Patent Issued for Interactive estimates of media delivery and user interactions based on secure merges of de-identified records (USPTO 11620673): DeepIntent Inc.

2023 APR 25 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Bennett Andreyev, Kate (New York, NY, US), Paquette, Chris (Miami, FL, US), Werther Perlman, Jennifer (Hillsdale, NJ, US), Yazovskiy, Anton (Brooklyn, NY, US), filed on October 17, 2022, was published online on April 4, 2023.

The patent’s assignee for patent number 11620673 is DeepIntent Inc. (New York, New York, United States).

News editors obtained the following quote from the background information supplied by the inventors: “The approaches described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued. Therefore, unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Further, it should not be assumed that any of the approaches described in this section are well-understood, routine, or conventional merely by virtue of their inclusion in this section.

“Machine learning systems have become popular for solving various types of problems based on training data. A key benefit of a machine learning system is the ability to learn based on data, bypassing any requirements for manual coding of an algorithm. Instead, the machine learning system generates an algorithm or model through repeated computations using the training data.

“A potential drawback of machine learning systems is that determining specific internal operating mechanisms of the core machine learning engine can be difficult. Most machine learning systems are configured to generate fairly complex patterns based on the given training data. Because machine learning systems use complex algorithms and execute continuous learning, determining why a machine learning system produced a particular result from a set of input data can be difficult, if not impossible. In some situations, this can lead to a lack of accountability; in other situations, this feature protects the training data. Because a trained machine learning system exists separately from the training data, any data that is protected or sensitive data can be safeguarded during the use of the machine learning system.

“A trained machine learning system inherently protects the data used to train it. However, the training phase can create issues, especially when the data used to train the machine learning system is robust but protected. Many people provide data under the assurance that data security measures will be used. As an example, the Health Insurance Portability and Accountability Act (HIPAA) has stringent requirements on the protection of medical claims data which would prevent a person from viewing any of the medical claims data to train a machine learning system.

“Additionally, even when information is protected from viewing, the training data or machine learning system can still provide protected information to a viewer. For instance, a machine learning system using ten inputs could memorize a vast majority of people in the United States, thereby providing one-to-one recognition of individuals instead of providing an algorithm that produces a likelihood based on general patterns. But to validate the training data or the machine learning system would generally involve accessing the training data or machine learning system, thereby failing to provide the originally desired protections.

“Thus, there is a need for a system that can protect personal, private, confidential, or otherwise protected information during training and validation of a machine learning system that utilizes the protected information. Digital advertising technology (ad tech) uses distributed computer systems under stored program control to determine what media or contents that user computers are accessing, as well as what digital advertising units to select and transmit or place in media, content or other locations. Ad tech systems have developed sophisticated means for bidding on the placement of electronic ad units within websites, mobile device feeds and other applications. However, present ad tech systems still suffer from many limitations.

“Many advertising agencies, pharmaceutical companies, medical equipment companies, insurance companies and other healthcare related firms wish to enhance media delivery, advertising and content engagement, impressions, clicks, and reach of healthcare products and services and related content to clinically relevant individuals. Advertising campaign and content deployment can entail any of advertising, data, and media platforms and systems for targeted distribution of product information. Determining the appropriate online identities of relevant individuals and where to deliver information regarding specific products and services can be challenging given the myriad types of medical conditions, the multitude of different products in the healthcare industry, as well as the diversity of demographic attributes and other individual and clinical behavior that must be considered. Combinations of health data, prescription data, demographic data, user location, certification, appointment scheduling, payment data, online behavior, automated content recognition (ACR) data, media consumption and interaction data, business-individual relationship data, and other information relating to individuals are not generally accessible to agencies for use in determining which individuals would be best fit for distributing information pertaining to particular products or may be outdated, not fully comprehensive and not coordinated with other data, and therefore limited in its utility. Still another challenge is maintaining the privacy of individuals who are subjects of the data. Thus, advertising, data, and media platforms and systems often distribute product information to individuals who would not benefit from such distribution and/or omit distribution to many individuals who would benefit.

