Method and system for generating a response structure using a chatbot user interface

1 . A system for generating a response structure using a chatbot user interface, wherein the system comprises:

a display device, wherein the display device displays a graphical user interface;

at least a computing device, wherein the computing device comprises:

a memory; and

at least a processor communicatively connected to the memory, wherein the memory contains instructions configuring the at least a processor to:

receive a first query using a chatbot interface operating on the display device;

generate an action protocol as a function of the first query, wherein generating the action protocol comprises:

generating a set of requested data constraints using a constraint machine-learning model, wherein generating the set of requested data constraints comprises:

training the constraint machine-learning model, wherein training the constraint machine-learning model comprises:

 sanitizing training data to eliminate noise, wherein the training data comprises a plurality of query data correlated with a plurality of example constraint data;

 determining that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and

 removing the at least one training data entry from the training data to create sanitized training data; and

 training the constraint machine-learning model using the sanitized training data until the constraint machine-learning model satisfies a convergence test, wherein sanitizing of the training data accelerates convergence of the constraint machine-learning model; and

generating the set of requested data constraints using the trained constraint machine-learning model; and

mapping the set of requested data constraints to a range of database entries;

generate a response structure as a function of the action protocol, wherein generating the response comprises:

retrieving requested data from a database using the range of database entries specified by the action protocol;

inputting the requested data and the query associated with the action protocol into a second machine-learning model; and

generating the response structure under control of the action protocol using the second machine-learning model;

configure the display device to display the response structure using the chatbot interface;

receive, through the chatbot interface, a second query from a user;

identify one or more new parameters from the second query;

adjust the set of requested data constraints of the action protocol as a function of the one or more new parameters; and

reconfigure one or more visual elements of the response structure as a function of the adjusted set of requested data constraints.

2 . The system of claim 1 , wherein generating the action protocol comprises parsing a database.

3 . The system of claim 2 , wherein parsing the database comprises:

searching the range of database entries;

generating a request for additional information in an event that the range of database entries are empty;

presenting, using the display device, the request for additional information to a user; and

receiving, as user input, the additional information in response to the request for additional information.

4 . The system of claim 1 , wherein generating the response structure comprises generating at least a slide file.

5 . The system of claim 1 , wherein the constraint machine-learning model is iteratively trained as a function of user feedback relating to an accuracy of an output of the constraint machine-learning model.

6 . The system of claim 1 , wherein the constraint machine-learning model comprises a classifier configured to classify the first query to the set of requested data constraints.

7 . The system of claim 1 , wherein configuring the display device to display the response structure comprises generating a display data structure using a plurality of visual elements and at least an event handler.

8 . A method for generating a response structure using a chatbot user interface, wherein the method comprises:

receiving, by at least a processor, a first query using a chatbot interface operating on a display device;

generating, by the at least a processor, an action protocol as a function of the first query, wherein generating the action protocol comprises:

generating a set of requested data constraints using a constraint machine-learning model, wherein generating the set of requested data constraints comprises:

training the constraint machine-learning model, wherein training the constraint machine-learning model comprises:

sanitizing training data to eliminate noise, wherein the training data comprises a plurality of query data correlated with a plurality of example constraint data;

determining that at least one training data entry of the training data has a signal to noise ratio below a threshold value;

removing the at least one training data entry from the training data to create sanitized training data; and

training the constraint machine-learning model using the sanitized training data until the constraint machine-learning model satisfies a convergence test, wherein sanitizing of the training data accelerates convergence of the constraint machine-learning model; and

generating the set of requested data constraints using the trained constraint machine-learning model; and

mapping the set of requested data constraints to a range of database entries;

generating, by the at least a processor, a response structure as a function of the action protocol, wherein generating the response comprises:

retrieving requested data from a database using the range of database entries specified by the action protocol;

inputting the requested data and the query associated with the action protocol into a second machine-learning model; and

generating the response structure under control of the action protocol using the second machine-learning model;

configuring, by the at least a processor, the display device to display the response structure using the chatbot interface;

receiving, through the chatbot interface, a second query from a user;

identifying, using the at least a processor, one or more new parameters from the second query;

adjusting, using the at least a processor, the set of requested data constraints of the action protocol as a function of the one or more new parameters; and

reconfiguring, using the at least a processor, one or more visual elements of the response structure as a function of the adjusted set of requested data constraints.

9 . The method of claim 8 , wherein generating the action protocol comprises parsing a database.

10 . The method of claim 9 , wherein parsing the database comprises:

searching the range of database entries;

generating a request for additional information in an event that the range of database entries are empty;

presenting, using the display device, the request for additional information to a user; and

receiving, as user input, the additional information in response to the request for additional information.

11 . The method of claim 8 , wherein generating the response structure comprises generating at least a slide file.

12 . The method of claim 8 , wherein the constraint machine-learning model is iteratively trained as a function of user feedback relating to an accuracy of an output of the constraint machine-learning model.

13 . The method of claim 8 , wherein the constraint machine-learning model comprises a classifier configured to classify the first query into one or more data constraints.

14 . The method of claim 8 , wherein configuring the display device to display the response structure comprises generating a display data structure using a plurality of visual elements and at least an event handler.

15 . The system of claim 1 , wherein reconfiguring one or more visual elements of the response structure as a function of the adjusted set of requested data constraints comprises:

mapping the adjusted set of requested data constraints to a second range of database entries; and

retrieving a second set of requested data from the database using the second range of database entries, wherein retrieving the second set of requested data from the database using the second range of database entries comprises identifying redundant data retrieval as a function of the range of database entries and the second range of database entries.

16 . The system of claim 15 , wherein retrieving the second set of requested data from the database using the second range of database entries further comprises retrieving data for the redundant data retrieval from a cache.

17 . The system of claim 16 , wherein the memory contains instructions further configuring the at least a processor to store the requested data in the cache.

18 . The method of claim 8 , wherein reconfiguring one or more visual elements of the response structure as a function of the adjusted set of requested data constraints comprises:

mapping the adjusted set of requested data constraints to a second range of database entries; and

retrieving a second set of requested data from the database using the second range of database entries, wherein retrieving the second set of requested data from the database using the second range of database entries comprises identifying redundant data retrieval as a function of the range of database entries and the second range of database entries.

19 . The method of claim 18 , wherein retrieving the second set of requested data from the database using the second range of database entries further comprises retrieving data for the redundant data retrieval from a cache.

20 . The method of claim 19 , further comprising storing, using the at least a processor, the requested data in the cache.