Autocomplete prediction engine providing automatic form filling from email and ticket extractions
A method is provided. The method is executed by an autocomplete prediction engine implemented as a computer program within a computing environment. The autocomplete prediction engine executes automated communication mining on a communication. The method includes processing the communication to extract intents and entities related to each intent. The method includes providing the intents and the entities into forms using a language model to provide a conversational or natural language understanding of the communication.
1. A method executed by an autocomplete prediction engine implemented as a computer program within a computing environment, the autocomplete prediction engine executing automated communication mining on a communication, the method comprising:
generating, by the autocomplete prediction engine, a pre-training dataset by parsing through each article, a type of each article, abstractions, and structured information in a database to collect at least a plurality of article types;
processing, by the autocomplete prediction engine, the communication comprising conversational message data or text between two or more computers, systems, or users, the processing of the communication comprising:
extracting two or more intents and a set of entities related to each intent of the two or more intents from the conversational message data or text of the communication, the autocomplete prediction engine being pre-trained on the pre-training dataset for extracting the two or more intents and the set of entities utilizing each type of the plurality of article types; and
providing, by the autocomplete prediction engine, the two or more intents and the sets of entities into one or more forms and one or more demarcations into the communication using a language model to provide a conversational or natural language understanding of the communication.
2. The method of claim 1 , wherein the autocomplete prediction engine achieves the conversational or natural language understanding of the communication to ascertain and implement a desire within the communication.
3. The method of claim 1 , wherein the message comprises an email conversation, a service ticket, a short message service message, a transcript, a text message, or a chat message.
4. The method of claim 1 , wherein each intent of the two or more intents comprises a desire, goal, or purpose of the communication or of portions of data in the communication.
5. The method of claim 1 , wherein each entity of the set of entities comprises data of the communication.
6. The method of claim 1 , wherein the language model comprises a FLAN-T5 model.
7. The method of claim 1 , wherein the autocomplete prediction engine converts the pre-training dataset into a JavaScript Object Notation (JSON) object.
8. A computer program product comprising an autocomplete prediction engine, the computer program product stored on a non- transitory computer readable medium and executable by one or more processors to cause the autocomplete prediction engine to implement automated communication mining on a communication, operations of the computer program product comprising:
generating, by the autocomplete prediction engine, a pre-training dataset by parsing through each article, a type of each article, abstractions, and structured information in a database to collect at least a plurality of articles;
processing, by the autocomplete prediction engine, the communication comprising conversational message data or text between two or more computers, systems, or users, the processing of the communication comprising:
extracting two or more intents and a set of entities related to each intent of the two or more intents from the conversational message data or text of the communication, the autocomplete prediction engine being pre-trained on the pre-training dataset for extracting the two or more intents and the set of entities utilizing each type of the plurality of article types; and
providing, by the autocomplete prediction engine, the two or more intents and the sets of entities into one or more forms and one or more demarcations into the communication using a language model to provide a conversational or natural language understanding of the communication.
9. The computer program product of claim 8 , wherein the autocomplete prediction engine achieves the conversational or natural language understanding of the communication to ascertain and implement a desire within the communication.
10. The computer program product of claim 8 , wherein the message comprises an email conversation, a service ticket, a short message service message, a transcript, a text message, or a chat message.
11. The computer program product of claim 8 , wherein each intent of the two or more intents comprises a desire, goal, or purpose of the communication or of portions of data in the communication.
12. The computer program product of claim 8 , wherein each entity of the set of entities comprises data of the communication.
13. The computer program product of claim 8 , wherein the language model comprises a FLAN-T5 model.
14. The computer program product of claim 8 , wherein the autocomplete prediction engine converts the pre-training dataset into a JavaScript Object Notation (JSON) object.
15. The method of claim 1 , wherein the autocomplete prediction engine generates the pre-training dataset from at least the database comprising abstractions and structured information from at least one or more web-pages.
16. The method of claim 1 , wherein the autocomplete prediction engine provides a unified interface comprising a first sub-interface presenting the two or more intents, the sets of entities, and the one or more forms and first sub-interface presenting the one or more demarcations and the communication.
17. The method of claim 1 , wherein the one or more demarcations respectively corresponding to the two or more intents and the sets of entities.