“Data sellers are known to sell data defining audience segments into advertising and media platforms and systems, like demand-side platforms (DSPs). These approaches usually allow for only minimal customization of the audience to be targeted and rely on buckets or segments of cookie or device data that have been manually tagged to indicate a particular audience characteristic. Other data providers offer data via platforms which provide counts and aggregations for how many users with various attributes are recorded in a database of individuals; these platforms do not have the technology required to combine, query, and transfer audience data for optimal use. The lack of integration in this approach precludes accurate and comprehensive forecasting of engagement with advertisements in real time. Furthermore, existing systems may use individual data stores based on browser cookie limitations and provide no sound way to unify digital identity data with third-party data.

“Therefore, there is an acute need in the field to address the technical problem of how to automatically join and/or correlate disparate datasets of healthcare data in conjunction with digital presence data relating to clinically relevant individuals to find better ways of transmitting relevant content to these parties in real time, including providing distribution costs and performance data. There is also a need for better tools for planning campaigns in terms of creating clinically relevant audiences, forecasting estimates of media delivery, reach, and cost, and statistical results of supplying audience data to advertising, data, and media platforms and systems. There is also a further need for better tools for creating the framework to research, assess, and analyze potential audiences and data sources or potential individual and patient reach.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “The appended claims may serve as a summary of the disclosure.”

The claims supplied by the inventors are:

“1. A computer implemented method comprising: receiving and storing in relational database tables in a secure data processing environment comprising one or more first virtual machine instances coupled to one or more first data stores, master data comprising records having first de-identified token values associated with health data and second data comprising records having second de-identified token values associated with historical media delivery data; in the secure data processing environment, executing one or more database table join operations to merge the master data and the second data to produce a joined table having records comprising third de-identified token values associated with the health data and the second data; receiving, using one or more virtual computing instances of a service provider environment, one or more filter specifications that define a target audience and a forecast request, and in real time in response to the forecast request: based on the one or more filter specifications, executing one or more queries to the joined table in the secure data processing environment; receiving, in the service provider environment, de-identified aggregated data that the secure data processing environment has generated based upon the one or more queries to the joined table; based on the de-identified aggregated data and second data, generating an estimate of media delivery reach; presenting the estimate of the media delivery reach to a user computer that is communicatively coupled to the service provider environment.

“2. The method of claim 1, further comprising generating the estimate of media delivery reach as an estimate of one of: media delivery reach to the target audience; an estimate of a number of interactions the target audience may take with delivered media; an estimate of a number of behaviors the target audience may perform after viewing deliver media.

“3. The method of claim 1, the second data comprising any one or more of: advertising data; media data; individual data; demographic data; historical digital advertising data comprising any of media deliveries or impressions, opportunities, or clicks; television ACR data.

“4. The method of claim 1, further comprising: receiving and storing in relational database tables in a secure data processing environment comprising one or more first virtual machine instances coupled to one or more first data stores; the master data comprising first records having first de-identified token values associated with health data; the second data comprising second records having second de-identified token values associated with demographic data; third data comprising third records having third de-identified token values associated with historical media delivery data comprising one or more of television ACR data, impressions, opportunities, and clicks; executing the one or more database table join operations to merge the master data, the second data, and the third data to produce the joined table having records comprising fourth de-identified token values associated with the health data, the demographic data, and the historical media delivery data.

“5. The method of claim 1, further comprising receiving the master data from one or more data sources separate from the secure data processing environment.

“6. The method of claim 1, the joined table comprising records having first de-identified token values associated with demographic data and health data for one or more of: clinical medical data, prescription data specifying drug prescriptions, and/or medical claims data.

“7. The method of claim 1, the master data comprising a single dataset or one or more decentralized data sets that combine to create a federated dataset.

“8. The method of claim 3, the demographic data comprising one or more of demographic segments, gender, and age and geographic location data of an individual, the geographic location data including but not limited to an address, latitude-longitude (lat-long) data, GPS coordinates, DMA (designated marketing area), ZIP code, city, county, or another geographical unit.

