Abstract

The present disclosure relates to a method and a system for automatically generating Artificial Intelligence (AI) powered prototypes. Here, a plurality of AI models is provided in a user interface of the system. Further, a selection of a set of the AI models is received via the user interface. For each of the set of the AI models, identification of input features and data sources is received via the user interface for training each of the plurality of AI models. Further, a selection of one or more rules for aggregating model inputs and model outputs is received via the user interface to form one or more searchable tables of sample data for at least one of the artificial intelligence models. The one or more rules include one or more categories of filtering criteria for populating the one or more searchable tables. In response to the user input, the model inputs in the data sources as defined by the input features are identified and a link between the model inputs and the artificial intelligence model is defined. Further, the one or more searchable tables having one or more columns corresponding to the one or more categories are created. Further, an order of operation of the set of artificial intelligence models is received via the user interface. In the order of operation, an output of one or more first AI models is used as an input for one or more second AI models. Thereafter, an AI ensemble that comprises the set of AI models is generated.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS