Generating machine learning model prompts for analyzing collections of unstructured data

A system comprising:

• one or more processors;
• and
• a computer-readable medium storing instructions that are operable when executed by the one or more processors to perform operations comprising:
• receiving user input indicating:
• a set of characteristic attributes to extract from unstructured data in a plurality of documents;
• and
• a set of issue attributes to identify in the unstructured data in the plurality of documents;
• for each characteristic attribute of the set of characteristic attributes, instantiating a characteristic attribute class that includes information defining the respective characteristic attribute;
• for each issue attribute of the set of issue attributes, instantiating an issue attribute class that includes information defining the respective issue attribute;
• constructing a prompt that includes instructions for an ML model to analyze the unstructured data in the plurality of documents, wherein constructing the prompt includes:
• for each instantiated characteristic attribute class, generating a prompt string that includes instructions for extracting the respective characteristic attribute based on the information defining the respective characteristic attribute;
• for each instantiated issue attribute class, generating a prompt string that includes instructions for identifying the respective issue attribute based on the information defining the respective issue attribute;
• and
• combining the generated prompt strings to form the prompt;
• providing the prompt to the ML model and causing the ML model to analyze the unstructured data in the plurality of documents according to the prompt;
• and
• receiving, from the ML model, results in response to the prompt, the results comprising a representation of documents that are determined to be relevant to the prompt based on a score calculated from one or more of the following:
• one or more characteristic attributes extracted from the respective document, or presence of one or more issue attributes identified in the respective document.

A non-transitory computer-readable medium storing instructions that are operable when executed by a data-processing apparatus to perform operations comprising:

• receiving user input indicating:
• a set of characteristic attributes to extract from unstructured data in a plurality of documents;
• and
• a set of issue attributes to identify in the unstructured data in the plurality of documents;
• for each characteristic attribute of the set of characteristic attributes, instantiating a characteristic attribute class that includes information defining the respective characteristic attribute;
• for each issue attribute of the set of issue attributes, instantiating an issue attribute class that includes information defining the respective issue attribute;
• constructing a prompt that includes instructions for an ML model to analyze the unstructured data in the plurality of documents, wherein constructing the prompt includes:
• for each instantiated characteristic attribute class, generating a prompt string that includes instructions for extracting the respective characteristic attribute based on the information defining the respective characteristic attribute;
• for each instantiated issue attribute class, generating a prompt string that includes instructions for identifying the respective issue attribute based on the information defining the respective issue attribute;
• and
• combining the generated prompt strings to form the prompt;
• providing the prompt to the ML model and causing the ML model to analyze the unstructured data in the plurality of documents according to the prompt;
• and
• receiving, from the ML model, results in response to the prompt, the results comprising a representation of documents that are determined to be relevant to the prompt based on a score calculated from one or more of the following:
• one or more characteristic attributes extracted from the respective document, or presence of one or more issue attributes identified in the respective document.