Automated outcome classification systems in contact interactions, and methods

1. A disposition analysis system comprising:

a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations which comprise:

receiving text of a connected contact interaction;

determining, by a natural language processor, a lexeme, a sentiment, entities, and key phrases from the text;

training a neural network to assign a contact disposition to the connected contact interaction by providing training data comprising transcripts classified as having a callback disposition, a do-not-call disposition, and a positive with payment amount to be paid by a customer disposition;

assigning, by the trained neural network, the contact disposition to the connected contact interaction based on the text, the lexeme, the sentiment, the entities, and the key phrases;

generating a disposition response to the connected contact interaction based on the assigned contact disposition, wherein:

the disposition response comprises scheduling a callback to the customer for a specific date and time, and

obtaining the specific date and time from the entities and the key phrases from the text of the connected contact interaction; and

presenting the generated disposition response to a user,

wherein the lexeme comprises a base or root of a word or series of words.

2. The disposition analysis system of claim 1 , wherein the entities comprise people, places, objects, dates, times, quantities, or a combination thereof.

3. The disposition analysis system of claim 1 , wherein the connected contact interaction comprises a call interaction, and the operations further comprise converting the call interaction to the text.

4. The disposition analysis system of claim 1 , wherein the operations further comprise recording the generated disposition response.

5. The disposition analysis system of claim 1 , wherein the assigned contact disposition indicates that a specific agent should call the customer back, or that any agent can call the customer back.

6. A method of generating a disposition response, which comprises:

receiving text of a connected contact interaction;

determining, by a natural language processor, a lexeme, a sentiment, entities, and key phrases from the text;

training a neural network to assign a contact disposition to the connected contact interaction by providing training data comprising transcripts classified as having a callback disposition, a do-not-call disposition, and a positive with payment amount to be paid by a customer disposition;

assigning, by the trained neural network, the contact disposition to the connected contact interaction based on the text, the lexeme, the sentiment, the entities, and the key phrases;

generating a disposition response to the connected contact interaction based on the assigned contact disposition, wherein:

the disposition response comprises scheduling a callback to the customer for a specific date and time, and

obtaining the specific date and time from the entities and the key phrases from the text of the connected contact interaction; and

presenting the generated disposition response to a user,

wherein the lexeme comprises a base or root of a word or series of words.

7. The method of claim 6 , wherein the connected contact interaction comprises a call interaction, and the method further comprises converting the call interaction to the text.

8. The method of claim 6 , further comprising recording the generated disposition response.

9. The method of claim 6 , wherein the assigned contact disposition indicates that a specific agent should call the customer back, or that any agent can call the customer back.

10. A non-transitory computer-readable medium having stored thereon computer-readable instructions executable by a processor to perform operations which comprise:

receiving text of a connected contact interaction;

determining, by a natural language processor, a lexeme, a sentiment, entities, and key phrases from the text;

training a neural network to assign a contact disposition to the connected contact interaction by providing training data comprising transcripts classified as having a callback disposition, a do-not-call disposition, and a positive with payment amount to be paid by a customer disposition;

assigning, by the trained neural network, the contact disposition to the connected contact interaction based on the text, the lexeme, the sentiment, the entities, and the key phrases;

generating a disposition response to the connected contact interaction based on the assigned contact disposition, wherein:

the disposition response comprises scheduling a callback to the customer for a specific date and time, and

obtaining the specific date and time from the entities and the key phrases from the text of the connected contact interaction; and

presenting the generated disposition response to a user,

wherein the lexeme comprises a base or root of a word or series of words.

11. The non-transitory computer-readable medium of claim 10 , wherein the connected contact interaction comprises a call interaction, and the operations further comprise converting the call interaction to the text.

12. The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise recording the generated disposition response.

13. The non-transitory computer-readable medium of claim 10 , wherein the assigned contact disposition indicates that a specific agent should call the customer back, or that any agent can call the customer back.