Patent Issued for Methods and systems for electronic generation of narratives (USPTO 11886465): United Services Automobile Association

2024 FEB 16 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Horgan, John Luke (San Antonio, TX, US), Waldmeier, Michael James (Helotes, TX, US), filed on May 1, 2017, was published online on January 30, 2024.

The assignee for this patent, patent number 11886465, is United Services Automobile Association (San Antonio, Texas, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Traditionally, a human being views, assesses, and examines data to generate insights and analytics from a data set. Such assessment can be done, for example, by applying complex analytical tools and/or spreadsheets to the data set. Analyzing large sets of data can require extensive time and resources. Further, complex analytics may not be easily communicated and understood by an average user who is not a data scientist or a computer programmer.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Various embodiments of the present disclosure relate generally to an electronic (automated) tool for the generation of narratives that are easily understood and communicated by average users based on collected data. A narrative can be, for example, one or more sentences that can be included in an email, displayable on a website or a mobile application, or included as part of an electronic document for distribution and use. The narratives can be, for example, related to best-practice recommendations or suggestions for goods or services. By tracking user response to the narratives, organizations can determine which narratives are most effective in eliciting reactions or feedback from users. Thus, embodiments of the present disclosure provide a way for users to create, deploy, and analyze test results of targeted narratives with little effort.

“Conventionally, organizations overload consumers with information that is not effective in eliciting reactions from users. On the contrary, narratives that are customized to a user (e.g., preferences, financial status, age, goals, habits, and other such information) are more likely to generate attention from users. Embodiments of the present disclosure are directed at automatic generation of narratives and their deployment in a user population for testing which narrative(s) is/are likely to elicit responses, feedback, or actions from users. Furthermore, embodiments of the present disclosure use machine learning methods to identify trends and patterns in user data. User data can be historical data or real-time data relating to a user’s financial history, personal data, or demographics. For example, user data can be used to determine that if a user’s average monthly income is above a threshold amount, then deploying a first narrative is more likely to be effective.

“The user data can be collected from users by an entity or organization that runs the disclosed system. In some embodiments, such data can be publicly or privately available information provided by third parties to the entity or organization that runs the disclosed system. In accordance with disclosed embodiments, there is no limitation on data type, data format, data variables, data size, data structures, data schema or the sources that provide the data. Further, the disclosed tool can apply to data of any size and thus offers robustness and scalability to any size of data set.

“One of the technological advances of some embodiments of automatic narrative generation is the time savings and reduced amount of manpower and resources used to test the specific structure and content of information that is likely to elicit maximum interest and response from users (e.g., consumers of goods or services). Typically, personnel from an IT department, a data analytics team, or a marketing department are involved in determining “what comments/statements” are most effective in generating attention from consumers. The disclosed technology provides an advantage in that a manager or a departmental head can create and deploy narratives without relying on the help of other departments (e.g., IT) or market research divisions external or internal to a company or an organization. Such capabilities can benefit organizations by keeping the organization’s business intelligence internal to the organization without sharing such “secret” business data with outside vendors or third parties.

“Other examples of the technological advancement include, but are not limited to, the following: 1) the capability to integrate the auto-generated narratives into any document or communication; 2) the capability to integrate the generated narratives with third party software and applications for mobile and/or web; 3) a machine-generated way to measure results from deploying different narratives to a user population without incurring the high costs of a pilot program, marketing campaign, or advertisements; and 4) a mechanism to detect trackable actions from users.”

The claims supplied by the inventors are:

“1. A non-transitory computer-readable medium comprising a set of instructions that, when executed by one or more processors, cause a machine to perform the operations of: receiving, at a server, information relating to users in a user population from one or more data sources; in response to determining that a subset of the information satisfies one or more criteria, generating a narrative corresponding to the subset of the information by applying business rules to the information, wherein the narrative is generated using a decision tree, wherein the decision tree and the business rules are displayed on a graphical user interface (GUI), wherein the GUI includes a main window and a side bar adjacent to the main window, wherein the business rules are displayed in the side bar and movable from the side bar into the main window according to a drag-and-drop mechanism, wherein the business rules include conditions for transmitting the narrative, wherein generating the narrative includes receiving, via the drag-and-drop mechanism, the conditions for transmitting the narrative; assigning the narrative to one or more predefined categories, the one or more predefined categories defined based on the one or more criteria; transmitting the narrative to a first group of the users associated with the subset of the information according to the conditions; detecting information relating to trackable actions of a financial event performed by a subset of the first group of the users in response to the first group of the users receiving the narrative, wherein the subset of the first group of users is associated with a demographic; determining an effectiveness rating of the narrative based on a ratio of a number of the subset of users to a number of the first group of users performing the trackable actions; generating an updated narrative based on applying the detected information relating to the trackable actions of the financial event to the decision tree, and the determined effectiveness rating; transmitting the updated narrative to a second group of users associated with the demographic; receiving a user response to the updated narrative; and sending a recommendation and/or a prediction to the second group of users based on the user response to the updated narrative.

