Patent Issued for Automatic data integration for performance measurement of multiple separate digital transmissions with continuous optimization (USPTO 11328319): Deepintent Inc.

2022 MAY 26 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Adathiya, Nuupur (Maharashtra, IN), Dakic, Vaso (Irvine, CA, US), Gandhe, Sourabh (Maharashtra, IN), He, Sara (New York, NY, US), Kulkarni, Chinmay (Maharashtra, IN), Paquette, Chris (New York, NY, US), Romanovski, Pavel (Wallington, NJ, US), Werther, Jen (Hillsdale, NJ, US), Yazovskiy, Anton (Scotch Plains, NJ, US), filed on November 10, 2021, was published online on May 10, 2022, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11328319 is assigned to Deepintent Inc. (New York, New York, United States).

The following quote was obtained by the news editors 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.

“Digital advertising technology (ad tech) uses distributed computer systems under stored program control to determine what media or contents user computers are accessing, as well as what digital advertising units to select, transmit, or place in media, content, or other locations. Ad tech systems have developed sophisticated means for real-time 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 advertising impressions of healthcare products and services to applicable healthcare providers (HCPs) and consumers. Impression deployment may entail demand side platform (DSP) systems for targeted distribution of product information. Determining the appropriate online HCP identities and targetable consumers and where to deliver information regarding specific products and services may be challenging given the myriad types of medical conditions, HCPs and their practice histories, requirements for patient privacy under the Health Insurance Portability and Accountability Act (HIPAA), and the multitude of different products in the healthcare industry. Clinical medical data, prescribing behavior data, National Provider Identifier (NPI) data, demographic data, certification, appointment scheduling, payment data, and other information relating to an NPI is not generally accessible to agencies and advertisers for use in determining which HCPs would be the best fit for distributing information pertaining to particular products, or information pertaining to an NPI may not be fully comprehensive, or not coordinated with other data, and therefore limited in their utility. Thus, DSP systems often distribute product information to HCPs whose patients would not benefit from such distribution and/or omit distribution to many HCPs whose patients would benefit.

“Data sellers often may sell data defining audience segments into a DSP. These approaches usually allow for only minimal customization of the audience to be targeted or cause significant delay in a customization that greatly reduces the relevance 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 HCPs; these platforms do not have a DSP and thus require an intermediary to transfer audience data to a DSP. The lack of integration in this approach precludes providing HCP-specific reporting 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 to enable more real-time customization and relevancy of the advertisement.

“Furthermore, existing technology provides no effective means to measure the effect of healthcare advertisements on patient results and provider behavior change as there is no effective means to digitally combine or join ad serving data with healthcare data (real-world evidence) and then, on an ongoing basis, customize and optimize the messaging based on campaign measurements of promotional response and/or near real-time clinical events. There are also no effective ways to measure the interactions between consumers and service providers and how certain advertisements lead to improved health results, including minimal ability to link offline behavior change to online campaign impression data. Integration of campaigns directed at HCPs and patients is impractical or does not exist. Even if this data could be determined, there is no practical or effective way to optimize DSPs or bids based on campaign measurements to account for the results.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “SUMMARY OF PARTICULAR EMBODIMENTS

“The appended claims may serve as a summary of the invention.”

The claims supplied by the inventors are:

“1. A computer-implemented method comprising: automatically executing, in a first iteration: using a measurement server computer, obtaining, from a demand-side platform (DSP), impression data specifying a first set of campaigns that are associated with a first set of one or more healthcare attributes, the first set of campaigns being among a plurality of different campaigns executed by the DSP; using the measurement server computer, obtaining a plurality of records with de-identified consumer tokens representing consumers who have received digital impressions of the first set of campaigns that are associated with the same first set of healthcare attributes; using analytics instructions executing in a database server, accessing a database comprising de-identified tokenized claims data records, each of the data records relating to at least one claim concerning a prescription of a specified product and including at least one of the consumer tokens; using the analytics instructions, executing one or more database join operations on the claims data records and consumer tokens to cause outputting a result set of one or more integrated measurement records specifying one or more measured goal campaigns among the plurality of different campaigns, the one or more measured goal campaigns being associated with the prescription of the specified product in at least one claims data record that is associated with at least one of the consumer tokens; receiving, at the measurement server computer, the integrated measurement records from the database server; using the measurement server computer, generating and causing presenting one or more analytics reports based on the integrated measurement records; and using the measurement server computer, executing a post call to the database server to register new campaign impression data to the database server; and automatically executing the method in one or more second iterations using the new campaign impression data.

“2. The method of claim 1, further comprising determining, based on the integrated measurement records, a change in prescription writing behavior that is associated with one of the advertisements delivered on behalf of the measured goal campaign, the measured goal campaign being associated with the consumer tokens, and presenting the change in the analytics reports.

“3. The method of claim 1, further comprising training a machine learning model using a training dataset comprising features selected from the plurality of records and the de-identified tokenized claims data records to produce an optimization model, the machine learning model being trained to receive other integrated measurement records for other campaigns and to output predicted bid values for use in automatically adjusting one or more parameters of the DSP, for a target campaign among the plurality of different campaigns.

