Artificial intelligence system with augmented document capture and processing systems and methods
A document capture server receives a document image from a document capture client and processes the image into an electronic document containing textual content. During capture, the document capture server determines a graphical layout of the document, extracts keywords from the document, classifies the document accordingly, and calls an artificial intelligence (AI) platform to gain insights on the textual content. The AI platform analyzes the textual content and returns additional, insightful data such as a sentiment of the textual content. The document capture server can validate the additional data, integrate the additional data in a process or workflow, and/or provide the textual content and the additional data to a content repository or a computing facility operating in an enterprise computing environment. The document capture server can provide validated data to the AI platform to improve future analyses by the AI platform.
1. A method, comprising:
obtaining an electronic document, wherein the electronic document was created by processing an image of a document into the electronic document, including recognizing textual content of the document;
processing at least the textual content of the electronic document to determine a set of terms, a set of keywords, and a class for the electronic document, wherein the class is based in part on the keywords extracted from the set of terms;
obtaining, from an artificial intelligence (AI) platform server computer, AI data corresponding to the electronic document, the obtaining including querying the AI platform based on the determined class of the electronic document, wherein the AI platform server computer analyzes at least a portion of the textual content of the electronic document utilizing the class and returns the AI data corresponding to the electronic document; and
providing the electronic document and the AI data corresponding to the electronic document to a content repository or a computing facility operating in an enterprise computing environment.
2. The method of claim 1 , wherein the processing of the at least the textual content of the electronic document comprises graphical classification, classification based on the set of terms, zonal extraction, or free form extraction.
3. The method of claim 1 , wherein the document is a paper document.
4. The method of claim 1 , wherein determining a class for the electronic document is based at least in part on the terms extracted from the textual content of the electronic document.
5. The method of claim 1 , wherein the AI data comprises enriched metadata.
6. The method of claim 5 , wherein the enriched metadata comprises one or more semantic or tonality indicators corresponding to the portion of textual content.
7. The method of claim 1 , wherein the querying of the AI platform is based on an identifier for a knowledge base to apply in determining AI data.
8. A system, comprising:
a processor;
a non-transitory computer-readable medium, comprising instructions for:
obtaining an electronic document, wherein the electronic document was created by processing an image of a document into the electronic document, including recognizing textual content of the document;
processing at least the textual content of the electronic document to determine a set of terms, a set of keywords and a class for the electronic document, wherein the class is based in part on the keywords extracted from the set of terms;
obtaining, from an artificial intelligence (AI) platform server computer, AI data corresponding to the electronic document, the obtaining including querying the AI platform based on the determined class of the electronic document, wherein the AI platform server computer analyzes at least a portion of the textual content of the electronic document utilizing the class and returns the AI data corresponding to the electronic document; and
providing the electronic document and the AI data corresponding to the electronic document to a content repository or a computing facility operating in an enterprise computing environment.
9. The system of claim 8 , wherein the processing of the at least the textual content of the electronic document comprises graphical classification, classification based on the set of terms, zonal extraction, or free form extraction.
10. The system of claim 8 , wherein the document is a paper document.
11. The system of claim 8 , wherein determining a class for the electronic document is based at least in part on the terms extracted from the textual content of the electronic document.
12. The system of claim 8 , wherein the AI data comprises enriched metadata.
13. The system of claim 12 , wherein the enriched metadata comprises one or more semantic or tonality indicators corresponding to the portion of textual content.
14. The system of claim 8 , wherein the querying of the AI platform is based on an identifier for a knowledge base to apply in determining AI data.
15. A non-transitory computer readable medium storing instructions for:
obtaining an electronic document, wherein the electronic document was created by processing an image of a document into the electronic document, including recognizing textual content of the document;
processing at least the textual content of the electronic document to determine a set of terms, a set of keywords, and a class for the electronic document, wherein the class is based in part on the keywords extracted from the set of terms;
obtaining, from an artificial intelligence (AI) platform server computer, AI data corresponding to the electronic document, the obtaining including querying the AI platform based on the determined class of the electronic document, wherein the AI platform server computer analyzes at least a portion of the textual content of the electronic document utilizing the class and returns the AI data corresponding to the electronic document; and
providing the electronic document and the AI data corresponding to the electronic document to a content repository or a computing facility operating in an enterprise computing environment.
16. The non-transitory computer readable medium of claim 15 , wherein the processing of the at least the textual content of the electronic document comprises graphical classification, classification based on the set of terms, zonal extraction, or free form extraction.
17. The non-transitory computer readable medium of claim 15 , wherein the document is a paper document.
18. The non-transitory computer readable medium of claim 15 , wherein determining a class for the electronic document is based at least in part on the terms extracted from the textual content of the electronic document.
19. The non-transitory computer readable medium of claim 15 , wherein the AI data comprises enriched metadata.
20. The non-transitory computer readable medium of claim 19 , wherein the enriched metadata comprises one or more semantic or tonality indicators corresponding to the portion of textual content.
21. The non-transitory computer readable medium of claim 15 , wherein the querying of the AI platform is based on an identifier for a knowledge base to apply in determining AI data.