information on this patent, see: Ahani, Asieh. Systems and methods for electronic request routing and distribution. U.S. Patent Number 11463585, filed September 14, 2020, and published online on October 4, 2022. 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=11463585.PN.&OS=PN/11463585RS=PN/11463585

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