Systems and methods for regulating provision of messages with content from disparate sources based on risk and feedback data

Inventors

Guttikonda, Sudheer • Morse, William • Qiu, Chuanhan • Speier, Austin

Assignees

Click Therapeutics Inc

Abstract

Aspects of the present disclosure are directed to systems, methods, and computer readable media for regulating digital therapeutic content for provision. A computing system may identify a digital therapeutic content to be provided via a network. The computing system may apply the digital therapeutic content to a machine learning (ML) model having a set of weights. The computing system may determine, from applying the digital therapeutic content to the ML model, an indication as of one of compliance or non-compliance. The computing system may store, using one or more data structures, an association between the digital therapeutic content and the indication used to control provision of the digital therapeutic content via the network, by (i) restricting the digital therapeutic content from provision responsive to determining the indication of non-compliance and (ii) permitting the digital therapeutic content to be provided responsive to determining the indication of compliance.

Core Innovation

A method and system for digital therapeutic content receive an identification of input digital therapeutic content via a user interface, apply the input digital therapeutic content to a machine learning model having a set of weights, and select at least a portion of the input digital therapeutic content identified as non-compliant based on applying the input digital therapeutic content to the machine learning model output. The approach causes information associated with the non-compliant portion to be presented via the user interface and generates feedback data using interactions with the user interface.

The machine learning model is trained by identifying a training dataset identifying training digital therapeutic content and a label identifying one of compliance or non-compliance for provision, applying the training digital therapeutic content into the machine learning model to generate an output, and updating, based on comparing the label with the output, at least one of the set of weights of the machine learning model. The method and system further train the machine learning model by updating at least one of the set of weights using the feedback data generated using the interactions.

In the claimed workflow, user interactions through the user interface provide information used for subsequent training, and the machine learning model is applied to determine compliance-related behavior, including selection of a portion identified as non-compliant. Dependent refinements additionally indicate that compliance can be associated with a risk score and threshold condition, that provision of the digital therapeutic content can be restricted to a network, that content can be textual and/or visual, and that presentation in a session relates to at least partial concurrence with administering medication to a user to address a condition.

Claims Coverage

The patent provides two independent claims, a method and a system, that share a common inventive workflow. The independent claims include seven inventive features covering labeled training, non-compliant portion selection, user-interface presentation, feedback generation, and further training of the machine learning model using that feedback.

Across the independent claims, the inventive coverage centers on a closed loop where labeled training data trains a machine learning model, the model is applied to input digital therapeutic content to identify a non-compliant portion, the user interface presents information associated with that portion, user interactions generate feedback data, and the machine learning model is further trained by updating at least one set of weights using the feedback data.

Stated Advantages

Documented Applications