Systems, methods, and apparatuses for implementing data upload, processing, and predictive query API exposure

摘要

Disclosed herein are systems and methods for implementing data upload, processing, and predictive query API exposure including means for receiving a dataset in a tabular form, the dataset having a plurality of rows and a plurality of columns; processing the dataset to generate indices representing probabilistic relationships between the rows and the columns of the dataset; storing the indices in a database; exposing an Application Programming Interface (API) to query the indices in the database; receiving a request for a predictive query or a latent structure query against the indices in the database; querying the database for a prediction based on the request via the API; and returning the prediction responsive to the request. Other related embodiments are further disclosed.

主权项

1. A method comprising:
receiving a dataset in a tabular form, the dataset having a plurality of rows and a plurality of columns; processing the dataset to generate indices representing probabilistic relationships between the rows and the columns of the dataset, wherein the processing includes learning a joint probability distribution over the dataset to identify and describe the probabilistic relationship between elements of the dataset, the learning being controlled by a default set of configuration parameters; storing the indices in a database; exposing an Application Programming Interface (API) to query the indices in the database system; receiving a request for a predictive query or a latent structure query against the indices in the database system, wherein the request includes at least one specified column as an input parameter with the predictive query or the latent structure query; querying the database system for a predictive result set or a latent structure result responsive to the request for the predictive query or the latent structure query respectively, the querying submitted to the database system via the API using the predictive query or the latent structure query and the at least one specified column as the input parameter to the querying; and returning the predictive result set or a latent structure result responsive to the request, wherein a confidence indicator is returned with the predictive result set or a latent structure result, the confidence indicator indicating whether a predictive relationship or a latent relationship exist between the at least one specified column and elements of the predictive result set or a latent structure result.