Using a client-side machine learning model dynamically in a mobile enterprise application on a mobile device

A non-transitory computer-readable medium containing program instructions, which when executed by one or more processors, cause the one or more processors to carry out the steps of:

• responsive to a user of the development platform logging in from a remote computer, presenting to a remote computer of the user of the development platform a user interface (UI) displaying a ML model configuration page;
• receiving from the ML model configuration page a user upload of a trained ML model and configuration data, the configuration data including an input data format and an output data format of the trained ML model;
• storing the uploaded trained ML model and the configuration data in a tenant database of the user in the development platform;
• generating, by the development platform and based on the configuration data, an Application Programming interface (API) for the trained ML model and storing the API in the tenant database of the user, wherein the generating the API is performed without using an API provided by the user, wherein the generated API is configured to pass input in the input data format to the trained ML model and configured to receive output in the output data format from the trained ML model for further processing or display;
• and
• downloading the trained ML model and the generated API and the configuration data to the mobile enterprise application installed on a mobile device.

A multi-tenant development platform, comprising:

• a mobile enterprise application installed on a plurality of mobile devices of a tenant, the mobile enterprise application having a hybrid structure comprising a web layer and a native layer;
• and
• one or more servers including instructions stored thereon that, in response to execution by the multi-tenant development platform, are operable to:
• receive, by the one or more servers, an upload of a trained ML model and configuration data from a tenant user, wherein the configuration data defines an input data format and an output data format of the trained ML model;
• generate, by the one or more servers and based on the configuration data, an Application Programming Interface (API) for the trained ML model and download the API to the mobile enterprise application on the mobile devices, wherein the API is generated without using an API provided by the tenant, wherein the generated API is configured to pass input in the input data format to the trained ML model and configured to receive output in the output data format from the trained ML model for further processing or display;
• and
• download, by the one or more servers, the trained ML model to the mobile enterprise application on the plurality of mobile devices in response to a request by the native layer of the mobile enterprise application.