Dynamic intent classification based on environment variables
To prevent intent classifiers from potentially choosing intents that are ineligible for the current input due to policies, dynamic intent classification systems and methods are provided that dynamically control the possible set of intents using environment variables (also referred to as external variables). Associations between environment variables and ineligible intents, referred to as culling rules, are used.
1. A dynamic intent classification system, comprising:
a processor; and
a memory operably coupled to the processor, the memory having computer-executable instructions stored thereon that, when executed by the processor causes the system to:
generate and store, in a database, a plurality of culling rules based at least in part on environment variables;
receive, at a natural language understanding (NLU) component, a user input;
alter a classifier of the NLU component, wherein the classifier comprises a language model, and wherein the classifier is altered using the plurality of culling rules without retraining or redeployment of the language model;
determine, using the classifier, an intent based at least in part on the user input and the plurality of culling rules; and
output, by the NLU component, a response to the user input based at least in part on the determined intent.
2. The system of claim 1 , wherein the database and the classifier are comprised within a computing device.
3. The system of claim 1 , wherein the database and the classifier are comprised within a chatbot.
4. The system of claim 3 , wherein the chatbot is configured to provide a processed language output based on the intent.
5. The system of claim 1 , wherein the classifier is a rule-based classifier, a tree-based classifier, a grammar-based classifier, or a statistically-trained classifier.
6. The system of claim 1 , wherein the environment variables comprise at least one of time of day or input channel.
7. The system of claim 1 , wherein the classifier is alterable using the culling rules to generate a plurality of culled intents.
8. The system of claim 1 , wherein the classifier is configured to eliminate ineligible intents.
9. A method of providing a response to input data using dynamic intent classification based on environment variables, the method comprising:
maintaining a plurality of culling rules based on a plurality of environment variables, at a natural language understanding (NLU) component;
receiving an input data at the NLU component;
altering a classifier of the NLU component, wherein the classifier comprises a language model, and wherein the classifier is altered using the plurality of culling rules without retraining or redeployment of the language model;
determining an intent for the input data using the culling rules, at the classifier of the NLU component; and
outputting, by the NLU component, a response to the input data based at least in part on the determined intent.
10. The method of claim 9 , further comprising providing a processed language output, by a chatbot, based on the intent.
11. The method of claim 9 , further comprising:
receiving the plurality of environment variables at the NLU component; and
determining the plurality of culling rules using the plurality of environment variables.
12. The method of claim 9 , further comprising altering the classifier using the culling rules to generate a plurality of culled intents.
13. The method of claim 9 , further comprising configuring the classifier to eliminate ineligible intents using the culling rules.
14. The method of claim 9 , further comprising maintaining the plurality of culling rules in storage external to the classifier.
15. The method of claim 9 , wherein the classifier is a rule-based classifier, a tree-based classifier, a grammar-based classifier, or a statistically-trained classifier.
16. The method of claim 9 , wherein the plurality of environment variables comprise at least one of time of day or input channel.
17. A method comprising:
receiving a plurality of culling rules at a classifier of a natural language understanding (NLU) component, wherein the plurality of culling rules are based on a plurality of environment variables; and
receiving, at the NLU component, a user input;
altering the classifier of the NLU component, wherein the classifier comprises a language model, and wherein the classifier is altered using the plurality of culling rules without retraining or redeployment of the language model;
determining, using the classifier, an intent based at least in part on the user input and the plurality of culling rules; and
outputting, by the NLU component, a response to the user input based at least in part on the determined intent.
18. The method of claim 17 , further comprising maintaining the plurality of culling rules in storage external to the classifier.
19. The method of claim 17 , wherein the classifier is a rule-based classifier, a tree-based classifier, a grammar-based classifier, or a statistically-trained classifier.
20. The method of claim 17 , further comprising configuring the classifier to eliminate ineligible intents using the culling rules.