Automatically rectifying in real-time anomalies in natural language processing systems
A method for automatically rectifying in real-time anomalies in natural language processing systems. The method can include receiving command data from a user device of a user. The command data can correspond to a user request. The method further can include retrieving, from a new template database, a new request template corresponding to the user request. Additionally, the method can include retrieving, from the new template database, an output instruction corresponding to the new request template, when the new request template is found. The method further can include determining, by a machine learning system, the output instruction corresponding to the user request, when the new request template is not found. The method also can include transmitting the output instruction to a request processing system. The request processing system can be configured to perform the output instruction and transmit, to the user device, a response to the user request. Other embodiments are disclosed.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, perform:
receiving command data from a user device of a user, wherein the command data corresponds to a user request;
retrieving, from a new template database, a new request template corresponding to the user request;
when the new request template is found, retrieving, from the new template database, an output corresponding to the new request template;
when the new request template is not found, determining, by machine learning, an output corresponding to the user request;
extracting entity information from entity data of the user request;
retrieving, from an entity rule database, one or more entity rules corresponding to the entity data;
when the one or more entity rules are found, overwriting the entity information corresponding to the one or more entity rules;
after extracting the entity information, outputting the output corresponding to the new request template or the user request; and
after outputting the output, transmitting, to the user device, a response to the user.
2. The system in claim 1 , wherein:
the new template database comprises one or more new frequently-asked-questions (FAQ) templates and one or more corresponding new FAQ answers; and
when the one or more new FAQ templates comprise the new request template, the one or more corresponding new FAQ answers comprise the output corresponding to the new request template.
3. The system in claim 1 , wherein:
the new template database comprises an in-memory database.
4. The system in claim 3 , wherein:
the computing instructions, when executed on the one or more processors, further perform:
loading at least a portion of the new template database at a frequency; and
the frequency is at least as great as a predetermined frequency threshold.
5. The system in claim 1 , wherein:
the command data comprise audio data; and
the computing instructions, when executed on the one or more processors, further perform:
determining, in real-time after receiving the command data, using automated speech recognition processing, the user request from the audio data.
6. The system in claim 5 , wherein:
the computing instructions, when executed on the one or more processors, further perform:
retrieving, from a new pattern database, in real-time after determining the user request from the audio data, a new pattern template corresponding to the user request; and
when the new pattern template is found, revising the user request based on the new pattern template.
7. The system in claim 6 , wherein:
the new pattern database comprises an in-memory database.
8. The system in claim 1 , wherein:
the computing instructions, when executed on the one or more processors, further perform:
receiving, from a user interface executed on an admin device, an admin command associated with a second new request template; and
performing, after receiving the admin command, the admin command associated with the second new request template at the new template database.
9. The system in claim 1 , wherein:
the entity rule database comprises an in-memory database.
10. A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
receiving command data from a user device of a user, wherein the command data corresponds to a user request;
retrieving, from a new template database, a new request template corresponding to the user request;
when the new request template is found, retrieving, from the new template database, an output corresponding to the new request template;
when the new request template is not found, determining, by machine learning, an output corresponding to the user request;
extracting entity information from entity data of the user request;
retrieving, from an entity rule database, one or more entity rules corresponding to the entity data;
when the one or more entity rules are found, overwriting the entity information corresponding to the one or more entity rules;
after extracting the entity information, outputting the output corresponding to the new request template or the user request; and
after outputting the output, transmitting, to the user device, a response to the user.
11. The method in claim 10 , wherein:
the new template database comprises one or more new frequently-asked-questions (FAQ) templates and one or more corresponding new FAQ answers; and
when the one or more new FAQ templates comprise the new request template, the one or more corresponding new FAQ answers comprise the output corresponding to the new request template.
12. The method in claim 10 , wherein:
the new template database comprises an in-memory database.
13. The method in claim 12 further comprising:
loading at least a portion of the new template database at a frequency,
wherein:
the frequency is at least as great as a predetermined frequency threshold.
14. The method in claim 10 further comprising:
determining, in real-time after receiving the command data, using automated speech recognition processing, the user request from audio data of the command data.
15. The method in claim 14 further comprising:
retrieving, from a new pattern database, in real-time after determining the user request from the audio data, a new pattern template corresponding to the user request; and
when the new pattern template is found, revising the user request based on the new pattern template.
16. The method in claim 15 , wherein:
the new pattern database comprises an in-memory database.
17. The method in claim 10 further comprising:
receiving, from a user interface executed on an admin device, an admin command associated with a second new request template; and
performing, after receiving the admin command, the admin command associated with the second new request template at the new template database.
18. The method in claim 10 , wherein:
the entity rule database comprises an in-memory database.
19. The system in claim 9 , wherein:
the computing instructions, when executed on the one or more processors, further perform:
loading at least a portion of the entity rule database at a frequency; and
the frequency is at least as great as a predetermined frequency threshold.
20. The method in claim 18 further comprising:
loading at least a portion of the entity rule database at a frequency,
wherein:
the frequency is at least as great as a predetermined frequency threshold.