Systems and methods for user classification with respect to a chatbot
A system includes a computing device configured to prompt a user to provide an open-ended query, receive, from an input device, the open-ended query, process the open-ended query with an artificial intelligence model. The computing device further classifies the user as either a first or second user level based on attributes of the open-ended query, and executes a rules-engine to analyze the intents and the entities identified by the artificial intelligence model and identify a fulfillment task from a plurality of rule defined tasks corresponding to the analysis of the intents and the entities such that the fulfillment task is identified to fulfill at least the intents. In response to classifying the user as the first user level, the computing device executes the fulfillment task, and in response to classifying the user as the second user level, the user is prompted with closed-ended inquiries to obtain additional intents or entities.
1. A system comprising:
a computing device comprising a processor and a non-transitory computer readable memory, the computing device configured to:
prompt a user to provide an open-ended query,
receive, from an input device, the open-ended query,
process the open-ended query with an artificial intelligence model implemented by the computing device, the artificial intelligence model trained to identify one or more intents and one or more entities expressed in the open-ended query,
classify the user as either a first user level or a second user level based on one or more attributes of the open-ended query, where the first user level indicates the user is more experienced with the system than the second user level,
execute a rules-engine configured to analyze the one or more intents and the one or more entities identified by the artificial intelligence model and identify a fulfillment task from a plurality of rule defined tasks corresponding to the analysis of the one or more intents and the one or more entities such that the fulfillment task is identified to fulfill at least the one or more intents, wherein each of the plurality of rule defined tasks includes one or more required parameters defining one or more task specific intents and entities to fulfill the task,
in response to classifying the user as the first user level:
prompt the user with one or more additional open-ended inquiries to obtain one or more additional intents or one or more additional entities, and
execute the fulfillment task, and
in response to classifying the user as the second user level, prompt the user with one or more closed-ended inquiries to obtain one or more additional intents or one or more additional entities from the user.
2. The system of claim 1 , wherein the computing device configured to apply a prioritization of one or more rules associated with the plurality of rule defined tasks based on the classification of the user as first level user or a second level user to use the one or more rules as prioritized to identify the fulfillment task.
3. The system of claim 1 , wherein to prompt the user, the computing device configured to generate a voice prompt and transmit the voice prompt through a voice response system to the user, generate a text-based prompt and display the text-based prompt via a display on a mobile device of the user, or combinations thereof.
4. The system of claim 1 , wherein the artificial intelligence model includes natural language processing configured to parse the open-ended query to identify the one or more intents and the one or more entities.
5. The system of claim 1 , wherein the computing device is further configured to:
determine the one or more attributes of the open-ended query, wherein the one or more attributes include at least one of a length of the open-ended query, a number of intents expressed in the open-ended query, or a number of entities expressed in the open-ended query,
determine that at least one of the length of the open-ended query exceeds a predetermined length threshold, the number of intents expressed in the open-ended query exceeds a predetermined intents threshold, or the number of entities expressed in the open-ended query exceeds a predetermined entities threshold, and
when at least one of the at least one of the length of the open-ended query exceeds the predetermined length threshold, the number of intents expressed in the open-ended query exceeds the predetermined intents threshold, or the number of entities expressed in the open-ended query exceeds the predetermined entities threshold, classify the user as the first user level.
6. The system of claim 1 , wherein identifying the fulfillment task from the plurality of rule defined tasks corresponding to the analysis of the one or more intents and the one or more entities comprises scoring the plurality of rule defined tasks based on a total number of the one or more required parameters defining the one or more task specific intents and entities to fulfill the fulfillment task that are satisfied by the one or more intents and the one or more entities expressed in the open-ended query, and
selecting the fulfillment task with a highest score determined by the scoring process.
7. The system of claim 1 , wherein the computing device is further configured to:
iteratively,
process additional open-ended responses from the user in response to the one or more additional open-ended inquiries with the artificial intelligence model implemented by the computing device,
execute the rules-engine configured to analyze the one or more additional intents or the one or more entities identified by the artificial intelligence model, and
update identification of the fulfillment task from the plurality of rule defined tasks corresponding to the analysis of the one or more additional intents or the one or more entities.
8. The system of claim 1 , wherein the task includes at least one of adding a new policy, removing an existing policy, or changing an existing policy.
9. The system of claim 1 , wherein the computing device is further configured to:
retrieve information pertaining to one or more intents expressed in the open-ended query from a third party source.