“2. The non-transitory computer-readable medium of claim 1, wherein the narrative includes one or more sentences.

“3. The non-transitory computer-readable medium of claim 1, wherein the subset is a first subset, the one or more criteria is a first set of criteria, the subset of the first group of users associated with the subset of the information is a first user subset, and the information relating to the trackable actions is a first trackable information, wherein the set of instructions, when executed by the one or more processors, further cause the machine to perform the operations of: in response to determining that a second subset of the information satisfies a second set of criteria, generating a second narrative corresponding to the second subset of the information by applying the business rules to the information; assigning the second narrative to the one or more predefined categories, the one or more predefined categories defined based on the second set of criteria; transmitting the second narrative to a second user subset; detecting a second trackable information relating to trackable actions performed by the second user subset in response to the second user subset receiving the second narrative; and comparing the first trackable information with the second trackable information to determine whether the narrative or the second narrative should be used.

“4. The non-transitory computer-readable medium of claim 1, wherein the set of instructions, when executed by the one or more processors, further cause the machine to perform the operations of: revising the narrative based at least on the information relating to the trackable actions performed by the subset of the first group of users.

“5. The non-transitory computer-readable medium of claim 1, wherein the decision tree utilizes at least one IF-THEN construction.

“6. The non-transitory computer-readable medium of claim 1, wherein the narrative is included in one or more of the following: an email, an electronic document, or a notification on a web portal accessible via a mobile application program or a website hosted at the server.

“7. The non-transitory computer-readable medium of claim 1, wherein the one or more data sources are selected from: a third party database storing publicly available or privately available information relating to the user, a user in the user population, a bank, a financial institution, an insurance provider, or a social media network.

“8. The non-transitory computer-readable medium of claim 1, wherein the trackable actions performed by the subset of the first group of users are in real time or almost real time.

“9. The non-transitory computer-readable medium of claim 1, wherein the narrative is stored in a database along with additional narratives, the additional narratives associated with the one or more predefined categories.

“10. A method implemented by a computer server comprising: receiving, at a server, information relating to users in a user population from one or more data sources; in response to determining that a subset of the information satisfies one or more criteria, generating a narrative corresponding to the subset of the information by applying business rules to the information, wherein the narrative is generated using a decision tree, wherein the decision tree and the business rules are displayed on a graphical user interface (GUI), wherein the GUI includes a main window and a side bar adjacent to the main window, wherein the business rules are displayed in the side bar and movable from the side bar into the main window according to a drag-and-drop mechanism, wherein the business rules include conditions for transmitting the narrative, wherein generating the narrative includes receiving, via the drag-and-drop mechanism, the conditions for transmitting the narrative; assigning the narrative to one or more predefined categories, the one or more predefined categories defined based on the one or more criteria; transmitting the narrative to a first group of the users associated with the subset of the information according to the conditions; detecting information relating to trackable actions of a financial event performed by a subset of the first group of the users in response to the first group of the users receiving the narrative, wherein the subset of the first group of users is associated with a demographic; determining an effectiveness rating of the narrative based on a ratio of a number of the subset of users to a number of the first group of users performing the trackable actions; generating an updated narrative based on applying the detected information relating to the trackable actions of the financial event to the decision tree, and the determined effectiveness rating; transmitting the updated narrative to a second group of users associated with the demographic; receiving a user response to the updated narrative; and sending a recommendation and/or a prediction to the second group of users based on the user response to the updated narrative.

“11. The method of claim 10, wherein the subset is a first subset, the one or more criteria is a first set of criteria, the subset of the first group of users associated with the subset of the information is a first user subset, and the information relating to the trackable actions is a first trackable information, wherein the method further comprises: in response to determining that a second subset of the information satisfies a second set of criteria, generating a second narrative corresponding to the second subset of the information by applying the business rules to the information; assigning the second narrative to the one or more predefined categories, the one or more predefined categories defined based on the second set of criteria; transmitting the second narrative to a second user subset; detecting a second trackable information relating to trackable actions performed by the second user subset in response to the second user subset receiving the second narrative; and comparing the first trackable information with the second trackable information to determine whether the narrative or the second narrative should be used.

“12. The method of claim 10, wherein the narrative includes one or more sentences.”

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

For more information, see this patent: Horgan, John Luke. Methods and systems for electronic generation of narratives. U.S. Patent Number 11886465, filed May 1, 2017, and published online on January 30, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11886465)&db=USPAT&type=ids

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