“9. The method of claim 1, further comprising transmitting the filter specifications that define a target audience to one or more targets for activation that serve media to cause presentation of a targeted media delivery on a computer associated with members of the target audience.

“10. The method of claim 9, the filter specifications being transmitted with instructions for use by one or more of an advertising exchange, media server and/or media and advertisement display channel.

“11. The method of claim 1, further comprising receiving the historical digital media delivery data and/or opportunities data from the advertising, data, and media platform or system; receiving the demographic data from a demographic data service provider separate from the service provider environment; calling a third-party token service to generate the second de-identified token values for the demographic data to associate the second de-identified token values with demographic segments, and to generate the third de-identified token values for the historical media delivery data that associates third de-identified token values with one or more of media deliveries or impressions, opportunities, and clicks; programmatically copying the demographic data and historical media delivery data to a first data store in the secure data processing environment.

“12. The method of claim 1, further comprising receiving the historical digital media delivery data and/or opportunities data from the platform; receiving the demographic data from a demographic data service provider separate from the service provider environment; generating the second de-identified token values for the demographic data to associate the second de-identified token values with demographic segments, and generating the third de-identified token values for the historical media delivery data that associates third de-identified token values with one or more of media deliveries or impressions, opportunities, and clicks; programmatically copying the demographic data and historical media delivery data to a first data store in the secure data processing environment.

“13. The method of claim 1, further comprising generating and displaying a graphical user interface that is programmed to receive input from the user computer specifying filter attributes for one or more of: for health data by diagnosis, prescription drug use or procedure, for healthcare system interactions such as in-office healthcare provider visitations or telehealth visitations, for health insurance coverage, for health insurance providers, for genetic information, for survey responses, for geography, for demographic attributes, for ad opportunities, for media deliveries or impressions, for ACR, for diagnosis codes, for prescription drug codes, and for procedure codes, by publisher, by media owner, by media and advertising platform, by data provider.

“14. The method of claim 5, the advertising, data, and media platform or system being programmed for generating instructions for ranking media deliveries or impressions based upon one or more of target procedure codes, target diagnosis codes, counts of unique patients, or estimated numbers of media deliveries or impressions; generating instructions for submitting bids for purchasing media deliveries or impressions based upon the ranking of the media deliveries or impressions.

“15. The method of claim 1, the master data comprising records having first deidentified token values associated with health data.

“16. The method of claim 1, the master data comprising records having first deidentified token values associated with any of: medical clinical codes comprising any of International Statistical Classification of Diseases and Related Health Problems (ICD) codes, Current Procedural Terminology (CPT) codes, Healthcare Common Procedure Coding System (HCPCS) codes, J codes, or National Drug Code (NDC) codes for prescriptions, or LOINC codes for laboratory tests.

“17. The method of claim 1, further comprising: receiving a query that specifies one or more filter criteria; based on the one or more filter criteria, and based on the de-identified aggregated statistics data and historical media delivery data from an advertising, media, or data platform or system, generating an updated estimate of the number of media deliveries or impressions that the advertising, media, or data platform or system can deliver to the target audience or an updated estimate of a number of interactions the target audience may take with delivered media or an updated estimate of a number of behaviors the target audience may perform after viewing deliver media; presenting the updated estimate and the de-identified aggregated statistics data to the user computer.

“18. The method of claim 1, further comprising the ability to forecast the delivery of digital content such as digital advertisements, optionally including data specifying a distribution or counts of potential media deliveries or impressions, clicks, or other interactions, or delivery of digital advertisements to one or more specified media channels, applications, or websites, by publisher, by media owner, by media or advertising platform, or by data provider.”

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

For additional information on this patent, see: Bennett Andreyev, Kate. Interactive estimates of media delivery and user interactions based on secure merges of de-identified records. U.S. Patent Number 11620673, filed October 17, 2022, and published online on April 4, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11620673)&db=USPAT&type=ids

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