10. A method for employing a chatbot, the method comprising:
prompting, via a computing device, a user to provide an open-ended query;
receiving, at the computing device from an input device, the open-ended query;
process the open-ended query with an artificial intelligence model implemented by the computing device, the artificial intelligence model trained to identify one or more intents and one or more entities expressed in the open-ended query;
classifying the user as either a first user level or a second user level based on one or more attributes of the open-ended query, where the first user level indicates the user is more experienced with the chatbot than the second user level;
executing a rules-engine configured to analyze the one or more intents and the one or more entities identified by the artificial intelligence model and identify a fulfillment task from a plurality of rule defined tasks corresponding to the analysis of the one or more intents and the one or more entities such that the fulfillment task is identified to fulfill at least the one or more intents, wherein each of the plurality of rule defined tasks includes one or more required parameters defining one or more task specific intents and entities to fulfill the task;
in response to classifying the user as the first user level:
prompting the user with one or more additional open-ended inquiries to obtain one or more additional intents or one or more additional entities, and
executing the fulfillment task, and
in response to classifying the user as the second user level, prompting the user with one or more closed-ended inquiries to obtain one or more additional intents or one or more additional entities from the user.
11. The method of claim 10 , wherein further comprising applying a prioritization of one or more rules associated with the plurality of rule defined tasks based on the classification of the user as the first user level or the second user level to use the one or more rules as prioritized to identify the fulfillment task.
12. The method of claim 10 , wherein prompting the user comprises generating a voice prompt and transmitting the voice prompt through a voice response system to the user, generating a text-based prompt and displaying the text-based prompt via a display on a mobile device of the user, or combinations thereof.
13. The method of claim 10 , wherein the artificial intelligence model includes natural language processing configured to parse the open-ended query to identify the one or more intents and the one or more entities.
14. The method of claim 10 , further comprising:
determining one or more attributes of the open-ended query, wherein the one or more attributes include at least one of a length of the open-ended query, a number of intents expressed in the open-ended query, or a number of entities expressed in the open-ended query,
determining that at least one of the length of the open-ended query exceeds a predetermined length threshold, the number of intents expressed in the open-ended query exceeds a predetermined intents threshold, or the number of entities expressed in the open-ended query exceeds a predetermined entities threshold, and
when the at least one of the length of the open-ended query exceeds the predetermined length threshold, the number of intents expressed in the open-ended query exceeds the predetermined intents threshold, or the number of entities expressed in the open-ended query exceeds the predetermined entities threshold, classifying the user as the first user level.
15. The method of claim 10 , wherein identifying the task from the plurality of rule defined tasks corresponding to the analysis of the one or more intents and the one or more entities includes scoring the plurality of rule defined tasks based a total number of the one or more required parameters defining the one or more task specific intents and entities to fulfill the fulfillment task that are satisfied by the one or more intents and the one or more entities expressed in the open-ended query, and
selecting the task with a highest score determined by the scoring process.
16. The method of claim 10 , further comprising:
iteratively,
processing additional open-ended responses from the user in response to the one or more additional open-ended inquiries with the artificial intelligence model implemented by the computing device,
executing the rules-engine configured to analyze the one or more additional intents or the one or more entities identified by the artificial intelligence model, and
updating identification of the fulfillment task from the plurality of rule defined tasks corresponding to the analysis of the one or more additional intents or the one or more entities.
17. A non-transitory computer-readable medium storing instructions that, when executed by a computer processor, cause the computer processor to perform a method associated with a chatbot, the method comprising:
prompting a user to provide an open-ended query;
receiving the open-ended query;
processing the open-ended query with an artificial intelligence model implemented by the computer processor, the artificial intelligence model trained to identify one or more intents and one or more entities expressed in the open-ended query;
classifying the user as either a first user level or a second user level based on one or more attributes of the open-ended query, where the first user level indicates the user is more experienced with the chatbot than the second user level;
executing a rules-engine configured to analyze the one or more intents and the one or more entities identified by the artificial intelligence model and identify a fulfillment task from a plurality of rule defined tasks corresponding to the analysis of the one or more intents and the one or more entities such that the fulfillment task is identified to fulfill at least the one or more intents, wherein each of the plurality of rule defined tasks includes one or more required parameters defining one or more task specific intents and entities to fulfill the task;
in response to classifying the user as the first user level:
prompting the user with one or more additional open-ended inquiries to obtain one or more additional intents or one or more additional entities, and
executing the fulfillment task, and
in response to classifying the user as the second user level, prompting the user with one or more closed-ended inquiries to obtain one or more additional intents or one or more additional entities from the user.
18. The non-transitory computer-readable medium of claim 17 , further comprising:
applying a prioritization of one or more rules associated with the plurality of rule defined tasks based on the classification of the user as the first user level or the second user level to use the one or more rules as prioritized to identify the fulfillment task; and
iteratively,
processing additional open-ended responses from the user in response to the one or more additional open-ended inquiries with the artificial intelligence model implemented by the computer processor,
executing the rules-engine configured to analyze the one or more additional intents or the one or more entities identified by the artificial intelligence model, and
updating identification of the fulfillment task from the plurality of rule defined tasks corresponding to the analysis of the one or more additional intents or the one or more entities.