Enterprise application query enrichment for language models

1 . A method for generating queries comprising:

receiving, by one or more processors, via a user interface of an enterprise application, a request for assistance with handling a task identified in an enterprise application record, the record comprising a work order or purchase order regarding an asset;

determining, by the one or more processors using an enterprise interpretation model comprising a first machine learning model, data corresponding to the record to generate a first query;

generating, by the one or more processors using the enterprise interpretation model, a second query for a second machine learning model trained to provide assistance with the enterprise application, wherein the second query is generated using the data corresponding to the record and the first query automatically obtained using the first machine learning model, and the second query is generated with asset-specific technical attributes to form a structured prompt configured to prompt a response from the second machine learning model that provides focused information tailored to the asset identified in the enterprise application record in response to the request for assistance;

providing, by the one or more processors, the second query to the second machine learning model; and

outputting, by the one or more processors, via the user interface of the enterprise application, the response from the second machine learning model.

2 . The method of claim 1 , wherein the second machine learning model is a language model, large language model, or generative model.

3 . The method of claim 1 , wherein the first machine learning model is a natural language processing model, a language model, or a large language model.

4 . The method of claim 1 , wherein the record is one of a plurality of unique records of the enterprise application.

5 . The method of claim 4 , wherein the data corresponding to the record includes data within the record and data stored in association with an asset identified in the record.

6 . The method of claim 4 , wherein the record is associated with an asset and comprises data corresponding to the asset.

7 . The method of claim 6 , wherein the record further contains a task or problem associated with the asset.

8 . A system for generating queries comprising:

one or more processors configured to:

receive, via a user interface of an enterprise application, a request for assistance with handling a task identified in an enterprise application record, the record comprising a work order or purchase order regarding an asset;

determine, using an enterprise interpretation model comprising a first machine learning model, data corresponding to the record to generate a first query;

generate, using the enterprise interpretation model, a second query for a second machine learning model trained to provide assistance with the enterprise application, wherein the second query is generated using the data corresponding to the record and the first query automatically obtained using the first machine learning model, and the second query is generated with asset-specific technical attributes to form a structured prompt configured to prompt a response from the second machine learning model that provides focused information tailored to the asset identified in the enterprise application record in response to the request for assistance;

provide the second query to the second machine learning model; and

output, via the user interface of the enterprise application, the response from the second machine learning model.

9 . The system of claim 8 , wherein the second machine learning model is a language model, large language model, or generative model.

10 . The system of claim 8 , wherein the first machine learning model is a natural language processing model, a language model, or a large language model.

11 . The system of claim 8 , wherein the record is one of a plurality of unique records of the enterprise application.

12 . The system of claim 11 , wherein the data corresponding to the record includes data within the record and data stored in association with an asset identified in the record.

13 . The system of claim 11 , wherein the record is associated with an asset and comprises data corresponding to the asset.

14 . The system of claim 13 , wherein the record further contains a task or problem associated with the asset.

15 . A non-transitory computer readable medium storing instructions, that when executed by one or more processors, cause the one or more processors to:

receive, via a user interface of an enterprise application, a request for assistance with handling a task identified in an enterprise application record, the record comprising a work order or purchase order regarding an asset;

determine, using an enterprise interpretation model comprising a first machine learning model, data corresponding to the record to generate a first query;

generate, using the enterprise interpretation model, a second query for a second machine learning model trained to provide assistance with the enterprise application, wherein the second query is generated using the data corresponding to the record and the first query automatically obtained using the first machine learning model, and the second query is generated with asset-specific technical attributes to form a structured prompt configured to prompt a response from the second machine learning model that provides focused information tailored to the asset identified in the enterprise application record in response to the request for assistance;

provide the second query to the second machine learning model; and

output, via the user interface of the enterprise application, the response from the second machine learning model.

16 . The non-transitory computer readable medium of claim 15 , wherein the first and second machine learning models are language models, large language models, and/or generative models.