US 2023/0141408 A1 · UTILIZING MACHINE LEARNING AND NATURAL LANGUAGE GENERATION MODELS TO GENERATE A DIGITIZED DYNAMIC CLIENT SOLUTION

Abstract

A device may receive historical project data identifying experiences and/or work product from previous projects and client data identifying a client with a problem, and may process the historical project data and the client data, with machine learning models, to generate recommendations for the problem and confidence scores for the recommendations. The device may process the recommendations and the confidence scores, with an NLG model, to generate a solution to the problem and content for the solution, and may generate a digitized dynamic client solution to the problem based on the solution and the content. The device may provide the digitized dynamic client solution to a user device, and may receive feedback on the digitized dynamic client solution from the user device. The device may generate a final digitized dynamic client solution based on the feedback, and may perform actions based on the final digitized dynamic client solution.

Claims20

Dependent claims

A method, comprising:

receiving, by a device, historical project data identifying experiences and/or work product from previous projects and client data identifying a client with a problem;
processing, by the device, the historical project data and the client data, with one or more machine learning models, to generate recommendations for the problem of the client and confidence scores for the recommendations;
processing, by the device, the recommendations and the confidence scores, with a natural language generation model, to generate a solution to the problem of the client and content for the solution;
generating, by the device, a digitized dynamic client solution to the problem based on the solution and the content for the solution;
providing, by the device, the digitized dynamic client solution to one or more user devices;
receiving, by the device, feedback on the digitized dynamic client solution from the one or more user devices;
generating, by the device, a final digitized dynamic client solution based on the feedback on the digitized dynamic client solution;
and
performing, by the device, one or more actions based on the final digitized dynamic client solution.

6 more elements

A device, comprising:

one or more memories;
and
one or more processors, coupled to the one or more memories, configured to:
receive historical project data identifying experiences and/or work product from previous projects and client data identifying a client with a problem;
process the historical project data and the client data, with one or more machine learning models, to generate recommendations for the problem of the client and confidence scores for the recommendations,
wherein each of the recommendations includes:
a template structure,
one or more content sections for the template structure,
a design for the template structure, and
one or more templates generated by subject matter experts;
process the recommendations and the confidence scores, with a natural language generation model, to generate a solution to the problem of the client and content for the solution;
generate a digitized dynamic client solution to the problem based on the solution and the content for the solution;
provide the digitized dynamic client solution to one or more user devices;
receive feedback on the digitized dynamic client solution from the one or more user devices;
generate a final digitized dynamic client solution based on the feedback on the digitized dynamic client solution;
and
perform one or more actions based on the final digitized dynamic client solution.

14 more elements

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the device to:
receive historical project data identifying experiences and/or work product from previous projects and client data identifying a client with a problem,
wherein the client data includes data identifying one or more of:
a financial analysis associated with the client,
key financial insights associated with the client,
earnings call transcripts associated with the client,
priorities associated with the client,
operational key performance indicators associated with the client, or
value propositions associated with the client;
process the historical project data and the client data, with one or more machine learning models, to generate recommendations for the problem of the client and confidence scores for the recommendations;
process the recommendations and the confidence scores, with a natural language generation model, to generate a solution to the problem of the client and content for the solution;
generate a digitized dynamic client solution to the problem based on the solution and the content for the solution;
provide the digitized dynamic client solution to one or more user devices;
receive feedback on the digitized dynamic client solution from the one or more user devices;
generate a final digitized dynamic client solution based on the feedback on the digitized dynamic client solution;
and
perform one or more actions based on the final digitized dynamic client solution.

14 more elements

Dependencies are inferred from the claim text.

Utilizing machine learning and natural language generation models to generate a digitized dynamic client solution

Life of this patent

Utilizing machine learning and natural language generation models to generate a digitized dynamic client solution

Life of this patent

Abstract

Claims20