Techniques to add smart device information to machine learning for increased context

A method for contextualized information exchange, comprising:

• receiving information from a user;
• inferring an inferred result, based on the information and health information associated with the user via a first chatbot model, the first chatbot model trained based on data, the data comprising multiple different data types captured from a computing device for contextualization of dialog data, stored in a data structure, with a chain of values, in a standardized format for use in training the first chatbot model, including individual probability values indicating a probability of correspondence between each of a plurality of data elements and probability values indicating a probability of a relationship between the data elements having a correspondence, wherein the chain of values is generated with the data elements that have been transformed, wherein each data element is transformed by a transformation that is selected based on the data type associated with the respective data element, wherein the data comprises non-dialog data including the health information captured by a smart device associated with the user;
• and
• generating information to exchange with the user based on the inferred result.

A non-transitory machine-readable medium comprising instructions, wherein execution of the instructions causes processing circuitry to perform functions to:

• receive information from a user;
• infer an inferred result, based on the information and health information associated with the user via a first chatbot model, the first chatbot model trained based on data, the data comprising multiple different data types captured from a computing device for contextualization of dialog data, stored in a data structure, with a chain of values, in a standardized format for use in training the first chatbot model, including individual probability values indicating a probability of correspondence between each of a plurality of data elements and probability values indicating a probability of a relationship between the data elements having a correspondence, wherein the chain of values is generated with the data elements that have been transformed, wherein each data element is transformed by a transformation that is selected based on the data type associated with the respective data element, wherein the data comprises non-dialog data including the health information captured by a smart device associated with the user;
• and
• generate information to exchange with the user based on the inferred result.