DYNAMIC RECREATION OF EXISTING WORKFLOW IVR MENUS USING INTELLIGENT GENERATIVE MODELS

1 . A computerized method for converting an interactive voice response (IVR) tree into a natural language conversion architecture, wherein the computerized method comprises the following steps:

converting IVR tree audio data into IVR tree text data, the IVR tree audio data includes spoken language generated using the IVR tree during a phone call;

providing the IVR tree text data to a machine learning model with instructions on how to evaluate the IVR tree text data; and

the machine learning model generating a set of natural language prompts based upon the IVR tree text data, wherein the set of natural language prompts include instructions for directing a received call based upon caller voice input.

2 . The computerized method of claim 1 that further comprises the step of providing an internal IVR architecture data together with the IVR tree text data to the machine learning model, the set of natural language prompts are generated based upon the internal IVR architecture data, and the instructions include how to evaluate the internal IVR architecture data.

3 . The computerized method of claim 2 that further comprises the step of supplementing the IVR tree text data with the internal IVR architecture data prior to providing the IVR tree text data to the machine learning model.

4 . The computerized method of claim 1 , wherein the step of converting IVR tree audio data into IVR tree text data includes utilizing a speech-to-text module to convert the IVR tree audio data into the IVR tree text data.

5 . The computerized method of claim 1 , wherein the step of converting IVR tree audio data into IVR tree text data includes using a depth-first traversal technique for traversing the IVR tree text data.

6 . The computerized method of claim 1 , wherein the IVR tree text data comprises a structured text file.

7 . The computerized method of claim 1 , wherein the machine learning model comprises a machine learning transformer model.

8 . A computerized system configured to convert an interactive voice response (IVR) tree into a natural language conversion architecture, wherein the computerized system comprises:

a processor configured to convert IVR tree audio data into IVR tree text data, the IVR tree audio data includes spoken language generated using the IVR tree during a phone call; and

a machine learning model configured to receive the IVR tree text data for generating a set of natural language prompts based upon the IVR tree text data, wherein the set of natural language prompts include instructions for directing a received call based upon caller voice input.

9 . The computerized system of claim 8 that further comprises a database comprising an internal IVR architecture data, the machine learning model is configured to receive the internal IVR architecture data together with the IVR tree text data for generating the set of natural language prompts based upon the IVR tree text data and the internal IVR architecture data.

10 . The computerized system of claim 9 , wherein the processor is further configured to supplement the IVR tree text data using the internal IVR architecture data prior to providing the IVR tree text data to the machine learning model.

11 . The computerized system of claim 8 , wherein the processor comprises a speech-to-text module to convert the spoken language into the IVR tree text data.

12 . The computerized system of claim 8 , wherein the processor uses a depth-first traversal technique for traversing the IVR tree text data when converting the spoken language into the IVR tree text data.

13 . The computerized system of claim 8 , wherein the IVR tree text data comprises a structured text file.

14 . The computerized system of claim 8 , wherein the machine learning model comprises a machine learning transformer model.

15 . The computerized system of claim 8 that further comprises a large language model (LLM) module configured to analyze the set of natural language prompts.

16 . A computerized apparatus configured to convert an interactive voice response (IVR) tree into a natural language conversion architecture, wherein the computerized apparatus comprises: (a) a processor; (b) a machine learning model; and (c) a tangible, non-transitory memory configured to communicate with the processor, the non-transitory memory having stored instructions which, when executed by the processor, are configured to cause the computerized apparatus to execute a method including the following steps:

the processor converting IVR tree audio data into IVR tree text data, the IVR tree audio data includes spoken language generated using an IVR tree during a phone call;

providing the IVR tree text data to the machine learning model with instructions on how to evaluate the IVR tree text data; and

the machine learning model generating a set of natural language prompts based upon the IVR tree text data, wherein the set of natural language prompts include instructions for directing a received call based upon caller voice input.

17 . The computerized apparatus of claim 16 that further comprises a database comprising an internal IVR architecture data, the machine learning model is configured to receive the internal IVR architecture data together with the IVR tree text data for generating the set of natural language prompts based upon the IVR tree text data and the internal IVR architecture data.

18 . The computerized apparatus of claim 17 , wherein the processor is further configured to supplement the IVR tree text data using the internal IVR architecture data prior to providing the IVR tree text data to the machine learning model.

19 . The computerized apparatus of claim 16 , wherein the processor uses a depth-first traversal technique for traversing the IVR tree text data when converting the spoken language into the IVR tree text data.

20 . The computerized apparatus of claim 16 , wherein the machine learning model comprises a machine learning transformer model.