“4. The method of claim 3, the optimization model comprising one of a random forest model, a neural network, a logistic regression, or a gradient boosted decision tree.

“5. The method of claim 3, the training dataset further comprising other features selected from an attributes dataset comprising personal and demographics data associated with the consumers.

“6. The method of claim 3, further comprising: using the optimization model, determining, based on the integrated measurement records, costs of each of the one or more measured campaigns, and in response, automatically signaling the DSP to change one or more configuration parameters to cause increasing spending on at least one of the measured campaigns having a lowest cost per prescription of the particular product.

“7. The method of claim 3, further comprising: using the optimization model, receiving bid request data and an attributes dataset comprising personal and demographics data, and outputting predictions of bid values; updating a bidder of the DSP using the predictions of bid values output from the optimization model; serving one or more advertisements from the DSP based on the bidder having been updated.

“8. The method of claim 1, wherein the generating and causing presenting of the one or more analytics reports comprises generating a data value indicating an elapsed time between a timestamp of a first digital impression associated with a particular campaign among the plurality of different campaigns and a first measured campaign of the particular campaign.

“9. The method of claim 1, each de-identified consumer token being linked to a first healthcare attribute of the first set of healthcare attributes and is further linked to a first de-identified tokenized claims data record from among the set of de-identified tokenized claims data records.

“10. The method of claim 1, each campaign in the first set of campaigns being defined in the DSP using at least one clinical attribute in the first set of healthcare attributes, each clinical attribute comprising any of an ICD-10 code, CPT code, or NDC code.

“11. One or more non-transitory storage media storing instructions which, when executed by one or more measurement computing server devices, cause performance of a method, the method comprising: automatically executing, in a first iteration: using a measurement server computer, obtaining, from a demand-side platform (DSP), impression data specifying a first set of campaigns that are associated with a first set of one or more healthcare attributes, the first set of campaigns being among a plurality of different campaigns executed by the DSP; using the measurement server computer, obtaining a plurality of records with de-identified consumer tokens representing consumers who have received digital impressions of the first set of campaigns that are associated with the same first set of healthcare attributes; using analytics instructions executing in a database server, accessing a database comprising de-identified tokenized claims data records, each of the data records relating to at least one claim concerning a prescription of a specified product and including at least one of the consumer tokens; using the analytics instructions, executing one or more database join operations on the claims data records and consumer tokens to cause outputting a result set of one or more integrated measurement records specifying one or more measured goal campaigns among the plurality of different campaigns, the one or more measured goal campaigns being associated with the prescription of the specified product in at least one claims data record that is associated with at least one of the consumer tokens; receiving, at the measurement server computer, the integrated measurement records from the database server; using the measurement server computer, generating and causing presenting one or more analytics reports based on the integrated measurement records; and using the measurement server computer, executing a post call to the database server to register new campaign impression data to the database server; and automatically executing the method in one or more second iterations using the new campaign impression data.

“12. The storage media of claim 11, further comprising sequences of instructions which when executed cause the one or more measurement computing server devices to perform determining, based on the integrated measurement records, a change in prescription writing behavior that is associated with one of the advertisements delivered on behalf of the measured goal campaign, the measured goal campaign being associated with the consumer tokens, and presenting the change in the analytics reports.

“13. The storage media of claim 11, further comprising sequences of instructions which when executed cause the one or more measurement computing server devices to perform training a machine learning model using a training dataset comprising features selected from the plurality of records and the de-identified tokenized claims data records to produce an optimization model, the machine learning model being trained to receive other integrated measurement records for other campaigns and to output predicted bid values for use in automatically adjusting one or more parameters of the DSP, for a target campaign among the plurality of different campaigns.

“14. The storage media of claim 13, the optimization model comprising one of a random forest model, a neural network, a logistic regression, or a gradient boosted decision tree.

“15. The storage media of claim 13, the training dataset further comprising other features selected from an attributes dataset comprising personal and demographics data associated with the consumers.

“16. The storage media of claim 13, further comprising sequences of instructions which when executed cause the one or more measurement computing server devices to perform, using the optimization model, determining, based on the integrated measurement records, costs of each of the one or more measured campaigns, and in response, automatically signaling the DSP to change one or more configuration parameters to cause increasing spending on at least one of the measured campaigns having a lowest cost per prescription of the particular product.

“17. The storage media of claim 13, further comprising sequences of instructions which when executed cause the one or more measurement computing server devices to perform, using the optimization model, receiving bid request data and an attributes dataset comprising personal and demographics data, and outputting predictions of bid values; updating a bidder of the DSP using the predictions of bid values output from the optimization model; serving one or more advertisements from the DSP based on the bidder having been updated.”

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

URL and more information on this patent, see: Adathiya, Nuupur. Automatic data integration for performance measurement of multiple separate digital transmissions with continuous optimization. U.S. Patent Number 11328319, filed November 10, 2021, and published online on May 10, 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=11328319.PN.&OS=PN/11328319RS=PN/11328319

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