Intuit, Inc.

Courtney M Ferguson

Phillip J Ohme

Roger Charles Meike

Amir R Eftekhari

Ann Catherine Jose

Safia Ata Ali

Shaozhuo Jia

Malathy Muthu

Paul Hsu

Phouphet Sihavong

Hannah Anokye

Ryan Rich

Xianzhi Hu

Mohsin Akhtar Malik

Alexis Kim Tymofiev

Andrew Holmes

Certain aspects provide a computer-implemented method for evaluating social media marketing campaigns using artificial intelligence (AI). The method comprises using a large language model (LLM) to generate a plurality of AI personas. Each AI persona represents a different segment of a target audience of a marketing campaign. The method uses a transformer model, a decision tree-based model, and a natural language processing (NLP) model to predict a response, a rating, and a feedback to the marketing campaign for each AI persona that represents a different segment of the target audience. The predicted responses, ratings, and feedback for the AI personas that represent different segments of the target audience are aggregated to form an evaluation of the marketing campaign for each segment of the target audience. The method sends the evaluation of the marketing campaign to a user.

Artificial intelligence-based methods and systems for generating responses, ratings, and feedback of social media marketing campaigns

Systems and methods are described for ingesting and interpretation email messages. A pattern registry is generated for emails associated with a plurality of users based on a machine learning model interpretation of the emails. Email messages are received by a server computer, which performs pattern matching for each email message with the pattern registry. For example, embeddings for the emails may be extracted and compared to embeddings stored in a pattern database. Information for the emails is extracted based on the results of the pattern matching. For example, if a matching pattern is present in the pattern registry, the information for the email may be extracted based on the matching pattern. On the other hand, if no matching pattern is present in the pattern registry, the information for the email may be extracted using a machine learning model, such as a large language model, and the pattern registry is updated.

Ingestion and interpretation of electronic mail

The disclosed embodiments provide a system that facilitates use of an electronic device. During operation, the system displays, by an application on the electronic device, a user interface comprising a first set of user-interface elements for obtaining data from a user. Upon detecting a first swiping gesture through the user interface, the system submits the data for processing by the application. The system then updates the user interface with a second set of user-interface elements based on the submitted data.

Committing data in electronic devices using swiping gestures

An intermediate computer receives or accesses current year electronic payroll data of employees including a taxpayer and a prior year electronic tax return of the taxpayer. During preparation of an electronic tax return utilizing a tax return preparation application, the intermediate computer receives an image of a current year electronic tax document from a taxpayer computing device, processes the image to transform the image into current year electronic tax data and executes specific rules to validate the current year electronic tax data for entry into the electronic tax return based at least in part upon certain current year electronic tax return data derived from the image, the data of the prior year electronic tax return and data of the current year electronic payroll data. A discrepancy within these different data sources may indicate a life event, and screens and questions regarding a life event are presented to the taxpayer.

Computer-implemented methods systems and articles of manufacture for validating electronic tax return data

Growing community of inventors

San Diego, CA, United States of America

Courtney M Ferguson