Systems and methods for search engine based web ticket minimization
Various embodiments described herein relate to a system for providing automated solutions, in response to a query of a user. The system may include a search engine-based web service, which may receive information from a database and may enable the user to troubleshoot their query. The search engine-based web service may include an artificial intelligence based chat service. The user may use the artificial intelligence based chat service to submit the query. In response, an intelligent virtual assistant of the artificial intelligence based chat service may process the query and return the solutions from the database, which may be appropriately related to subject matter of the query.
1. A server-implemented method comprising:
generating, by a server, an authenticated session based upon authentication credentials associated with a user operating a user device, the authentication credentials corresponding to a first level of authentication;
receiving, by the server, a text-based query entered in a web portal in the authenticated session from the user device;
parsing, by the server, the text-based query to determine one or more relevant keywords based upon one or more predetermined rules;
executing, by the server, a machine learning model to retrieve one or more web documents based upon the one or more relevant keywords, wherein the one or more web documents are associated with a plurality of levels of authentication;
filtering, subsequent to receiving the text-based query by the server, the one or more web documents to generate a filtered set of web documents based upon the authentication credentials, wherein the filtering redacts a portion of at least one web document, the portion having a second level of authentication higher than the first level of authentication of the authentication credentials; and
displaying, by the server on the user device, the at least one web document having the portion redacted of the filtered set of web documents.
2. The server-implemented method according to claim 1 , wherein the web portal comprises an intelligent virtual assistant.
3. The server-implemented method according to claim 2 , wherein the intelligent virtual assistant is configured to perform tasks for the user based on analysis of one or more questions in the text-based query.
4. The server-implemented method according to claim 3 , wherein the one or more questions comprises a text input, a voice input, and an image input.
5. The server-implemented method according to claim 1 , further comprising:
training, by the server, the machine learning model using a training dataset, wherein the training dataset comprises measurements taken on a sample of a plurality of web documents and a plurality of questions stored in a database.
6. The server-implemented method according to claim 1 , further comprising:
retraining, by the server, the machine learning model using an updated training dataset, wherein the updated training dataset comprises measurements taken on a sample of a new set of web documents and a new set of questions added in a database.
7. The server-implemented method according to claim 1 , wherein the redacted portion of the at least one web document is a text or an image.
8. The server-implemented method according to claim 1 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a number of times the relevant keyword is used in the text-based query.
9. The server-implemented method according to claim 1 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a meaning and context of the relevant keyword in the text-based query.
10. The server-implemented method according to claim 1 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a type of content in the text-based query.
11. A system comprising:
a non-transitory storage medium storing a plurality of web documents; and
a server configured to:
generate an authenticated session based upon authentication credentials associated with a user operating a user device, the authentication credentials corresponding to a first level of authentication;
receive a text-based query entered in a web portal in the authenticated session from the user device;
parse the text-based query to determine one or more relevant keywords based upon one or more predetermined rules;
execute a machine learning model to retrieve one or more web documents from the non-transitory storage medium based upon the one or more relevant keywords, wherein the one or more web documents are associated with a plurality of levels of authentication;
filter, subsequent to receiving the text-based query, the one or more web documents to generate a filtered set of web documents based upon the authentication credentials based upon the authentication credentials, the portion having a second level of authentication higher than the first level of authentication of the authentication credentials; and
provide, for display to the user device, the at least one web document having the portion redacted of the filtered set of web documents.
12. The system according to claim 11 , wherein the web portal comprises an intelligent virtual assistant.
13. The system according to claim 12 , wherein the intelligent virtual assistant is configured to perform tasks for the user based on analysis of one or more questions in the text-based query.
14. The system according to claim 13 , wherein the one or more questions comprises a text input, a voice input, and an image input.
15. The system according to claim 11 , wherein the server is configured to train the machine learning model using a training dataset, wherein the training dataset comprises measurements taken on a sample of a plurality of web documents and a plurality of questions stored in a database.
16. The system according to claim 11 , wherein the server is configured to retrain the machine learning model using an updated training dataset, wherein the updated training dataset comprises measurements taken on a sample of a new set of web documents and a new set of questions added in a database.
17. The system according to claim 11 , wherein the redacted portion of the at least one web document is a text or an image.
18. The system according to claim 11 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a number of times the relevant keyword is used in the text-based query.
19. The system according to claim 11 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a meaning and context of the relevant keyword in the text-based query.
20. The system according to claim 11 , wherein the one or more predetermined rules comprises a rule to select a relevant keyword from the text-based query based on a type of content in the text-based query.