Computing device and method for populating digital forms from un-parsed data

• US 10,832,656 B1
• Filed: 02/25/2020
• Issued: 11/10/2020
• Est. Priority Date: 02/25/2020
• Status: Active Grant

• Current Assignee: Smart Solutions IP LLC
• Original Assignee: Smart Solutions IP LLC
• Inventors: Shaya, Fawzi
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US16/800,416
• Time in Patent Office: 259 Days
• Field of Search: 704270, 704231, 704235, 7079991, 707999102, 709223, 382187, 715235, 715236, 715249, 715255, 715264, 715273, 715277, 717110, 717140
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A computing device is disclosed which includes a processor and non-transient memory operably connected to the processor. The non-transient memory includes instructions that, when executed by the processor cause the processor to extract a plurality of sub-strings from a character string, analyze each sub-string for compliance with each of several field definitions, where each of the field definitions corresponds to a field in a digital form, and populate some of the fields in the digital form based on the analysis of each sub-string for compliance with the field definitions.

Claims

1. A computing device comprising:

a processor;

non-transient memory operably connected to the processor, the non-transient memory comprising instructions that, when executed by the processor, cause the processor to perform a method comprising the following steps;

retrieving a digital form comprising a plurality of fields;

retrieving a plurality of field definitions associated with the plurality of fields;

generating a character string by applying a speech recognition algorithm to audio data comprising a user'"'"'s speech;

recognizing a plurality of target keywords in the character string;

extracting a plurality of sub-strings from the character string based on the target keywords;

generating a numerical score by analyzing each sub-string for compliance with each of the plurality of field definitions, where each of the plurality of field definitions comprises a field name and a data type and corresponds to one of the plurality of fields in the digital form, where each sub-string is analyzed in real-time while the user speaks; and

populating a plurality of the fields in the digital form based on the numerical score generated during the analysis of each sub-string for compliance with each of the plurality of field definitions.

2. The computing device of claim 1, where each of the plurality of field definitions further comprises a size limit.

3. The computing device of claim 1, where the plurality of field definitions further comprises target keywords associated with the plurality of fields in the digital form.

4. The computing device of claim 1, where analyzing each sub-string for compliance with each of a plurality of field definitions comprises applying a pattern-recognition algorithm to the sub-strings and the field definitions.

5. The computing device of claim 4, where the pattern-recognition algorithm is generated using machine learning.

6. The computing device of claim 4, where the method further comprises retrieving the pattern-recognition algorithm.

7. The computing device of claim 6 where the pattern-recognition algorithm is retrieved from a remote server.

8. The computing device of claim 6 where the pattern-recognition algorithm is retrieved from the non-transient memory.

9. The computing device of claim 1, where populating the plurality of the fields in the digital form occurs in real-time while the user speaks.

10. The computing device of claim 1 where the digital form and the field definitions are retrieved from a remote server.

11. The computing device of claim 1 where the digital form and the field definitions are retrieved from the non-transient memory.

12. A computing device comprising:

a processor;

non-transient memory operably connected to the processor, the non-transient memory comprising instructions that, when executed by the processor, cause the processor to perform a method comprising the following steps;

retrieving a digital form comprising a plurality of fields;

generating a plurality of field definitions associated with the plurality of fields, based on the digital form;

generating a character string by applying a speech recognition algorithm to audio data comprising a user'"'"'s speech;

recognizing a plurality of target keywords in the character string;

extracting a plurality of sub-strings from the character string based on the target keywords;

generating a numerical score by analyzing each sub-string for compliance with each of the plurality of field definitions, where each of the plurality of field definitions comprises a field name and a data type and corresponds to one of the plurality of fields in the digital form, where each sub-string is analyzed in real-time while the user speaks; and

populating a plurality of the fields in the digital form based on the numerical score generated during the analysis of each sub-string for compliance with each of the plurality of field definitions.

13. The computing device of claim 12, where each of the plurality of field definitions further comprises a size limit.

14. The computing device of claim 12, where the plurality of field definitions further comprises target keywords associated with the plurality of fields in the digital form.

15. The computing device of claim 12, where analyzing each sub-string for compliance with each of a plurality of field definitions comprises applying a pattern-recognition algorithm to the sub-strings and the field definitions.

16. The computing device of claim 15, where the pattern-recognition algorithm is generated using machine learning.

17. The computing device of claim 15, where the method further comprises retrieving the pattern-recognition algorithm.

18. The computing device of claim 17 where the pattern-recognition algorithm is retrieved from a remote server.

19. The computing device of claim 17 where the pattern-recognition algorithm is retrieved from the non-transient memory.

20. The computing device of claim 12, where populating the plurality of the fields in the digital form occurs in real-time while the user speaks.

21. The computing device of claim 12 where the digital form is retrieved from a remote server.

22. The computing device of claim 12 where the digital form is retrieved from the non-transient memory.