Systems and methods for automatically populating information in a graphical user interface using natural language processing
The present disclosure relates to systems, methods, and computer-readable media for performing natural language processing on a clinical note or audio information associated with medical personnel. A computer-implemented method performed by one or more processors for populating a graphical user interface with data associated with a voice input. The method may include receiving a voice input, generating a first text based on the voice input, comparing the text against a computer model, identifying a data field in the text, selecting a form field based on the identified data field, extracting a second text based on the generated text, and populating the second text in the selected form field.
1. A computer-implemented method which, when executed, causes one or more processors to perform the computer-implemented method for populating a graphical user interface with data associated with a voice input, the method comprising:
receiving a voice input, wherein the receiving comprises identifying, by analyzing characteristics of the voice input, a source of the voice input;
generating a first text based on the voice input, wherein the generating comprises comparing the voice input against at least one computer model selected based upon a source of the voice input;
identifying, for each word in the first text, a meaning of each of the words in the first text;
identifying a plurality of data fields within a form to be populated with text from the first text;
identifying, for each of the words in the first text using the at least one computer model trained on a machine learning system and identifying entity patterns, a data field of the plurality of data fields to be populated with at least one of the words within the first text, wherein a data field of the plurality of data fields is identified based upon the meanings of each of the words; and
populating the plurality of data fields with the words in the first text, wherein the populating comprises identifying at least one words within the first text does not match an entity pattern for the corresponding of the plurality of data fields and populating the corresponding of the plurality of data fields with a second text different than the at least one words within the first text and matching the entity pattern for the corresponding of the plurality of data fields, wherein the second text is generated based on inferring, by employing one or more computer models, the second text from one of the first text and the received voice input based upon the meaning of the at least one words within the first text and wherein the second text is not directly disclosed in the first text and the received voice input.
2. The computer implemented method of claim 1 further comprising:
converting the voice input to text on an application programming interface.
3. The computer implemented method of claim 1 wherein:
the at least one computer model comprises a natural language processing model.
4. The computer implemented method of claim 1 wherein:
the at least one computer model comprises a plurality of models, the plurality of models comprising a lexical parser, a gender classifier, a part of speech tagger, a named entity recognizer, and a conference resolution mapper.
5. The computer implemented method of claim 1 , further comprising: storing the voice input in a memory.
6. The computer implemented method of claim 1 , further comprising: populating a date and/or a time in a form field based on algorithm calculation.
7. The computer implemented method of claim 1 , further comprising: fragmenting a sentence in a text.
8. The computer implemented method of claim 7 , further comprising: assigning a value to a fragment.
9. The computer implemented method of claim 1 , further comprising: ranking the at least one computer model based on analyzation of voice input.
10. A non-transitory computer-readable medium storing instructions which, when executed, cause one or more processors to perform a computerized method for populating a graphical user interface with data associated with a conversation, comprising:
receiving a voice input, wherein the receiving comprises identifying, by analyzing characteristics of the voice input, a source of the voice input;
generating a first text based on the voice input, wherein the generating comprises comparing the voice input against at least one computer model selected based upon a source of the voice input;
identifying, for each word in the first text, a meaning of each of the words in the first text;
identifying a plurality of data fields within a form to be populated with text from the first text;
identifying, for each of the words in the first text using the at least one computer model trained on a machine learning system and identifying entity patterns, a data field of the plurality of data fields to be populated with at least one of the words within the first text, wherein a data field of the plurality of data fields is identified based upon the meanings of each of the words; and
populating the plurality of data fields with the words in the first text, wherein the populating comprises identifying at least one words within the first text does not match an entity pattern for the corresponding of the plurality of data fields and populating the corresponding of the plurality of data fields with a second text different than the at least one words within the first text and matching the entity pattern for the corresponding of the plurality of data fields, wherein the second text is generated based on inferring, by employing one or more computer models, the second text from one of the first text and the received voice input based upon the meaning of the at least one words within the first text and wherein the second text is not directly disclosed in the first text and the received voice input.
11. The non-transitory computer-readable medium of claim 10 further comprising:
converting the voice input to text on an application programming interface.
12. The non-transitory computer-readable medium of claim 10 wherein:
the at least one computer model comprises a natural language processing model.
13. The non-transitory computer-readable medium of claim 10 wherein:
the at least one computer model comprises a plurality of models, the plurality of models comprising a lexical parser, a gender classifier, a part of speech tagger, a named entity recognizer, and a conference resolution mapper.
14. The non-transitory computer-readable medium of claim 10 , further comprising: populating a date and/or a time in a form field based on algorithm calculation.
15. The non-transitory computer-readable medium of claim 10 , further comprising: fragmenting a sentence in a text.
16. The non-transitory computer-readable medium of claim 15 , further comprising: assigning a value to a fragment.
17. A system for populating a graphical user interface with data associated with a conversation, the system comprising:
an audio sensor;
a memory storing instructions;
a database comprising at least one computer model; and
a processor configured to execute the stored instructions to perform operations comprising:
receiving a voice input, wherein the receiving comprises identifying, by analyzing characteristics of the voice input, a source of the voice input;
generating a first text based on the voice input, wherein the generating comprises comparing the voice input against the at least one computer model selected based upon a source of the voice input;
identifying, for each word in the first text, a meaning of each of the words in the first text;
identifying a plurality of data fields within a form to be populated with text from the first text;
identifying, for each of the words in the first text using the at least one computer model trained on a machine learning system and identifying entity patterns, a data field of the plurality of data fields to be populated with at least one of the words within the first text, wherein a data field of the plurality of data fields is identified based upon the meanings of each of the words; and
populating the plurality of data fields with the words in the first text, wherein the populating comprises identifying at least one words within the first text does not match an entity pattern for the corresponding of the plurality of data fields and populating the corresponding of the plurality of data fields with a second text different than the at least one words within the first text and matching the entity pattern for the corresponding of the plurality of data fields, wherein the second text is generated based on inferring, by employing one or more computer models, the second text from one of the first text and the received voice input based upon the meaning of the at least one words within the first text and wherein the second text is not directly disclosed in the first text and the received voice input.
18. The system of claim 17 wherein:
the at least one computer model comprises a plurality of models, the plurality of models comprising a lexical parser, a gender classifier, a part of speech tagger, a named entity recognizer, and a conference resolution mapper.